[2024-08-01 15:38:13,997][00034] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json... [2024-08-01 15:38:14,000][00034] Rollout worker 0 uses device cpu [2024-08-01 15:38:14,001][00034] Rollout worker 1 uses device cpu [2024-08-01 15:38:14,002][00034] Rollout worker 2 uses device cpu [2024-08-01 15:38:14,003][00034] Rollout worker 3 uses device cpu [2024-08-01 15:38:14,004][00034] Rollout worker 4 uses device cpu [2024-08-01 15:38:14,004][00034] Rollout worker 5 uses device cpu [2024-08-01 15:38:14,005][00034] Rollout worker 6 uses device cpu [2024-08-01 15:38:14,006][00034] Rollout worker 7 uses device cpu [2024-08-01 15:38:14,007][00034] Rollout worker 8 uses device cpu [2024-08-01 15:38:14,009][00034] Rollout worker 9 uses device cpu [2024-08-01 15:38:14,010][00034] Rollout worker 10 uses device cpu [2024-08-01 15:38:14,011][00034] Rollout worker 11 uses device cpu [2024-08-01 15:38:14,012][00034] Rollout worker 12 uses device cpu [2024-08-01 15:38:14,013][00034] Rollout worker 13 uses device cpu [2024-08-01 15:38:14,014][00034] Rollout worker 14 uses device cpu [2024-08-01 15:38:14,014][00034] Rollout worker 15 uses device cpu [2024-08-01 15:38:14,886][00034] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-01 15:38:14,887][00034] InferenceWorker_p0-w0: min num requests: 5 [2024-08-01 15:38:14,957][00034] Starting all processes... [2024-08-01 15:38:14,959][00034] Starting process learner_proc0 [2024-08-01 15:38:15,064][00034] Starting all processes... [2024-08-01 15:38:15,073][00034] Starting process inference_proc0-0 [2024-08-01 15:38:15,074][00034] Starting process rollout_proc0 [2024-08-01 15:38:15,075][00034] Starting process rollout_proc1 [2024-08-01 15:38:15,075][00034] Starting process rollout_proc2 [2024-08-01 15:38:15,075][00034] Starting process rollout_proc3 [2024-08-01 15:38:15,076][00034] Starting process rollout_proc4 [2024-08-01 15:38:15,078][00034] Starting process rollout_proc5 [2024-08-01 15:38:15,079][00034] Starting process rollout_proc6 [2024-08-01 15:38:15,079][00034] Starting process rollout_proc7 [2024-08-01 15:38:15,079][00034] Starting process rollout_proc8 [2024-08-01 15:38:15,081][00034] Starting process rollout_proc9 [2024-08-01 15:38:15,081][00034] Starting process rollout_proc10 [2024-08-01 15:38:15,081][00034] Starting process rollout_proc11 [2024-08-01 15:38:15,081][00034] Starting process rollout_proc12 [2024-08-01 15:38:15,081][00034] Starting process rollout_proc13 [2024-08-01 15:38:15,082][00034] Starting process rollout_proc14 [2024-08-01 15:38:15,475][00034] Starting process rollout_proc15 [2024-08-01 15:38:29,405][00112] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-01 15:38:29,407][00112] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2024-08-01 15:38:29,478][00112] Num visible devices: 1 [2024-08-01 15:38:29,526][00112] Setting fixed seed 0 [2024-08-01 15:38:29,530][00112] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-01 15:38:29,531][00112] Initializing actor-critic model on device cuda:0 [2024-08-01 15:38:29,531][00112] RunningMeanStd input shape: (23,) [2024-08-01 15:38:29,534][00112] RunningMeanStd input shape: (3, 72, 128) [2024-08-01 15:38:29,535][00112] RunningMeanStd input shape: (1,) [2024-08-01 15:38:29,651][00112] ConvEncoder: input_channels=3 [2024-08-01 15:38:30,599][00112] Conv encoder output size: 512 [2024-08-01 15:38:30,601][00112] Policy head output size: 640 [2024-08-01 15:38:30,749][00145] Worker 12 uses CPU cores [0] [2024-08-01 15:38:30,812][00137] Worker 5 uses CPU cores [1] [2024-08-01 15:38:30,814][00140] Worker 7 uses CPU cores [3] [2024-08-01 15:38:30,813][00133] Worker 1 uses CPU cores [1] [2024-08-01 15:38:30,825][00138] Worker 4 uses CPU cores [0] [2024-08-01 15:38:30,828][00112] Created Actor Critic model with architecture: [2024-08-01 15:38:30,829][00112] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (measurements): RunningMeanStdInPlace() (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ReLU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ReLU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ReLU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ReLU) ) ) ) (measurements_head): Sequential( (0): Linear(in_features=23, out_features=128, bias=True) (1): ReLU() (2): Linear(in_features=128, out_features=128, bias=True) (3): ReLU() ) ) (core): ModelCoreRNN( (core): LSTM(640, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=39, bias=True) ) ) [2024-08-01 15:38:30,839][00135] Worker 2 uses CPU cores [2] [2024-08-01 15:38:30,851][00136] Worker 3 uses CPU cores [3] [2024-08-01 15:38:30,909][00147] Worker 14 uses CPU cores [2] [2024-08-01 15:38:30,945][00132] Worker 0 uses CPU cores [0] [2024-08-01 15:38:30,985][00139] Worker 8 uses CPU cores [0] [2024-08-01 15:38:31,009][00143] Worker 10 uses CPU cores [2] [2024-08-01 15:38:31,016][00142] Worker 9 uses CPU cores [1] [2024-08-01 15:38:31,022][00141] Worker 6 uses CPU cores [2] [2024-08-01 15:38:31,029][00134] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-01 15:38:31,029][00134] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2024-08-01 15:38:31,045][00144] Worker 11 uses CPU cores [3] [2024-08-01 15:38:31,065][00146] Worker 13 uses CPU cores [1] [2024-08-01 15:38:31,074][00148] Worker 15 uses CPU cores [3] [2024-08-01 15:38:31,074][00134] Num visible devices: 1 [2024-08-01 15:38:31,251][00112] Using optimizer [2024-08-01 15:38:32,339][00112] No checkpoints found [2024-08-01 15:38:32,340][00112] Did not load from checkpoint, starting from scratch! [2024-08-01 15:38:32,340][00112] Initialized policy 0 weights for model version 0 [2024-08-01 15:38:32,343][00112] LearnerWorker_p0 finished initialization! [2024-08-01 15:38:32,343][00112] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2024-08-01 15:38:32,437][00134] RunningMeanStd input shape: (23,) [2024-08-01 15:38:32,437][00134] RunningMeanStd input shape: (3, 72, 128) [2024-08-01 15:38:32,438][00134] RunningMeanStd input shape: (1,) [2024-08-01 15:38:32,454][00134] ConvEncoder: input_channels=3 [2024-08-01 15:38:32,574][00134] Conv encoder output size: 512 [2024-08-01 15:38:32,575][00134] Policy head output size: 640 [2024-08-01 15:38:32,647][00034] Inference worker 0-0 is ready! [2024-08-01 15:38:32,648][00034] All inference workers are ready! Signal rollout workers to start! [2024-08-01 15:38:32,861][00143] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,862][00141] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,860][00135] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,857][00147] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,865][00136] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,865][00146] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,867][00142] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,865][00133] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,865][00139] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,865][00140] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,866][00137] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,864][00148] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,867][00145] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,868][00144] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,872][00138] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,873][00143] Port 41300 is available [2024-08-01 15:38:32,875][00143] Using port 41300 [2024-08-01 15:38:32,875][00141] Port 40900 is available [2024-08-01 15:38:32,870][00147] Port 41700 is available [2024-08-01 15:38:32,871][00132] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 15:38:32,876][00141] Using port 40900 [2024-08-01 15:38:32,875][00135] Port 40500 is available [2024-08-01 15:38:32,877][00147] Using port 41700 [2024-08-01 15:38:32,877][00135] Using port 40500 [2024-08-01 15:38:32,870][00139] Port 41100 is available [2024-08-01 15:38:32,875][00146] Port 41600 is available [2024-08-01 15:38:32,879][00146] Using port 41600 [2024-08-01 15:38:32,879][00139] Using port 41100 [2024-08-01 15:38:32,880][00133] Port 40400 is available [2024-08-01 15:38:32,879][00136] Port 40600 is available [2024-08-01 15:38:32,879][00142] Port 41200 is available [2024-08-01 15:38:32,875][00145] Port 41500 is available [2024-08-01 15:38:32,882][00145] Using port 41500 [2024-08-01 15:38:32,882][00133] Using port 40400 [2024-08-01 15:38:32,881][00137] Port 40800 is available [2024-08-01 15:38:32,882][00136] Using port 40600 [2024-08-01 15:38:32,881][00140] Port 41000 is available [2024-08-01 15:38:32,882][00142] Using port 41200 [2024-08-01 15:38:32,883][00137] Using port 40800 [2024-08-01 15:38:32,883][00140] Using port 41000 [2024-08-01 15:38:32,880][00138] Port 40700 is available [2024-08-01 15:38:32,883][00144] Port 41400 is available [2024-08-01 15:38:32,884][00148] Port 41800 is available [2024-08-01 15:38:32,884][00132] Port 40300 is available [2024-08-01 15:38:32,886][00138] Using port 40700 [2024-08-01 15:38:32,886][00144] Using port 41400 [2024-08-01 15:38:32,886][00132] Using port 40300 [2024-08-01 15:38:32,886][00148] Using port 41800 [2024-08-01 15:38:33,072][00141] Port 40901 is available [2024-08-01 15:38:33,065][00143] Port 41301 is available [2024-08-01 15:38:33,074][00141] Using port 40901 [2024-08-01 15:38:33,074][00143] Using port 41301 [2024-08-01 15:38:33,073][00146] Port 41601 is available [2024-08-01 15:38:33,078][00139] Port 41101 is available [2024-08-01 15:38:33,075][00133] Port 40401 is available [2024-08-01 15:38:33,078][00139] Using port 41101 [2024-08-01 15:38:33,078][00146] Using port 41601 [2024-08-01 15:38:33,069][00147] Port 41701 is available [2024-08-01 15:38:33,078][00133] Using port 40401 [2024-08-01 15:38:33,079][00147] Using port 41701 [2024-08-01 15:38:33,077][00137] Port 40801 is available [2024-08-01 15:38:33,077][00140] Port 41001 is available [2024-08-01 15:38:33,080][00140] Using port 41001 [2024-08-01 15:38:33,080][00137] Using port 40801 [2024-08-01 15:38:33,079][00144] Port 41401 is available [2024-08-01 15:38:33,082][00144] Using port 41401 [2024-08-01 15:38:33,081][00136] Port 40601 is available [2024-08-01 15:38:33,087][00132] Port 40301 is available [2024-08-01 15:38:33,087][00136] Using port 40601 [2024-08-01 15:38:33,082][00142] Port 41201 is available [2024-08-01 15:38:33,088][00142] Using port 41201 [2024-08-01 15:38:33,088][00148] Port 41801 is available [2024-08-01 15:38:33,088][00132] Using port 40301 [2024-08-01 15:38:33,082][00145] Port 41501 is available [2024-08-01 15:38:33,089][00135] Port 40501 is available [2024-08-01 15:38:33,092][00145] Using port 41501 [2024-08-01 15:38:33,089][00148] Using port 41801 [2024-08-01 15:38:33,092][00135] Using port 40501 [2024-08-01 15:38:33,097][00138] Port 40701 is available [2024-08-01 15:38:33,098][00138] Using port 40701 [2024-08-01 15:38:33,279][00146] Port 41602 is available [2024-08-01 15:38:33,276][00144] Port 41402 is available [2024-08-01 15:38:33,281][00144] Using port 41402 [2024-08-01 15:38:33,280][00140] Port 41002 is available [2024-08-01 15:38:33,281][00146] Using port 41602 [2024-08-01 15:38:33,284][00140] Using port 41002 [2024-08-01 15:38:33,278][00141] Port 40902 is available [2024-08-01 15:38:33,281][00148] Port 41802 is available [2024-08-01 15:38:33,281][00137] Port 40802 is available [2024-08-01 15:38:33,280][00136] Port 40602 is available [2024-08-01 15:38:33,285][00148] Using port 41802 [2024-08-01 15:38:33,284][00133] Port 40402 is available [2024-08-01 15:38:33,284][00141] Using port 40902 [2024-08-01 15:38:33,285][00147] Port 41702 is available [2024-08-01 15:38:33,285][00136] Using port 40602 [2024-08-01 15:38:33,285][00137] Using port 40802 [2024-08-01 15:38:33,286][00133] Using port 40402 [2024-08-01 15:38:33,289][00139] Port 41102 is available [2024-08-01 15:38:33,286][00147] Using port 41702 [2024-08-01 15:38:33,288][00132] Port 40302 is available [2024-08-01 15:38:33,289][00139] Using port 41102 [2024-08-01 15:38:33,289][00132] Using port 40302 [2024-08-01 15:38:33,284][00142] Port 41202 is available [2024-08-01 15:38:33,294][00142] Using port 41202 [2024-08-01 15:38:33,291][00143] Port 41302 is available [2024-08-01 15:38:33,296][00145] Port 41502 is available [2024-08-01 15:38:33,296][00143] Using port 41302 [2024-08-01 15:38:33,297][00145] Using port 41502 [2024-08-01 15:38:33,296][00135] Port 40502 is available [2024-08-01 15:38:33,298][00138] Port 40702 is available [2024-08-01 15:38:33,301][00138] Using port 40702 [2024-08-01 15:38:33,301][00135] Using port 40502 [2024-08-01 15:38:33,484][00140] Port 41003 is available [2024-08-01 15:38:33,484][00144] Port 41403 is available [2024-08-01 15:38:33,484][00140] Using port 41003 [2024-08-01 15:38:33,486][00141] Port 40903 is available [2024-08-01 15:38:33,482][00147] Port 41703 is available [2024-08-01 15:38:33,487][00141] Using port 40903 [2024-08-01 15:38:33,485][00144] Using port 41403 [2024-08-01 15:38:33,490][00148] Port 41803 is available [2024-08-01 15:38:33,490][00148] Using port 41803 [2024-08-01 15:38:33,487][00147] Using port 41703 [2024-08-01 15:38:33,495][00136] Port 40603 is available [2024-08-01 15:38:33,496][00136] Using port 40603 [2024-08-01 15:38:33,500][00133] Port 40403 is available [2024-08-01 15:38:33,495][00132] Port 40303 is available [2024-08-01 15:38:33,494][00146] Port 41603 is available [2024-08-01 15:38:33,501][00132] Using port 40303 [2024-08-01 15:38:33,494][00143] Port 41303 is available [2024-08-01 15:38:33,503][00143] Using port 41303 [2024-08-01 15:38:33,502][00146] Using port 41603 [2024-08-01 15:38:33,501][00133] Using port 40403 [2024-08-01 15:38:33,508][00145] Port 41503 is available [2024-08-01 15:38:33,499][00137] Port 40803 is available [2024-08-01 15:38:33,500][00139] Port 41103 is available [2024-08-01 15:38:33,507][00135] Port 40503 is available [2024-08-01 15:38:33,510][00137] Using port 40803 [2024-08-01 15:38:33,510][00139] Using port 41103 [2024-08-01 15:38:33,510][00135] Using port 40503 [2024-08-01 15:38:33,511][00145] Using port 41503 [2024-08-01 15:38:33,522][00138] Port 40703 is available [2024-08-01 15:38:33,519][00142] Port 41203 is available [2024-08-01 15:38:33,522][00138] Using port 40703 [2024-08-01 15:38:33,522][00142] Using port 41203 [2024-08-01 15:38:33,701][00140] Port 41004 is available [2024-08-01 15:38:33,697][00147] Port 41704 is available [2024-08-01 15:38:33,706][00147] Using port 41704 [2024-08-01 15:38:33,701][00140] Using port 41004 [2024-08-01 15:38:33,705][00141] Port 40904 is available [2024-08-01 15:38:33,710][00141] Using port 40904 [2024-08-01 15:38:33,715][00144] Port 41404 is available [2024-08-01 15:38:33,715][00144] Using port 41404 [2024-08-01 15:38:33,717][00132] Port 40304 is available [2024-08-01 15:38:33,721][00136] Port 40604 is available [2024-08-01 15:38:33,723][00148] Port 41804 is available [2024-08-01 15:38:33,723][00132] Using port 40304 [2024-08-01 15:38:33,723][00136] Using port 40604 [2024-08-01 15:38:33,724][00148] Using port 41804 [2024-08-01 15:38:33,724][00143] Port 41304 is available [2024-08-01 15:38:33,727][00143] Using port 41304 [2024-08-01 15:38:33,719][00133] Port 40404 is available [2024-08-01 15:38:33,727][00133] Using port 40404 [2024-08-01 15:38:33,725][00146] Port 41604 is available [2024-08-01 15:38:33,734][00139] Port 41104 is available [2024-08-01 15:38:33,731][00146] Using port 41604 [2024-08-01 15:38:33,735][00135] Port 40504 is available [2024-08-01 15:38:33,735][00139] Using port 41104 [2024-08-01 15:38:33,737][00135] Using port 40504 [2024-08-01 15:38:33,736][00137] Port 40804 is available [2024-08-01 15:38:33,742][00145] Port 41504 is available [2024-08-01 15:38:33,739][00137] Using port 40804 [2024-08-01 15:38:33,739][00138] Port 40704 is available [2024-08-01 15:38:33,742][00145] Using port 41504 [2024-08-01 15:38:33,743][00138] Using port 40704 [2024-08-01 15:38:33,749][00142] Port 41204 is available [2024-08-01 15:38:33,750][00142] Using port 41204 [2024-08-01 15:38:33,838][00034] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:33,895][00140] Port 41005 is available [2024-08-01 15:38:33,899][00140] Using port 41005 [2024-08-01 15:38:33,907][00144] Port 41405 is available [2024-08-01 15:38:33,905][00147] Port 41705 is available [2024-08-01 15:38:33,914][00147] Using port 41705 [2024-08-01 15:38:33,914][00144] Using port 41405 [2024-08-01 15:38:33,915][00136] Port 40605 is available [2024-08-01 15:38:33,919][00136] Using port 40605 [2024-08-01 15:38:33,911][00141] Port 40905 is available [2024-08-01 15:38:33,922][00141] Using port 40905 [2024-08-01 15:38:33,928][00146] Port 41605 is available [2024-08-01 15:38:33,932][00146] Using port 41605 [2024-08-01 15:38:33,933][00132] Port 40305 is available [2024-08-01 15:38:33,934][00148] Port 41805 is available [2024-08-01 15:38:33,936][00148] Using port 41805 [2024-08-01 15:38:33,935][00132] Using port 40305 [2024-08-01 15:38:33,934][00139] Port 41105 is available [2024-08-01 15:38:33,932][00143] Port 41305 is available [2024-08-01 15:38:33,942][00139] Using port 41105 [2024-08-01 15:38:33,937][00133] Port 40405 is available [2024-08-01 15:38:33,945][00133] Using port 40405 [2024-08-01 15:38:33,942][00143] Using port 41305 [2024-08-01 15:38:33,939][00135] Port 40505 is available [2024-08-01 15:38:33,948][00135] Using port 40505 [2024-08-01 15:38:33,942][00142] Port 41205 is available [2024-08-01 15:38:33,951][00142] Using port 41205 [2024-08-01 15:38:33,951][00145] Port 41505 is available [2024-08-01 15:38:33,958][00145] Using port 41505 [2024-08-01 15:38:33,963][00138] Port 40705 is available [2024-08-01 15:38:33,964][00138] Using port 40705 [2024-08-01 15:38:33,961][00137] Port 40805 is available [2024-08-01 15:38:33,971][00137] Using port 40805 [2024-08-01 15:38:34,078][00140] Port 41006 is available [2024-08-01 15:38:34,086][00140] Using port 41006 [2024-08-01 15:38:34,094][00136] Port 40606 is available [2024-08-01 15:38:34,105][00136] Using port 40606 [2024-08-01 15:38:34,102][00144] Port 41406 is available [2024-08-01 15:38:34,105][00147] Port 41706 is available [2024-08-01 15:38:34,110][00144] Using port 41406 [2024-08-01 15:38:34,110][00147] Using port 41706 [2024-08-01 15:38:34,109][00141] Port 40906 is available [2024-08-01 15:38:34,121][00141] Using port 40906 [2024-08-01 15:38:34,123][00146] Port 41606 is available [2024-08-01 15:38:34,126][00146] Using port 41606 [2024-08-01 15:38:34,141][00148] Port 41806 is available [2024-08-01 15:38:34,143][00148] Using port 41806 [2024-08-01 15:38:34,139][00133] Port 40406 is available [2024-08-01 15:38:34,148][00133] Using port 40406 [2024-08-01 15:38:34,143][00139] Port 41106 is available [2024-08-01 15:38:34,151][00139] Using port 41106 [2024-08-01 15:38:34,147][00132] Port 40306 is available [2024-08-01 15:38:34,153][00143] Port 41306 is available [2024-08-01 15:38:34,158][00132] Using port 40306 [2024-08-01 15:38:34,158][00142] Port 41206 is available [2024-08-01 15:38:34,150][00135] Port 40506 is available [2024-08-01 15:38:34,158][00143] Using port 41306 [2024-08-01 15:38:34,159][00135] Using port 40506 [2024-08-01 15:38:34,158][00142] Using port 41206 [2024-08-01 15:38:34,169][00145] Port 41506 is available [2024-08-01 15:38:34,170][00145] Using port 41506 [2024-08-01 15:38:34,181][00137] Port 40806 is available [2024-08-01 15:38:34,181][00137] Using port 40806 [2024-08-01 15:38:34,180][00138] Port 40706 is available [2024-08-01 15:38:34,189][00138] Using port 40706 [2024-08-01 15:38:34,277][00140] Port 41007 is available [2024-08-01 15:38:34,280][00140] Using port 41007 [2024-08-01 15:38:34,279][00136] Port 40607 is available [2024-08-01 15:38:34,289][00136] Using port 40607 [2024-08-01 15:38:34,294][00144] Port 41407 is available [2024-08-01 15:38:34,297][00147] Port 41707 is available [2024-08-01 15:38:34,307][00147] Using port 41707 [2024-08-01 15:38:34,304][00144] Using port 41407 [2024-08-01 15:38:34,316][00141] Port 40907 is available [2024-08-01 15:38:34,316][00141] Using port 40907 [2024-08-01 15:38:34,309][00146] Port 41607 is available [2024-08-01 15:38:34,322][00146] Using port 41607 [2024-08-01 15:38:34,333][00133] Port 40407 is available [2024-08-01 15:38:34,343][00133] Using port 40407 [2024-08-01 15:38:34,347][00148] Port 41807 is available [2024-08-01 15:38:34,348][00148] Using port 41807 [2024-08-01 15:38:34,340][00142] Port 41207 is available [2024-08-01 15:38:34,350][00142] Using port 41207 [2024-08-01 15:38:34,352][00143] Port 41307 is available [2024-08-01 15:38:34,352][00139] Port 41107 is available [2024-08-01 15:38:34,353][00143] Using port 41307 [2024-08-01 15:38:34,354][00139] Using port 41107 [2024-08-01 15:38:34,354][00132] Port 40307 is available [2024-08-01 15:38:34,356][00135] Port 40507 is available [2024-08-01 15:38:34,361][00132] Using port 40307 [2024-08-01 15:38:34,361][00135] Using port 40507 [2024-08-01 15:38:34,364][00137] Port 40807 is available [2024-08-01 15:38:34,373][00137] Using port 40807 [2024-08-01 15:38:34,365][00145] Port 41507 is available [2024-08-01 15:38:34,374][00145] Using port 41507 [2024-08-01 15:38:34,381][00138] Port 40707 is available [2024-08-01 15:38:34,387][00138] Using port 40707 [2024-08-01 15:38:34,424][00140] Port 41008 is available [2024-08-01 15:38:34,431][00140] Using port 41008 [2024-08-01 15:38:34,432][00136] Port 40608 is available [2024-08-01 15:38:34,435][00136] Using port 40608 [2024-08-01 15:38:34,447][00147] Port 41708 is available [2024-08-01 15:38:34,453][00147] Using port 41708 [2024-08-01 15:38:34,457][00144] Port 41408 is available [2024-08-01 15:38:34,457][00144] Using port 41408 [2024-08-01 15:38:34,466][00141] Port 40908 is available [2024-08-01 15:38:34,466][00141] Using port 40908 [2024-08-01 15:38:34,468][00146] Port 41608 is available [2024-08-01 15:38:34,471][00146] Using port 41608 [2024-08-01 15:38:34,492][00133] Port 40408 is available [2024-08-01 15:38:34,492][00133] Using port 40408 [2024-08-01 15:38:34,491][00142] Port 41208 is available [2024-08-01 15:38:34,498][00142] Using port 41208 [2024-08-01 15:38:34,492][00148] Port 41808 is available [2024-08-01 15:38:34,501][00148] Using port 41808 [2024-08-01 15:38:34,506][00143] Port 41308 is available [2024-08-01 15:38:34,515][00143] Using port 41308 [2024-08-01 15:38:34,512][00132] Port 40308 is available [2024-08-01 15:38:34,515][00132] Using port 40308 [2024-08-01 15:38:34,516][00135] Port 40508 is available [2024-08-01 15:38:34,519][00135] Using port 40508 [2024-08-01 15:38:34,519][00139] Port 41108 is available [2024-08-01 15:38:34,524][00139] Using port 41108 [2024-08-01 15:38:34,525][00137] Port 40808 is available [2024-08-01 15:38:34,519][00145] Port 41508 is available [2024-08-01 15:38:34,528][00145] Using port 41508 [2024-08-01 15:38:34,525][00137] Using port 40808 [2024-08-01 15:38:34,543][00138] Port 40708 is available [2024-08-01 15:38:34,543][00138] Using port 40708 [2024-08-01 15:38:34,575][00140] Port 41009 is available [2024-08-01 15:38:34,584][00140] Using port 41009 [2024-08-01 15:38:34,584][00136] Port 40609 is available [2024-08-01 15:38:34,593][00136] Using port 40609 [2024-08-01 15:38:34,602][00147] Port 41709 is available [2024-08-01 15:38:34,608][00147] Using port 41709 [2024-08-01 15:38:34,601][00144] Port 41409 is available [2024-08-01 15:38:34,611][00144] Using port 41409 [2024-08-01 15:38:34,619][00141] Port 40909 is available [2024-08-01 15:38:34,617][00146] Port 41609 is available [2024-08-01 15:38:34,620][00141] Using port 40909 [2024-08-01 15:38:34,623][00146] Using port 41609 [2024-08-01 15:38:34,640][00133] Port 40409 is available [2024-08-01 15:38:34,649][00133] Using port 40409 [2024-08-01 15:38:34,648][00142] Port 41209 is available [2024-08-01 15:38:34,651][00142] Using port 41209 [2024-08-01 15:38:34,647][00148] Port 41809 is available [2024-08-01 15:38:34,654][00148] Using port 41809 [2024-08-01 15:38:34,663][00143] Port 41309 is available [2024-08-01 15:38:34,664][00143] Using port 41309 [2024-08-01 15:38:34,672][00132] Port 40309 is available [2024-08-01 15:38:34,673][00132] Using port 40309 [2024-08-01 15:38:34,668][00135] Port 40509 is available [2024-08-01 15:38:34,676][00135] Using port 40509 [2024-08-01 15:38:34,672][00139] Port 41109 is available [2024-08-01 15:38:34,671][00137] Port 40809 is available [2024-08-01 15:38:34,681][00137] Using port 40809 [2024-08-01 15:38:34,679][00139] Using port 41109 [2024-08-01 15:38:34,681][00145] Port 41509 is available [2024-08-01 15:38:34,691][00145] Using port 41509 [2024-08-01 15:38:34,695][00138] Port 40709 is available [2024-08-01 15:38:34,701][00138] Using port 40709 [2024-08-01 15:38:34,728][00140] Port 41010 is available [2024-08-01 15:38:34,732][00140] Using port 41010 [2024-08-01 15:38:34,739][00136] Port 40610 is available [2024-08-01 15:38:34,740][00136] Using port 40610 [2024-08-01 15:38:34,753][00147] Port 41710 is available [2024-08-01 15:38:34,762][00147] Using port 41710 [2024-08-01 15:38:34,762][00144] Port 41410 is available [2024-08-01 15:38:34,763][00144] Using port 41410 [2024-08-01 15:38:34,771][00141] Port 40910 is available [2024-08-01 15:38:34,776][00141] Using port 40910 [2024-08-01 15:38:34,777][00146] Port 41610 is available [2024-08-01 15:38:34,780][00146] Using port 41610 [2024-08-01 15:38:34,796][00133] Port 40410 is available [2024-08-01 15:38:34,800][00133] Using port 40410 [2024-08-01 15:38:34,802][00142] Port 41210 is available [2024-08-01 15:38:34,807][00148] Port 41810 is available [2024-08-01 15:38:34,809][00142] Using port 41210 [2024-08-01 15:38:34,809][00148] Using port 41810 [2024-08-01 15:38:34,812][00143] Port 41310 is available [2024-08-01 15:38:34,821][00143] Using port 41310 [2024-08-01 15:38:34,820][00135] Port 40510 is available [2024-08-01 15:38:34,826][00135] Using port 40510 [2024-08-01 15:38:34,822][00137] Port 40810 is available [2024-08-01 15:38:34,834][00137] Using port 40810 [2024-08-01 15:38:34,834][00132] Port 40310 is available [2024-08-01 15:38:34,833][00139] Port 41110 is available [2024-08-01 15:38:34,835][00132] Using port 40310 [2024-08-01 15:38:34,835][00139] Using port 41110 [2024-08-01 15:38:34,845][00145] Port 41510 is available [2024-08-01 15:38:34,846][00145] Using port 41510 [2024-08-01 15:38:34,860][00138] Port 40710 is available [2024-08-01 15:38:34,862][00138] Using port 40710 [2024-08-01 15:38:34,876][00034] Heartbeat connected on Batcher_0 [2024-08-01 15:38:34,881][00034] Heartbeat connected on LearnerWorker_p0 [2024-08-01 15:38:34,881][00140] Port 41011 is available [2024-08-01 15:38:34,883][00140] Using port 41011 [2024-08-01 15:38:34,885][00136] Port 40611 is available [2024-08-01 15:38:34,890][00136] Using port 40611 [2024-08-01 15:38:34,887][00140] Using port 41000 on host... [2024-08-01 15:38:34,895][00136] Using port 40600 on host... [2024-08-01 15:38:34,905][00144] Port 41411 is available [2024-08-01 15:38:34,905][00144] Using port 41411 [2024-08-01 15:38:34,905][00147] Port 41711 is available [2024-08-01 15:38:34,908][00147] Using port 41711 [2024-08-01 15:38:34,907][00144] Using port 41400 on host... [2024-08-01 15:38:34,919][00147] Using port 41700 on host... [2024-08-01 15:38:34,919][00034] Heartbeat connected on InferenceWorker_p0-w0 [2024-08-01 15:38:34,916][00141] Port 40911 is available [2024-08-01 15:38:34,923][00141] Using port 40911 [2024-08-01 15:38:34,928][00141] Using port 40900 on host... [2024-08-01 15:38:34,947][00148] Port 41811 is available [2024-08-01 15:38:34,949][00148] Using port 41811 [2024-08-01 15:38:34,949][00146] Port 41611 is available [2024-08-01 15:38:34,952][00146] Using port 41611 [2024-08-01 15:38:34,954][00148] Using port 41800 on host... [2024-08-01 15:38:34,958][00143] Port 41311 is available [2024-08-01 15:38:34,958][00146] Using port 41600 on host... [2024-08-01 15:38:34,961][00135] Port 40511 is available [2024-08-01 15:38:34,964][00143] Using port 41311 [2024-08-01 15:38:34,964][00133] Port 40411 is available [2024-08-01 15:38:34,965][00133] Using port 40411 [2024-08-01 15:38:34,966][00143] Using port 41300 on host... [2024-08-01 15:38:34,973][00135] Using port 40511 [2024-08-01 15:38:34,973][00133] Using port 40400 on host... [2024-08-01 15:38:34,976][00135] Using port 40500 on host... [2024-08-01 15:38:34,982][00142] Port 41211 is available [2024-08-01 15:38:34,990][00142] Using port 41211 [2024-08-01 15:38:34,992][00142] Using port 41200 on host... [2024-08-01 15:38:35,003][00145] Port 41511 is available [2024-08-01 15:38:35,010][00145] Using port 41511 [2024-08-01 15:38:35,006][00132] Port 40311 is available [2024-08-01 15:38:35,014][00137] Port 40811 is available [2024-08-01 15:38:35,014][00137] Using port 40811 [2024-08-01 15:38:35,009][00139] Port 41111 is available [2024-08-01 15:38:35,012][00132] Using port 40311 [2024-08-01 15:38:35,014][00139] Using port 41111 [2024-08-01 15:38:35,018][00145] Using port 41500 on host... [2024-08-01 15:38:35,024][00137] Using port 40800 on host... [2024-08-01 15:38:35,021][00132] Using port 40300 on host... [2024-08-01 15:38:35,019][00139] Using port 41100 on host... [2024-08-01 15:38:35,029][00138] Port 40711 is available [2024-08-01 15:38:35,043][00138] Using port 40711 [2024-08-01 15:38:35,045][00138] Using port 40700 on host... [2024-08-01 15:38:36,960][00146] Initialized w:13 v:0 player:0 [2024-08-01 15:38:36,961][00143] Initialized w:10 v:0 player:0 [2024-08-01 15:38:36,962][00136] Initialized w:3 v:0 player:0 [2024-08-01 15:38:36,965][00141] Initialized w:6 v:0 player:0 [2024-08-01 15:38:36,960][00148] Initialized w:15 v:0 player:0 [2024-08-01 15:38:36,965][00140] Initialized w:7 v:0 player:0 [2024-08-01 15:38:36,968][00135] Initialized w:2 v:0 player:0 [2024-08-01 15:38:36,968][00144] Initialized w:11 v:0 player:0 [2024-08-01 15:38:36,971][00147] Initialized w:14 v:0 player:0 [2024-08-01 15:38:36,972][00146] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,973][00136] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,972][00143] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,975][00146] Using port 41601 on host... [2024-08-01 15:38:36,972][00148] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,973][00140] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,976][00141] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,977][00135] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,977][00147] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,974][00144] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,979][00136] Using port 40601 on host... [2024-08-01 15:38:36,977][00148] Using port 41801 on host... [2024-08-01 15:38:36,980][00143] Using port 41301 on host... [2024-08-01 15:38:36,980][00140] Using port 41001 on host... [2024-08-01 15:38:36,979][00144] Using port 41401 on host... [2024-08-01 15:38:36,978][00141] Using port 40901 on host... [2024-08-01 15:38:36,982][00135] Using port 40501 on host... [2024-08-01 15:38:36,983][00147] Using port 41701 on host... [2024-08-01 15:38:36,987][00133] Initialized w:1 v:0 player:0 [2024-08-01 15:38:36,990][00142] Initialized w:9 v:0 player:0 [2024-08-01 15:38:36,992][00142] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,989][00133] Decorrelating experience for 0 frames... [2024-08-01 15:38:36,997][00142] Using port 41201 on host... [2024-08-01 15:38:36,999][00133] Using port 40401 on host... [2024-08-01 15:38:37,002][00137] Initialized w:5 v:0 player:0 [2024-08-01 15:38:37,005][00137] Decorrelating experience for 0 frames... [2024-08-01 15:38:37,009][00137] Using port 40801 on host... [2024-08-01 15:38:37,032][00139] Initialized w:8 v:0 player:0 [2024-08-01 15:38:37,031][00132] Initialized w:0 v:0 player:0 [2024-08-01 15:38:37,037][00139] Decorrelating experience for 0 frames... [2024-08-01 15:38:37,035][00132] Decorrelating experience for 0 frames... [2024-08-01 15:38:37,040][00139] Using port 41101 on host... [2024-08-01 15:38:37,041][00132] Using port 40301 on host... [2024-08-01 15:38:37,068][00145] Initialized w:12 v:0 player:0 [2024-08-01 15:38:37,076][00138] Initialized w:4 v:0 player:0 [2024-08-01 15:38:37,070][00145] Decorrelating experience for 0 frames... [2024-08-01 15:38:37,079][00145] Using port 41501 on host... [2024-08-01 15:38:37,078][00138] Decorrelating experience for 0 frames... [2024-08-01 15:38:37,083][00138] Using port 40701 on host... [2024-08-01 15:38:38,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:38,985][00136] Initialized w:3 v:1 player:0 [2024-08-01 15:38:38,987][00133] Initialized w:1 v:1 player:0 [2024-08-01 15:38:38,989][00144] Initialized w:11 v:1 player:0 [2024-08-01 15:38:38,992][00142] Initialized w:9 v:1 player:0 [2024-08-01 15:38:38,994][00137] Initialized w:5 v:1 player:0 [2024-08-01 15:38:38,988][00136] Decorrelating experience for 32 frames... [2024-08-01 15:38:38,991][00144] Decorrelating experience for 32 frames... [2024-08-01 15:38:38,989][00133] Decorrelating experience for 32 frames... [2024-08-01 15:38:38,999][00146] Initialized w:13 v:1 player:0 [2024-08-01 15:38:38,996][00137] Decorrelating experience for 32 frames... [2024-08-01 15:38:38,997][00142] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,010][00148] Initialized w:15 v:1 player:0 [2024-08-01 15:38:39,005][00146] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,014][00140] Initialized w:7 v:1 player:0 [2024-08-01 15:38:39,017][00132] Initialized w:0 v:1 player:0 [2024-08-01 15:38:39,019][00132] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,012][00148] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,020][00139] Initialized w:8 v:1 player:0 [2024-08-01 15:38:39,016][00140] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,025][00139] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,046][00141] Initialized w:6 v:1 player:0 [2024-08-01 15:38:39,048][00147] Initialized w:14 v:1 player:0 [2024-08-01 15:38:39,051][00135] Initialized w:2 v:1 player:0 [2024-08-01 15:38:39,054][00143] Initialized w:10 v:1 player:0 [2024-08-01 15:38:39,050][00147] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,053][00141] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,058][00135] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,056][00143] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,093][00138] Initialized w:4 v:1 player:0 [2024-08-01 15:38:39,095][00138] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,129][00145] Initialized w:12 v:1 player:0 [2024-08-01 15:38:39,131][00145] Decorrelating experience for 32 frames... [2024-08-01 15:38:39,239][00132] Using port 40302 on host... [2024-08-01 15:38:39,241][00137] Using port 40802 on host... [2024-08-01 15:38:39,248][00133] Using port 40402 on host... [2024-08-01 15:38:39,253][00144] Using port 41402 on host... [2024-08-01 15:38:39,258][00146] Using port 41602 on host... [2024-08-01 15:38:39,255][00136] Using port 40602 on host... [2024-08-01 15:38:39,264][00142] Using port 41202 on host... [2024-08-01 15:38:39,272][00139] Using port 41102 on host... [2024-08-01 15:38:39,279][00148] Using port 41802 on host... [2024-08-01 15:38:39,287][00140] Using port 41002 on host... [2024-08-01 15:38:39,321][00143] Using port 41302 on host... [2024-08-01 15:38:39,332][00138] Using port 40702 on host... [2024-08-01 15:38:39,329][00135] Using port 40502 on host... [2024-08-01 15:38:39,332][00147] Using port 41702 on host... [2024-08-01 15:38:39,334][00141] Using port 40902 on host... [2024-08-01 15:38:39,359][00145] Using port 41502 on host... [2024-08-01 15:38:41,227][00133] Initialized w:1 v:2 player:0 [2024-08-01 15:38:41,235][00144] Initialized w:11 v:2 player:0 [2024-08-01 15:38:41,232][00133] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,237][00144] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,242][00132] Initialized w:0 v:2 player:0 [2024-08-01 15:38:41,244][00132] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,245][00146] Initialized w:13 v:2 player:0 [2024-08-01 15:38:41,248][00142] Initialized w:9 v:2 player:0 [2024-08-01 15:38:41,252][00137] Initialized w:5 v:2 player:0 [2024-08-01 15:38:41,255][00136] Initialized w:3 v:2 player:0 [2024-08-01 15:38:41,251][00146] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,256][00136] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,250][00142] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,254][00137] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,270][00139] Initialized w:8 v:2 player:0 [2024-08-01 15:38:41,272][00139] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,314][00148] Initialized w:15 v:2 player:0 [2024-08-01 15:38:41,316][00148] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,331][00140] Initialized w:7 v:2 player:0 [2024-08-01 15:38:41,333][00140] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,357][00147] Initialized w:14 v:2 player:0 [2024-08-01 15:38:41,360][00147] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,358][00135] Initialized w:2 v:2 player:0 [2024-08-01 15:38:41,365][00135] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,371][00145] Initialized w:12 v:2 player:0 [2024-08-01 15:38:41,374][00138] Initialized w:4 v:2 player:0 [2024-08-01 15:38:41,373][00145] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,382][00143] Initialized w:10 v:2 player:0 [2024-08-01 15:38:41,383][00143] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,378][00138] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,385][00141] Initialized w:6 v:2 player:0 [2024-08-01 15:38:41,394][00141] Decorrelating experience for 64 frames... [2024-08-01 15:38:41,690][00132] Using port 40303 on host... [2024-08-01 15:38:41,707][00144] Using port 41403 on host... [2024-08-01 15:38:41,709][00136] Using port 40603 on host... [2024-08-01 15:38:41,712][00142] Using port 41203 on host... [2024-08-01 15:38:41,719][00133] Using port 40403 on host... [2024-08-01 15:38:41,725][00139] Using port 41103 on host... [2024-08-01 15:38:41,728][00146] Using port 41603 on host... [2024-08-01 15:38:41,744][00137] Using port 40803 on host... [2024-08-01 15:38:41,802][00148] Using port 41803 on host... [2024-08-01 15:38:41,814][00140] Using port 41003 on host... [2024-08-01 15:38:41,829][00145] Using port 41503 on host... [2024-08-01 15:38:41,832][00138] Using port 40703 on host... [2024-08-01 15:38:41,844][00147] Using port 41703 on host... [2024-08-01 15:38:41,873][00135] Using port 40503 on host... [2024-08-01 15:38:41,880][00143] Using port 41303 on host... [2024-08-01 15:38:41,884][00141] Using port 40903 on host... [2024-08-01 15:38:43,780][00142] Initialized w:9 v:3 player:0 [2024-08-01 15:38:43,785][00146] Initialized w:13 v:3 player:0 [2024-08-01 15:38:43,788][00132] Initialized w:0 v:3 player:0 [2024-08-01 15:38:43,788][00142] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,790][00132] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,793][00146] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,797][00139] Initialized w:8 v:3 player:0 [2024-08-01 15:38:43,801][00139] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,801][00133] Initialized w:1 v:3 player:0 [2024-08-01 15:38:43,803][00133] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,804][00136] Initialized w:3 v:3 player:0 [2024-08-01 15:38:43,806][00136] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,808][00144] Initialized w:11 v:3 player:0 [2024-08-01 15:38:43,809][00144] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:43,850][00137] Initialized w:5 v:3 player:0 [2024-08-01 15:38:43,852][00137] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,885][00148] Initialized w:15 v:3 player:0 [2024-08-01 15:38:43,891][00148] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,906][00138] Initialized w:4 v:3 player:0 [2024-08-01 15:38:43,908][00138] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,916][00140] Initialized w:7 v:3 player:0 [2024-08-01 15:38:43,922][00140] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,936][00145] Initialized w:12 v:3 player:0 [2024-08-01 15:38:43,938][00145] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,964][00147] Initialized w:14 v:3 player:0 [2024-08-01 15:38:43,966][00147] Decorrelating experience for 96 frames... [2024-08-01 15:38:43,985][00135] Initialized w:2 v:3 player:0 [2024-08-01 15:38:43,987][00135] Decorrelating experience for 96 frames... [2024-08-01 15:38:44,014][00141] Initialized w:6 v:3 player:0 [2024-08-01 15:38:44,016][00141] Decorrelating experience for 96 frames... [2024-08-01 15:38:44,039][00143] Initialized w:10 v:3 player:0 [2024-08-01 15:38:44,041][00143] Decorrelating experience for 96 frames... [2024-08-01 15:38:44,441][00132] Using port 40304 on host... [2024-08-01 15:38:44,447][00133] Using port 40404 on host... [2024-08-01 15:38:44,475][00136] Using port 40604 on host... [2024-08-01 15:38:44,487][00139] Using port 41104 on host... [2024-08-01 15:38:44,484][00144] Using port 41404 on host... [2024-08-01 15:38:44,484][00142] Using port 41204 on host... [2024-08-01 15:38:44,492][00146] Using port 41604 on host... [2024-08-01 15:38:44,531][00137] Using port 40804 on host... [2024-08-01 15:38:44,566][00148] Using port 41804 on host... [2024-08-01 15:38:44,577][00140] Using port 41004 on host... [2024-08-01 15:38:44,600][00138] Using port 40704 on host... [2024-08-01 15:38:44,621][00145] Using port 41504 on host... [2024-08-01 15:38:44,682][00147] Using port 41704 on host... [2024-08-01 15:38:44,730][00135] Using port 40504 on host... [2024-08-01 15:38:44,747][00141] Using port 40904 on host... [2024-08-01 15:38:44,752][00143] Using port 41304 on host... [2024-08-01 15:38:46,711][00133] Initialized w:1 v:4 player:0 [2024-08-01 15:38:46,718][00133] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,738][00142] Initialized w:9 v:4 player:0 [2024-08-01 15:38:46,742][00142] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,776][00146] Initialized w:13 v:4 player:0 [2024-08-01 15:38:46,778][00146] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,810][00137] Initialized w:5 v:4 player:0 [2024-08-01 15:38:46,812][00137] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,835][00144] Initialized w:11 v:4 player:0 [2024-08-01 15:38:46,837][00144] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,838][00136] Initialized w:3 v:4 player:0 [2024-08-01 15:38:46,845][00136] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,919][00140] Initialized w:7 v:4 player:0 [2024-08-01 15:38:46,921][00140] Decorrelating experience for 128 frames... [2024-08-01 15:38:46,957][00148] Initialized w:15 v:4 player:0 [2024-08-01 15:38:46,958][00148] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,135][00147] Initialized w:14 v:4 player:0 [2024-08-01 15:38:47,137][00147] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,198][00143] Initialized w:10 v:4 player:0 [2024-08-01 15:38:47,204][00141] Initialized w:6 v:4 player:0 [2024-08-01 15:38:47,203][00143] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,206][00141] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,228][00135] Initialized w:2 v:4 player:0 [2024-08-01 15:38:47,233][00135] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,577][00132] Initialized w:0 v:4 player:0 [2024-08-01 15:38:47,580][00132] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,641][00139] Initialized w:8 v:4 player:0 [2024-08-01 15:38:47,648][00139] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,753][00138] Initialized w:4 v:4 player:0 [2024-08-01 15:38:47,756][00138] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,774][00145] Initialized w:12 v:4 player:0 [2024-08-01 15:38:47,778][00145] Decorrelating experience for 128 frames... [2024-08-01 15:38:47,888][00144] Using port 41405 on host... [2024-08-01 15:38:47,890][00136] Using port 40605 on host... [2024-08-01 15:38:47,910][00140] Using port 41005 on host... [2024-08-01 15:38:47,964][00148] Using port 41805 on host... [2024-08-01 15:38:48,120][00147] Using port 41705 on host... [2024-08-01 15:38:48,177][00143] Using port 41305 on host... [2024-08-01 15:38:48,208][00141] Using port 40905 on host... [2024-08-01 15:38:48,250][00135] Using port 40505 on host... [2024-08-01 15:38:48,360][00133] Using port 40405 on host... [2024-08-01 15:38:48,374][00142] Using port 41205 on host... [2024-08-01 15:38:48,389][00146] Using port 41605 on host... [2024-08-01 15:38:48,425][00137] Using port 40805 on host... [2024-08-01 15:38:48,562][00132] Using port 40305 on host... [2024-08-01 15:38:48,688][00139] Using port 41105 on host... [2024-08-01 15:38:48,738][00138] Using port 40705 on host... [2024-08-01 15:38:48,763][00145] Using port 41505 on host... [2024-08-01 15:38:48,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:49,998][00136] Initialized w:3 v:5 player:0 [2024-08-01 15:38:50,001][00144] Initialized w:11 v:5 player:0 [2024-08-01 15:38:50,006][00144] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,008][00136] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,033][00140] Initialized w:7 v:5 player:0 [2024-08-01 15:38:50,039][00140] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,180][00148] Initialized w:15 v:5 player:0 [2024-08-01 15:38:50,182][00148] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,293][00147] Initialized w:14 v:5 player:0 [2024-08-01 15:38:50,297][00147] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,333][00143] Initialized w:10 v:5 player:0 [2024-08-01 15:38:50,336][00143] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,414][00135] Initialized w:2 v:5 player:0 [2024-08-01 15:38:50,416][00141] Initialized w:6 v:5 player:0 [2024-08-01 15:38:50,418][00141] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,423][00135] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,554][00142] Initialized w:9 v:5 player:0 [2024-08-01 15:38:50,559][00133] Initialized w:1 v:5 player:0 [2024-08-01 15:38:50,556][00142] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,561][00133] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,604][00146] Initialized w:13 v:5 player:0 [2024-08-01 15:38:50,607][00137] Initialized w:5 v:5 player:0 [2024-08-01 15:38:50,611][00146] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,609][00137] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,800][00132] Initialized w:0 v:5 player:0 [2024-08-01 15:38:50,802][00132] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,932][00139] Initialized w:8 v:5 player:0 [2024-08-01 15:38:50,934][00139] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,942][00138] Initialized w:4 v:5 player:0 [2024-08-01 15:38:50,944][00138] Decorrelating experience for 160 frames... [2024-08-01 15:38:50,973][00145] Initialized w:12 v:5 player:0 [2024-08-01 15:38:50,980][00145] Decorrelating experience for 160 frames... [2024-08-01 15:38:51,245][00136] Using port 40606 on host... [2024-08-01 15:38:51,260][00144] Using port 41406 on host... [2024-08-01 15:38:51,265][00140] Using port 41006 on host... [2024-08-01 15:38:51,378][00148] Using port 41806 on host... [2024-08-01 15:38:51,555][00147] Using port 41706 on host... [2024-08-01 15:38:51,698][00143] Using port 41306 on host... [2024-08-01 15:38:51,743][00135] Using port 40506 on host... [2024-08-01 15:38:51,752][00141] Using port 40906 on host... [2024-08-01 15:38:51,846][00142] Using port 41206 on host... [2024-08-01 15:38:51,865][00133] Using port 40406 on host... [2024-08-01 15:38:51,869][00137] Using port 40806 on host... [2024-08-01 15:38:51,877][00146] Using port 41606 on host... [2024-08-01 15:38:51,894][00132] Using port 40306 on host... [2024-08-01 15:38:52,142][00138] Using port 40706 on host... [2024-08-01 15:38:52,144][00139] Using port 41106 on host... [2024-08-01 15:38:52,153][00145] Using port 41506 on host... [2024-08-01 15:38:53,430][00140] Initialized w:7 v:6 player:0 [2024-08-01 15:38:53,434][00140] Decorrelating experience for 192 frames... [2024-08-01 15:38:53,444][00144] Initialized w:11 v:6 player:0 [2024-08-01 15:38:53,447][00144] Decorrelating experience for 192 frames... [2024-08-01 15:38:53,470][00136] Initialized w:3 v:6 player:0 [2024-08-01 15:38:53,475][00136] Decorrelating experience for 192 frames... [2024-08-01 15:38:53,705][00148] Initialized w:15 v:6 player:0 [2024-08-01 15:38:53,707][00148] Decorrelating experience for 192 frames... [2024-08-01 15:38:53,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:53,904][00147] Initialized w:14 v:6 player:0 [2024-08-01 15:38:53,920][00147] Decorrelating experience for 192 frames... [2024-08-01 15:38:53,980][00143] Initialized w:10 v:6 player:0 [2024-08-01 15:38:53,982][00143] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,041][00141] Initialized w:6 v:6 player:0 [2024-08-01 15:38:54,044][00141] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,058][00142] Initialized w:9 v:6 player:0 [2024-08-01 15:38:54,058][00135] Initialized w:2 v:6 player:0 [2024-08-01 15:38:54,061][00142] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,070][00135] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,074][00146] Initialized w:13 v:6 player:0 [2024-08-01 15:38:54,082][00133] Initialized w:1 v:6 player:0 [2024-08-01 15:38:54,084][00146] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,083][00133] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,116][00137] Initialized w:5 v:6 player:0 [2024-08-01 15:38:54,118][00137] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,243][00132] Initialized w:0 v:6 player:0 [2024-08-01 15:38:54,244][00132] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,407][00139] Initialized w:8 v:6 player:0 [2024-08-01 15:38:54,419][00138] Initialized w:4 v:6 player:0 [2024-08-01 15:38:54,415][00139] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,427][00138] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,439][00145] Initialized w:12 v:6 player:0 [2024-08-01 15:38:54,445][00145] Decorrelating experience for 192 frames... [2024-08-01 15:38:54,972][00144] Using port 41407 on host... [2024-08-01 15:38:54,989][00136] Using port 40607 on host... [2024-08-01 15:38:54,997][00140] Using port 41007 on host... [2024-08-01 15:38:55,178][00148] Using port 41807 on host... [2024-08-01 15:38:55,347][00147] Using port 41707 on host... [2024-08-01 15:38:55,405][00143] Using port 41307 on host... [2024-08-01 15:38:55,467][00141] Using port 40907 on host... [2024-08-01 15:38:55,474][00135] Using port 40507 on host... [2024-08-01 15:38:55,682][00133] Using port 40407 on host... [2024-08-01 15:38:55,689][00146] Using port 41607 on host... [2024-08-01 15:38:55,697][00137] Using port 40807 on host... [2024-08-01 15:38:55,707][00142] Using port 41207 on host... [2024-08-01 15:38:55,715][00132] Using port 40307 on host... [2024-08-01 15:38:55,920][00145] Using port 41507 on host... [2024-08-01 15:38:55,936][00139] Using port 41107 on host... [2024-08-01 15:38:55,956][00138] Using port 40707 on host... [2024-08-01 15:38:57,094][00140] Initialized w:7 v:7 player:0 [2024-08-01 15:38:57,098][00144] Initialized w:11 v:7 player:0 [2024-08-01 15:38:57,105][00144] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,110][00140] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,121][00136] Initialized w:3 v:7 player:0 [2024-08-01 15:38:57,124][00136] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,386][00148] Initialized w:15 v:7 player:0 [2024-08-01 15:38:57,389][00148] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,454][00147] Initialized w:14 v:7 player:0 [2024-08-01 15:38:57,460][00147] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,593][00143] Initialized w:10 v:7 player:0 [2024-08-01 15:38:57,595][00143] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,613][00141] Initialized w:6 v:7 player:0 [2024-08-01 15:38:57,616][00135] Initialized w:2 v:7 player:0 [2024-08-01 15:38:57,617][00135] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,615][00141] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,863][00133] Initialized w:1 v:7 player:0 [2024-08-01 15:38:57,866][00133] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,887][00137] Initialized w:5 v:7 player:0 [2024-08-01 15:38:57,889][00142] Initialized w:9 v:7 player:0 [2024-08-01 15:38:57,893][00146] Initialized w:13 v:7 player:0 [2024-08-01 15:38:57,897][00137] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,892][00142] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,895][00146] Decorrelating experience for 224 frames... [2024-08-01 15:38:57,977][00132] Initialized w:0 v:7 player:0 [2024-08-01 15:38:57,984][00132] Decorrelating experience for 224 frames... [2024-08-01 15:38:58,143][00139] Initialized w:8 v:7 player:0 [2024-08-01 15:38:58,148][00145] Initialized w:12 v:7 player:0 [2024-08-01 15:38:58,145][00139] Decorrelating experience for 224 frames... [2024-08-01 15:38:58,154][00138] Initialized w:4 v:7 player:0 [2024-08-01 15:38:58,151][00145] Decorrelating experience for 224 frames... [2024-08-01 15:38:58,156][00138] Decorrelating experience for 224 frames... [2024-08-01 15:38:58,735][00144] Using port 41408 on host... [2024-08-01 15:38:58,836][00136] Using port 40608 on host... [2024-08-01 15:38:58,839][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:38:58,864][00140] Using port 41008 on host... [2024-08-01 15:38:59,114][00148] Using port 41808 on host... [2024-08-01 15:38:59,190][00147] Using port 41708 on host... [2024-08-01 15:38:59,317][00141] Using port 40908 on host... [2024-08-01 15:38:59,338][00135] Using port 40508 on host... [2024-08-01 15:38:59,363][00143] Using port 41308 on host... [2024-08-01 15:38:59,609][00142] Using port 41208 on host... [2024-08-01 15:38:59,654][00146] Using port 41608 on host... [2024-08-01 15:38:59,659][00132] Using port 40308 on host... [2024-08-01 15:38:59,673][00133] Using port 40408 on host... [2024-08-01 15:38:59,686][00137] Using port 40808 on host... [2024-08-01 15:38:59,816][00145] Using port 41508 on host... [2024-08-01 15:38:59,878][00139] Using port 41108 on host... [2024-08-01 15:38:59,886][00138] Using port 40708 on host... [2024-08-01 15:39:00,880][00144] Initialized w:11 v:8 player:0 [2024-08-01 15:39:00,882][00144] Decorrelating experience for 256 frames... [2024-08-01 15:39:00,967][00136] Initialized w:3 v:8 player:0 [2024-08-01 15:39:00,970][00136] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,002][00140] Initialized w:7 v:8 player:0 [2024-08-01 15:39:01,006][00140] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,367][00148] Initialized w:15 v:8 player:0 [2024-08-01 15:39:01,369][00148] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,384][00147] Initialized w:14 v:8 player:0 [2024-08-01 15:39:01,397][00147] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,500][00141] Initialized w:6 v:8 player:0 [2024-08-01 15:39:01,502][00135] Initialized w:2 v:8 player:0 [2024-08-01 15:39:01,507][00135] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,509][00141] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,596][00143] Initialized w:10 v:8 player:0 [2024-08-01 15:39:01,599][00143] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,880][00142] Initialized w:9 v:8 player:0 [2024-08-01 15:39:01,887][00142] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,940][00133] Initialized w:1 v:8 player:0 [2024-08-01 15:39:01,942][00133] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,957][00146] Initialized w:13 v:8 player:0 [2024-08-01 15:39:01,963][00146] Decorrelating experience for 256 frames... [2024-08-01 15:39:01,978][00132] Initialized w:0 v:8 player:0 [2024-08-01 15:39:01,980][00132] Decorrelating experience for 256 frames... [2024-08-01 15:39:02,011][00137] Initialized w:5 v:8 player:0 [2024-08-01 15:39:02,014][00137] Decorrelating experience for 256 frames... [2024-08-01 15:39:02,132][00145] Initialized w:12 v:8 player:0 [2024-08-01 15:39:02,134][00145] Decorrelating experience for 256 frames... [2024-08-01 15:39:02,177][00138] Initialized w:4 v:8 player:0 [2024-08-01 15:39:02,182][00138] Decorrelating experience for 256 frames... [2024-08-01 15:39:02,191][00139] Initialized w:8 v:8 player:0 [2024-08-01 15:39:02,195][00139] Decorrelating experience for 256 frames... [2024-08-01 15:39:02,884][00144] Using port 41409 on host... [2024-08-01 15:39:02,970][00136] Using port 40609 on host... [2024-08-01 15:39:03,059][00140] Using port 41009 on host... [2024-08-01 15:39:03,357][00147] Using port 41709 on host... [2024-08-01 15:39:03,359][00135] Using port 40509 on host... [2024-08-01 15:39:03,357][00148] Using port 41809 on host... [2024-08-01 15:39:03,448][00141] Using port 40909 on host... [2024-08-01 15:39:03,584][00143] Using port 41309 on host... [2024-08-01 15:39:03,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:03,872][00132] Using port 40309 on host... [2024-08-01 15:39:03,897][00133] Using port 40409 on host... [2024-08-01 15:39:03,916][00142] Using port 41209 on host... [2024-08-01 15:39:03,958][00146] Using port 41609 on host... [2024-08-01 15:39:03,982][00137] Using port 40809 on host... [2024-08-01 15:39:04,187][00145] Using port 41509 on host... [2024-08-01 15:39:04,193][00139] Using port 41109 on host... [2024-08-01 15:39:04,205][00138] Using port 40709 on host... [2024-08-01 15:39:05,075][00144] Initialized w:11 v:9 player:0 [2024-08-01 15:39:05,077][00144] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,105][00136] Initialized w:3 v:9 player:0 [2024-08-01 15:39:05,107][00136] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,227][00140] Initialized w:7 v:9 player:0 [2024-08-01 15:39:05,229][00140] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,566][00135] Initialized w:2 v:9 player:0 [2024-08-01 15:39:05,571][00135] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,611][00147] Initialized w:14 v:9 player:0 [2024-08-01 15:39:05,618][00147] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,679][00148] Initialized w:15 v:9 player:0 [2024-08-01 15:39:05,681][00148] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,698][00141] Initialized w:6 v:9 player:0 [2024-08-01 15:39:05,701][00141] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,857][00143] Initialized w:10 v:9 player:0 [2024-08-01 15:39:05,866][00143] Decorrelating experience for 288 frames... [2024-08-01 15:39:05,999][00133] Initialized w:1 v:9 player:0 [2024-08-01 15:39:06,001][00142] Initialized w:9 v:9 player:0 [2024-08-01 15:39:06,003][00133] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,004][00142] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,060][00146] Initialized w:13 v:9 player:0 [2024-08-01 15:39:06,063][00146] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,170][00137] Initialized w:5 v:9 player:0 [2024-08-01 15:39:06,172][00137] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,277][00132] Initialized w:0 v:9 player:0 [2024-08-01 15:39:06,279][00132] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,488][00145] Initialized w:12 v:9 player:0 [2024-08-01 15:39:06,494][00139] Initialized w:8 v:9 player:0 [2024-08-01 15:39:06,498][00145] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,498][00139] Decorrelating experience for 288 frames... [2024-08-01 15:39:06,535][00138] Initialized w:4 v:9 player:0 [2024-08-01 15:39:06,537][00138] Decorrelating experience for 288 frames... [2024-08-01 15:39:07,199][00144] Using port 41410 on host... [2024-08-01 15:39:07,362][00136] Using port 40610 on host... [2024-08-01 15:39:07,457][00140] Using port 41010 on host... [2024-08-01 15:39:07,713][00135] Using port 40510 on host... [2024-08-01 15:39:07,751][00148] Using port 41810 on host... [2024-08-01 15:39:07,773][00147] Using port 41710 on host... [2024-08-01 15:39:07,927][00141] Using port 40910 on host... [2024-08-01 15:39:08,028][00143] Using port 41310 on host... [2024-08-01 15:39:08,161][00142] Using port 41210 on host... [2024-08-01 15:39:08,173][00133] Using port 40410 on host... [2024-08-01 15:39:08,224][00146] Using port 41610 on host... [2024-08-01 15:39:08,309][00137] Using port 40810 on host... [2024-08-01 15:39:08,387][00132] Using port 40310 on host... [2024-08-01 15:39:08,694][00139] Using port 41110 on host... [2024-08-01 15:39:08,739][00145] Using port 41510 on host... [2024-08-01 15:39:08,748][00138] Using port 40710 on host... [2024-08-01 15:39:08,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:09,424][00144] Initialized w:11 v:10 player:0 [2024-08-01 15:39:09,426][00144] Decorrelating experience for 320 frames... [2024-08-01 15:39:09,494][00136] Initialized w:3 v:10 player:0 [2024-08-01 15:39:09,495][00136] Decorrelating experience for 320 frames... [2024-08-01 15:39:09,609][00140] Initialized w:7 v:10 player:0 [2024-08-01 15:39:09,611][00140] Decorrelating experience for 320 frames... [2024-08-01 15:39:09,793][00135] Initialized w:2 v:10 player:0 [2024-08-01 15:39:09,801][00135] Decorrelating experience for 320 frames... [2024-08-01 15:39:09,816][00147] Initialized w:14 v:10 player:0 [2024-08-01 15:39:09,817][00147] Decorrelating experience for 320 frames... [2024-08-01 15:39:09,964][00141] Initialized w:6 v:10 player:0 [2024-08-01 15:39:09,967][00141] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,025][00148] Initialized w:15 v:10 player:0 [2024-08-01 15:39:10,028][00148] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,116][00143] Initialized w:10 v:10 player:0 [2024-08-01 15:39:10,118][00143] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,193][00142] Initialized w:9 v:10 player:0 [2024-08-01 15:39:10,194][00142] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,202][00133] Initialized w:1 v:10 player:0 [2024-08-01 15:39:10,203][00133] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,235][00146] Initialized w:13 v:10 player:0 [2024-08-01 15:39:10,241][00146] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,328][00137] Initialized w:5 v:10 player:0 [2024-08-01 15:39:10,330][00137] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,549][00132] Initialized w:0 v:10 player:0 [2024-08-01 15:39:10,551][00132] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,781][00139] Initialized w:8 v:10 player:0 [2024-08-01 15:39:10,784][00139] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,810][00145] Initialized w:12 v:10 player:0 [2024-08-01 15:39:10,813][00145] Decorrelating experience for 320 frames... [2024-08-01 15:39:10,822][00138] Initialized w:4 v:10 player:0 [2024-08-01 15:39:10,824][00138] Decorrelating experience for 320 frames... [2024-08-01 15:39:11,505][00144] Using port 41411 on host... [2024-08-01 15:39:11,692][00140] Using port 41011 on host... [2024-08-01 15:39:11,743][00136] Using port 40611 on host... [2024-08-01 15:39:11,937][00135] Using port 40511 on host... [2024-08-01 15:39:12,013][00148] Using port 41811 on host... [2024-08-01 15:39:12,025][00147] Using port 41711 on host... [2024-08-01 15:39:12,155][00141] Using port 40911 on host... [2024-08-01 15:39:12,211][00143] Using port 41311 on host... [2024-08-01 15:39:12,301][00133] Using port 40411 on host... [2024-08-01 15:39:12,364][00142] Using port 41211 on host... [2024-08-01 15:39:12,375][00146] Using port 41611 on host... [2024-08-01 15:39:12,439][00137] Using port 40811 on host... [2024-08-01 15:39:12,790][00132] Using port 40311 on host... [2024-08-01 15:39:12,923][00139] Using port 41111 on host... [2024-08-01 15:39:12,950][00138] Using port 40711 on host... [2024-08-01 15:39:12,974][00145] Using port 41511 on host... [2024-08-01 15:39:13,605][00144] Initialized w:11 v:11 player:0 [2024-08-01 15:39:13,607][00144] Decorrelating experience for 352 frames... [2024-08-01 15:39:13,789][00140] Initialized w:7 v:11 player:0 [2024-08-01 15:39:13,791][00140] Decorrelating experience for 352 frames... [2024-08-01 15:39:13,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:13,872][00136] Initialized w:3 v:11 player:0 [2024-08-01 15:39:13,874][00136] Decorrelating experience for 352 frames... [2024-08-01 15:39:13,939][00135] Initialized w:2 v:11 player:0 [2024-08-01 15:39:13,941][00135] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,002][00147] Initialized w:14 v:11 player:0 [2024-08-01 15:39:14,003][00147] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,164][00148] Initialized w:15 v:11 player:0 [2024-08-01 15:39:14,172][00141] Initialized w:6 v:11 player:0 [2024-08-01 15:39:14,167][00148] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,181][00143] Initialized w:10 v:11 player:0 [2024-08-01 15:39:14,177][00141] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,183][00143] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,367][00133] Initialized w:1 v:11 player:0 [2024-08-01 15:39:14,371][00133] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,403][00142] Initialized w:9 v:11 player:0 [2024-08-01 15:39:14,405][00142] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,411][00146] Initialized w:13 v:11 player:0 [2024-08-01 15:39:14,417][00146] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,521][00137] Initialized w:5 v:11 player:0 [2024-08-01 15:39:14,523][00137] Decorrelating experience for 352 frames... [2024-08-01 15:39:14,943][00132] Initialized w:0 v:11 player:0 [2024-08-01 15:39:14,945][00132] Decorrelating experience for 352 frames... [2024-08-01 15:39:15,014][00138] Initialized w:4 v:11 player:0 [2024-08-01 15:39:15,015][00138] Decorrelating experience for 352 frames... [2024-08-01 15:39:15,017][00139] Initialized w:8 v:11 player:0 [2024-08-01 15:39:15,018][00139] Decorrelating experience for 352 frames... [2024-08-01 15:39:15,094][00145] Initialized w:12 v:11 player:0 [2024-08-01 15:39:15,096][00145] Decorrelating experience for 352 frames... [2024-08-01 15:39:16,255][00144] Port 41412 is available [2024-08-01 15:39:16,262][00144] Using port 41412 [2024-08-01 15:39:16,289][00136] Port 40612 is available [2024-08-01 15:39:16,294][00136] Using port 40612 [2024-08-01 15:39:16,427][00144] Port 41413 is available [2024-08-01 15:39:16,429][00144] Using port 41413 [2024-08-01 15:39:16,451][00140] Port 41012 is available [2024-08-01 15:39:16,455][00140] Using port 41012 [2024-08-01 15:39:16,454][00136] Port 40613 is available [2024-08-01 15:39:16,466][00136] Using port 40613 [2024-08-01 15:39:16,548][00135] Port 40512 is available [2024-08-01 15:39:16,550][00135] Using port 40512 [2024-08-01 15:39:16,587][00147] Port 41712 is available [2024-08-01 15:39:16,588][00147] Using port 41712 [2024-08-01 15:39:16,589][00144] Port 41414 is available [2024-08-01 15:39:16,590][00144] Using port 41414 [2024-08-01 15:39:16,619][00140] Port 41013 is available [2024-08-01 15:39:16,621][00136] Port 40614 is available [2024-08-01 15:39:16,619][00140] Using port 41013 [2024-08-01 15:39:16,621][00136] Using port 40614 [2024-08-01 15:39:16,694][00135] Port 40513 is available [2024-08-01 15:39:16,699][00135] Using port 40513 [2024-08-01 15:39:16,706][00143] Port 41312 is available [2024-08-01 15:39:16,712][00143] Using port 41312 [2024-08-01 15:39:16,726][00147] Port 41713 is available [2024-08-01 15:39:16,733][00147] Using port 41713 [2024-08-01 15:39:16,741][00144] Port 41415 is available [2024-08-01 15:39:16,743][00141] Port 40912 is available [2024-08-01 15:39:16,746][00141] Using port 40912 [2024-08-01 15:39:16,742][00144] Using port 41415 [2024-08-01 15:39:16,766][00140] Port 41014 is available [2024-08-01 15:39:16,769][00140] Using port 41014 [2024-08-01 15:39:16,775][00136] Port 40615 is available [2024-08-01 15:39:16,776][00136] Using port 40615 [2024-08-01 15:39:16,780][00148] Port 41812 is available [2024-08-01 15:39:16,785][00148] Using port 41812 [2024-08-01 15:39:16,838][00135] Port 40514 is available [2024-08-01 15:39:16,844][00135] Using port 40514 [2024-08-01 15:39:16,843][00143] Port 41313 is available [2024-08-01 15:39:16,856][00143] Using port 41313 [2024-08-01 15:39:16,870][00147] Port 41714 is available [2024-08-01 15:39:16,873][00147] Using port 41714 [2024-08-01 15:39:16,883][00141] Port 40913 is available [2024-08-01 15:39:16,892][00141] Using port 40913 [2024-08-01 15:39:16,905][00144] Port 41416 is available [2024-08-01 15:39:16,909][00144] Using port 41416 [2024-08-01 15:39:16,924][00140] Port 41015 is available [2024-08-01 15:39:16,923][00136] Port 40616 is available [2024-08-01 15:39:16,925][00140] Using port 41015 [2024-08-01 15:39:16,925][00136] Using port 40616 [2024-08-01 15:39:16,931][00148] Port 41813 is available [2024-08-01 15:39:16,938][00148] Using port 41813 [2024-08-01 15:39:16,969][00133] Port 40412 is available [2024-08-01 15:39:16,976][00133] Using port 40412 [2024-08-01 15:39:16,983][00142] Port 41212 is available [2024-08-01 15:39:16,982][00135] Port 40515 is available [2024-08-01 15:39:16,989][00135] Using port 40515 [2024-08-01 15:39:16,989][00142] Using port 41212 [2024-08-01 15:39:16,993][00143] Port 41314 is available [2024-08-01 15:39:16,997][00143] Using port 41314 [2024-08-01 15:39:17,009][00147] Port 41715 is available [2024-08-01 15:39:17,019][00147] Using port 41715 [2024-08-01 15:39:17,027][00141] Port 40914 is available [2024-08-01 15:39:17,034][00141] Using port 40914 [2024-08-01 15:39:17,033][00146] Port 41612 is available [2024-08-01 15:39:17,044][00146] Using port 41612 [2024-08-01 15:39:17,056][00144] Port 41417 is available [2024-08-01 15:39:17,056][00144] Using port 41417 [2024-08-01 15:39:17,077][00140] Port 41016 is available [2024-08-01 15:39:17,080][00140] Using port 41016 [2024-08-01 15:39:17,074][00136] Port 40617 is available [2024-08-01 15:39:17,083][00136] Using port 40617 [2024-08-01 15:39:17,085][00148] Port 41814 is available [2024-08-01 15:39:17,086][00148] Using port 41814 [2024-08-01 15:39:17,118][00137] Port 40812 is available [2024-08-01 15:39:17,122][00137] Using port 40812 [2024-08-01 15:39:17,119][00133] Port 40413 is available [2024-08-01 15:39:17,127][00133] Using port 40413 [2024-08-01 15:39:17,125][00135] Port 40516 is available [2024-08-01 15:39:17,133][00135] Using port 40516 [2024-08-01 15:39:17,133][00142] Port 41213 is available [2024-08-01 15:39:17,137][00142] Using port 41213 [2024-08-01 15:39:17,136][00143] Port 41315 is available [2024-08-01 15:39:17,146][00143] Using port 41315 [2024-08-01 15:39:17,158][00147] Port 41716 is available [2024-08-01 15:39:17,161][00147] Using port 41716 [2024-08-01 15:39:17,170][00141] Port 40915 is available [2024-08-01 15:39:17,181][00141] Using port 40915 [2024-08-01 15:39:17,184][00146] Port 41613 is available [2024-08-01 15:39:17,193][00146] Using port 41613 [2024-08-01 15:39:17,209][00144] Port 41418 is available [2024-08-01 15:39:17,215][00144] Using port 41418 [2024-08-01 15:39:17,227][00140] Port 41017 is available [2024-08-01 15:39:17,231][00140] Using port 41017 [2024-08-01 15:39:17,224][00136] Port 40618 is available [2024-08-01 15:39:17,232][00136] Using port 40618 [2024-08-01 15:39:17,239][00148] Port 41815 is available [2024-08-01 15:39:17,241][00148] Using port 41815 [2024-08-01 15:39:17,272][00133] Port 40414 is available [2024-08-01 15:39:17,272][00133] Using port 40414 [2024-08-01 15:39:17,266][00137] Port 40813 is available [2024-08-01 15:39:17,271][00135] Port 40517 is available [2024-08-01 15:39:17,275][00137] Using port 40813 [2024-08-01 15:39:17,278][00135] Using port 40517 [2024-08-01 15:39:17,279][00143] Port 41316 is available [2024-08-01 15:39:17,284][00142] Port 41214 is available [2024-08-01 15:39:17,283][00143] Using port 41316 [2024-08-01 15:39:17,284][00142] Using port 41214 [2024-08-01 15:39:17,299][00147] Port 41717 is available [2024-08-01 15:39:17,300][00147] Using port 41717 [2024-08-01 15:39:17,328][00141] Port 40916 is available [2024-08-01 15:39:17,329][00141] Using port 40916 [2024-08-01 15:39:17,334][00146] Port 41614 is available [2024-08-01 15:39:17,344][00146] Using port 41614 [2024-08-01 15:39:17,360][00144] Port 41419 is available [2024-08-01 15:39:17,365][00144] Using port 41419 [2024-08-01 15:39:17,380][00140] Port 41018 is available [2024-08-01 15:39:17,381][00140] Using port 41018 [2024-08-01 15:39:17,385][00136] Port 40619 is available [2024-08-01 15:39:17,389][00136] Using port 40619 [2024-08-01 15:39:17,393][00148] Port 41816 is available [2024-08-01 15:39:17,396][00148] Using port 41816 [2024-08-01 15:39:17,419][00133] Port 40415 is available [2024-08-01 15:39:17,419][00135] Port 40518 is available [2024-08-01 15:39:17,425][00133] Using port 40415 [2024-08-01 15:39:17,425][00135] Using port 40518 [2024-08-01 15:39:17,426][00143] Port 41317 is available [2024-08-01 15:39:17,430][00143] Using port 41317 [2024-08-01 15:39:17,425][00137] Port 40814 is available [2024-08-01 15:39:17,430][00137] Using port 40814 [2024-08-01 15:39:17,432][00142] Port 41215 is available [2024-08-01 15:39:17,437][00142] Using port 41215 [2024-08-01 15:39:17,448][00147] Port 41718 is available [2024-08-01 15:39:17,454][00147] Using port 41718 [2024-08-01 15:39:17,462][00141] Port 40917 is available [2024-08-01 15:39:17,472][00141] Using port 40917 [2024-08-01 15:39:17,493][00146] Port 41615 is available [2024-08-01 15:39:17,493][00146] Using port 41615 [2024-08-01 15:39:17,489][00132] Port 40312 is available [2024-08-01 15:39:17,497][00132] Using port 40312 [2024-08-01 15:39:17,519][00144] Port 41420 is available [2024-08-01 15:39:17,520][00144] Using port 41420 [2024-08-01 15:39:17,534][00140] Port 41019 is available [2024-08-01 15:39:17,534][00140] Using port 41019 [2024-08-01 15:39:17,545][00136] Port 40620 is available [2024-08-01 15:39:17,545][00136] Using port 40620 [2024-08-01 15:39:17,548][00148] Port 41817 is available [2024-08-01 15:39:17,553][00148] Using port 41817 [2024-08-01 15:39:17,573][00133] Port 40416 is available [2024-08-01 15:39:17,573][00133] Using port 40416 [2024-08-01 15:39:17,574][00137] Port 40815 is available [2024-08-01 15:39:17,575][00143] Port 41318 is available [2024-08-01 15:39:17,575][00137] Using port 40815 [2024-08-01 15:39:17,577][00143] Using port 41318 [2024-08-01 15:39:17,581][00135] Port 40519 is available [2024-08-01 15:39:17,582][00135] Using port 40519 [2024-08-01 15:39:17,577][00142] Port 41216 is available [2024-08-01 15:39:17,584][00142] Using port 41216 [2024-08-01 15:39:17,583][00138] Port 40712 is available [2024-08-01 15:39:17,589][00138] Using port 40712 [2024-08-01 15:39:17,588][00139] Port 41112 is available [2024-08-01 15:39:17,595][00139] Using port 41112 [2024-08-01 15:39:17,598][00147] Port 41719 is available [2024-08-01 15:39:17,609][00147] Using port 41719 [2024-08-01 15:39:17,616][00141] Port 40918 is available [2024-08-01 15:39:17,622][00141] Using port 40918 [2024-08-01 15:39:17,636][00146] Port 41616 is available [2024-08-01 15:39:17,640][00146] Using port 41616 [2024-08-01 15:39:17,645][00132] Port 40313 is available [2024-08-01 15:39:17,655][00132] Using port 40313 [2024-08-01 15:39:17,674][00144] Port 41421 is available [2024-08-01 15:39:17,675][00144] Using port 41421 [2024-08-01 15:39:17,690][00140] Port 41020 is available [2024-08-01 15:39:17,697][00140] Using port 41020 [2024-08-01 15:39:17,701][00136] Port 40621 is available [2024-08-01 15:39:17,697][00148] Port 41818 is available [2024-08-01 15:39:17,701][00136] Using port 40621 [2024-08-01 15:39:17,703][00148] Using port 41818 [2024-08-01 15:39:17,710][00145] Port 41512 is available [2024-08-01 15:39:17,715][00145] Using port 41512 [2024-08-01 15:39:17,724][00133] Port 40417 is available [2024-08-01 15:39:17,724][00133] Using port 40417 [2024-08-01 15:39:17,723][00137] Port 40816 is available [2024-08-01 15:39:17,725][00137] Using port 40816 [2024-08-01 15:39:17,720][00143] Port 41319 is available [2024-08-01 15:39:17,729][00143] Using port 41319 [2024-08-01 15:39:17,726][00135] Port 40520 is available [2024-08-01 15:39:17,734][00135] Using port 40520 [2024-08-01 15:39:17,731][00142] Port 41217 is available [2024-08-01 15:39:17,737][00142] Using port 41217 [2024-08-01 15:39:17,741][00139] Port 41113 is available [2024-08-01 15:39:17,742][00139] Using port 41113 [2024-08-01 15:39:17,743][00138] Port 40713 is available [2024-08-01 15:39:17,748][00138] Using port 40713 [2024-08-01 15:39:17,763][00147] Port 41720 is available [2024-08-01 15:39:17,763][00147] Using port 41720 [2024-08-01 15:39:17,767][00141] Port 40919 is available [2024-08-01 15:39:17,773][00141] Using port 40919 [2024-08-01 15:39:17,783][00146] Port 41617 is available [2024-08-01 15:39:17,790][00146] Using port 41617 [2024-08-01 15:39:17,803][00132] Port 40314 is available [2024-08-01 15:39:17,810][00132] Using port 40314 [2024-08-01 15:39:17,832][00144] Port 41422 is available [2024-08-01 15:39:17,843][00144] Using port 41422 [2024-08-01 15:39:17,855][00140] Port 41021 is available [2024-08-01 15:39:17,860][00140] Using port 41021 [2024-08-01 15:39:17,859][00148] Port 41819 is available [2024-08-01 15:39:17,866][00148] Using port 41819 [2024-08-01 15:39:17,861][00136] Port 40622 is available [2024-08-01 15:39:17,859][00145] Port 41513 is available [2024-08-01 15:39:17,869][00136] Using port 40622 [2024-08-01 15:39:17,871][00145] Using port 41513 [2024-08-01 15:39:17,879][00137] Port 40817 is available [2024-08-01 15:39:17,882][00137] Using port 40817 [2024-08-01 15:39:17,874][00133] Port 40418 is available [2024-08-01 15:39:17,880][00143] Port 41320 is available [2024-08-01 15:39:17,885][00143] Using port 41320 [2024-08-01 15:39:17,884][00133] Using port 40418 [2024-08-01 15:39:17,888][00135] Port 40521 is available [2024-08-01 15:39:17,895][00135] Using port 40521 [2024-08-01 15:39:17,896][00142] Port 41218 is available [2024-08-01 15:39:17,896][00142] Using port 41218 [2024-08-01 15:39:17,904][00138] Port 40714 is available [2024-08-01 15:39:17,898][00139] Port 41114 is available [2024-08-01 15:39:17,905][00138] Using port 40714 [2024-08-01 15:39:17,905][00139] Using port 41114 [2024-08-01 15:39:17,914][00147] Port 41721 is available [2024-08-01 15:39:17,918][00147] Using port 41721 [2024-08-01 15:39:17,930][00141] Port 40920 is available [2024-08-01 15:39:17,930][00141] Using port 40920 [2024-08-01 15:39:17,938][00146] Port 41618 is available [2024-08-01 15:39:17,945][00146] Using port 41618 [2024-08-01 15:39:17,963][00132] Port 40315 is available [2024-08-01 15:39:17,972][00132] Using port 40315 [2024-08-01 15:39:18,002][00144] Port 41423 is available [2024-08-01 15:39:18,005][00144] Using port 41423 [2024-08-01 15:39:18,017][00144] Using port 41412 on host... [2024-08-01 15:39:18,019][00140] Port 41022 is available [2024-08-01 15:39:18,024][00140] Using port 41022 [2024-08-01 15:39:18,023][00148] Port 41820 is available [2024-08-01 15:39:18,025][00148] Using port 41820 [2024-08-01 15:39:18,032][00145] Port 41514 is available [2024-08-01 15:39:18,023][00136] Port 40623 is available [2024-08-01 15:39:18,032][00136] Using port 40623 [2024-08-01 15:39:18,032][00145] Using port 41514 [2024-08-01 15:39:18,039][00133] Port 40419 is available [2024-08-01 15:39:18,040][00133] Using port 40419 [2024-08-01 15:39:18,034][00136] Using port 40612 on host... [2024-08-01 15:39:18,045][00137] Port 40818 is available [2024-08-01 15:39:18,045][00137] Using port 40818 [2024-08-01 15:39:18,049][00143] Port 41321 is available [2024-08-01 15:39:18,049][00143] Using port 41321 [2024-08-01 15:39:18,044][00142] Port 41219 is available [2024-08-01 15:39:18,053][00142] Using port 41219 [2024-08-01 15:39:18,057][00138] Port 40715 is available [2024-08-01 15:39:18,057][00138] Using port 40715 [2024-08-01 15:39:18,057][00135] Port 40522 is available [2024-08-01 15:39:18,072][00135] Using port 40522 [2024-08-01 15:39:18,079][00139] Port 41115 is available [2024-08-01 15:39:18,079][00139] Using port 41115 [2024-08-01 15:39:18,095][00147] Port 41722 is available [2024-08-01 15:39:18,100][00147] Using port 41722 [2024-08-01 15:39:18,109][00141] Port 40921 is available [2024-08-01 15:39:18,115][00141] Using port 40921 [2024-08-01 15:39:18,111][00146] Port 41619 is available [2024-08-01 15:39:18,117][00146] Using port 41619 [2024-08-01 15:39:18,124][00132] Port 40316 is available [2024-08-01 15:39:18,135][00132] Using port 40316 [2024-08-01 15:39:18,180][00148] Port 41821 is available [2024-08-01 15:39:18,186][00140] Port 41023 is available [2024-08-01 15:39:18,188][00148] Using port 41821 [2024-08-01 15:39:18,188][00140] Using port 41023 [2024-08-01 15:39:18,193][00145] Port 41515 is available [2024-08-01 15:39:18,203][00140] Using port 41012 on host... [2024-08-01 15:39:18,205][00137] Port 40819 is available [2024-08-01 15:39:18,205][00137] Using port 40819 [2024-08-01 15:39:18,194][00145] Using port 41515 [2024-08-01 15:39:18,231][00138] Port 40716 is available [2024-08-01 15:39:18,230][00133] Port 40420 is available [2024-08-01 15:39:18,232][00133] Using port 40420 [2024-08-01 15:39:18,233][00142] Port 41220 is available [2024-08-01 15:39:18,237][00142] Using port 41220 [2024-08-01 15:39:18,257][00139] Port 41116 is available [2024-08-01 15:39:18,257][00139] Using port 41116 [2024-08-01 15:39:18,232][00138] Using port 40716 [2024-08-01 15:39:18,268][00143] Port 41322 is available [2024-08-01 15:39:18,269][00143] Using port 41322 [2024-08-01 15:39:18,274][00146] Port 41620 is available [2024-08-01 15:39:18,285][00146] Using port 41620 [2024-08-01 15:39:18,297][00135] Port 40523 is available [2024-08-01 15:39:18,297][00135] Using port 40523 [2024-08-01 15:39:18,303][00132] Port 40317 is available [2024-08-01 15:39:18,312][00132] Using port 40317 [2024-08-01 15:39:18,335][00135] Using port 40512 on host... [2024-08-01 15:39:18,340][00148] Port 41822 is available [2024-08-01 15:39:18,347][00148] Using port 41822 [2024-08-01 15:39:18,361][00147] Port 41723 is available [2024-08-01 15:39:18,362][00147] Using port 41723 [2024-08-01 15:39:18,373][00137] Port 40820 is available [2024-08-01 15:39:18,374][00137] Using port 40820 [2024-08-01 15:39:18,379][00133] Port 40421 is available [2024-08-01 15:39:18,379][00133] Using port 40421 [2024-08-01 15:39:18,387][00142] Port 41221 is available [2024-08-01 15:39:18,387][00142] Using port 41221 [2024-08-01 15:39:18,388][00147] Using port 41712 on host... [2024-08-01 15:39:18,376][00145] Port 41516 is available [2024-08-01 15:39:18,393][00141] Port 40922 is available [2024-08-01 15:39:18,396][00141] Using port 40922 [2024-08-01 15:39:18,390][00145] Using port 41516 [2024-08-01 15:39:18,423][00146] Port 41621 is available [2024-08-01 15:39:18,424][00146] Using port 41621 [2024-08-01 15:39:18,494][00148] Port 41823 is available [2024-08-01 15:39:18,495][00138] Port 40717 is available [2024-08-01 15:39:18,498][00148] Using port 41823 [2024-08-01 15:39:18,498][00138] Using port 40717 [2024-08-01 15:39:18,492][00139] Port 41117 is available [2024-08-01 15:39:18,501][00139] Using port 41117 [2024-08-01 15:39:18,505][00148] Using port 41812 on host... [2024-08-01 15:39:18,518][00143] Port 41323 is available [2024-08-01 15:39:18,537][00143] Using port 41323 [2024-08-01 15:39:18,541][00133] Port 40422 is available [2024-08-01 15:39:18,546][00143] Using port 41312 on host... [2024-08-01 15:39:18,549][00133] Using port 40422 [2024-08-01 15:39:18,552][00142] Port 41222 is available [2024-08-01 15:39:18,546][00137] Port 40821 is available [2024-08-01 15:39:18,553][00142] Using port 41222 [2024-08-01 15:39:18,554][00137] Using port 40821 [2024-08-01 15:39:18,568][00141] Port 40923 is available [2024-08-01 15:39:18,577][00141] Using port 40923 [2024-08-01 15:39:18,579][00141] Using port 40912 on host... [2024-08-01 15:39:18,591][00146] Port 41622 is available [2024-08-01 15:39:18,598][00132] Port 40318 is available [2024-08-01 15:39:18,598][00132] Using port 40318 [2024-08-01 15:39:18,592][00146] Using port 41622 [2024-08-01 15:39:18,687][00133] Port 40423 is available [2024-08-01 15:39:18,695][00133] Using port 40423 [2024-08-01 15:39:18,694][00142] Port 41223 is available [2024-08-01 15:39:18,698][00142] Using port 41223 [2024-08-01 15:39:18,699][00137] Port 40822 is available [2024-08-01 15:39:18,696][00145] Port 41517 is available [2024-08-01 15:39:18,703][00142] Using port 41212 on host... [2024-08-01 15:39:18,701][00145] Using port 41517 [2024-08-01 15:39:18,704][00133] Using port 40412 on host... [2024-08-01 15:39:18,699][00137] Using port 40822 [2024-08-01 15:39:18,725][00138] Port 40718 is available [2024-08-01 15:39:18,719][00139] Port 41118 is available [2024-08-01 15:39:18,725][00138] Using port 40718 [2024-08-01 15:39:18,726][00139] Using port 41118 [2024-08-01 15:39:18,781][00132] Port 40319 is available [2024-08-01 15:39:18,782][00132] Using port 40319 [2024-08-01 15:39:18,798][00146] Port 41623 is available [2024-08-01 15:39:18,798][00146] Using port 41623 [2024-08-01 15:39:18,800][00146] Using port 41612 on host... [2024-08-01 15:39:18,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:18,853][00145] Port 41518 is available [2024-08-01 15:39:18,862][00145] Using port 41518 [2024-08-01 15:39:18,879][00139] Port 41119 is available [2024-08-01 15:39:18,880][00138] Port 40719 is available [2024-08-01 15:39:18,882][00139] Using port 41119 [2024-08-01 15:39:18,882][00138] Using port 40719 [2024-08-01 15:39:18,911][00137] Port 40823 is available [2024-08-01 15:39:18,911][00137] Using port 40823 [2024-08-01 15:39:18,921][00137] Using port 40812 on host... [2024-08-01 15:39:18,958][00132] Port 40320 is available [2024-08-01 15:39:18,958][00132] Using port 40320 [2024-08-01 15:39:19,057][00145] Port 41519 is available [2024-08-01 15:39:19,069][00145] Using port 41519 [2024-08-01 15:39:19,075][00139] Port 41120 is available [2024-08-01 15:39:19,085][00139] Using port 41120 [2024-08-01 15:39:19,080][00138] Port 40720 is available [2024-08-01 15:39:19,086][00138] Using port 40720 [2024-08-01 15:39:19,140][00132] Port 40321 is available [2024-08-01 15:39:19,150][00132] Using port 40321 [2024-08-01 15:39:19,201][00145] Port 41520 is available [2024-08-01 15:39:19,209][00145] Using port 41520 [2024-08-01 15:39:19,227][00139] Port 41121 is available [2024-08-01 15:39:19,230][00139] Using port 41121 [2024-08-01 15:39:19,226][00138] Port 40721 is available [2024-08-01 15:39:19,235][00138] Using port 40721 [2024-08-01 15:39:19,282][00132] Port 40322 is available [2024-08-01 15:39:19,292][00132] Using port 40322 [2024-08-01 15:39:19,467][00145] Port 41521 is available [2024-08-01 15:39:19,475][00145] Using port 41521 [2024-08-01 15:39:19,486][00139] Port 41122 is available [2024-08-01 15:39:19,492][00139] Using port 41122 [2024-08-01 15:39:19,488][00138] Port 40722 is available [2024-08-01 15:39:19,496][00138] Using port 40722 [2024-08-01 15:39:19,592][00132] Port 40323 is available [2024-08-01 15:39:19,663][00132] Using port 40323 [2024-08-01 15:39:19,666][00132] Using port 40312 on host... [2024-08-01 15:39:19,849][00145] Port 41522 is available [2024-08-01 15:39:19,849][00145] Using port 41522 [2024-08-01 15:39:19,870][00139] Port 41123 is available [2024-08-01 15:39:19,873][00139] Using port 41123 [2024-08-01 15:39:19,874][00138] Port 40723 is available [2024-08-01 15:39:19,881][00138] Using port 40723 [2024-08-01 15:39:19,883][00139] Using port 41112 on host... [2024-08-01 15:39:19,884][00138] Using port 40712 on host... [2024-08-01 15:39:19,994][00145] Port 41523 is available [2024-08-01 15:39:19,994][00145] Using port 41523 [2024-08-01 15:39:19,997][00145] Using port 41512 on host... [2024-08-01 15:39:20,080][00136] Initialized w:3 v:12 player:0 [2024-08-01 15:39:20,083][00136] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,085][00144] Initialized w:11 v:12 player:0 [2024-08-01 15:39:20,088][00144] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,288][00140] Initialized w:7 v:12 player:0 [2024-08-01 15:39:20,290][00140] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,780][00148] Initialized w:15 v:12 player:0 [2024-08-01 15:39:20,788][00148] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,880][00142] Initialized w:9 v:12 player:0 [2024-08-01 15:39:20,884][00142] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,917][00133] Initialized w:1 v:12 player:0 [2024-08-01 15:39:20,919][00133] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,957][00146] Initialized w:13 v:12 player:0 [2024-08-01 15:39:20,961][00146] Decorrelating experience for 384 frames... [2024-08-01 15:39:20,998][00135] Initialized w:2 v:12 player:0 [2024-08-01 15:39:20,999][00135] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,014][00147] Initialized w:14 v:12 player:0 [2024-08-01 15:39:21,016][00147] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,123][00137] Initialized w:5 v:12 player:0 [2024-08-01 15:39:21,128][00137] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,199][00143] Initialized w:10 v:12 player:0 [2024-08-01 15:39:21,203][00143] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,243][00141] Initialized w:6 v:12 player:0 [2024-08-01 15:39:21,252][00141] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,866][00132] Initialized w:0 v:12 player:0 [2024-08-01 15:39:21,868][00132] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,985][00138] Initialized w:4 v:12 player:0 [2024-08-01 15:39:21,986][00138] Decorrelating experience for 384 frames... [2024-08-01 15:39:21,988][00139] Initialized w:8 v:12 player:0 [2024-08-01 15:39:21,990][00139] Decorrelating experience for 384 frames... [2024-08-01 15:39:22,131][00145] Initialized w:12 v:12 player:0 [2024-08-01 15:39:22,133][00145] Decorrelating experience for 384 frames... [2024-08-01 15:39:22,713][00136] Using port 40613 on host... [2024-08-01 15:39:22,752][00144] Using port 41413 on host... [2024-08-01 15:39:22,838][00140] Using port 41013 on host... [2024-08-01 15:39:23,212][00148] Using port 41813 on host... [2024-08-01 15:39:23,439][00142] Using port 41213 on host... [2024-08-01 15:39:23,587][00146] Using port 41613 on host... [2024-08-01 15:39:23,628][00137] Using port 40813 on host... [2024-08-01 15:39:23,645][00133] Using port 40413 on host... [2024-08-01 15:39:23,648][00135] Using port 40513 on host... [2024-08-01 15:39:23,664][00147] Using port 41713 on host... [2024-08-01 15:39:23,749][00143] Using port 41313 on host... [2024-08-01 15:39:23,789][00141] Using port 40913 on host... [2024-08-01 15:39:23,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:24,377][00132] Using port 40313 on host... [2024-08-01 15:39:24,556][00139] Using port 41113 on host... [2024-08-01 15:39:24,648][00138] Using port 40713 on host... [2024-08-01 15:39:24,660][00145] Using port 41513 on host... [2024-08-01 15:39:24,846][00136] Initialized w:3 v:13 player:0 [2024-08-01 15:39:24,855][00136] Decorrelating experience for 416 frames... [2024-08-01 15:39:24,856][00144] Initialized w:11 v:13 player:0 [2024-08-01 15:39:24,859][00144] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,030][00140] Initialized w:7 v:13 player:0 [2024-08-01 15:39:25,035][00140] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,491][00142] Initialized w:9 v:13 player:0 [2024-08-01 15:39:25,492][00142] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,553][00148] Initialized w:15 v:13 player:0 [2024-08-01 15:39:25,557][00146] Initialized w:13 v:13 player:0 [2024-08-01 15:39:25,559][00146] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,555][00148] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,599][00135] Initialized w:2 v:13 player:0 [2024-08-01 15:39:25,601][00135] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,602][00147] Initialized w:14 v:13 player:0 [2024-08-01 15:39:25,604][00147] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,620][00137] Initialized w:5 v:13 player:0 [2024-08-01 15:39:25,621][00137] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,668][00143] Initialized w:10 v:13 player:0 [2024-08-01 15:39:25,672][00143] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,681][00133] Initialized w:1 v:13 player:0 [2024-08-01 15:39:25,683][00133] Decorrelating experience for 416 frames... [2024-08-01 15:39:25,768][00141] Initialized w:6 v:13 player:0 [2024-08-01 15:39:25,771][00141] Decorrelating experience for 416 frames... [2024-08-01 15:39:26,460][00132] Initialized w:0 v:13 player:0 [2024-08-01 15:39:26,462][00132] Decorrelating experience for 416 frames... [2024-08-01 15:39:26,615][00139] Initialized w:8 v:13 player:0 [2024-08-01 15:39:26,618][00139] Decorrelating experience for 416 frames... [2024-08-01 15:39:26,683][00138] Initialized w:4 v:13 player:0 [2024-08-01 15:39:26,685][00138] Decorrelating experience for 416 frames... [2024-08-01 15:39:26,702][00145] Initialized w:12 v:13 player:0 [2024-08-01 15:39:26,704][00145] Decorrelating experience for 416 frames... [2024-08-01 15:39:27,667][00144] Using port 41414 on host... [2024-08-01 15:39:27,685][00136] Using port 40614 on host... [2024-08-01 15:39:27,839][00140] Using port 41014 on host... [2024-08-01 15:39:28,256][00148] Using port 41814 on host... [2024-08-01 15:39:28,302][00146] Using port 41614 on host... [2024-08-01 15:39:28,346][00142] Using port 41214 on host... [2024-08-01 15:39:28,423][00137] Using port 40814 on host... [2024-08-01 15:39:28,431][00147] Using port 41714 on host... [2024-08-01 15:39:28,437][00135] Using port 40514 on host... [2024-08-01 15:39:28,448][00133] Using port 40414 on host... [2024-08-01 15:39:28,502][00143] Using port 41314 on host... [2024-08-01 15:39:28,623][00141] Using port 40914 on host... [2024-08-01 15:39:28,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:29,182][00132] Using port 40314 on host... [2024-08-01 15:39:29,279][00139] Using port 41114 on host... [2024-08-01 15:39:29,457][00138] Using port 40714 on host... [2024-08-01 15:39:29,466][00145] Using port 41514 on host... [2024-08-01 15:39:29,817][00136] Initialized w:3 v:14 player:0 [2024-08-01 15:39:29,819][00144] Initialized w:11 v:14 player:0 [2024-08-01 15:39:29,821][00136] Decorrelating experience for 448 frames... [2024-08-01 15:39:29,822][00144] Decorrelating experience for 448 frames... [2024-08-01 15:39:29,944][00140] Initialized w:7 v:14 player:0 [2024-08-01 15:39:29,947][00140] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,339][00142] Initialized w:9 v:14 player:0 [2024-08-01 15:39:30,340][00142] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,346][00146] Initialized w:13 v:14 player:0 [2024-08-01 15:39:30,347][00146] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,412][00147] Initialized w:14 v:14 player:0 [2024-08-01 15:39:30,414][00147] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,421][00137] Initialized w:5 v:14 player:0 [2024-08-01 15:39:30,422][00137] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,437][00135] Initialized w:2 v:14 player:0 [2024-08-01 15:39:30,439][00135] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,457][00133] Initialized w:1 v:14 player:0 [2024-08-01 15:39:30,459][00143] Initialized w:10 v:14 player:0 [2024-08-01 15:39:30,462][00143] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,465][00133] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,542][00148] Initialized w:15 v:14 player:0 [2024-08-01 15:39:30,549][00148] Decorrelating experience for 448 frames... [2024-08-01 15:39:30,609][00141] Initialized w:6 v:14 player:0 [2024-08-01 15:39:30,611][00141] Decorrelating experience for 448 frames... [2024-08-01 15:39:31,260][00132] Initialized w:0 v:14 player:0 [2024-08-01 15:39:31,262][00132] Decorrelating experience for 448 frames... [2024-08-01 15:39:31,332][00139] Initialized w:8 v:14 player:0 [2024-08-01 15:39:31,334][00139] Decorrelating experience for 448 frames... [2024-08-01 15:39:31,479][00138] Initialized w:4 v:14 player:0 [2024-08-01 15:39:31,481][00138] Decorrelating experience for 448 frames... [2024-08-01 15:39:31,540][00145] Initialized w:12 v:14 player:0 [2024-08-01 15:39:31,541][00145] Decorrelating experience for 448 frames... [2024-08-01 15:39:32,787][00144] Using port 41415 on host... [2024-08-01 15:39:32,783][00136] Using port 40615 on host... [2024-08-01 15:39:32,899][00140] Using port 41015 on host... [2024-08-01 15:39:33,319][00142] Using port 41215 on host... [2024-08-01 15:39:33,390][00148] Using port 41815 on host... [2024-08-01 15:39:33,391][00146] Using port 41615 on host... [2024-08-01 15:39:33,404][00137] Using port 40815 on host... [2024-08-01 15:39:33,408][00135] Using port 40515 on host... [2024-08-01 15:39:33,443][00147] Using port 41715 on host... [2024-08-01 15:39:33,474][00143] Using port 41315 on host... [2024-08-01 15:39:33,530][00133] Using port 40415 on host... [2024-08-01 15:39:33,637][00141] Using port 40915 on host... [2024-08-01 15:39:33,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:34,329][00139] Using port 41115 on host... [2024-08-01 15:39:34,339][00132] Using port 40315 on host... [2024-08-01 15:39:34,465][00138] Using port 40715 on host... [2024-08-01 15:39:34,528][00145] Using port 41515 on host... [2024-08-01 15:39:34,910][00144] Initialized w:11 v:15 player:0 [2024-08-01 15:39:34,912][00136] Initialized w:3 v:15 player:0 [2024-08-01 15:39:34,914][00144] Decorrelating experience for 480 frames... [2024-08-01 15:39:34,915][00136] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,002][00140] Initialized w:7 v:15 player:0 [2024-08-01 15:39:35,004][00140] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,390][00135] Initialized w:2 v:15 player:0 [2024-08-01 15:39:35,391][00142] Initialized w:9 v:15 player:0 [2024-08-01 15:39:35,392][00135] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,393][00142] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,402][00146] Initialized w:13 v:15 player:0 [2024-08-01 15:39:35,403][00146] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,429][00147] Initialized w:14 v:15 player:0 [2024-08-01 15:39:35,431][00147] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,444][00143] Initialized w:10 v:15 player:0 [2024-08-01 15:39:35,446][00143] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,446][00137] Initialized w:5 v:15 player:0 [2024-08-01 15:39:35,448][00137] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,548][00133] Initialized w:1 v:15 player:0 [2024-08-01 15:39:35,551][00133] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,622][00141] Initialized w:6 v:15 player:0 [2024-08-01 15:39:35,624][00141] Decorrelating experience for 480 frames... [2024-08-01 15:39:35,713][00148] Initialized w:15 v:15 player:0 [2024-08-01 15:39:35,715][00148] Decorrelating experience for 480 frames... [2024-08-01 15:39:36,419][00139] Initialized w:8 v:15 player:0 [2024-08-01 15:39:36,421][00139] Decorrelating experience for 480 frames... [2024-08-01 15:39:36,454][00132] Initialized w:0 v:15 player:0 [2024-08-01 15:39:36,456][00132] Decorrelating experience for 480 frames... [2024-08-01 15:39:36,543][00138] Initialized w:4 v:15 player:0 [2024-08-01 15:39:36,545][00138] Decorrelating experience for 480 frames... [2024-08-01 15:39:36,656][00145] Initialized w:12 v:15 player:0 [2024-08-01 15:39:36,660][00145] Decorrelating experience for 480 frames... [2024-08-01 15:39:38,024][00144] Using port 41416 on host... [2024-08-01 15:39:38,070][00140] Using port 41016 on host... [2024-08-01 15:39:38,162][00136] Using port 40616 on host... [2024-08-01 15:39:38,452][00146] Using port 41616 on host... [2024-08-01 15:39:38,505][00142] Using port 41216 on host... [2024-08-01 15:39:38,587][00135] Using port 40516 on host... [2024-08-01 15:39:38,634][00137] Using port 40816 on host... [2024-08-01 15:39:38,666][00147] Using port 41716 on host... [2024-08-01 15:39:38,671][00143] Using port 41316 on host... [2024-08-01 15:39:38,681][00148] Using port 41816 on host... [2024-08-01 15:39:38,745][00133] Using port 40416 on host... [2024-08-01 15:39:38,763][00141] Using port 40916 on host... [2024-08-01 15:39:38,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:39,596][00139] Using port 41116 on host... [2024-08-01 15:39:39,719][00138] Using port 40716 on host... [2024-08-01 15:39:39,750][00132] Using port 40316 on host... [2024-08-01 15:39:39,905][00145] Using port 41516 on host... [2024-08-01 15:39:40,094][00144] Initialized w:11 v:16 player:0 [2024-08-01 15:39:40,096][00144] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,123][00140] Initialized w:7 v:16 player:0 [2024-08-01 15:39:40,125][00140] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,261][00136] Initialized w:3 v:16 player:0 [2024-08-01 15:39:40,263][00136] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,526][00146] Initialized w:13 v:16 player:0 [2024-08-01 15:39:40,528][00146] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,538][00142] Initialized w:9 v:16 player:0 [2024-08-01 15:39:40,540][00142] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,553][00135] Initialized w:2 v:16 player:0 [2024-08-01 15:39:40,554][00135] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,613][00143] Initialized w:10 v:16 player:0 [2024-08-01 15:39:40,616][00143] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,634][00137] Initialized w:5 v:16 player:0 [2024-08-01 15:39:40,636][00137] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,652][00147] Initialized w:14 v:16 player:0 [2024-08-01 15:39:40,655][00147] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,709][00141] Initialized w:6 v:16 player:0 [2024-08-01 15:39:40,711][00141] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,769][00133] Initialized w:1 v:16 player:0 [2024-08-01 15:39:40,771][00133] Decorrelating experience for 512 frames... [2024-08-01 15:39:40,918][00148] Initialized w:15 v:16 player:0 [2024-08-01 15:39:40,924][00148] Decorrelating experience for 512 frames... [2024-08-01 15:39:41,749][00139] Initialized w:8 v:16 player:0 [2024-08-01 15:39:41,758][00139] Decorrelating experience for 512 frames... [2024-08-01 15:39:41,870][00132] Initialized w:0 v:16 player:0 [2024-08-01 15:39:41,872][00132] Decorrelating experience for 512 frames... [2024-08-01 15:39:41,873][00138] Initialized w:4 v:16 player:0 [2024-08-01 15:39:41,876][00138] Decorrelating experience for 512 frames... [2024-08-01 15:39:42,068][00145] Initialized w:12 v:16 player:0 [2024-08-01 15:39:42,070][00145] Decorrelating experience for 512 frames... [2024-08-01 15:39:43,438][00144] Using port 41417 on host... [2024-08-01 15:39:43,627][00140] Using port 41017 on host... [2024-08-01 15:39:43,780][00136] Using port 40617 on host... [2024-08-01 15:39:43,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:43,948][00142] Using port 41217 on host... [2024-08-01 15:39:44,051][00137] Using port 40817 on host... [2024-08-01 15:39:44,067][00146] Using port 41617 on host... [2024-08-01 15:39:44,145][00143] Using port 41317 on host... [2024-08-01 15:39:44,179][00135] Using port 40517 on host... [2024-08-01 15:39:44,225][00148] Using port 41817 on host... [2024-08-01 15:39:44,276][00133] Using port 40417 on host... [2024-08-01 15:39:44,272][00147] Using port 41717 on host... [2024-08-01 15:39:44,452][00141] Using port 40917 on host... [2024-08-01 15:39:45,282][00139] Using port 41117 on host... [2024-08-01 15:39:45,314][00132] Using port 40317 on host... [2024-08-01 15:39:45,373][00138] Using port 40717 on host... [2024-08-01 15:39:45,568][00144] Initialized w:11 v:17 player:0 [2024-08-01 15:39:45,572][00144] Decorrelating experience for 544 frames... [2024-08-01 15:39:45,616][00145] Using port 41517 on host... [2024-08-01 15:39:45,702][00140] Initialized w:7 v:17 player:0 [2024-08-01 15:39:45,706][00140] Decorrelating experience for 544 frames... [2024-08-01 15:39:45,911][00136] Initialized w:3 v:17 player:0 [2024-08-01 15:39:45,916][00136] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,003][00142] Initialized w:9 v:17 player:0 [2024-08-01 15:39:46,005][00142] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,074][00137] Initialized w:5 v:17 player:0 [2024-08-01 15:39:46,076][00137] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,084][00146] Initialized w:13 v:17 player:0 [2024-08-01 15:39:46,085][00146] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,140][00143] Initialized w:10 v:17 player:0 [2024-08-01 15:39:46,142][00143] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,173][00135] Initialized w:2 v:17 player:0 [2024-08-01 15:39:46,175][00135] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,274][00147] Initialized w:14 v:17 player:0 [2024-08-01 15:39:46,278][00147] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,341][00133] Initialized w:1 v:17 player:0 [2024-08-01 15:39:46,343][00133] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,434][00141] Initialized w:6 v:17 player:0 [2024-08-01 15:39:46,437][00141] Decorrelating experience for 544 frames... [2024-08-01 15:39:46,456][00148] Initialized w:15 v:17 player:0 [2024-08-01 15:39:46,461][00148] Decorrelating experience for 544 frames... [2024-08-01 15:39:47,434][00139] Initialized w:8 v:17 player:0 [2024-08-01 15:39:47,436][00139] Decorrelating experience for 544 frames... [2024-08-01 15:39:47,448][00132] Initialized w:0 v:17 player:0 [2024-08-01 15:39:47,449][00132] Decorrelating experience for 544 frames... [2024-08-01 15:39:47,466][00138] Initialized w:4 v:17 player:0 [2024-08-01 15:39:47,468][00138] Decorrelating experience for 544 frames... [2024-08-01 15:39:47,726][00145] Initialized w:12 v:17 player:0 [2024-08-01 15:39:47,728][00145] Decorrelating experience for 544 frames... [2024-08-01 15:39:48,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:49,062][00144] Using port 41418 on host... [2024-08-01 15:39:49,273][00140] Using port 41018 on host... [2024-08-01 15:39:49,374][00136] Using port 40618 on host... [2024-08-01 15:39:49,635][00146] Using port 41618 on host... [2024-08-01 15:39:49,644][00142] Using port 41218 on host... [2024-08-01 15:39:49,652][00137] Using port 40818 on host... [2024-08-01 15:39:49,736][00143] Using port 41318 on host... [2024-08-01 15:39:49,863][00133] Using port 40418 on host... [2024-08-01 15:39:49,874][00135] Using port 40518 on host... [2024-08-01 15:39:49,905][00148] Using port 41818 on host... [2024-08-01 15:39:49,912][00147] Using port 41718 on host... [2024-08-01 15:39:50,080][00141] Using port 40918 on host... [2024-08-01 15:39:51,173][00139] Using port 41118 on host... [2024-08-01 15:39:51,185][00132] Using port 40318 on host... [2024-08-01 15:39:51,200][00144] Initialized w:11 v:18 player:0 [2024-08-01 15:39:51,202][00144] Decorrelating experience for 576 frames... [2024-08-01 15:39:51,277][00138] Using port 40718 on host... [2024-08-01 15:39:51,382][00140] Initialized w:7 v:18 player:0 [2024-08-01 15:39:51,391][00140] Decorrelating experience for 576 frames... [2024-08-01 15:39:51,486][00136] Initialized w:3 v:18 player:0 [2024-08-01 15:39:51,489][00136] Decorrelating experience for 576 frames... [2024-08-01 15:39:51,682][00145] Using port 41518 on host... [2024-08-01 15:39:51,997][00137] Initialized w:5 v:18 player:0 [2024-08-01 15:39:51,998][00137] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,046][00146] Initialized w:13 v:18 player:0 [2024-08-01 15:39:52,047][00146] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,051][00142] Initialized w:9 v:18 player:0 [2024-08-01 15:39:52,052][00142] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,161][00143] Initialized w:10 v:18 player:0 [2024-08-01 15:39:52,163][00143] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,244][00135] Initialized w:2 v:18 player:0 [2024-08-01 15:39:52,247][00135] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,312][00147] Initialized w:14 v:18 player:0 [2024-08-01 15:39:52,314][00147] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,401][00133] Initialized w:1 v:18 player:0 [2024-08-01 15:39:52,403][00133] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,474][00141] Initialized w:6 v:18 player:0 [2024-08-01 15:39:52,477][00141] Decorrelating experience for 576 frames... [2024-08-01 15:39:52,605][00148] Initialized w:15 v:18 player:0 [2024-08-01 15:39:52,607][00148] Decorrelating experience for 576 frames... [2024-08-01 15:39:53,610][00139] Initialized w:8 v:18 player:0 [2024-08-01 15:39:53,612][00139] Decorrelating experience for 576 frames... [2024-08-01 15:39:53,640][00132] Initialized w:0 v:18 player:0 [2024-08-01 15:39:53,642][00132] Decorrelating experience for 576 frames... [2024-08-01 15:39:53,661][00138] Initialized w:4 v:18 player:0 [2024-08-01 15:39:53,663][00138] Decorrelating experience for 576 frames... [2024-08-01 15:39:53,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:54,061][00145] Initialized w:12 v:18 player:0 [2024-08-01 15:39:54,063][00145] Decorrelating experience for 576 frames... [2024-08-01 15:39:55,550][00144] Using port 41419 on host... [2024-08-01 15:39:55,775][00140] Using port 41019 on host... [2024-08-01 15:39:55,860][00136] Using port 40619 on host... [2024-08-01 15:39:55,912][00137] Using port 40819 on host... [2024-08-01 15:39:56,076][00143] Using port 41319 on host... [2024-08-01 15:39:56,117][00146] Using port 41619 on host... [2024-08-01 15:39:56,152][00142] Using port 41219 on host... [2024-08-01 15:39:56,211][00135] Using port 40519 on host... [2024-08-01 15:39:56,287][00147] Using port 41719 on host... [2024-08-01 15:39:56,290][00148] Using port 41819 on host... [2024-08-01 15:39:56,376][00133] Using port 40419 on host... [2024-08-01 15:39:56,543][00141] Using port 40919 on host... [2024-08-01 15:39:57,463][00138] Using port 40719 on host... [2024-08-01 15:39:57,513][00132] Using port 40319 on host... [2024-08-01 15:39:57,582][00139] Using port 41119 on host... [2024-08-01 15:39:57,726][00144] Initialized w:11 v:19 player:0 [2024-08-01 15:39:57,728][00144] Decorrelating experience for 608 frames... [2024-08-01 15:39:57,827][00145] Using port 41519 on host... [2024-08-01 15:39:57,903][00140] Initialized w:7 v:19 player:0 [2024-08-01 15:39:57,912][00140] Decorrelating experience for 608 frames... [2024-08-01 15:39:57,992][00136] Initialized w:3 v:19 player:0 [2024-08-01 15:39:57,993][00136] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,013][00137] Initialized w:5 v:19 player:0 [2024-08-01 15:39:58,015][00137] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,190][00143] Initialized w:10 v:19 player:0 [2024-08-01 15:39:58,192][00143] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,198][00146] Initialized w:13 v:19 player:0 [2024-08-01 15:39:58,199][00146] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,210][00142] Initialized w:9 v:19 player:0 [2024-08-01 15:39:58,212][00142] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,302][00135] Initialized w:2 v:19 player:0 [2024-08-01 15:39:58,304][00135] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,349][00147] Initialized w:14 v:19 player:0 [2024-08-01 15:39:58,351][00147] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,490][00133] Initialized w:1 v:19 player:0 [2024-08-01 15:39:58,492][00133] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,515][00148] Initialized w:15 v:19 player:0 [2024-08-01 15:39:58,517][00148] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,684][00141] Initialized w:6 v:19 player:0 [2024-08-01 15:39:58,687][00141] Decorrelating experience for 608 frames... [2024-08-01 15:39:58,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:39:59,605][00138] Initialized w:4 v:19 player:0 [2024-08-01 15:39:59,606][00138] Decorrelating experience for 608 frames... [2024-08-01 15:39:59,625][00132] Initialized w:0 v:19 player:0 [2024-08-01 15:39:59,627][00132] Decorrelating experience for 608 frames... [2024-08-01 15:39:59,644][00139] Initialized w:8 v:19 player:0 [2024-08-01 15:39:59,646][00139] Decorrelating experience for 608 frames... [2024-08-01 15:39:59,954][00145] Initialized w:12 v:19 player:0 [2024-08-01 15:39:59,956][00145] Decorrelating experience for 608 frames... [2024-08-01 15:40:01,712][00144] Using port 41420 on host... [2024-08-01 15:40:01,896][00136] Using port 40620 on host... [2024-08-01 15:40:02,046][00137] Using port 40820 on host... [2024-08-01 15:40:02,046][00140] Using port 41020 on host... [2024-08-01 15:40:02,335][00135] Using port 40520 on host... [2024-08-01 15:40:02,357][00146] Using port 41620 on host... [2024-08-01 15:40:02,390][00142] Using port 41220 on host... [2024-08-01 15:40:02,444][00147] Using port 41720 on host... [2024-08-01 15:40:02,463][00143] Using port 41320 on host... [2024-08-01 15:40:02,521][00148] Using port 41820 on host... [2024-08-01 15:40:02,532][00133] Using port 40420 on host... [2024-08-01 15:40:02,777][00141] Using port 40920 on host... [2024-08-01 15:40:03,632][00138] Using port 40720 on host... [2024-08-01 15:40:03,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:03,862][00132] Using port 40320 on host... [2024-08-01 15:40:03,885][00139] Using port 41120 on host... [2024-08-01 15:40:03,938][00144] Initialized w:11 v:20 player:0 [2024-08-01 15:40:03,940][00144] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,121][00136] Initialized w:3 v:20 player:0 [2024-08-01 15:40:04,123][00136] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,220][00145] Using port 41520 on host... [2024-08-01 15:40:04,326][00140] Initialized w:7 v:20 player:0 [2024-08-01 15:40:04,328][00140] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,408][00137] Initialized w:5 v:20 player:0 [2024-08-01 15:40:04,410][00137] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,593][00135] Initialized w:2 v:20 player:0 [2024-08-01 15:40:04,595][00135] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,615][00143] Initialized w:10 v:20 player:0 [2024-08-01 15:40:04,616][00143] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,622][00147] Initialized w:14 v:20 player:0 [2024-08-01 15:40:04,624][00147] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,624][00146] Initialized w:13 v:20 player:0 [2024-08-01 15:40:04,626][00146] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,662][00142] Initialized w:9 v:20 player:0 [2024-08-01 15:40:04,664][00142] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,837][00133] Initialized w:1 v:20 player:0 [2024-08-01 15:40:04,845][00133] Decorrelating experience for 640 frames... [2024-08-01 15:40:04,869][00148] Initialized w:15 v:20 player:0 [2024-08-01 15:40:04,872][00148] Decorrelating experience for 640 frames... [2024-08-01 15:40:05,023][00141] Initialized w:6 v:20 player:0 [2024-08-01 15:40:05,029][00141] Decorrelating experience for 640 frames... [2024-08-01 15:40:05,813][00138] Initialized w:4 v:20 player:0 [2024-08-01 15:40:05,815][00138] Decorrelating experience for 640 frames... [2024-08-01 15:40:05,920][00132] Initialized w:0 v:20 player:0 [2024-08-01 15:40:05,922][00132] Decorrelating experience for 640 frames... [2024-08-01 15:40:05,960][00139] Initialized w:8 v:20 player:0 [2024-08-01 15:40:05,962][00139] Decorrelating experience for 640 frames... [2024-08-01 15:40:06,323][00145] Initialized w:12 v:20 player:0 [2024-08-01 15:40:06,326][00145] Decorrelating experience for 640 frames... [2024-08-01 15:40:08,326][00136] Using port 40621 on host... [2024-08-01 15:40:08,338][00144] Using port 41421 on host... [2024-08-01 15:40:08,541][00140] Using port 41021 on host... [2024-08-01 15:40:08,710][00137] Using port 40821 on host... [2024-08-01 15:40:08,828][00147] Using port 41721 on host... [2024-08-01 15:40:08,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:08,842][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth... [2024-08-01 15:40:08,878][00148] Using port 41821 on host... [2024-08-01 15:40:08,883][00142] Using port 41221 on host... [2024-08-01 15:40:08,912][00146] Using port 41621 on host... [2024-08-01 15:40:08,931][00143] Using port 41321 on host... [2024-08-01 15:40:09,032][00135] Using port 40521 on host... [2024-08-01 15:40:09,057][00133] Using port 40421 on host... [2024-08-01 15:40:09,387][00141] Using port 40921 on host... [2024-08-01 15:40:10,143][00138] Using port 40721 on host... [2024-08-01 15:40:10,189][00139] Using port 41121 on host... [2024-08-01 15:40:10,282][00132] Using port 40321 on host... [2024-08-01 15:40:10,469][00136] Initialized w:3 v:21 player:0 [2024-08-01 15:40:10,471][00136] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,501][00144] Initialized w:11 v:21 player:0 [2024-08-01 15:40:10,504][00144] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,622][00145] Using port 41521 on host... [2024-08-01 15:40:10,700][00140] Initialized w:7 v:21 player:0 [2024-08-01 15:40:10,702][00140] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,839][00137] Initialized w:5 v:21 player:0 [2024-08-01 15:40:10,841][00137] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,932][00147] Initialized w:14 v:21 player:0 [2024-08-01 15:40:10,933][00147] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,952][00142] Initialized w:9 v:21 player:0 [2024-08-01 15:40:10,954][00142] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,972][00146] Initialized w:13 v:21 player:0 [2024-08-01 15:40:10,974][00146] Decorrelating experience for 672 frames... [2024-08-01 15:40:10,975][00143] Initialized w:10 v:21 player:0 [2024-08-01 15:40:10,977][00143] Decorrelating experience for 672 frames... [2024-08-01 15:40:11,078][00135] Initialized w:2 v:21 player:0 [2024-08-01 15:40:11,080][00135] Decorrelating experience for 672 frames... [2024-08-01 15:40:11,111][00133] Initialized w:1 v:21 player:0 [2024-08-01 15:40:11,113][00133] Decorrelating experience for 672 frames... [2024-08-01 15:40:11,129][00148] Initialized w:15 v:21 player:0 [2024-08-01 15:40:11,133][00148] Decorrelating experience for 672 frames... [2024-08-01 15:40:11,468][00141] Initialized w:6 v:21 player:0 [2024-08-01 15:40:11,471][00141] Decorrelating experience for 672 frames... [2024-08-01 15:40:12,306][00138] Initialized w:4 v:21 player:0 [2024-08-01 15:40:12,308][00138] Decorrelating experience for 672 frames... [2024-08-01 15:40:12,339][00139] Initialized w:8 v:21 player:0 [2024-08-01 15:40:12,351][00139] Decorrelating experience for 672 frames... [2024-08-01 15:40:12,388][00132] Initialized w:0 v:21 player:0 [2024-08-01 15:40:12,392][00132] Decorrelating experience for 672 frames... [2024-08-01 15:40:12,781][00145] Initialized w:12 v:21 player:0 [2024-08-01 15:40:12,783][00145] Decorrelating experience for 672 frames... [2024-08-01 15:40:13,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:14,687][00144] Using port 41422 on host... [2024-08-01 15:40:14,867][00136] Using port 40622 on host... [2024-08-01 15:40:15,135][00140] Using port 41022 on host... [2024-08-01 15:40:15,326][00137] Using port 40822 on host... [2024-08-01 15:40:15,397][00147] Using port 41722 on host... [2024-08-01 15:40:15,522][00142] Using port 41222 on host... [2024-08-01 15:40:15,543][00146] Using port 41622 on host... [2024-08-01 15:40:15,567][00143] Using port 41322 on host... [2024-08-01 15:40:15,574][00148] Using port 41822 on host... [2024-08-01 15:40:15,696][00133] Using port 40422 on host... [2024-08-01 15:40:15,723][00135] Using port 40522 on host... [2024-08-01 15:40:15,870][00141] Using port 40922 on host... [2024-08-01 15:40:16,691][00139] Using port 41122 on host... [2024-08-01 15:40:16,786][00138] Using port 40722 on host... [2024-08-01 15:40:16,803][00144] Initialized w:11 v:22 player:0 [2024-08-01 15:40:16,805][00144] Decorrelating experience for 704 frames... [2024-08-01 15:40:16,902][00132] Using port 40322 on host... [2024-08-01 15:40:16,976][00136] Initialized w:3 v:22 player:0 [2024-08-01 15:40:16,978][00136] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,236][00140] Initialized w:7 v:22 player:0 [2024-08-01 15:40:17,239][00140] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,291][00145] Using port 41522 on host... [2024-08-01 15:40:17,414][00137] Initialized w:5 v:22 player:0 [2024-08-01 15:40:17,416][00137] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,464][00147] Initialized w:14 v:22 player:0 [2024-08-01 15:40:17,465][00147] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,569][00142] Initialized w:9 v:22 player:0 [2024-08-01 15:40:17,571][00142] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,573][00146] Initialized w:13 v:22 player:0 [2024-08-01 15:40:17,574][00146] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,579][00143] Initialized w:10 v:22 player:0 [2024-08-01 15:40:17,581][00143] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,754][00135] Initialized w:2 v:22 player:0 [2024-08-01 15:40:17,756][00135] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,786][00133] Initialized w:1 v:22 player:0 [2024-08-01 15:40:17,788][00133] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,859][00148] Initialized w:15 v:22 player:0 [2024-08-01 15:40:17,861][00148] Decorrelating experience for 704 frames... [2024-08-01 15:40:17,950][00141] Initialized w:6 v:22 player:0 [2024-08-01 15:40:17,952][00141] Decorrelating experience for 704 frames... [2024-08-01 15:40:18,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:18,904][00139] Initialized w:8 v:22 player:0 [2024-08-01 15:40:18,906][00139] Decorrelating experience for 704 frames... [2024-08-01 15:40:19,003][00138] Initialized w:4 v:22 player:0 [2024-08-01 15:40:19,005][00138] Decorrelating experience for 704 frames... [2024-08-01 15:40:19,062][00132] Initialized w:0 v:22 player:0 [2024-08-01 15:40:19,064][00132] Decorrelating experience for 704 frames... [2024-08-01 15:40:19,500][00145] Initialized w:12 v:22 player:0 [2024-08-01 15:40:19,502][00145] Decorrelating experience for 704 frames... [2024-08-01 15:40:21,448][00144] Using port 41423 on host... [2024-08-01 15:40:21,656][00140] Using port 41023 on host... [2024-08-01 15:40:21,761][00136] Using port 40623 on host... [2024-08-01 15:40:22,049][00147] Using port 41723 on host... [2024-08-01 15:40:22,188][00143] Using port 41323 on host... [2024-08-01 15:40:22,190][00137] Using port 40823 on host... [2024-08-01 15:40:22,233][00148] Using port 41823 on host... [2024-08-01 15:40:22,288][00142] Using port 41223 on host... [2024-08-01 15:40:22,306][00146] Using port 41623 on host... [2024-08-01 15:40:22,405][00133] Using port 40423 on host... [2024-08-01 15:40:22,545][00141] Using port 40923 on host... [2024-08-01 15:40:22,547][00135] Using port 40523 on host... [2024-08-01 15:40:23,616][00144] Initialized w:11 v:23 player:0 [2024-08-01 15:40:23,621][00144] Decorrelating experience for 736 frames... [2024-08-01 15:40:23,796][00140] Initialized w:7 v:23 player:0 [2024-08-01 15:40:23,799][00140] Decorrelating experience for 736 frames... [2024-08-01 15:40:23,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:23,915][00136] Initialized w:3 v:23 player:0 [2024-08-01 15:40:23,925][00136] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,221][00138] Using port 40723 on host... [2024-08-01 15:40:24,344][00139] Using port 41123 on host... [2024-08-01 15:40:24,449][00147] Initialized w:14 v:23 player:0 [2024-08-01 15:40:24,451][00147] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,470][00132] Using port 40323 on host... [2024-08-01 15:40:24,541][00143] Initialized w:10 v:23 player:0 [2024-08-01 15:40:24,543][00143] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,708][00137] Initialized w:5 v:23 player:0 [2024-08-01 15:40:24,713][00137] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,735][00148] Initialized w:15 v:23 player:0 [2024-08-01 15:40:24,737][00148] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,754][00142] Initialized w:9 v:23 player:0 [2024-08-01 15:40:24,756][00142] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,769][00146] Initialized w:13 v:23 player:0 [2024-08-01 15:40:24,772][00146] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,875][00141] Initialized w:6 v:23 player:0 [2024-08-01 15:40:24,877][00141] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,905][00135] Initialized w:2 v:23 player:0 [2024-08-01 15:40:24,907][00135] Decorrelating experience for 736 frames... [2024-08-01 15:40:24,916][00133] Initialized w:1 v:23 player:0 [2024-08-01 15:40:24,920][00133] Decorrelating experience for 736 frames... [2024-08-01 15:40:25,108][00145] Using port 41523 on host... [2024-08-01 15:40:26,687][00138] Initialized w:4 v:23 player:0 [2024-08-01 15:40:26,690][00138] Decorrelating experience for 736 frames... [2024-08-01 15:40:26,752][00139] Initialized w:8 v:23 player:0 [2024-08-01 15:40:26,753][00139] Decorrelating experience for 736 frames... [2024-08-01 15:40:26,872][00132] Initialized w:0 v:23 player:0 [2024-08-01 15:40:26,874][00132] Decorrelating experience for 736 frames... [2024-08-01 15:40:27,344][00145] Initialized w:12 v:23 player:0 [2024-08-01 15:40:27,346][00145] Decorrelating experience for 736 frames... [2024-08-01 15:40:28,757][00034] Heartbeat connected on RolloutWorker_w11 [2024-08-01 15:40:28,770][00034] Heartbeat connected on RolloutWorker_w3 [2024-08-01 15:40:28,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:29,088][00034] Heartbeat connected on RolloutWorker_w7 [2024-08-01 15:40:29,441][00034] Heartbeat connected on RolloutWorker_w15 [2024-08-01 15:40:29,555][00034] Heartbeat connected on RolloutWorker_w5 [2024-08-01 15:40:29,565][00034] Heartbeat connected on RolloutWorker_w14 [2024-08-01 15:40:29,636][00034] Heartbeat connected on RolloutWorker_w9 [2024-08-01 15:40:29,819][00034] Heartbeat connected on RolloutWorker_w10 [2024-08-01 15:40:29,851][00034] Heartbeat connected on RolloutWorker_w6 [2024-08-01 15:40:29,859][00034] Heartbeat connected on RolloutWorker_w13 [2024-08-01 15:40:29,938][00034] Heartbeat connected on RolloutWorker_w1 [2024-08-01 15:40:29,982][00034] Heartbeat connected on RolloutWorker_w2 [2024-08-01 15:40:31,764][00034] Heartbeat connected on RolloutWorker_w4 [2024-08-01 15:40:31,921][00034] Heartbeat connected on RolloutWorker_w8 [2024-08-01 15:40:32,348][00034] Heartbeat connected on RolloutWorker_w0 [2024-08-01 15:40:32,903][00034] Heartbeat connected on RolloutWorker_w12 [2024-08-01 15:40:33,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 88.8. Samples: 3996. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:36,961][00112] Signal inference workers to stop experience collection... [2024-08-01 15:40:37,003][00134] InferenceWorker_p0-w0: stopping experience collection [2024-08-01 15:40:38,838][00034] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 247.2. Samples: 11124. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2024-08-01 15:40:41,858][00112] Signal inference workers to resume experience collection... [2024-08-01 15:40:41,859][00134] InferenceWorker_p0-w0: resuming experience collection [2024-08-01 15:40:43,838][00034] Fps is (10 sec: 1638.4, 60 sec: 273.1, 300 sec: 126.0). Total num frames: 16384. Throughput: 0: 247.2. Samples: 11124. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2024-08-01 15:40:48,839][00034] Fps is (10 sec: 2457.5, 60 sec: 409.6, 300 sec: 182.0). Total num frames: 24576. Throughput: 0: 435.5. Samples: 19596. Policy #0 lag: (min: 0.0, avg: 3.3, max: 4.0) [2024-08-01 15:40:52,690][00134] Updated weights for policy 0, policy_version 11 (0.0019) [2024-08-01 15:40:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 819.2, 300 sec: 351.1). Total num frames: 49152. Throughput: 0: 657.3. Samples: 29580. Policy #0 lag: (min: 0.0, avg: 3.9, max: 10.0) [2024-08-01 15:40:58,839][00034] Fps is (10 sec: 3686.3, 60 sec: 1024.0, 300 sec: 423.7). Total num frames: 61440. Throughput: 0: 762.7. Samples: 34320. Policy #0 lag: (min: 0.0, avg: 1.6, max: 6.0) [2024-08-01 15:41:03,839][00034] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 491.5). Total num frames: 73728. Throughput: 0: 980.0. Samples: 44100. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:41:05,705][00134] Updated weights for policy 0, policy_version 21 (0.0024) [2024-08-01 15:41:08,838][00034] Fps is (10 sec: 3686.7, 60 sec: 1638.4, 300 sec: 634.2). Total num frames: 98304. Throughput: 0: 1199.5. Samples: 53976. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:41:13,838][00034] Fps is (10 sec: 4096.1, 60 sec: 1911.5, 300 sec: 716.8). Total num frames: 114688. Throughput: 0: 1315.2. Samples: 59184. Policy #0 lag: (min: 0.0, avg: 1.4, max: 6.0) [2024-08-01 15:41:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2048.0, 300 sec: 744.7). Total num frames: 122880. Throughput: 0: 1449.1. Samples: 69204. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:41:19,344][00134] Updated weights for policy 0, policy_version 31 (0.0028) [2024-08-01 15:41:23,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2457.6, 300 sec: 867.4). Total num frames: 147456. Throughput: 0: 1513.9. Samples: 79248. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:41:28,841][00034] Fps is (10 sec: 3685.3, 60 sec: 2662.3, 300 sec: 912.8). Total num frames: 159744. Throughput: 0: 1626.6. Samples: 84324. Policy #0 lag: (min: 0.0, avg: 1.6, max: 6.0) [2024-08-01 15:41:29,802][00134] Updated weights for policy 0, policy_version 41 (0.0031) [2024-08-01 15:41:33,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2867.2, 300 sec: 955.7). Total num frames: 172032. Throughput: 0: 1649.1. Samples: 93804. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 15:41:38,838][00034] Fps is (10 sec: 3687.5, 60 sec: 3276.8, 300 sec: 1062.7). Total num frames: 196608. Throughput: 0: 1649.1. Samples: 103788. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 15:41:43,221][00134] Updated weights for policy 0, policy_version 51 (0.0024) [2024-08-01 15:41:43,839][00034] Fps is (10 sec: 4095.8, 60 sec: 3276.8, 300 sec: 1121.0). Total num frames: 212992. Throughput: 0: 1658.9. Samples: 108972. Policy #0 lag: (min: 1.0, avg: 3.1, max: 7.0) [2024-08-01 15:41:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 1155.3). Total num frames: 225280. Throughput: 0: 1664.8. Samples: 119016. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:41:53,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3276.8, 300 sec: 1228.8). Total num frames: 245760. Throughput: 0: 1667.5. Samples: 129012. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 15:41:55,488][00134] Updated weights for policy 0, policy_version 61 (0.0019) [2024-08-01 15:41:58,839][00034] Fps is (10 sec: 3686.3, 60 sec: 3345.1, 300 sec: 1278.8). Total num frames: 262144. Throughput: 0: 1664.8. Samples: 134100. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 15:42:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 1306.8). Total num frames: 274432. Throughput: 0: 1652.3. Samples: 143556. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:42:07,047][00134] Updated weights for policy 0, policy_version 71 (0.0019) [2024-08-01 15:42:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 1371.7). Total num frames: 294912. Throughput: 0: 1648.5. Samples: 153432. Policy #0 lag: (min: 0.0, avg: 3.9, max: 7.0) [2024-08-01 15:42:08,842][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth... [2024-08-01 15:42:13,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3208.5, 300 sec: 1396.4). Total num frames: 307200. Throughput: 0: 1649.7. Samples: 158556. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 15:42:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 1438.2). Total num frames: 323584. Throughput: 0: 1663.2. Samples: 168648. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 15:42:19,234][00134] Updated weights for policy 0, policy_version 81 (0.0020) [2024-08-01 15:42:23,838][00034] Fps is (10 sec: 3686.5, 60 sec: 3276.8, 300 sec: 1495.9). Total num frames: 344064. Throughput: 0: 1660.8. Samples: 178524. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 15:42:28,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3277.0, 300 sec: 1516.4). Total num frames: 356352. Throughput: 0: 1655.2. Samples: 183456. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 15:42:32,698][00134] Updated weights for policy 0, policy_version 91 (0.0032) [2024-08-01 15:42:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 1570.1). Total num frames: 376832. Throughput: 0: 1658.7. Samples: 193656. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:42:38,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 1605.0). Total num frames: 393216. Throughput: 0: 1641.1. Samples: 202860. Policy #0 lag: (min: 0.0, avg: 2.2, max: 6.0) [2024-08-01 15:42:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 1638.4). Total num frames: 409600. Throughput: 0: 1641.3. Samples: 207960. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:42:44,518][00134] Updated weights for policy 0, policy_version 101 (0.0019) [2024-08-01 15:42:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 1654.5). Total num frames: 421888. Throughput: 0: 1652.3. Samples: 217908. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 15:42:53,842][00034] Fps is (10 sec: 3275.5, 60 sec: 3276.6, 300 sec: 1701.4). Total num frames: 442368. Throughput: 0: 1654.8. Samples: 227904. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:42:56,847][00134] Updated weights for policy 0, policy_version 111 (0.0019) [2024-08-01 15:42:58,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 1731.1). Total num frames: 458752. Throughput: 0: 1654.4. Samples: 233004. Policy #0 lag: (min: 0.0, avg: 2.2, max: 6.0) [2024-08-01 15:43:03,838][00034] Fps is (10 sec: 3687.9, 60 sec: 3413.3, 300 sec: 1774.9). Total num frames: 479232. Throughput: 0: 1656.3. Samples: 243180. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:43:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 1787.3). Total num frames: 491520. Throughput: 0: 1638.1. Samples: 252240. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:43:11,140][00134] Updated weights for policy 0, policy_version 121 (0.0025) [2024-08-01 15:43:13,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3345.0, 300 sec: 1813.9). Total num frames: 507904. Throughput: 0: 1637.8. Samples: 257160. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 15:43:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 1825.2). Total num frames: 520192. Throughput: 0: 1630.9. Samples: 267048. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:43:21,476][00134] Updated weights for policy 0, policy_version 131 (0.0020) [2024-08-01 15:43:23,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3276.8, 300 sec: 1864.4). Total num frames: 540672. Throughput: 0: 1644.3. Samples: 276852. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 15:43:28,839][00034] Fps is (10 sec: 4095.9, 60 sec: 3413.3, 300 sec: 1902.2). Total num frames: 561152. Throughput: 0: 1644.8. Samples: 281976. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:43:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 1916.1). Total num frames: 565248. Throughput: 0: 1645.6. Samples: 291960. Policy #0 lag: (min: 0.0, avg: 4.2, max: 7.0) [2024-08-01 15:43:34,945][00134] Updated weights for policy 0, policy_version 141 (0.0019) [2024-08-01 15:43:38,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3276.8, 300 sec: 1999.4). Total num frames: 589824. Throughput: 0: 1630.5. Samples: 301272. Policy #0 lag: (min: 0.0, avg: 4.1, max: 7.0) [2024-08-01 15:43:43,839][00034] Fps is (10 sec: 4505.5, 60 sec: 3345.1, 300 sec: 2068.8). Total num frames: 610304. Throughput: 0: 1623.7. Samples: 306072. Policy #0 lag: (min: 0.0, avg: 2.2, max: 6.0) [2024-08-01 15:43:48,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 2082.7). Total num frames: 614400. Throughput: 0: 1613.6. Samples: 315792. Policy #0 lag: (min: 0.0, avg: 4.3, max: 7.0) [2024-08-01 15:43:49,481][00134] Updated weights for policy 0, policy_version 151 (0.0020) [2024-08-01 15:43:53,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3277.0, 300 sec: 2166.0). Total num frames: 638976. Throughput: 0: 1627.7. Samples: 325488. Policy #0 lag: (min: 0.0, avg: 4.4, max: 7.0) [2024-08-01 15:43:58,554][00134] Updated weights for policy 0, policy_version 161 (0.0020) [2024-08-01 15:43:58,838][00034] Fps is (10 sec: 4505.6, 60 sec: 3345.1, 300 sec: 2235.4). Total num frames: 659456. Throughput: 0: 1629.6. Samples: 330492. Policy #0 lag: (min: 0.0, avg: 2.2, max: 6.0) [2024-08-01 15:44:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 2249.3). Total num frames: 663552. Throughput: 0: 1628.0. Samples: 340308. Policy #0 lag: (min: 0.0, avg: 4.4, max: 7.0) [2024-08-01 15:44:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 2332.6). Total num frames: 688128. Throughput: 0: 1626.1. Samples: 350028. Policy #0 lag: (min: 0.0, avg: 4.2, max: 7.0) [2024-08-01 15:44:08,847][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000168_688128.pth... [2024-08-01 15:44:09,010][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth [2024-08-01 15:44:13,274][00134] Updated weights for policy 0, policy_version 171 (0.0020) [2024-08-01 15:44:13,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3208.6, 300 sec: 2374.3). Total num frames: 700416. Throughput: 0: 1604.8. Samples: 354192. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:44:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 2415.9). Total num frames: 712704. Throughput: 0: 1584.3. Samples: 363252. Policy #0 lag: (min: 0.0, avg: 3.8, max: 9.0) [2024-08-01 15:44:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 2485.4). Total num frames: 733184. Throughput: 0: 1591.7. Samples: 372900. Policy #0 lag: (min: 0.0, avg: 3.9, max: 9.0) [2024-08-01 15:44:28,344][00134] Updated weights for policy 0, policy_version 181 (0.0019) [2024-08-01 15:44:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2513.1). Total num frames: 741376. Throughput: 0: 1595.2. Samples: 377856. Policy #0 lag: (min: 0.0, avg: 2.7, max: 8.0) [2024-08-01 15:44:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 2582.6). Total num frames: 761856. Throughput: 0: 1589.1. Samples: 387300. Policy #0 lag: (min: 0.0, avg: 4.2, max: 7.0) [2024-08-01 15:44:38,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2638.1). Total num frames: 778240. Throughput: 0: 1581.3. Samples: 396648. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:44:38,948][00134] Updated weights for policy 0, policy_version 191 (0.0020) [2024-08-01 15:44:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2679.8). Total num frames: 790528. Throughput: 0: 1576.5. Samples: 401436. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 15:44:48,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3276.8, 300 sec: 2749.2). Total num frames: 811008. Throughput: 0: 1551.2. Samples: 410112. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:44:52,449][00134] Updated weights for policy 0, policy_version 201 (0.0020) [2024-08-01 15:44:53,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2804.7). Total num frames: 827392. Throughput: 0: 1550.7. Samples: 419808. Policy #0 lag: (min: 0.0, avg: 2.2, max: 6.0) [2024-08-01 15:44:58,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 2846.4). Total num frames: 839680. Throughput: 0: 1564.5. Samples: 424596. Policy #0 lag: (min: 0.0, avg: 2.0, max: 6.0) [2024-08-01 15:45:03,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3208.5, 300 sec: 2901.9). Total num frames: 856064. Throughput: 0: 1585.9. Samples: 434616. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:45:05,786][00134] Updated weights for policy 0, policy_version 211 (0.0019) [2024-08-01 15:45:08,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2971.3). Total num frames: 876544. Throughput: 0: 1584.8. Samples: 444216. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 15:45:13,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.2, 300 sec: 3013.0). Total num frames: 888832. Throughput: 0: 1587.7. Samples: 449304. Policy #0 lag: (min: 0.0, avg: 2.3, max: 6.0) [2024-08-01 15:45:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 3054.6). Total num frames: 901120. Throughput: 0: 1576.3. Samples: 458232. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 15:45:18,992][00134] Updated weights for policy 0, policy_version 221 (0.0020) [2024-08-01 15:45:23,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 3124.1). Total num frames: 921600. Throughput: 0: 1583.7. Samples: 467916. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:45:28,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3179.6). Total num frames: 937984. Throughput: 0: 1590.9. Samples: 473028. Policy #0 lag: (min: 0.0, avg: 3.8, max: 8.0) [2024-08-01 15:45:29,970][00134] Updated weights for policy 0, policy_version 231 (0.0019) [2024-08-01 15:45:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 950272. Throughput: 0: 1618.4. Samples: 482940. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 15:45:38,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3208.5, 300 sec: 3235.1). Total num frames: 970752. Throughput: 0: 1619.2. Samples: 492672. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:45:43,214][00134] Updated weights for policy 0, policy_version 241 (0.0028) [2024-08-01 15:45:43,839][00034] Fps is (10 sec: 3686.1, 60 sec: 3276.8, 300 sec: 3262.9). Total num frames: 987136. Throughput: 0: 1622.9. Samples: 497628. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:45:48,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 999424. Throughput: 0: 1604.0. Samples: 506796. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:45:53,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3208.5, 300 sec: 3249.0). Total num frames: 1019904. Throughput: 0: 1587.5. Samples: 515652. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:45:57,071][00134] Updated weights for policy 0, policy_version 251 (0.0021) [2024-08-01 15:45:58,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3208.5, 300 sec: 3249.0). Total num frames: 1032192. Throughput: 0: 1580.0. Samples: 520404. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 15:46:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3208.6, 300 sec: 3221.3). Total num frames: 1048576. Throughput: 0: 1592.3. Samples: 529884. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:46:08,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3140.3, 300 sec: 3221.3). Total num frames: 1064960. Throughput: 0: 1585.3. Samples: 539256. Policy #0 lag: (min: 0.0, avg: 2.9, max: 8.0) [2024-08-01 15:46:08,845][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000260_1064960.pth... [2024-08-01 15:46:09,017][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth [2024-08-01 15:46:09,182][00134] Updated weights for policy 0, policy_version 261 (0.0020) [2024-08-01 15:46:13,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3208.6, 300 sec: 3249.0). Total num frames: 1081344. Throughput: 0: 1580.0. Samples: 544128. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 15:46:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3207.4). Total num frames: 1093632. Throughput: 0: 1568.0. Samples: 553500. Policy #0 lag: (min: 0.0, avg: 2.8, max: 8.0) [2024-08-01 15:46:23,839][00034] Fps is (10 sec: 2457.4, 60 sec: 3071.9, 300 sec: 3207.4). Total num frames: 1105920. Throughput: 0: 1543.7. Samples: 562140. Policy #0 lag: (min: 0.0, avg: 3.5, max: 6.0) [2024-08-01 15:46:24,165][00134] Updated weights for policy 0, policy_version 271 (0.0020) [2024-08-01 15:46:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3235.1). Total num frames: 1126400. Throughput: 0: 1536.8. Samples: 566784. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 15:46:33,840][00034] Fps is (10 sec: 3276.7, 60 sec: 3140.2, 300 sec: 3193.5). Total num frames: 1138688. Throughput: 0: 1542.1. Samples: 576192. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 15:46:36,033][00134] Updated weights for policy 0, policy_version 281 (0.0020) [2024-08-01 15:46:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3193.5). Total num frames: 1155072. Throughput: 0: 1555.7. Samples: 585660. Policy #0 lag: (min: 0.0, avg: 3.9, max: 8.0) [2024-08-01 15:46:43,838][00034] Fps is (10 sec: 3277.2, 60 sec: 3072.0, 300 sec: 3207.4). Total num frames: 1171456. Throughput: 0: 1555.0. Samples: 590376. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 15:46:43,872][00147] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:46:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3193.5). Total num frames: 1187840. Throughput: 0: 1549.9. Samples: 599628. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:46:49,973][00134] Updated weights for policy 0, policy_version 291 (0.0022) [2024-08-01 15:46:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3179.6). Total num frames: 1200128. Throughput: 0: 1535.2. Samples: 608340. Policy #0 lag: (min: 0.0, avg: 2.8, max: 8.0) [2024-08-01 15:46:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3193.5). Total num frames: 1216512. Throughput: 0: 1529.9. Samples: 612972. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:47:02,396][00134] Updated weights for policy 0, policy_version 301 (0.0033) [2024-08-01 15:47:03,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3193.5). Total num frames: 1236992. Throughput: 0: 1529.9. Samples: 622344. Policy #0 lag: (min: 0.0, avg: 3.4, max: 6.0) [2024-08-01 15:47:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3193.5). Total num frames: 1249280. Throughput: 0: 1549.1. Samples: 631848. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:47:13,839][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3179.6). Total num frames: 1261568. Throughput: 0: 1548.0. Samples: 636444. Policy #0 lag: (min: 0.0, avg: 3.0, max: 8.0) [2024-08-01 15:47:16,261][00134] Updated weights for policy 0, policy_version 311 (0.0020) [2024-08-01 15:47:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3179.6). Total num frames: 1282048. Throughput: 0: 1547.0. Samples: 645804. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:47:23,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3179.6). Total num frames: 1294336. Throughput: 0: 1540.8. Samples: 654996. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:47:25,592][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:47:28,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3072.0, 300 sec: 3165.7). Total num frames: 1310720. Throughput: 0: 1524.5. Samples: 658980. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 15:47:30,403][00134] Updated weights for policy 0, policy_version 321 (0.0020) [2024-08-01 15:47:32,548][00148] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:47:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3165.7). Total num frames: 1327104. Throughput: 0: 1530.4. Samples: 668496. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:47:38,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3072.0, 300 sec: 3151.8). Total num frames: 1339392. Throughput: 0: 1541.1. Samples: 677688. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:47:42,145][00134] Updated weights for policy 0, policy_version 331 (0.0021) [2024-08-01 15:47:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3165.7). Total num frames: 1355776. Throughput: 0: 1539.5. Samples: 682248. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:47:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3151.9). Total num frames: 1372160. Throughput: 0: 1538.9. Samples: 691596. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:47:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3138.0). Total num frames: 1384448. Throughput: 0: 1532.8. Samples: 700824. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:47:56,516][00134] Updated weights for policy 0, policy_version 341 (0.0020) [2024-08-01 15:47:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3138.0). Total num frames: 1404928. Throughput: 0: 1532.8. Samples: 705420. Policy #0 lag: (min: 0.0, avg: 2.1, max: 6.0) [2024-08-01 15:48:01,140][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:48:03,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 3124.1). Total num frames: 1413120. Throughput: 0: 1524.5. Samples: 714408. Policy #0 lag: (min: 0.0, avg: 3.5, max: 9.0) [2024-08-01 15:48:08,839][00034] Fps is (10 sec: 2457.5, 60 sec: 3003.7, 300 sec: 3124.1). Total num frames: 1429504. Throughput: 0: 1526.4. Samples: 723684. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 15:48:08,847][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000349_1429504.pth... [2024-08-01 15:48:09,021][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000168_688128.pth [2024-08-01 15:48:10,407][00134] Updated weights for policy 0, policy_version 351 (0.0033) [2024-08-01 15:48:13,838][00034] Fps is (10 sec: 4096.2, 60 sec: 3208.5, 300 sec: 3165.7). Total num frames: 1454080. Throughput: 0: 1538.4. Samples: 728208. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 15:48:18,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 3124.1). Total num frames: 1462272. Throughput: 0: 1533.9. Samples: 737520. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 15:48:21,658][00134] Updated weights for policy 0, policy_version 361 (0.0020) [2024-08-01 15:48:23,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 3110.2). Total num frames: 1478656. Throughput: 0: 1536.0. Samples: 746808. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 15:48:28,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3165.7). Total num frames: 1499136. Throughput: 0: 1542.4. Samples: 751656. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 15:48:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3110.2). Total num frames: 1507328. Throughput: 0: 1528.8. Samples: 760392. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:48:36,589][00134] Updated weights for policy 0, policy_version 371 (0.0025) [2024-08-01 15:48:38,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3140.3, 300 sec: 3110.2). Total num frames: 1527808. Throughput: 0: 1529.6. Samples: 769656. Policy #0 lag: (min: 0.0, avg: 3.9, max: 7.0) [2024-08-01 15:48:43,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3072.0, 300 sec: 3138.0). Total num frames: 1540096. Throughput: 0: 1531.5. Samples: 774336. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 15:48:48,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3072.0, 300 sec: 3110.2). Total num frames: 1556480. Throughput: 0: 1535.2. Samples: 783492. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:48:50,746][00134] Updated weights for policy 0, policy_version 381 (0.0030) [2024-08-01 15:48:53,838][00034] Fps is (10 sec: 3686.5, 60 sec: 3208.5, 300 sec: 3110.2). Total num frames: 1576960. Throughput: 0: 1533.9. Samples: 792708. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:48:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3124.1). Total num frames: 1585152. Throughput: 0: 1544.5. Samples: 797712. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:49:01,688][00134] Updated weights for policy 0, policy_version 391 (0.0020) [2024-08-01 15:49:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3140.3, 300 sec: 3096.3). Total num frames: 1601536. Throughput: 0: 1529.9. Samples: 806364. Policy #0 lag: (min: 0.0, avg: 2.1, max: 6.0) [2024-08-01 15:49:04,788][00147] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:49:07,670][00143] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:49:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3110.2). Total num frames: 1617920. Throughput: 0: 1526.7. Samples: 815508. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:49:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3110.2). Total num frames: 1630208. Throughput: 0: 1523.5. Samples: 820212. Policy #0 lag: (min: 0.0, avg: 3.9, max: 8.0) [2024-08-01 15:49:16,407][00134] Updated weights for policy 0, policy_version 401 (0.0020) [2024-08-01 15:49:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3096.3). Total num frames: 1646592. Throughput: 0: 1532.8. Samples: 829368. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 15:49:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3124.1). Total num frames: 1662976. Throughput: 0: 1537.9. Samples: 838860. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:49:28,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 3096.3). Total num frames: 1675264. Throughput: 0: 1536.3. Samples: 843468. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 15:49:29,968][00134] Updated weights for policy 0, policy_version 411 (0.0020) [2024-08-01 15:49:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3110.2). Total num frames: 1695744. Throughput: 0: 1540.5. Samples: 852816. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:49:38,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 3110.2). Total num frames: 1708032. Throughput: 0: 1528.0. Samples: 861468. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:49:43,411][00134] Updated weights for policy 0, policy_version 421 (0.0020) [2024-08-01 15:49:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3096.3). Total num frames: 1724416. Throughput: 0: 1520.3. Samples: 866124. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:49:48,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3072.0, 300 sec: 3096.3). Total num frames: 1740800. Throughput: 0: 1533.3. Samples: 875364. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:49:50,529][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:49:53,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 3096.3). Total num frames: 1753088. Throughput: 0: 1542.1. Samples: 884904. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 15:49:55,923][00134] Updated weights for policy 0, policy_version 431 (0.0020) [2024-08-01 15:49:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3096.3). Total num frames: 1769472. Throughput: 0: 1540.0. Samples: 889512. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:50:03,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 1785856. Throughput: 0: 1547.2. Samples: 898992. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:50:08,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3082.4). Total num frames: 1798144. Throughput: 0: 1528.2. Samples: 907632. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 15:50:08,845][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000439_1798144.pth... [2024-08-01 15:50:09,023][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000260_1064960.pth [2024-08-01 15:50:09,711][00134] Updated weights for policy 0, policy_version 441 (0.0020) [2024-08-01 15:50:13,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3140.2, 300 sec: 3110.2). Total num frames: 1818624. Throughput: 0: 1528.5. Samples: 912252. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:50:18,838][00034] Fps is (10 sec: 3686.6, 60 sec: 3140.3, 300 sec: 3096.3). Total num frames: 1835008. Throughput: 0: 1526.9. Samples: 921528. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 15:50:23,498][00134] Updated weights for policy 0, policy_version 451 (0.0020) [2024-08-01 15:50:23,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 1847296. Throughput: 0: 1539.2. Samples: 930732. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:50:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3096.3). Total num frames: 1863680. Throughput: 0: 1537.9. Samples: 935328. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:50:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 1875968. Throughput: 0: 1539.5. Samples: 944640. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 15:50:36,641][00134] Updated weights for policy 0, policy_version 461 (0.0030) [2024-08-01 15:50:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 1892352. Throughput: 0: 1531.8. Samples: 953832. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:50:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 1908736. Throughput: 0: 1521.1. Samples: 957960. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:50:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 1925120. Throughput: 0: 1520.0. Samples: 967392. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 15:50:49,781][00134] Updated weights for policy 0, policy_version 471 (0.0025) [2024-08-01 15:50:52,952][00147] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:50:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 1937408. Throughput: 0: 1534.4. Samples: 976680. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:50:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 1953792. Throughput: 0: 1534.2. Samples: 981288. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 15:51:03,558][00134] Updated weights for policy 0, policy_version 481 (0.0020) [2024-08-01 15:51:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 1970176. Throughput: 0: 1536.0. Samples: 990648. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:51:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3068.5). Total num frames: 1986560. Throughput: 0: 1538.7. Samples: 999972. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:51:09,011][00137] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:51:13,843][00034] Fps is (10 sec: 2865.9, 60 sec: 3003.5, 300 sec: 3068.5). Total num frames: 1998848. Throughput: 0: 1535.3. Samples: 1004424. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:51:16,116][00134] Updated weights for policy 0, policy_version 491 (0.0033) [2024-08-01 15:51:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3082.4). Total num frames: 2015232. Throughput: 0: 1528.0. Samples: 1013400. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:51:23,838][00034] Fps is (10 sec: 3278.3, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2031616. Throughput: 0: 1531.2. Samples: 1022736. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:51:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2043904. Throughput: 0: 1543.2. Samples: 1027404. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:51:29,669][00134] Updated weights for policy 0, policy_version 501 (0.0020) [2024-08-01 15:51:33,840][00034] Fps is (10 sec: 2866.7, 60 sec: 3071.9, 300 sec: 3068.5). Total num frames: 2060288. Throughput: 0: 1541.3. Samples: 1036752. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:51:38,839][00034] Fps is (10 sec: 3686.2, 60 sec: 3140.2, 300 sec: 3082.4). Total num frames: 2080768. Throughput: 0: 1545.0. Samples: 1046208. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:51:43,116][00134] Updated weights for policy 0, policy_version 511 (0.0020) [2024-08-01 15:51:43,838][00034] Fps is (10 sec: 3277.4, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2093056. Throughput: 0: 1550.9. Samples: 1051080. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:51:48,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2109440. Throughput: 0: 1532.3. Samples: 1059600. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 15:51:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2121728. Throughput: 0: 1529.6. Samples: 1068804. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 15:51:56,580][00134] Updated weights for policy 0, policy_version 521 (0.0020) [2024-08-01 15:51:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 2138112. Throughput: 0: 1533.2. Samples: 1073412. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 15:52:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2154496. Throughput: 0: 1543.7. Samples: 1082868. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 15:52:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2166784. Throughput: 0: 1549.3. Samples: 1092456. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:52:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000529_2166784.pth... [2024-08-01 15:52:09,033][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000349_1429504.pth [2024-08-01 15:52:09,408][00134] Updated weights for policy 0, policy_version 531 (0.0020) [2024-08-01 15:52:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.2, 300 sec: 3054.6). Total num frames: 2183168. Throughput: 0: 1545.3. Samples: 1096944. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:52:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2199552. Throughput: 0: 1528.6. Samples: 1105536. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:52:23,839][00034] Fps is (10 sec: 2866.9, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 2211840. Throughput: 0: 1524.3. Samples: 1114800. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:52:24,129][00134] Updated weights for policy 0, policy_version 541 (0.0023) [2024-08-01 15:52:24,427][00146] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:52:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3068.5). Total num frames: 2232320. Throughput: 0: 1520.3. Samples: 1119492. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:52:33,838][00034] Fps is (10 sec: 3686.7, 60 sec: 3140.4, 300 sec: 3082.4). Total num frames: 2248704. Throughput: 0: 1540.8. Samples: 1128936. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:52:37,165][00134] Updated weights for policy 0, policy_version 551 (0.0020) [2024-08-01 15:52:38,841][00034] Fps is (10 sec: 2866.4, 60 sec: 3003.6, 300 sec: 3068.5). Total num frames: 2260992. Throughput: 0: 1544.4. Samples: 1138308. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:52:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2277376. Throughput: 0: 1545.6. Samples: 1142964. Policy #0 lag: (min: 0.0, avg: 2.9, max: 8.0) [2024-08-01 15:52:48,850][00034] Fps is (10 sec: 3274.0, 60 sec: 3071.4, 300 sec: 3082.3). Total num frames: 2293760. Throughput: 0: 1539.9. Samples: 1152180. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:52:50,361][00134] Updated weights for policy 0, policy_version 561 (0.0030) [2024-08-01 15:52:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3068.5). Total num frames: 2310144. Throughput: 0: 1514.9. Samples: 1160628. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:52:58,838][00034] Fps is (10 sec: 2870.5, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2322432. Throughput: 0: 1519.7. Samples: 1165332. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:53:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2334720. Throughput: 0: 1544.0. Samples: 1175016. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:53:03,869][00134] Updated weights for policy 0, policy_version 571 (0.0020) [2024-08-01 15:53:04,377][00144] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:53:08,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3140.2, 300 sec: 3054.6). Total num frames: 2355200. Throughput: 0: 1540.5. Samples: 1184124. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:53:13,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3082.4). Total num frames: 2371584. Throughput: 0: 1539.5. Samples: 1188768. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:53:13,937][00138] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:53:17,180][00134] Updated weights for policy 0, policy_version 581 (0.0031) [2024-08-01 15:53:18,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2383872. Throughput: 0: 1530.7. Samples: 1197816. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:53:23,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3140.3, 300 sec: 3054.6). Total num frames: 2400256. Throughput: 0: 1513.9. Samples: 1206432. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 15:53:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2416640. Throughput: 0: 1513.9. Samples: 1211088. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 15:53:29,982][00134] Updated weights for policy 0, policy_version 591 (0.0020) [2024-08-01 15:53:33,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 2428928. Throughput: 0: 1526.0. Samples: 1220832. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:53:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.1, 300 sec: 3068.5). Total num frames: 2445312. Throughput: 0: 1544.5. Samples: 1230132. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 15:53:42,757][00134] Updated weights for policy 0, policy_version 601 (0.0019) [2024-08-01 15:53:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2461696. Throughput: 0: 1547.7. Samples: 1234980. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:53:45,702][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:53:46,851][00147] Large shaping reward -2.535 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.243, -81.0), ('ARMOR', -0.042, -42.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 15:53:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3004.3, 300 sec: 3040.8). Total num frames: 2473984. Throughput: 0: 1536.8. Samples: 1244172. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:53:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2490368. Throughput: 0: 1535.2. Samples: 1253208. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:53:57,424][00134] Updated weights for policy 0, policy_version 611 (0.0020) [2024-08-01 15:53:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2506752. Throughput: 0: 1531.5. Samples: 1257684. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:53:59,434][00140] Large shaping reward 3.551 for [('FRAGCOUNT', 3.0, 3.0), ('HITCOUNT', 0.03, 3.0), ('DAMAGECOUNT', 0.519, 173.0), ('weapon7', 0.002)] [2024-08-01 15:54:03,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3140.3, 300 sec: 3068.5). Total num frames: 2523136. Throughput: 0: 1540.3. Samples: 1267128. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:54:08,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2539520. Throughput: 0: 1554.9. Samples: 1276404. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:54:08,847][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000620_2539520.pth... [2024-08-01 15:54:09,019][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000439_1798144.pth [2024-08-01 15:54:09,249][00134] Updated weights for policy 0, policy_version 621 (0.0021) [2024-08-01 15:54:10,183][00147] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:54:13,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2555904. Throughput: 0: 1556.3. Samples: 1281120. Policy #0 lag: (min: 0.0, avg: 2.2, max: 7.0) [2024-08-01 15:54:17,635][00147] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:54:17,638][00147] Sum rewards: -12.898, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.060', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.010', 'AMMO2': '0.011', 'HITCOUNT': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'DAMAGECOUNT': '0.045', 'AMMO4': '0.054', 'weapon5': '0.092', 'WEAPON4': '0.100', 'WEAPON5': '0.200', 'AMMO3': '0.204', 'weapon4': '0.284', 'WEAPON3': '0.900', 'weapon3': '1.646', 'weapon2': '2.798'} [2024-08-01 15:54:18,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2568192. Throughput: 0: 1545.9. Samples: 1290396. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:54:18,840][00034] Avg episode reward: [(0, '-11.769')] [2024-08-01 15:54:18,850][00112] Saving new best policy, reward=-11.769! [2024-08-01 15:54:22,945][00134] Updated weights for policy 0, policy_version 631 (0.0020) [2024-08-01 15:54:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3096.3). Total num frames: 2588672. Throughput: 0: 1547.2. Samples: 1299756. Policy #0 lag: (min: 0.0, avg: 2.2, max: 7.0) [2024-08-01 15:54:23,840][00034] Avg episode reward: [(0, '-11.769')] [2024-08-01 15:54:23,891][00138] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:54:25,160][00147] DAMAGECOUNT value on done: 29.0 [2024-08-01 15:54:25,164][00147] Sum rewards: -1.471, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.624', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.006', 'WEAPON1': '0.020', 'HITCOUNT': '0.030', 'DAMAGECOUNT': '0.087', 'WEAPON4': '0.100', 'AMMO3': '0.106', 'WEAPON5': '0.200', 'weapon4': '0.204', 'weapon5': '0.492', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.524', 'weapon2': '2.782'} [2024-08-01 15:54:28,556][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:54:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 2596864. Throughput: 0: 1530.4. Samples: 1303848. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:54:28,843][00034] Avg episode reward: [(0, '-5.488')] [2024-08-01 15:54:28,848][00112] Saving new best policy, reward=-5.488! [2024-08-01 15:54:28,977][00141] DAMAGECOUNT value on done: 36.0 [2024-08-01 15:54:28,978][00141] Sum rewards: -8.348, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.945', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.003', 'AMMO5': '0.004', 'weapon4': '0.006', 'AMMO4': '0.015', 'HITCOUNT': '0.050', 'ARMOR': '0.068', 'weapon5': '0.084', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.108', 'AMMO3': '0.193', 'WEAPON3': '0.900', 'weapon3': '2.490', 'weapon2': '2.726'} [2024-08-01 15:54:31,057][00135] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:54:33,346][00143] DAMAGECOUNT value on done: 58.0 [2024-08-01 15:54:33,705][00147] DAMAGECOUNT value on done: 85.0 [2024-08-01 15:54:33,711][00147] Sum rewards: -6.607, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO2': '0.008', 'AMMO4': '0.042', 'HITCOUNT': '0.090', 'AMMO3': '0.103', 'WEAPON4': '0.200', 'weapon4': '0.204', 'DAMAGECOUNT': '0.255', 'ARMOR': '0.499', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.644', 'weapon2': '3.428'} [2024-08-01 15:54:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3082.4). Total num frames: 2617344. Throughput: 0: 1531.7. Samples: 1313100. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:54:33,841][00034] Avg episode reward: [(0, '-5.161')] [2024-08-01 15:54:33,843][00112] Saving new best policy, reward=-5.161! [2024-08-01 15:54:34,831][00144] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:54:34,837][00144] Sum rewards: -7.314, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.004', 'HITCOUNT': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'DAMAGECOUNT': '0.060', 'weapon5': '0.094', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.163', 'weapon4': '0.262', 'WEAPON3': '0.900', 'weapon3': '1.742', 'weapon2': '3.272'} [2024-08-01 15:54:36,735][00141] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:54:36,741][00141] Sum rewards: -3.458, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.535', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.014', 'AMMO2': '0.034', 'weapon5': '0.060', 'AMMO3': '0.099', 'ARMOR': '0.100', 'AMMO4': '0.168', 'WEAPON5': '0.300', 'weapon4': '0.364', 'WEAPON4': '0.400', 'WEAPON3': '0.600', 'weapon3': '2.164', 'weapon2': '2.274'} [2024-08-01 15:54:37,287][00134] Updated weights for policy 0, policy_version 641 (0.0021) [2024-08-01 15:54:38,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2629632. Throughput: 0: 1536.0. Samples: 1322328. Policy #0 lag: (min: 0.0, avg: 2.2, max: 7.0) [2024-08-01 15:54:38,842][00034] Avg episode reward: [(0, '-5.280')] [2024-08-01 15:54:39,010][00135] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:54:39,588][00136] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:54:40,145][00139] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:54:40,149][00139] Sum rewards: -0.508, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.455', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.005', 'HITCOUNT': '0.050', 'weapon5': '0.066', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.123', 'DAMAGECOUNT': '0.210', 'weapon4': '0.370', 'ARMOR': '0.473', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.888', 'weapon2': '2.868'} [2024-08-01 15:54:40,194][00148] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:54:41,302][00143] DAMAGECOUNT value on done: 79.0 [2024-08-01 15:54:41,456][00147] DAMAGECOUNT value on done: 195.0 [2024-08-01 15:54:41,459][00147] Sum rewards: -11.164, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.460', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.013', 'AMMO2': '0.020', 'AMMO4': '0.098', 'HITCOUNT': '0.130', 'weapon4': '0.166', 'weapon5': '0.172', 'WEAPON5': '0.200', 'AMMO3': '0.262', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.585', 'WEAPON3': '1.400', 'weapon3': '1.938', 'weapon2': '3.012'} [2024-08-01 15:54:41,502][00140] DAMAGECOUNT value on done: 249.0 [2024-08-01 15:54:41,521][00140] Sum rewards: -4.420, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'weapon4': '0.126', 'AMMO3': '0.184', 'weapon5': '0.260', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.747', 'WEAPON3': '0.900', 'weapon3': '1.752', 'FRAGCOUNT': '2.000', 'weapon2': '2.698'} [2024-08-01 15:54:42,814][00144] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:54:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2646016. Throughput: 0: 1538.9. Samples: 1326936. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 15:54:43,840][00034] Avg episode reward: [(0, '-4.532')] [2024-08-01 15:54:43,843][00112] Saving new best policy, reward=-4.532! [2024-08-01 15:54:44,134][00132] DAMAGECOUNT value on done: 314.0 [2024-08-01 15:54:44,135][00132] Sum rewards: -3.212, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.667', 'AMMO5': '0.003', 'AMMO2': '0.009', 'ARMOR': '0.032', 'AMMO4': '0.044', 'HITCOUNT': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.142', 'weapon5': '0.146', 'WEAPON4': '0.200', 'WEAPON3': '0.800', 'weapon4': '0.806', 'DAMAGECOUNT': '0.942', 'weapon3': '1.684', 'FRAGCOUNT': '2.000', 'weapon2': '2.468'} [2024-08-01 15:54:44,587][00141] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:54:45,246][00145] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:54:45,252][00145] Sum rewards: -3.887, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO5': '0.005', 'AMMO2': '0.009', 'AMMO4': '0.046', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'DAMAGECOUNT': '0.210', 'weapon4': '0.338', 'ARMOR': '0.475', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.482', 'weapon2': '3.210'} [2024-08-01 15:54:46,459][00135] DAMAGECOUNT value on done: 115.0 [2024-08-01 15:54:47,938][00136] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:54:47,940][00136] Sum rewards: -0.610, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.835', 'AMMO2': '0.003', 'AMMO4': '0.017', 'ARMOR': '0.020', 'weapon4': '0.064', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.151', 'DAMAGECOUNT': '0.465', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.400', 'weapon3': '2.704'} [2024-08-01 15:54:47,969][00139] DAMAGECOUNT value on done: 130.0 [2024-08-01 15:54:47,972][00139] Sum rewards: -0.335, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.450', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'ARMOR': '0.032', 'weapon5': '0.062', 'HITCOUNT': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.144', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.234', 'weapon3': '3.304'} [2024-08-01 15:54:48,427][00148] DAMAGECOUNT value on done: 119.0 [2024-08-01 15:54:48,492][00138] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:54:48,493][00138] Sum rewards: 0.360, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.380', 'AMMO5': '0.005', 'AMMO2': '0.015', 'ARMOR': '0.052', 'HITCOUNT': '0.060', 'AMMO4': '0.073', 'WEAPON5': '0.100', 'weapon5': '0.102', 'AMMO3': '0.110', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.210', 'weapon4': '0.210', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon2': '2.308', 'weapon3': '2.596'} [2024-08-01 15:54:48,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3140.3, 300 sec: 3082.4). Total num frames: 2662400. Throughput: 0: 1533.9. Samples: 1336152. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:54:48,841][00034] Avg episode reward: [(0, '-3.982')] [2024-08-01 15:54:48,847][00112] Saving new best policy, reward=-3.982! [2024-08-01 15:54:48,853][00143] DAMAGECOUNT value on done: 394.0 [2024-08-01 15:54:48,854][00143] Sum rewards: -3.547, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO5': '0.004', 'AMMO2': '0.010', 'ARMOR': '0.040', 'AMMO4': '0.051', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.100', 'HITCOUNT': '0.140', 'weapon4': '0.180', 'AMMO3': '0.196', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.182', 'FRAGCOUNT': '2.000', 'weapon3': '2.262', 'weapon2': '2.628'} [2024-08-01 15:54:48,861][00147] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:54:48,862][00147] Sum rewards: -9.275, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'HITCOUNT': '0.010', 'AMMO2': '0.020', 'ARMOR': '0.032', 'DAMAGECOUNT': '0.045', 'weapon5': '0.054', 'AMMO4': '0.098', 'WEAPON5': '0.100', 'weapon4': '0.156', 'AMMO3': '0.180', 'WEAPON4': '0.300', 'WEAPON3': '1.000', 'weapon3': '1.710', 'weapon2': '3.176'} [2024-08-01 15:54:49,402][00134] Updated weights for policy 0, policy_version 651 (0.0020) [2024-08-01 15:54:49,556][00140] DAMAGECOUNT value on done: 45.0 [2024-08-01 15:54:50,379][00144] DAMAGECOUNT value on done: 250.0 [2024-08-01 15:54:50,381][00144] Sum rewards: -5.048, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.005', 'weapon4': '0.030', 'WEAPON4': '0.100', 'AMMO3': '0.158', 'HITCOUNT': '0.170', 'ARMOR': '0.487', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.750', 'FRAGCOUNT': '2.000', 'weapon3': '2.020', 'weapon2': '3.208'} [2024-08-01 15:54:51,640][00141] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:54:51,739][00132] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:54:51,745][00132] Sum rewards: -9.185, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'AMMO5': '0.004', 'ARMOR': '0.004', 'AMMO2': '0.012', 'HITCOUNT': '0.020', 'DAMAGECOUNT': '0.045', 'AMMO4': '0.062', 'WEAPON5': '0.100', 'AMMO3': '0.110', 'weapon5': '0.118', 'WEAPON4': '0.200', 'weapon4': '0.202', 'WEAPON3': '0.500', 'weapon3': '0.996', 'FRAGCOUNT': '1.000', 'weapon2': '4.222'} [2024-08-01 15:54:52,755][00145] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:54:52,760][00145] Sum rewards: -4.165, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.795', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.004', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'ARMOR': '0.068', 'weapon5': '0.088', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.182', 'DAMAGECOUNT': '0.360', 'weapon4': '0.384', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '1.760', 'weapon2': '3.542'} [2024-08-01 15:54:53,688][00135] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:54:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2674688. Throughput: 0: 1539.2. Samples: 1345668. Policy #0 lag: (min: 0.0, avg: 2.2, max: 7.0) [2024-08-01 15:54:53,842][00034] Avg episode reward: [(0, '-4.185')] [2024-08-01 15:54:55,453][00139] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:54:55,469][00139] Sum rewards: -1.887, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.050', 'AMMO2': '0.014', 'weapon4': '0.032', 'ARMOR': '0.048', 'AMMO4': '0.072', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.152', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon2': '2.344', 'weapon3': '2.650'} [2024-08-01 15:54:55,662][00136] DAMAGECOUNT value on done: 223.0 [2024-08-01 15:54:55,663][00136] Sum rewards: -2.068, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.334', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.141', 'weapon5': '0.148', 'weapon4': '0.232', 'ARMOR': '0.470', 'DAMAGECOUNT': '0.669', 'WEAPON3': '0.700', 'weapon3': '1.926', 'FRAGCOUNT': '2.000', 'weapon2': '2.860'} [2024-08-01 15:54:56,026][00147] DAMAGECOUNT value on done: 115.0 [2024-08-01 15:54:56,028][00147] Sum rewards: -5.948, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.600', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.005', 'weapon4': '0.008', 'AMMO2': '0.011', 'ARMOR': '0.040', 'weapon5': '0.046', 'AMMO4': '0.057', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.172', 'DAMAGECOUNT': '0.345', 'WEAPON3': '0.700', 'weapon3': '2.392', 'weapon2': '3.106'} [2024-08-01 15:54:56,048][00138] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:54:56,090][00148] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:54:56,092][00148] Sum rewards: -7.559, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.598', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.009', 'weapon5': '0.044', 'HITCOUNT': '0.060', 'ARMOR': '0.088', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.145', 'DAMAGECOUNT': '0.165', 'weapon4': '0.172', 'WEAPON3': '0.600', 'weapon3': '1.304', 'weapon2': '3.774'} [2024-08-01 15:54:56,133][00143] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:54:57,159][00140] DAMAGECOUNT value on done: 89.0 [2024-08-01 15:54:57,161][00140] Sum rewards: -2.329, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.000', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'AMMO2': '0.021', 'HITCOUNT': '0.060', 'ARMOR': '0.075', 'AMMO4': '0.103', 'AMMO3': '0.144', 'weapon4': '0.254', 'DAMAGECOUNT': '0.267', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'weapon5': '0.416', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.546', 'weapon2': '2.948'} [2024-08-01 15:54:58,699][00144] DAMAGECOUNT value on done: 135.0 [2024-08-01 15:54:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2691072. Throughput: 0: 1537.3. Samples: 1350300. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:54:58,843][00034] Avg episode reward: [(0, '-4.242')] [2024-08-01 15:54:59,825][00141] DAMAGECOUNT value on done: 230.0 [2024-08-01 15:54:59,829][00141] Sum rewards: -9.617, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.440', 'AMMO5': '0.005', 'weapon5': '0.006', 'AMMO2': '0.020', 'AMMO4': '0.099', 'WEAPON5': '0.100', 'HITCOUNT': '0.210', 'AMMO3': '0.257', 'WEAPON4': '0.300', 'weapon4': '0.442', 'DAMAGECOUNT': '0.690', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon3': '2.046', 'weapon2': '2.848'} [2024-08-01 15:55:00,153][00146] DAMAGECOUNT value on done: 205.0 [2024-08-01 15:55:00,157][00146] Sum rewards: -5.444, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.025', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.059', 'ARMOR': '0.080', 'HITCOUNT': '0.140', 'AMMO3': '0.157', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.615', 'weapon4': '0.634', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.214', 'weapon2': '2.300'} [2024-08-01 15:55:00,455][00132] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:55:00,456][00132] Sum rewards: -5.179, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO5': '0.007', 'HITCOUNT': '0.030', 'AMMO2': '0.031', 'ARMOR': '0.093', 'AMMO4': '0.156', 'AMMO3': '0.157', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.304', 'DAMAGECOUNT': '0.360', 'weapon4': '0.452', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.106', 'weapon2': '2.434'} [2024-08-01 15:55:01,850][00145] DAMAGECOUNT value on done: 187.0 [2024-08-01 15:55:01,851][00145] Sum rewards: -8.444, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'HITCOUNT': '0.120', 'AMMO3': '0.209', 'DAMAGECOUNT': '0.561', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.414', 'weapon3': '2.866'} [2024-08-01 15:55:01,943][00135] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:55:01,946][00135] Sum rewards: -2.192, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'WEAPON1': '0.020', 'HITCOUNT': '0.020', 'AMMO2': '0.026', 'ARMOR': '0.032', 'DAMAGECOUNT': '0.060', 'AMMO3': '0.085', 'AMMO4': '0.130', 'WEAPON4': '0.300', 'WEAPON3': '0.500', 'weapon4': '0.596', 'FRAGCOUNT': '1.000', 'weapon3': '1.530', 'weapon2': '2.938'} [2024-08-01 15:55:03,001][00134] Updated weights for policy 0, policy_version 661 (0.0020) [2024-08-01 15:55:03,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3082.4). Total num frames: 2707456. Throughput: 0: 1518.6. Samples: 1358736. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 15:55:03,843][00034] Avg episode reward: [(0, '-4.335')] [2024-08-01 15:55:04,256][00136] DAMAGECOUNT value on done: 52.0 [2024-08-01 15:55:04,257][00136] Sum rewards: -7.827, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO5': '0.010', 'AMMO2': '0.015', 'weapon5': '0.020', 'HITCOUNT': '0.050', 'weapon4': '0.070', 'AMMO4': '0.072', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.156', 'AMMO3': '0.198', 'WEAPON5': '0.200', 'ARMOR': '0.500', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.242', 'weapon3': '2.270'} [2024-08-01 15:55:04,583][00139] DAMAGECOUNT value on done: 175.0 [2024-08-01 15:55:04,586][00139] Sum rewards: -4.074, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.930', 'AMMO2': '0.015', 'ARMOR': '0.024', 'AMMO4': '0.074', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.202', 'weapon4': '0.256', 'DAMAGECOUNT': '0.525', 'WEAPON3': '1.200', 'weapon2': '1.824', 'FRAGCOUNT': '2.000', 'weapon3': '3.266'} [2024-08-01 15:55:04,604][00142] DAMAGECOUNT value on done: 178.0 [2024-08-01 15:55:04,609][00142] Sum rewards: -2.744, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.300', 'ARMOR': '0.004', 'AMMO2': '0.010', 'AMMO4': '0.049', 'AMMO3': '0.101', 'HITCOUNT': '0.170', 'WEAPON4': '0.200', 'weapon4': '0.492', 'DAMAGECOUNT': '0.534', 'WEAPON3': '0.600', 'weapon3': '1.876', 'FRAGCOUNT': '2.000', 'weapon2': '2.770'} [2024-08-01 15:55:04,628][00147] DAMAGECOUNT value on done: 318.0 [2024-08-01 15:55:04,629][00147] Sum rewards: -8.161, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.500', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'AMMO5': '0.008', 'WEAPON4': '0.100', 'AMMO3': '0.142', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'weapon5': '0.290', 'weapon4': '0.346', 'ARMOR': '0.484', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.954', 'weapon3': '1.490', 'weapon2': '3.128'} [2024-08-01 15:55:04,654][00148] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:55:04,892][00143] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:55:05,064][00138] DAMAGECOUNT value on done: 14.0 [2024-08-01 15:55:05,735][00140] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:55:05,928][00137] DAMAGECOUNT value on done: 75.0 [2024-08-01 15:55:06,667][00144] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:06,673][00144] Sum rewards: -11.296, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.800', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.009', 'HITCOUNT': '0.010', 'ARMOR': '0.013', 'AMMO2': '0.014', 'WEAPON1': '0.020', 'DAMAGECOUNT': '0.030', 'AMMO4': '0.071', 'weapon5': '0.122', 'AMMO3': '0.169', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.448', 'WEAPON3': '0.800', 'weapon3': '1.128', 'weapon2': '3.670'} [2024-08-01 15:55:07,786][00146] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:08,359][00132] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:55:08,361][00132] Sum rewards: -3.489, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.095', 'AMMO5': '0.005', 'ARMOR': '0.010', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'HITCOUNT': '0.020', 'AMMO4': '0.057', 'DAMAGECOUNT': '0.060', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.115', 'weapon5': '0.150', 'weapon4': '0.338', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.130', 'weapon2': '2.390'} [2024-08-01 15:55:08,767][00141] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:55:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3054.7). Total num frames: 2719744. Throughput: 0: 1512.8. Samples: 1367832. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:55:08,840][00034] Avg episode reward: [(0, '-4.350')] [2024-08-01 15:55:09,618][00145] DAMAGECOUNT value on done: 135.0 [2024-08-01 15:55:09,620][00145] Sum rewards: -5.628, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.100', 'AMMO2': '0.008', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.039', 'weapon4': '0.048', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.158', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.118', 'weapon2': '3.414'} [2024-08-01 15:55:11,088][00135] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:55:11,776][00136] DAMAGECOUNT value on done: 202.0 [2024-08-01 15:55:11,779][00136] Sum rewards: -0.450, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'AMMO5': '0.004', 'AMMO2': '0.013', 'ARMOR': '0.036', 'weapon4': '0.052', 'AMMO4': '0.063', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.128', 'AMMO3': '0.162', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.606', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon3': '2.024', 'weapon2': '2.792'} [2024-08-01 15:55:12,122][00139] DAMAGECOUNT value on done: 52.0 [2024-08-01 15:55:12,282][00148] DAMAGECOUNT value on done: 208.0 [2024-08-01 15:55:12,282][00148] Sum rewards: -3.827, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO2': '0.010', 'AMMO5': '0.013', 'ARMOR': '0.016', 'AMMO4': '0.049', 'AMMO3': '0.078', 'WEAPON5': '0.100', 'weapon5': '0.108', 'weapon4': '0.126', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.624', 'weapon3': '2.014', 'weapon2': '3.214'} [2024-08-01 15:55:12,300][00142] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:55:12,501][00133] DAMAGECOUNT value on done: 45.0 [2024-08-01 15:55:12,598][00138] DAMAGECOUNT value on done: 99.0 [2024-08-01 15:55:12,600][00138] Sum rewards: -4.719, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO2': '0.014', 'AMMO4': '0.067', 'ARMOR': '0.074', 'HITCOUNT': '0.090', 'AMMO3': '0.155', 'weapon4': '0.158', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.297', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.436', 'weapon3': '2.570'} [2024-08-01 15:55:13,374][00140] DAMAGECOUNT value on done: 255.0 [2024-08-01 15:55:13,376][00140] Sum rewards: -3.321, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.896', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'HITCOUNT': '0.080', 'WEAPON5': '0.100', 'weapon5': '0.112', 'AMMO3': '0.162', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.900', 'weapon3': '1.950', 'FRAGCOUNT': '3.000', 'weapon2': '3.192'} [2024-08-01 15:55:13,683][00137] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:13,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 2736128. Throughput: 0: 1524.5. Samples: 1372452. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 15:55:13,840][00034] Avg episode reward: [(0, '-4.252')] [2024-08-01 15:55:14,112][00147] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:55:14,301][00144] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:14,430][00143] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:55:15,873][00132] DAMAGECOUNT value on done: 75.0 [2024-08-01 15:55:16,314][00146] DAMAGECOUNT value on done: 95.0 [2024-08-01 15:55:16,317][00146] Sum rewards: -3.511, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.310', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'weapon5': '0.008', 'AMMO5': '0.010', 'weapon4': '0.054', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.147', 'DAMAGECOUNT': '0.285', 'ARMOR': '0.486', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.208', 'weapon2': '3.752'} [2024-08-01 15:55:17,134][00145] DAMAGECOUNT value on done: 197.0 [2024-08-01 15:55:17,134][00141] DAMAGECOUNT value on done: 290.0 [2024-08-01 15:55:17,139][00141] Sum rewards: 0.028, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.250', 'AMMO5': '0.005', 'AMMO2': '0.009', 'ARMOR': '0.009', 'WEAPON1': '0.020', 'weapon5': '0.024', 'AMMO4': '0.042', 'WEAPON5': '0.100', 'AMMO3': '0.191', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'weapon4': '0.524', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.870', 'weapon2': '2.344', 'weapon3': '2.440', 'FRAGCOUNT': '3.000'} [2024-08-01 15:55:17,925][00134] Updated weights for policy 0, policy_version 671 (0.0020) [2024-08-01 15:55:18,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2752512. Throughput: 0: 1521.6. Samples: 1381572. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 15:55:18,841][00034] Avg episode reward: [(0, '-4.236')] [2024-08-01 15:55:19,166][00135] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:19,539][00139] DAMAGECOUNT value on done: 18.0 [2024-08-01 15:55:19,540][00139] Sum rewards: -5.777, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.675', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'ARMOR': '0.020', 'HITCOUNT': '0.030', 'DAMAGECOUNT': '0.054', 'AMMO3': '0.084', 'WEAPON4': '0.100', 'weapon4': '0.260', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.548', 'weapon2': '3.314'} [2024-08-01 15:55:19,814][00136] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:20,112][00138] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:55:20,293][00148] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:55:20,296][00148] Sum rewards: -3.269, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.495', 'AMMO2': '0.002', 'AMMO4': '0.010', 'ARMOR': '0.028', 'HITCOUNT': '0.140', 'AMMO3': '0.208', 'DAMAGECOUNT': '0.360', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.698', 'weapon3': '3.030'} [2024-08-01 15:55:20,675][00142] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:20,896][00133] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:55:21,367][00140] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:21,819][00147] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:55:22,233][00143] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:55:22,243][00144] DAMAGECOUNT value on done: 72.0 [2024-08-01 15:55:22,246][00144] Sum rewards: -5.308, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO5': '0.005', 'ARMOR': '0.028', 'weapon5': '0.032', 'AMMO2': '0.042', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'weapon4': '0.160', 'AMMO3': '0.178', 'AMMO4': '0.208', 'DAMAGECOUNT': '0.216', 'WEAPON4': '0.300', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.406', 'weapon2': '2.558'} [2024-08-01 15:55:22,293][00137] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:55:22,294][00137] Sum rewards: 0.985, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.720', 'AMMO2': '0.002', 'AMMO4': '0.010', 'ARMOR': '0.040', 'HITCOUNT': '0.060', 'AMMO3': '0.062', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.315', 'weapon7': '0.398', 'FRAGCOUNT': '1.000', 'weapon3': '1.686', 'weapon2': '2.892'} [2024-08-01 15:55:23,221][00132] DAMAGECOUNT value on done: 272.0 [2024-08-01 15:55:23,223][00132] Sum rewards: -3.561, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.544', 'AMMO4': '-0.061', 'AMMO2': '-0.012', 'AMMO5': '0.016', 'WEAPON1': '0.020', 'HITCOUNT': '0.100', 'AMMO3': '0.109', 'weapon5': '0.280', 'WEAPON5': '0.300', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.816', 'weapon3': '0.882', 'ARMOR': '0.949', 'weapon2': '3.734'} [2024-08-01 15:55:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2768896. Throughput: 0: 1521.6. Samples: 1390800. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 15:55:23,843][00034] Avg episode reward: [(0, '-4.177')] [2024-08-01 15:55:24,376][00146] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:24,687][00145] DAMAGECOUNT value on done: 190.0 [2024-08-01 15:55:24,694][00145] Sum rewards: -8.453, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.500', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.004', 'weapon4': '0.044', 'weapon5': '0.066', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.173', 'DAMAGECOUNT': '0.570', 'WEAPON3': '1.000', 'weapon3': '2.500', 'weapon2': '3.112'} [2024-08-01 15:55:25,341][00141] DAMAGECOUNT value on done: 71.0 [2024-08-01 15:55:27,093][00139] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:55:27,245][00135] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:27,304][00136] DAMAGECOUNT value on done: 80.0 [2024-08-01 15:55:27,755][00148] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:55:27,759][00148] Sum rewards: -4.604, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO5': '0.005', 'weapon5': '0.010', 'AMMO2': '0.020', 'WEAPON1': '0.040', 'HITCOUNT': '0.050', 'ARMOR': '0.092', 'WEAPON5': '0.100', 'AMMO4': '0.101', 'AMMO3': '0.113', 'DAMAGECOUNT': '0.120', 'weapon4': '0.248', 'WEAPON4': '0.300', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.508', 'weapon3': '2.568'} [2024-08-01 15:55:27,816][00138] DAMAGECOUNT value on done: 375.0 [2024-08-01 15:55:27,816][00138] Sum rewards: -4.765, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.245', 'AMMO2': '0.007', 'AMMO5': '0.017', 'AMMO4': '0.034', 'ARMOR': '0.036', 'HITCOUNT': '0.060', 'AMMO3': '0.123', 'weapon5': '0.178', 'weapon4': '0.180', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.125', 'weapon3': '1.600', 'FRAGCOUNT': '2.000', 'weapon2': '3.520'} [2024-08-01 15:55:28,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3140.3, 300 sec: 3082.4). Total num frames: 2785280. Throughput: 0: 1523.7. Samples: 1395504. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:55:28,840][00034] Avg episode reward: [(0, '-4.301')] [2024-08-01 15:55:28,889][00140] DAMAGECOUNT value on done: 80.0 [2024-08-01 15:55:28,890][00140] Sum rewards: -4.628, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.705', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.051', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'AMMO3': '0.156', 'weapon4': '0.234', 'DAMAGECOUNT': '0.240', 'ARMOR': '0.472', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.896', 'weapon2': '3.108'} [2024-08-01 15:55:29,251][00134] Updated weights for policy 0, policy_version 681 (0.0020) [2024-08-01 15:55:29,722][00142] DAMAGECOUNT value on done: 95.0 [2024-08-01 15:55:29,812][00133] DAMAGECOUNT value on done: 75.0 [2024-08-01 15:55:29,815][00133] Sum rewards: -6.297, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.200', 'AMMO2': '0.008', 'AMMO5': '0.009', 'AMMO4': '0.038', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.181', 'WEAPON5': '0.200', 'weapon5': '0.210', 'DAMAGECOUNT': '0.225', 'weapon4': '0.426', 'ARMOR': '0.496', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.060', 'weapon2': '2.380'} [2024-08-01 15:55:29,873][00144] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:55:29,875][00144] Sum rewards: -5.936, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO2': '0.010', 'AMMO4': '0.050', 'HITCOUNT': '0.060', 'DAMAGECOUNT': '0.165', 'WEAPON4': '0.200', 'AMMO3': '0.218', 'weapon4': '0.226', 'ARMOR': '0.493', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon3': '2.070', 'weapon2': '3.052'} [2024-08-01 15:55:29,939][00147] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:29,943][00147] Sum rewards: -11.120, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.766', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.003', 'HITCOUNT': '0.010', 'WEAPON1': '0.020', 'weapon4': '0.022', 'DAMAGECOUNT': '0.030', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.158', 'AMMO3': '0.202', 'ARMOR': '0.463', 'WEAPON3': '1.100', 'weapon3': '1.814', 'weapon2': '3.124'} [2024-08-01 15:55:30,496][00143] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:55:30,501][00143] Sum rewards: -3.378, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.012', 'WEAPON1': '0.040', 'HITCOUNT': '0.090', 'AMMO3': '0.155', 'WEAPON5': '0.200', 'weapon5': '0.200', 'DAMAGECOUNT': '0.300', 'ARMOR': '0.431', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.362', 'weapon2': '2.484'} [2024-08-01 15:55:31,162][00137] DAMAGECOUNT value on done: 54.0 [2024-08-01 15:55:31,167][00137] Sum rewards: -6.567, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.215', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO2': '0.015', 'HITCOUNT': '0.050', 'AMMO4': '0.073', 'WEAPON5': '0.100', 'AMMO3': '0.149', 'DAMAGECOUNT': '0.162', 'WEAPON4': '0.300', 'weapon4': '0.458', 'ARMOR': '0.512', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.284', 'weapon2': '3.332'} [2024-08-01 15:55:31,622][00132] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:55:33,172][00146] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:55:33,180][00146] Sum rewards: -4.979, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.544', 'AMMO4': '-0.047', 'AMMO2': '-0.009', 'ARMOR': '0.004', 'AMMO5': '0.005', 'HITCOUNT': '0.050', 'weapon5': '0.080', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.165', 'AMMO3': '0.177', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.384', 'weapon2': '2.756'} [2024-08-01 15:55:33,500][00141] DAMAGECOUNT value on done: 36.0 [2024-08-01 15:55:33,503][00145] DAMAGECOUNT value on done: 48.0 [2024-08-01 15:55:33,504][00145] Sum rewards: -5.908, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.200', 'AMMO4': '-0.008', 'AMMO2': '-0.001', 'ARMOR': '0.016', 'weapon4': '0.046', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.144', 'AMMO3': '0.157', 'WEAPON3': '0.900', 'weapon3': '1.964', 'FRAGCOUNT': '2.000', 'weapon2': '3.394'} [2024-08-01 15:55:33,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2935.4, 300 sec: 3054.6). Total num frames: 2793472. Throughput: 0: 1507.4. Samples: 1403988. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:55:33,843][00034] Avg episode reward: [(0, '-4.250')] [2024-08-01 15:55:35,478][00136] DAMAGECOUNT value on done: 140.0 [2024-08-01 15:55:35,482][00136] Sum rewards: -4.825, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO2': '0.003', 'AMMO4': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.060', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.153', 'weapon4': '0.218', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.354', 'weapon3': '2.434'} [2024-08-01 15:55:35,634][00135] DAMAGECOUNT value on done: 75.0 [2024-08-01 15:55:35,851][00139] DAMAGECOUNT value on done: 225.0 [2024-08-01 15:55:35,854][00139] Sum rewards: -4.055, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO4': '-0.038', 'AMMO2': '-0.008', 'AMMO5': '0.010', 'WEAPON5': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.207', 'DAMAGECOUNT': '0.675', 'WEAPON3': '1.000', 'weapon2': '2.612', 'weapon3': '2.906', 'FRAGCOUNT': '3.000'} [2024-08-01 15:55:35,876][00148] DAMAGECOUNT value on done: 115.0 [2024-08-01 15:55:35,877][00148] Sum rewards: -4.830, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.600', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'weapon5': '0.002', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.082', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.183', 'DAMAGECOUNT': '0.345', 'weapon4': '0.376', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.806', 'weapon2': '2.762'} [2024-08-01 15:55:36,637][00138] DAMAGECOUNT value on done: 172.0 [2024-08-01 15:55:36,641][00138] Sum rewards: -3.927, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.910', 'AMMO2': '0.009', 'AMMO4': '0.044', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.156', 'weapon4': '0.194', 'ARMOR': '0.482', 'DAMAGECOUNT': '0.516', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.218', 'weapon2': '3.094'} [2024-08-01 15:55:37,073][00140] DAMAGECOUNT value on done: 132.0 [2024-08-01 15:55:37,078][00140] Sum rewards: -5.984, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.305', 'AMMO5': '0.005', 'AMMO2': '0.021', 'ARMOR': '0.024', 'weapon5': '0.086', 'WEAPON5': '0.100', 'AMMO4': '0.106', 'HITCOUNT': '0.130', 'AMMO3': '0.170', 'weapon4': '0.180', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.396', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.676', 'weapon2': '2.726'} [2024-08-01 15:55:37,975][00144] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:55:38,093][00147] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:38,098][00147] Sum rewards: -4.680, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'ARMOR': '0.004', 'AMMO5': '0.005', 'HITCOUNT': '0.010', 'AMMO2': '0.023', 'weapon5': '0.026', 'DAMAGECOUNT': '0.045', 'WEAPON5': '0.100', 'AMMO4': '0.114', 'AMMO3': '0.173', 'WEAPON4': '0.200', 'weapon4': '0.556', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.976', 'weapon3': '2.748'} [2024-08-01 15:55:38,236][00142] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:38,404][00133] DAMAGECOUNT value on done: 370.0 [2024-08-01 15:55:38,407][00133] Sum rewards: 0.546, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.995', 'AMMO4': '-0.018', 'AMMO2': '-0.003', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.158', 'weapon4': '0.276', 'HITCOUNT': '0.280', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.110', 'weapon3': '1.884', 'FRAGCOUNT': '3.000', 'weapon2': '3.322'} [2024-08-01 15:55:38,792][00143] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2813952. Throughput: 0: 1497.6. Samples: 1413060. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 15:55:38,841][00034] Avg episode reward: [(0, '-4.187')] [2024-08-01 15:55:39,639][00137] DAMAGECOUNT value on done: 107.0 [2024-08-01 15:55:39,642][00137] Sum rewards: -2.506, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.360', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.003', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.108', 'weapon4': '0.118', 'weapon5': '0.144', 'AMMO3': '0.159', 'DAMAGECOUNT': '0.321', 'WEAPON3': '0.900', 'weapon3': '1.938', 'FRAGCOUNT': '2.000', 'weapon2': '3.124'} [2024-08-01 15:55:39,719][00132] DAMAGECOUNT value on done: 160.0 [2024-08-01 15:55:41,147][00145] DAMAGECOUNT value on done: 115.0 [2024-08-01 15:55:41,150][00145] Sum rewards: -6.530, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.120', 'AMMO2': '0.011', 'AMMO4': '0.056', 'HITCOUNT': '0.110', 'AMMO3': '0.159', 'WEAPON4': '0.200', 'weapon4': '0.296', 'DAMAGECOUNT': '0.345', 'ARMOR': '0.458', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.978', 'weapon2': '2.776'} [2024-08-01 15:55:41,229][00141] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:55:41,572][00146] DAMAGECOUNT value on done: 115.0 [2024-08-01 15:55:41,574][00146] Sum rewards: -1.266, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.940', 'ARMOR': '0.004', 'AMMO2': '0.035', 'HITCOUNT': '0.110', 'AMMO3': '0.121', 'AMMO4': '0.177', 'DAMAGECOUNT': '0.345', 'WEAPON4': '0.400', 'WEAPON3': '0.700', 'weapon4': '0.866', 'weapon3': '1.656', 'FRAGCOUNT': '2.000', 'weapon2': '2.760'} [2024-08-01 15:55:43,157][00135] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:55:43,174][00135] Sum rewards: -2.683, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.980', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'HITCOUNT': '0.050', 'ARMOR': '0.061', 'AMMO4': '0.079', 'AMMO3': '0.129', 'weapon4': '0.148', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.300', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.912', 'weapon3': '3.082'} [2024-08-01 15:55:43,557][00139] DAMAGECOUNT value on done: 219.0 [2024-08-01 15:55:43,557][00139] Sum rewards: -0.475, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.175', 'AMMO2': '0.000', 'AMMO4': '0.001', 'weapon5': '0.002', 'AMMO5': '0.010', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.131', 'HITCOUNT': '0.140', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon4': '0.292', 'DAMAGECOUNT': '0.657', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon2': '2.610', 'weapon3': '2.616'} [2024-08-01 15:55:43,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 2826240. Throughput: 0: 1498.9. Samples: 1417752. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 15:55:43,842][00034] Avg episode reward: [(0, '-4.242')] [2024-08-01 15:55:44,241][00136] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:44,500][00134] Updated weights for policy 0, policy_version 691 (0.0020) [2024-08-01 15:55:44,546][00138] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:55:44,549][00138] Sum rewards: -7.633, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.010', 'AMMO2': '0.029', 'ARMOR': '0.040', 'weapon5': '0.048', 'HITCOUNT': '0.050', 'WEAPON5': '0.100', 'AMMO4': '0.145', 'AMMO3': '0.176', 'DAMAGECOUNT': '0.210', 'WEAPON4': '0.300', 'weapon4': '0.394', 'WEAPON3': '0.900', 'weapon3': '2.116', 'weapon2': '2.990'} [2024-08-01 15:55:44,661][00148] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:55:45,707][00140] DAMAGECOUNT value on done: 138.0 [2024-08-01 15:55:45,709][00140] Sum rewards: -5.822, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO5': '0.008', 'AMMO2': '0.031', 'HITCOUNT': '0.050', 'ARMOR': '0.076', 'weapon5': '0.112', 'AMMO4': '0.153', 'AMMO3': '0.196', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.340', 'DAMAGECOUNT': '0.414', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '2.250', 'weapon2': '2.678'} [2024-08-01 15:55:45,843][00147] DAMAGECOUNT value on done: 272.0 [2024-08-01 15:55:46,223][00142] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:46,335][00133] DAMAGECOUNT value on done: 22.0 [2024-08-01 15:55:46,339][00144] DAMAGECOUNT value on done: 144.0 [2024-08-01 15:55:46,342][00144] Sum rewards: -3.217, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.600', 'AMMO2': '0.002', 'AMMO4': '0.010', 'weapon4': '0.034', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.170', 'DAMAGECOUNT': '0.432', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '2.694', 'weapon2': '2.734'} [2024-08-01 15:55:46,626][00143] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:55:47,233][00137] DAMAGECOUNT value on done: 54.0 [2024-08-01 15:55:47,725][00132] DAMAGECOUNT value on done: 208.0 [2024-08-01 15:55:47,728][00132] Sum rewards: -8.444, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.690', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.014', 'weapon5': '0.070', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'AMMO3': '0.256', 'ARMOR': '0.492', 'DAMAGECOUNT': '0.624', 'WEAPON3': '1.200', 'weapon3': '2.300', 'weapon2': '2.732'} [2024-08-01 15:55:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2842624. Throughput: 0: 1519.2. Samples: 1427100. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:55:48,840][00034] Avg episode reward: [(0, '-4.301')] [2024-08-01 15:55:49,041][00146] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:55:49,149][00141] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:55:49,562][00145] DAMAGECOUNT value on done: 282.0 [2024-08-01 15:55:49,567][00145] Sum rewards: -3.072, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.965', 'AMMO5': '0.003', 'AMMO2': '0.019', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'AMMO4': '0.093', 'WEAPON5': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.168', 'weapon5': '0.176', 'WEAPON4': '0.200', 'weapon4': '0.524', 'DAMAGECOUNT': '0.846', 'WEAPON3': '0.900', 'weapon3': '1.194', 'FRAGCOUNT': '3.000', 'weapon2': '3.194'} [2024-08-01 15:55:51,210][00135] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:55:51,526][00136] DAMAGECOUNT value on done: 164.0 [2024-08-01 15:55:51,529][00136] Sum rewards: -3.001, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.661', 'AMMO5': '0.003', 'AMMO2': '0.010', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.051', 'WEAPON5': '0.100', 'HITCOUNT': '0.150', 'weapon5': '0.186', 'weapon4': '0.188', 'AMMO3': '0.196', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.492', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '2.112', 'weapon2': '2.940'} [2024-08-01 15:55:51,854][00139] DAMAGECOUNT value on done: 90.0 [2024-08-01 15:55:51,900][00148] DAMAGECOUNT value on done: 22.0 [2024-08-01 15:55:52,728][00138] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:55:53,009][00140] DAMAGECOUNT value on done: 104.0 [2024-08-01 15:55:53,617][00147] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:55:53,618][00147] Sum rewards: -6.844, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.665', 'AMMO2': '0.019', 'ARMOR': '0.020', 'AMMO5': '0.029', 'AMMO4': '0.093', 'weapon4': '0.096', 'HITCOUNT': '0.110', 'AMMO3': '0.154', 'weapon5': '0.174', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.330', 'WEAPON5': '0.500', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.350', 'weapon2': '3.296'} [2024-08-01 15:55:53,695][00144] DAMAGECOUNT value on done: 135.0 [2024-08-01 15:55:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2859008. Throughput: 0: 1520.3. Samples: 1436244. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:55:53,840][00034] Avg episode reward: [(0, '-4.307')] [2024-08-01 15:55:54,442][00143] DAMAGECOUNT value on done: 175.0 [2024-08-01 15:55:54,692][00142] DAMAGECOUNT value on done: 59.0 [2024-08-01 15:55:54,698][00142] Sum rewards: -5.849, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.941', 'ARMOR': '0.032', 'AMMO2': '0.033', 'HITCOUNT': '0.070', 'AMMO3': '0.126', 'AMMO4': '0.164', 'DAMAGECOUNT': '0.177', 'WEAPON4': '0.500', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon4': '1.142', 'weapon3': '1.446', 'weapon2': '2.452'} [2024-08-01 15:55:54,988][00133] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:55:54,994][00133] Sum rewards: -5.571, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.065', 'ARMOR': '0.008', 'AMMO5': '0.010', 'AMMO2': '0.029', 'AMMO3': '0.117', 'HITCOUNT': '0.130', 'AMMO4': '0.143', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.465', 'weapon4': '0.484', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.186', 'weapon2': '2.572'} [2024-08-01 15:55:55,766][00132] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:55:55,854][00137] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:55:56,999][00141] DAMAGECOUNT value on done: 169.0 [2024-08-01 15:55:57,000][00141] Sum rewards: -1.943, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO2': '0.001', 'AMMO4': '0.004', 'ARMOR': '0.064', 'WEAPON4': '0.100', 'AMMO3': '0.149', 'HITCOUNT': '0.180', 'weapon4': '0.380', 'DAMAGECOUNT': '0.507', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.440', 'weapon3': '2.792'} [2024-08-01 15:55:57,454][00145] DAMAGECOUNT value on done: 406.0 [2024-08-01 15:55:57,457][00145] Sum rewards: 1.563, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.215', 'AMMO5': '0.003', 'AMMO2': '0.009', 'WEAPON1': '0.020', 'AMMO4': '0.043', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.155', 'weapon5': '0.226', 'HITCOUNT': '0.280', 'weapon4': '0.362', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.218', 'weapon2': '2.402', 'weapon3': '2.460', 'FRAGCOUNT': '4.000'} [2024-08-01 15:55:57,509][00146] DAMAGECOUNT value on done: 85.0 [2024-08-01 15:55:57,513][00146] Sum rewards: -7.037, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.805', 'AMMO2': '0.003', 'AMMO5': '0.004', 'weapon7': '0.012', 'AMMO4': '0.017', 'weapon4': '0.042', 'HITCOUNT': '0.080', 'weapon5': '0.086', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.171', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'DAMAGECOUNT': '0.255', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.492', 'weapon3': '2.806'} [2024-08-01 15:55:57,616][00134] Updated weights for policy 0, policy_version 701 (0.0019) [2024-08-01 15:55:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2875392. Throughput: 0: 1521.6. Samples: 1440924. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:55:58,841][00034] Avg episode reward: [(0, '-4.193')] [2024-08-01 15:55:59,039][00136] DAMAGECOUNT value on done: 77.0 [2024-08-01 15:55:59,042][00136] Sum rewards: -2.212, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.229', 'AMMO2': '0.030', 'HITCOUNT': '0.070', 'AMMO3': '0.131', 'weapon4': '0.148', 'AMMO4': '0.150', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.231', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.598', 'weapon2': '3.158'} [2024-08-01 15:55:59,243][00135] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:55:59,386][00148] DAMAGECOUNT value on done: 229.0 [2024-08-01 15:55:59,386][00148] Sum rewards: -4.179, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO5': '0.005', 'AMMO2': '0.009', 'AMMO4': '0.042', 'weapon5': '0.054', 'ARMOR': '0.071', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO3': '0.132', 'WEAPON4': '0.200', 'weapon4': '0.418', 'DAMAGECOUNT': '0.687', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.150', 'weapon3': '2.644'} [2024-08-01 15:56:00,233][00139] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:00,392][00140] DAMAGECOUNT value on done: 75.0 [2024-08-01 15:56:00,395][00140] Sum rewards: -2.145, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.855', 'AMMO5': '0.004', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.066', 'HITCOUNT': '0.070', 'AMMO3': '0.072', 'WEAPON5': '0.100', 'weapon5': '0.102', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.150', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.225', 'WEAPON4': '0.300', 'WEAPON3': '0.300', 'weapon3': '0.710', 'FRAGCOUNT': '1.000', 'weapon4': '1.130', 'weapon2': '2.718'} [2024-08-01 15:56:00,988][00144] DAMAGECOUNT value on done: 274.0 [2024-08-01 15:56:00,996][00144] Sum rewards: 0.620, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.020', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.006', 'WEAPON1': '0.020', 'AMMO3': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.200', 'weapon5': '0.206', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.822', 'FRAGCOUNT': '1.000', 'weapon3': '2.110', 'weapon2': '2.722'} [2024-08-01 15:56:01,391][00147] DAMAGECOUNT value on done: 125.0 [2024-08-01 15:56:01,399][00147] Sum rewards: -6.571, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'AMMO2': '0.012', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'AMMO4': '0.060', 'AMMO3': '0.103', 'HITCOUNT': '0.110', 'WEAPON4': '0.300', 'weapon4': '0.348', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.500', 'weapon3': '1.286', 'FRAGCOUNT': '3.000', 'weapon2': '4.018'} [2024-08-01 15:56:01,495][00138] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:56:01,500][00138] Sum rewards: -3.011, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.980', 'AMMO2': '0.010', 'HITCOUNT': '0.010', 'DAMAGECOUNT': '0.030', 'ARMOR': '0.044', 'AMMO4': '0.049', 'AMMO3': '0.160', 'WEAPON4': '0.200', 'weapon4': '0.302', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.740', 'weapon2': '3.124'} [2024-08-01 15:56:02,108][00142] DAMAGECOUNT value on done: 142.0 [2024-08-01 15:56:02,112][00142] Sum rewards: -1.489, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.061', 'AMMO3': '0.088', 'HITCOUNT': '0.120', 'WEAPON4': '0.200', 'weapon4': '0.232', 'DAMAGECOUNT': '0.426', 'WEAPON3': '0.600', 'ARMOR': '0.910', 'FRAGCOUNT': '1.000', 'weapon2': '2.466', 'weapon3': '2.836'} [2024-08-01 15:56:02,502][00133] DAMAGECOUNT value on done: 22.0 [2024-08-01 15:56:02,729][00143] DAMAGECOUNT value on done: 102.0 [2024-08-01 15:56:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3054.6). Total num frames: 2887680. Throughput: 0: 1520.6. Samples: 1449996. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:56:03,841][00034] Avg episode reward: [(0, '-4.213')] [2024-08-01 15:56:04,049][00137] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:04,049][00137] Sum rewards: -5.377, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'ARMOR': '0.052', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.180', 'AMMO3': '0.193', 'weapon4': '0.472', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '2.436', 'weapon2': '2.614'} [2024-08-01 15:56:05,175][00132] DAMAGECOUNT value on done: 28.0 [2024-08-01 15:56:05,385][00141] DAMAGECOUNT value on done: 347.0 [2024-08-01 15:56:05,386][00141] Sum rewards: -4.337, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO2': '0.009', 'AMMO5': '0.016', 'WEAPON1': '0.020', 'AMMO4': '0.046', 'WEAPON4': '0.100', 'weapon4': '0.118', 'HITCOUNT': '0.130', 'AMMO3': '0.201', 'weapon5': '0.298', 'WEAPON5': '0.400', 'ARMOR': '0.491', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.041', 'weapon3': '1.584', 'FRAGCOUNT': '2.500', 'weapon2': '3.398'} [2024-08-01 15:56:06,125][00146] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:56:06,126][00146] Sum rewards: -6.813, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.009', 'HITCOUNT': '0.010', 'weapon5': '0.024', 'AMMO2': '0.041', 'DAMAGECOUNT': '0.045', 'ARMOR': '0.048', 'WEAPON5': '0.100', 'AMMO3': '0.132', 'AMMO4': '0.204', 'weapon4': '0.418', 'WEAPON4': '0.500', 'WEAPON3': '0.800', 'weapon2': '2.432', 'weapon3': '2.574'} [2024-08-01 15:56:06,675][00145] DAMAGECOUNT value on done: 238.0 [2024-08-01 15:56:06,677][00145] Sum rewards: -8.079, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'AMMO2': '0.013', 'ARMOR': '0.028', 'weapon4': '0.028', 'AMMO4': '0.063', 'AMMO3': '0.197', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.714', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '2.108', 'weapon2': '3.010'} [2024-08-01 15:56:06,896][00136] DAMAGECOUNT value on done: 153.0 [2024-08-01 15:56:07,203][00148] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:56:07,521][00135] DAMAGECOUNT value on done: 131.0 [2024-08-01 15:56:07,527][00135] Sum rewards: -6.461, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.200', 'AMMO5': '0.005', 'AMMO2': '0.017', 'WEAPON1': '0.020', 'weapon5': '0.062', 'ARMOR': '0.064', 'AMMO4': '0.085', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.138', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.393', 'WEAPON3': '0.800', 'weapon4': '0.832', 'FRAGCOUNT': '1.000', 'weapon3': '1.862', 'weapon2': '2.460'} [2024-08-01 15:56:08,292][00140] DAMAGECOUNT value on done: 327.0 [2024-08-01 15:56:08,296][00140] Sum rewards: 3.954, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.430', 'weapon5': '0.002', 'AMMO2': '0.009', 'AMMO5': '0.010', 'ARMOR': '0.040', 'AMMO4': '0.043', 'AMMO3': '0.113', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.134', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.464', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.981', 'weapon2': '2.396', 'weapon3': '2.452', 'FRAGCOUNT': '4.000'} [2024-08-01 15:56:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3068.6). Total num frames: 2904064. Throughput: 0: 1510.1. Samples: 1458756. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 15:56:08,840][00034] Avg episode reward: [(0, '-4.261')] [2024-08-01 15:56:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000709_2904064.pth... [2024-08-01 15:56:08,911][00144] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:56:09,005][00139] DAMAGECOUNT value on done: 300.0 [2024-08-01 15:56:09,006][00139] Sum rewards: -7.056, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO2': '0.012', 'ARMOR': '0.036', 'AMMO4': '0.057', 'weapon4': '0.066', 'WEAPON4': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.175', 'DAMAGECOUNT': '0.900', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.358', 'weapon2': '2.800'} [2024-08-01 15:56:09,035][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000529_2166784.pth [2024-08-01 15:56:09,664][00147] DAMAGECOUNT value on done: 14.0 [2024-08-01 15:56:10,171][00138] DAMAGECOUNT value on done: 164.0 [2024-08-01 15:56:10,180][00138] Sum rewards: -7.923, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.825', 'AMMO5': '0.003', 'AMMO2': '0.033', 'HITCOUNT': '0.050', 'WEAPON5': '0.100', 'AMMO3': '0.148', 'weapon5': '0.158', 'AMMO4': '0.164', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.492', 'weapon4': '0.510', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.228', 'weapon2': '3.916'} [2024-08-01 15:56:10,645][00143] DAMAGECOUNT value on done: 139.0 [2024-08-01 15:56:10,650][00143] Sum rewards: -2.235, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.300', 'AMMO5': '0.003', 'AMMO2': '0.003', 'AMMO4': '0.014', 'ARMOR': '0.020', 'WEAPON1': '0.040', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.146', 'weapon4': '0.254', 'weapon5': '0.304', 'DAMAGECOUNT': '0.417', 'WEAPON3': '0.700', 'weapon3': '1.236', 'FRAGCOUNT': '2.000', 'weapon2': '3.868'} [2024-08-01 15:56:11,264][00134] Updated weights for policy 0, policy_version 711 (0.0021) [2024-08-01 15:56:11,401][00142] DAMAGECOUNT value on done: 222.0 [2024-08-01 15:56:11,408][00142] Sum rewards: -8.163, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.125', 'AMMO2': '0.018', 'ARMOR': '0.076', 'AMMO4': '0.091', 'HITCOUNT': '0.140', 'AMMO3': '0.197', 'WEAPON4': '0.300', 'weapon4': '0.566', 'DAMAGECOUNT': '0.666', 'WEAPON3': '1.100', 'weapon3': '1.978', 'FRAGCOUNT': '2.000', 'weapon2': '2.580'} [2024-08-01 15:56:11,965][00133] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:56:12,746][00137] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:56:12,832][00132] DAMAGECOUNT value on done: 157.0 [2024-08-01 15:56:12,836][00132] Sum rewards: -6.662, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.500', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'AMMO2': '0.030', 'weapon5': '0.064', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.134', 'AMMO4': '0.152', 'weapon4': '0.368', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.471', 'ARMOR': '0.472', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.194', 'weapon2': '2.868'} [2024-08-01 15:56:12,875][00141] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:13,788][00139] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:56:13,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2920448. Throughput: 0: 1508.2. Samples: 1463376. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:56:13,841][00034] Avg episode reward: [(0, '-4.304')] [2024-08-01 15:56:14,326][00146] DAMAGECOUNT value on done: 245.0 [2024-08-01 15:56:14,329][00146] Sum rewards: -4.345, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.064', 'AMMO2': '0.018', 'AMMO5': '0.020', 'ARMOR': '0.040', 'weapon5': '0.064', 'AMMO4': '0.089', 'HITCOUNT': '0.140', 'AMMO3': '0.147', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon4': '0.422', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.735', 'weapon3': '1.256', 'FRAGCOUNT': '2.000', 'weapon2': '3.238'} [2024-08-01 15:56:14,402][00136] DAMAGECOUNT value on done: 39.0 [2024-08-01 15:56:14,407][00136] Sum rewards: -11.335, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.850', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'ARMOR': '0.028', 'AMMO2': '0.028', 'weapon5': '0.046', 'HITCOUNT': '0.050', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.117', 'AMMO3': '0.119', 'AMMO4': '0.142', 'weapon4': '0.350', 'WEAPON4': '0.400', 'WEAPON3': '0.600', 'weapon3': '2.082', 'weapon2': '2.948'} [2024-08-01 15:56:14,415][00145] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:56:14,816][00148] DAMAGECOUNT value on done: 89.0 [2024-08-01 15:56:14,820][00148] Sum rewards: -11.032, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.770', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'AMMO2': '0.017', 'ARMOR': '0.028', 'weapon5': '0.046', 'HITCOUNT': '0.080', 'AMMO4': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.139', 'DAMAGECOUNT': '0.267', 'WEAPON4': '0.300', 'weapon4': '0.424', 'WEAPON3': '0.800', 'weapon3': '2.014', 'weapon2': '2.934'} [2024-08-01 15:56:15,452][00135] DAMAGECOUNT value on done: 48.0 [2024-08-01 15:56:15,893][00140] DAMAGECOUNT value on done: 130.0 [2024-08-01 15:56:15,898][00140] Sum rewards: -2.934, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'weapon5': '0.008', 'AMMO2': '0.010', 'AMMO5': '0.010', 'ARMOR': '0.016', 'AMMO4': '0.048', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.174', 'DAMAGECOUNT': '0.390', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.406', 'weapon2': '3.254'} [2024-08-01 15:56:16,353][00144] DAMAGECOUNT value on done: 109.0 [2024-08-01 15:56:16,359][00144] Sum rewards: -3.957, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.586', 'AMMO2': '0.014', 'AMMO4': '0.069', 'HITCOUNT': '0.100', 'AMMO3': '0.102', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.327', 'ARMOR': '0.531', 'WEAPON3': '0.600', 'weapon4': '0.834', 'FRAGCOUNT': '1.000', 'weapon3': '1.990', 'weapon2': '2.762'} [2024-08-01 15:56:16,371][00139] DAMAGECOUNT value on done: 158.0 [2024-08-01 15:56:17,233][00147] DAMAGECOUNT value on done: 166.0 [2024-08-01 15:56:17,540][00138] DAMAGECOUNT value on done: 66.0 [2024-08-01 15:56:17,543][00138] Sum rewards: -4.659, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO2': '0.002', 'AMMO5': '0.005', 'AMMO4': '0.012', 'ARMOR': '0.064', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.142', 'DAMAGECOUNT': '0.198', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'AMMO3': '0.228', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.520', 'weapon3': '2.710'} [2024-08-01 15:56:18,338][00143] DAMAGECOUNT value on done: 191.0 [2024-08-01 15:56:18,342][00143] Sum rewards: -8.247, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.430', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.009', 'AMMO2': '0.033', 'weapon5': '0.052', 'ARMOR': '0.092', 'AMMO3': '0.157', 'AMMO4': '0.163', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.573', 'weapon4': '0.740', 'WEAPON3': '0.800', 'weapon3': '1.982', 'weapon2': '2.802'} [2024-08-01 15:56:18,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.8, 300 sec: 3054.6). Total num frames: 2932736. Throughput: 0: 1528.3. Samples: 1472760. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:56:18,843][00034] Avg episode reward: [(0, '-4.279')] [2024-08-01 15:56:20,146][00142] DAMAGECOUNT value on done: 15.0 [2024-08-01 15:56:20,546][00141] DAMAGECOUNT value on done: 69.0 [2024-08-01 15:56:20,551][00141] Sum rewards: -3.525, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.585', 'AMMO5': '0.005', 'AMMO2': '0.013', 'ARMOR': '0.020', 'weapon5': '0.050', 'HITCOUNT': '0.060', 'AMMO4': '0.063', 'WEAPON5': '0.100', 'AMMO3': '0.192', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.207', 'weapon4': '0.462', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.082', 'weapon3': '2.706'} [2024-08-01 15:56:20,615][00133] DAMAGECOUNT value on done: 169.0 [2024-08-01 15:56:20,620][00133] Sum rewards: -3.627, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.624', 'AMMO5': '0.005', 'AMMO2': '0.012', 'HITCOUNT': '0.040', 'AMMO4': '0.062', 'WEAPON5': '0.100', 'AMMO3': '0.128', 'WEAPON4': '0.300', 'weapon5': '0.358', 'weapon4': '0.484', 'DAMAGECOUNT': '0.507', 'ARMOR': '0.561', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.114', 'weapon2': '3.726'} [2024-08-01 15:56:20,876][00132] DAMAGECOUNT value on done: 104.0 [2024-08-01 15:56:21,586][00137] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:56:21,874][00136] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:22,269][00148] DAMAGECOUNT value on done: 160.0 [2024-08-01 15:56:22,274][00148] Sum rewards: -1.050, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.720', 'AMMO5': '0.009', 'AMMO2': '0.009', 'HITCOUNT': '0.030', 'AMMO4': '0.046', 'AMMO3': '0.098', 'weapon5': '0.184', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.332', 'DAMAGECOUNT': '0.480', 'ARMOR': '0.498', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '2.098', 'weapon2': '2.736'} [2024-08-01 15:56:22,505][00145] DAMAGECOUNT value on done: 137.0 [2024-08-01 15:56:22,507][00145] Sum rewards: -1.373, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.975', 'AMMO5': '0.005', 'AMMO2': '0.011', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO4': '0.054', 'AMMO3': '0.065', 'HITCOUNT': '0.150', 'WEAPON4': '0.300', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.411', 'weapon4': '0.632', 'weapon3': '1.174', 'FRAGCOUNT': '2.000', 'weapon2': '3.928'} [2024-08-01 15:56:22,762][00135] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:56:22,765][00135] Sum rewards: 0.589, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.370', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'HITCOUNT': '0.060', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.144', 'weapon7': '0.160', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.300', 'ARMOR': '0.458', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.412', 'weapon3': '3.224'} [2024-08-01 15:56:23,365][00146] DAMAGECOUNT value on done: 23.0 [2024-08-01 15:56:23,494][00140] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:56:23,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2949120. Throughput: 0: 1530.7. Samples: 1481940. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:56:23,843][00034] Avg episode reward: [(0, '-4.254')] [2024-08-01 15:56:23,926][00144] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:56:23,929][00144] Sum rewards: -3.937, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.857', 'AMMO5': '0.005', 'AMMO2': '0.016', 'WEAPON1': '0.040', 'AMMO4': '0.077', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'weapon5': '0.120', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'weapon4': '0.260', 'ARMOR': '0.458', 'DAMAGECOUNT': '0.465', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.548', 'weapon2': '3.558'} [2024-08-01 15:56:24,092][00134] Updated weights for policy 0, policy_version 721 (0.0019) [2024-08-01 15:56:24,676][00147] DAMAGECOUNT value on done: 125.0 [2024-08-01 15:56:24,706][00139] DAMAGECOUNT value on done: 24.0 [2024-08-01 15:56:25,799][00143] DAMAGECOUNT value on done: 157.0 [2024-08-01 15:56:25,805][00143] Sum rewards: -6.029, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.495', 'AMMO5': '0.010', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'weapon5': '0.034', 'AMMO4': '0.050', 'weapon4': '0.054', 'WEAPON4': '0.100', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'AMMO3': '0.249', 'ARMOR': '0.467', 'DAMAGECOUNT': '0.471', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon3': '2.744', 'weapon2': '2.836'} [2024-08-01 15:56:26,268][00138] DAMAGECOUNT value on done: 375.0 [2024-08-01 15:56:26,272][00138] Sum rewards: 2.383, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.620', 'AMMO5': '0.007', 'AMMO2': '0.019', 'AMMO4': '0.092', 'AMMO3': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'HITCOUNT': '0.150', 'weapon7': '0.166', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon5': '0.238', 'WEAPON4': '0.300', 'weapon4': '0.388', 'ARMOR': '0.404', 'WEAPON3': '0.500', 'DAMAGECOUNT': '1.125', 'weapon3': '1.746', 'weapon2': '2.878', 'FRAGCOUNT': '3.000'} [2024-08-01 15:56:27,975][00142] DAMAGECOUNT value on done: 175.0 [2024-08-01 15:56:28,424][00141] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:56:28,498][00133] DAMAGECOUNT value on done: 80.0 [2024-08-01 15:56:28,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 3068.5). Total num frames: 2965504. Throughput: 0: 1532.3. Samples: 1486704. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:56:28,843][00034] Avg episode reward: [(0, '-4.201')] [2024-08-01 15:56:29,249][00132] DAMAGECOUNT value on done: 322.0 [2024-08-01 15:56:29,252][00132] Sum rewards: -0.584, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.705', 'AMMO2': '0.002', 'weapon7': '0.004', 'AMMO4': '0.008', 'ARMOR': '0.024', 'WEAPON4': '0.100', 'AMMO3': '0.109', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.246', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.966', 'FRAGCOUNT': '1.000', 'weapon2': '2.064', 'weapon3': '3.028'} [2024-08-01 15:56:29,257][00137] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:56:29,615][00136] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:29,945][00148] DAMAGECOUNT value on done: 140.0 [2024-08-01 15:56:29,948][00148] Sum rewards: -6.998, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.685', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO2': '0.031', 'HITCOUNT': '0.100', 'AMMO4': '0.153', 'WEAPON4': '0.200', 'weapon4': '0.200', 'AMMO3': '0.223', 'DAMAGECOUNT': '0.420', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.446', 'weapon3': '3.016'} [2024-08-01 15:56:30,662][00145] DAMAGECOUNT value on done: 143.0 [2024-08-01 15:56:30,669][00145] Sum rewards: -2.880, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.290', 'AMMO5': '0.012', 'AMMO2': '0.028', 'HITCOUNT': '0.030', 'ARMOR': '0.040', 'weapon5': '0.134', 'AMMO4': '0.141', 'AMMO3': '0.163', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'weapon4': '0.328', 'DAMAGECOUNT': '0.429', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.892', 'weapon2': '3.162'} [2024-08-01 15:56:30,671][00146] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:56:30,673][00146] Sum rewards: -6.309, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO2': '0.038', 'HITCOUNT': '0.100', 'AMMO4': '0.188', 'AMMO3': '0.232', 'DAMAGECOUNT': '0.315', 'WEAPON4': '0.400', 'ARMOR': '0.442', 'weapon4': '0.546', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.424', 'weapon3': '2.536'} [2024-08-01 15:56:30,975][00140] DAMAGECOUNT value on done: 140.0 [2024-08-01 15:56:30,978][00140] Sum rewards: -4.194, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO2': '0.006', 'AMMO4': '0.031', 'HITCOUNT': '0.130', 'AMMO3': '0.166', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.420', 'ARMOR': '0.456', 'weapon4': '0.500', 'WEAPON3': '0.800', 'weapon3': '1.394', 'FRAGCOUNT': '2.000', 'weapon2': '3.292'} [2024-08-01 15:56:31,352][00135] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:56:31,352][00135] Sum rewards: -6.069, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.019', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'HITCOUNT': '0.050', 'AMMO4': '0.094', 'AMMO3': '0.122', 'weapon5': '0.164', 'DAMAGECOUNT': '0.195', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.440', 'WEAPON3': '0.700', 'weapon3': '1.808', 'weapon2': '2.860'} [2024-08-01 15:56:31,413][00144] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:56:31,418][00144] Sum rewards: -12.753, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.695', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.009', 'AMMO2': '0.011', 'ARMOR': '0.036', 'AMMO4': '0.056', 'HITCOUNT': '0.070', 'weapon4': '0.132', 'weapon5': '0.148', 'DAMAGECOUNT': '0.165', 'AMMO3': '0.169', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON3': '0.800', 'weapon3': '1.136', 'weapon2': '4.560'} [2024-08-01 15:56:32,551][00139] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:56:33,021][00147] DAMAGECOUNT value on done: 110.0 [2024-08-01 15:56:33,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 2977792. Throughput: 0: 1531.2. Samples: 1496004. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 15:56:33,842][00034] Avg episode reward: [(0, '-4.427')] [2024-08-01 15:56:33,897][00138] DAMAGECOUNT value on done: 205.0 [2024-08-01 15:56:33,902][00138] Sum rewards: -2.280, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.160', 'AMMO5': '0.005', 'AMMO2': '0.021', 'ARMOR': '0.032', 'weapon5': '0.054', 'WEAPON5': '0.100', 'AMMO4': '0.105', 'AMMO3': '0.113', 'weapon4': '0.170', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.438', 'weapon2': '2.626'} [2024-08-01 15:56:34,746][00143] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:56:35,855][00142] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:35,864][00142] Sum rewards: -5.868, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.150', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.010', 'ARMOR': '0.032', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'weapon7': '0.100', 'weapon4': '0.128', 'AMMO6': '0.160', 'AMMO7': '0.160', 'AMMO3': '0.177', 'DAMAGECOUNT': '0.180', 'weapon5': '0.186', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.208', 'weapon2': '2.890'} [2024-08-01 15:56:36,366][00133] DAMAGECOUNT value on done: 221.0 [2024-08-01 15:56:36,369][00133] Sum rewards: -1.078, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.982', 'AMMO2': '0.012', 'ARMOR': '0.040', 'AMMO4': '0.061', 'AMMO3': '0.155', 'HITCOUNT': '0.170', 'WEAPON4': '0.200', 'weapon4': '0.296', 'DAMAGECOUNT': '0.663', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.406', 'weapon2': '2.600'} [2024-08-01 15:56:37,214][00137] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:56:37,539][00134] Updated weights for policy 0, policy_version 731 (0.0021) [2024-08-01 15:56:37,592][00136] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:56:37,592][00136] Sum rewards: -6.689, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.954', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'ARMOR': '0.016', 'AMMO2': '0.029', 'HITCOUNT': '0.040', 'AMMO4': '0.144', 'AMMO3': '0.157', 'weapon5': '0.198', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.360', 'weapon4': '0.596', 'WEAPON3': '0.800', 'weapon3': '2.104', 'weapon2': '2.664'} [2024-08-01 15:56:37,801][00141] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:56:37,874][00148] DAMAGECOUNT value on done: 127.0 [2024-08-01 15:56:37,880][00132] DAMAGECOUNT value on done: 390.0 [2024-08-01 15:56:37,880][00132] Sum rewards: -0.720, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.567', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'AMMO5': '0.009', 'ARMOR': '0.040', 'AMMO3': '0.147', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'weapon5': '0.210', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.170', 'weapon2': '2.526', 'weapon3': '2.764', 'FRAGCOUNT': '3.000'} [2024-08-01 15:56:38,547][00146] DAMAGECOUNT value on done: 144.0 [2024-08-01 15:56:38,554][00146] Sum rewards: -7.466, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.080', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO2': '0.038', 'weapon5': '0.054', 'HITCOUNT': '0.120', 'AMMO4': '0.188', 'AMMO3': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.396', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.432', 'ARMOR': '0.533', 'WEAPON3': '1.000', 'weapon3': '1.838', 'FRAGCOUNT': '2.000', 'weapon2': '2.936'} [2024-08-01 15:56:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 2998272. Throughput: 0: 1518.1. Samples: 1504560. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:56:38,842][00034] Avg episode reward: [(0, '-4.233')] [2024-08-01 15:56:39,001][00140] DAMAGECOUNT value on done: 275.0 [2024-08-01 15:56:39,003][00140] Sum rewards: -2.915, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO2': '0.004', 'AMMO5': '0.012', 'AMMO4': '0.019', 'ARMOR': '0.068', 'AMMO3': '0.084', 'HITCOUNT': '0.120', 'WEAPON4': '0.200', 'weapon5': '0.246', 'WEAPON5': '0.300', 'WEAPON3': '0.500', 'weapon4': '0.508', 'DAMAGECOUNT': '0.825', 'weapon3': '1.680', 'FRAGCOUNT': '2.000', 'weapon2': '3.098'} [2024-08-01 15:56:39,438][00144] DAMAGECOUNT value on done: 79.0 [2024-08-01 15:56:39,521][00145] DAMAGECOUNT value on done: 152.0 [2024-08-01 15:56:39,522][00145] Sum rewards: -1.568, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.050', 'AMMO2': '0.006', 'AMMO4': '0.030', 'ARMOR': '0.032', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.175', 'weapon7': '0.188', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.456', 'weapon4': '0.538', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.210', 'weapon2': '2.706'} [2024-08-01 15:56:40,115][00135] DAMAGECOUNT value on done: 12.0 [2024-08-01 15:56:40,487][00147] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:56:41,535][00139] DAMAGECOUNT value on done: 90.0 [2024-08-01 15:56:41,540][00139] Sum rewards: -3.107, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO2': '0.009', 'ARMOR': '0.036', 'AMMO4': '0.042', 'HITCOUNT': '0.070', 'AMMO3': '0.164', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.270', 'weapon4': '0.374', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.524', 'weapon3': '2.994'} [2024-08-01 15:56:41,704][00147] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:56:41,705][00147] Sum rewards: -8.404, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.560', 'AMMO2': '0.010', 'AMMO5': '0.016', 'AMMO4': '0.048', 'WEAPON4': '0.100', 'HITCOUNT': '0.100', 'AMMO3': '0.179', 'WEAPON5': '0.300', 'weapon5': '0.368', 'DAMAGECOUNT': '0.465', 'ARMOR': '0.904', 'WEAPON3': '1.000', 'weapon3': '1.836', 'FRAGCOUNT': '2.000', 'weapon2': '3.330'} [2024-08-01 15:56:42,939][00138] DAMAGECOUNT value on done: 335.0 [2024-08-01 15:56:42,943][00138] Sum rewards: -6.200, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.007', 'WEAPON4': '0.100', 'AMMO3': '0.194', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon5': '0.292', 'weapon4': '0.378', 'ARMOR': '0.484', 'DAMAGECOUNT': '1.005', 'WEAPON3': '1.100', 'FRAGCOUNT': '1.500', 'weapon3': '2.218', 'weapon2': '2.854'} [2024-08-01 15:56:43,021][00143] DAMAGECOUNT value on done: 136.0 [2024-08-01 15:56:43,025][00143] Sum rewards: -6.384, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'AMMO2': '0.031', 'ARMOR': '0.032', 'HITCOUNT': '0.090', 'AMMO4': '0.157', 'AMMO3': '0.197', 'weapon5': '0.240', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.408', 'weapon4': '0.474', 'WEAPON3': '1.100', 'weapon3': '2.126', 'weapon2': '2.258'} [2024-08-01 15:56:43,597][00142] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:56:43,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3010560. Throughput: 0: 1521.3. Samples: 1509384. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:56:43,842][00034] Avg episode reward: [(0, '-4.267')] [2024-08-01 15:56:44,285][00133] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:44,288][00133] Sum rewards: -10.335, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.380', 'AMMO2': '0.004', 'AMMO5': '0.007', 'AMMO4': '0.021', 'weapon4': '0.036', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'weapon5': '0.142', 'DAMAGECOUNT': '0.180', 'WEAPON5': '0.200', 'AMMO3': '0.248', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.354', 'weapon3': '2.902'} [2024-08-01 15:56:45,058][00137] DAMAGECOUNT value on done: 62.0 [2024-08-01 15:56:45,309][00136] DAMAGECOUNT value on done: 282.0 [2024-08-01 15:56:45,310][00136] Sum rewards: -2.655, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO5': '0.004', 'AMMO2': '0.006', 'AMMO4': '0.031', 'weapon5': '0.062', 'ARMOR': '0.068', 'WEAPON5': '0.100', 'AMMO3': '0.180', 'HITCOUNT': '0.180', 'WEAPON4': '0.200', 'weapon4': '0.316', 'DAMAGECOUNT': '0.846', 'WEAPON3': '0.900', 'weapon3': '1.734', 'FRAGCOUNT': '2.000', 'weapon2': '3.298'} [2024-08-01 15:56:45,490][00148] DAMAGECOUNT value on done: 136.0 [2024-08-01 15:56:45,492][00148] Sum rewards: -6.600, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.005', 'AMMO2': '0.010', 'weapon5': '0.030', 'ARMOR': '0.036', 'AMMO4': '0.049', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.180', 'WEAPON4': '0.200', 'weapon4': '0.290', 'DAMAGECOUNT': '0.360', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.846', 'weapon2': '2.964'} [2024-08-01 15:56:45,909][00132] DAMAGECOUNT value on done: 231.0 [2024-08-01 15:56:45,912][00132] Sum rewards: -2.003, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO5': '0.013', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.081', 'AMMO3': '0.118', 'HITCOUNT': '0.130', 'weapon5': '0.130', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.312', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.693', 'WEAPON3': '0.700', 'weapon3': '1.956', 'weapon2': '3.256'} [2024-08-01 15:56:46,043][00141] DAMAGECOUNT value on done: 85.0 [2024-08-01 15:56:46,044][00141] Sum rewards: -3.966, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO2': '0.022', 'ARMOR': '0.028', 'HITCOUNT': '0.100', 'AMMO4': '0.110', 'AMMO3': '0.185', 'DAMAGECOUNT': '0.255', 'weapon4': '0.270', 'WEAPON4': '0.300', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.374', 'weapon3': '2.930'} [2024-08-01 15:56:46,482][00146] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:56:46,646][00140] DAMAGECOUNT value on done: 90.0 [2024-08-01 15:56:46,648][00140] Sum rewards: -0.479, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.553', 'AMMO5': '0.009', 'AMMO2': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'HITCOUNT': '0.050', 'AMMO4': '0.067', 'WEAPON4': '0.100', 'AMMO3': '0.110', 'weapon4': '0.138', 'WEAPON5': '0.200', 'weapon5': '0.214', 'DAMAGECOUNT': '0.270', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.290', 'weapon3': '2.852'} [2024-08-01 15:56:47,166][00144] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:56:47,425][00145] DAMAGECOUNT value on done: 140.0 [2024-08-01 15:56:47,428][00145] Sum rewards: -2.909, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.250', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'AMMO4': '0.024', 'AMMO5': '0.029', 'HITCOUNT': '0.040', 'AMMO3': '0.114', 'DAMAGECOUNT': '0.420', 'ARMOR': '0.487', 'WEAPON5': '0.500', 'weapon5': '0.648', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '1.916', 'weapon3': '2.688'} [2024-08-01 15:56:48,083][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:56:48,772][00135] DAMAGECOUNT value on done: 241.0 [2024-08-01 15:56:48,777][00135] Sum rewards: -2.596, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'ARMOR': '0.004', 'AMMO5': '0.014', 'AMMO2': '0.035', 'weapon5': '0.082', 'AMMO3': '0.098', 'HITCOUNT': '0.120', 'AMMO4': '0.177', 'WEAPON5': '0.200', 'WEAPON4': '0.500', 'weapon4': '0.502', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.723', 'FRAGCOUNT': '1.000', 'weapon3': '2.130', 'weapon2': '2.748'} [2024-08-01 15:56:48,839][00034] Fps is (10 sec: 2457.5, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3022848. Throughput: 0: 1520.3. Samples: 1518408. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:56:48,842][00034] Avg episode reward: [(0, '-4.405')] [2024-08-01 15:56:49,445][00139] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:56:50,372][00147] DAMAGECOUNT value on done: 149.0 [2024-08-01 15:56:50,375][00147] Sum rewards: 1.211, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.335', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'AMMO4': '0.052', 'HITCOUNT': '0.110', 'AMMO3': '0.118', 'weapon7': '0.128', 'weapon4': '0.150', 'WEAPON4': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'DAMAGECOUNT': '0.447', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.504', 'weapon2': '2.812'} [2024-08-01 15:56:51,108][00142] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:56:51,248][00134] Updated weights for policy 0, policy_version 741 (0.0019) [2024-08-01 15:56:51,466][00138] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:56:51,469][00138] Sum rewards: -4.880, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.130', 'WEAPON1': '0.020', 'AMMO2': '0.040', 'ARMOR': '0.050', 'HITCOUNT': '0.110', 'AMMO3': '0.137', 'AMMO4': '0.202', 'DAMAGECOUNT': '0.465', 'WEAPON4': '0.500', 'weapon4': '0.514', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.050', 'weapon2': '2.862'} [2024-08-01 15:56:51,772][00133] DAMAGECOUNT value on done: 166.0 [2024-08-01 15:56:51,908][00143] DAMAGECOUNT value on done: 125.0 [2024-08-01 15:56:51,911][00143] Sum rewards: -4.481, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.792', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'weapon5': '0.010', 'ARMOR': '0.068', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.132', 'DAMAGECOUNT': '0.375', 'weapon4': '0.386', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.380', 'weapon2': '2.856'} [2024-08-01 15:56:52,526][00137] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:56:52,775][00136] DAMAGECOUNT value on done: 242.0 [2024-08-01 15:56:52,776][00136] Sum rewards: -1.055, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.190', 'AMMO4': '-0.053', 'AMMO2': '-0.010', 'WEAPON4': '0.100', 'AMMO3': '0.136', 'HITCOUNT': '0.160', 'weapon4': '0.592', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.726', 'FRAGCOUNT': '2.000', 'weapon3': '2.146', 'weapon2': '3.238'} [2024-08-01 15:56:52,872][00148] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:56:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 3043328. Throughput: 0: 1529.9. Samples: 1527600. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:56:53,841][00034] Avg episode reward: [(0, '-4.430')] [2024-08-01 15:56:54,094][00141] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:56:54,142][00140] DAMAGECOUNT value on done: 239.0 [2024-08-01 15:56:54,143][00140] Sum rewards: -0.688, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'ARMOR': '0.012', 'AMMO2': '0.018', 'AMMO5': '0.019', 'AMMO4': '0.092', 'AMMO3': '0.146', 'HITCOUNT': '0.170', 'weapon5': '0.206', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon4': '0.408', 'DAMAGECOUNT': '0.717', 'WEAPON3': '0.800', 'weapon3': '1.696', 'weapon2': '2.898', 'FRAGCOUNT': '3.000'} [2024-08-01 15:56:54,250][00146] DAMAGECOUNT value on done: 95.0 [2024-08-01 15:56:54,252][00146] Sum rewards: -2.107, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.955', 'AMMO5': '0.005', 'weapon5': '0.012', 'AMMO2': '0.037', 'HITCOUNT': '0.070', 'ARMOR': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.120', 'AMMO4': '0.187', 'DAMAGECOUNT': '0.285', 'WEAPON4': '0.400', 'weapon4': '0.610', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.896', 'weapon2': '2.842'} [2024-08-01 15:56:54,434][00132] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:56:54,596][00144] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:56:54,601][00144] Sum rewards: -7.330, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'FRAGCOUNT': '-3.000', 'AMMO2': '0.011', 'AMMO5': '0.014', 'HITCOUNT': '0.020', 'WEAPON1': '0.040', 'AMMO4': '0.054', 'DAMAGECOUNT': '0.060', 'AMMO3': '0.125', 'weapon4': '0.168', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'ARMOR': '0.480', 'weapon5': '0.598', 'WEAPON3': '0.600', 'weapon3': '1.622', 'weapon2': '2.888'} [2024-08-01 15:56:55,844][00145] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:56:56,255][00135] DAMAGECOUNT value on done: 229.0 [2024-08-01 15:56:56,258][00135] Sum rewards: -1.716, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.465', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.009', 'ARMOR': '0.056', 'weapon4': '0.076', 'weapon5': '0.092', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.171', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.687', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '2.404', 'weapon2': '3.142'} [2024-08-01 15:56:57,407][00139] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:56:57,829][00147] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:56:58,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3055616. Throughput: 0: 1532.8. Samples: 1532352. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 15:56:58,841][00034] Avg episode reward: [(0, '-4.371')] [2024-08-01 15:56:58,933][00138] DAMAGECOUNT value on done: 29.0 [2024-08-01 15:56:58,937][00138] Sum rewards: -5.477, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.200', 'AMMO2': '0.001', 'weapon5': '0.002', 'AMMO4': '0.004', 'AMMO5': '0.010', 'HITCOUNT': '0.040', 'weapon4': '0.050', 'DAMAGECOUNT': '0.087', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.148', 'WEAPON3': '0.900', 'ARMOR': '0.939', 'FRAGCOUNT': '1.000', 'weapon3': '2.760', 'weapon2': '3.082'} [2024-08-01 15:56:59,386][00143] DAMAGECOUNT value on done: 13.0 [2024-08-01 15:56:59,393][00143] Sum rewards: -6.442, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.001', 'AMMO5': '0.005', 'AMMO4': '0.007', 'HITCOUNT': '0.020', 'weapon5': '0.026', 'DAMAGECOUNT': '0.039', 'ARMOR': '0.057', 'WEAPON5': '0.100', 'AMMO3': '0.173', 'WEAPON4': '0.200', 'weapon4': '0.834', 'WEAPON3': '0.900', 'weapon3': '2.526', 'weapon2': '2.750'} [2024-08-01 15:57:00,521][00136] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:57:00,554][00148] DAMAGECOUNT value on done: 278.0 [2024-08-01 15:57:00,559][00148] Sum rewards: -5.472, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'FRAGCOUNT': '-1.000', 'AMMO5': '0.012', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'AMMO4': '0.067', 'AMMO3': '0.104', 'ARMOR': '0.108', 'weapon5': '0.218', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'WEAPON3': '0.600', 'weapon4': '0.696', 'DAMAGECOUNT': '0.834', 'weapon3': '1.700', 'weapon2': '3.076'} [2024-08-01 15:57:00,615][00142] DAMAGECOUNT value on done: 215.0 [2024-08-01 15:57:00,619][00142] Sum rewards: -5.214, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'ARMOR': '0.008', 'AMMO2': '0.016', 'AMMO4': '0.077', 'HITCOUNT': '0.130', 'AMMO3': '0.184', 'WEAPON4': '0.200', 'weapon4': '0.344', 'DAMAGECOUNT': '0.645', 'WEAPON3': '0.900', 'weapon3': '1.408', 'FRAGCOUNT': '2.000', 'weapon2': '3.514'} [2024-08-01 15:57:01,398][00141] DAMAGECOUNT value on done: 64.0 [2024-08-01 15:57:01,609][00133] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:57:01,613][00133] Sum rewards: -3.418, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.310', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.038', 'HITCOUNT': '0.050', 'AMMO4': '0.055', 'AMMO3': '0.132', 'WEAPON4': '0.200', 'weapon4': '0.232', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.532', 'weapon2': '2.756'} [2024-08-01 15:57:01,624][00140] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:57:01,730][00132] DAMAGECOUNT value on done: 10.0 [2024-08-01 15:57:02,171][00144] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:57:02,174][00144] Sum rewards: -5.699, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO5': '0.011', 'AMMO2': '0.016', 'HITCOUNT': '0.030', 'ARMOR': '0.072', 'AMMO4': '0.078', 'DAMAGECOUNT': '0.090', 'AMMO3': '0.107', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon5': '0.360', 'weapon4': '0.370', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.362', 'weapon2': '3.344'} [2024-08-01 15:57:02,369][00137] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:57:02,372][00137] Sum rewards: -3.605, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.000', 'AMMO2': '0.000', 'AMMO5': '0.017', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'AMMO3': '0.097', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.165', 'weapon5': '0.264', 'WEAPON5': '0.300', 'weapon4': '0.394', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.116', 'weapon2': '2.732'} [2024-08-01 15:57:02,399][00141] Large shaping reward -2.506 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 15:57:03,145][00145] DAMAGECOUNT value on done: 260.0 [2024-08-01 15:57:03,149][00145] Sum rewards: -7.679, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.145', 'AMMO5': '0.005', 'AMMO2': '0.026', 'WEAPON5': '0.100', 'weapon5': '0.122', 'AMMO4': '0.128', 'HITCOUNT': '0.190', 'AMMO3': '0.202', 'WEAPON4': '0.400', 'weapon4': '0.702', 'DAMAGECOUNT': '0.780', 'WEAPON3': '1.100', 'weapon3': '1.786', 'FRAGCOUNT': '2.000', 'weapon2': '2.676'} [2024-08-01 15:57:03,622][00135] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:57:03,839][00034] Fps is (10 sec: 2866.9, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 3072000. Throughput: 0: 1530.6. Samples: 1541640. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:57:03,842][00034] Avg episode reward: [(0, '-4.524')] [2024-08-01 15:57:04,031][00146] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:57:05,058][00139] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:57:05,099][00134] Updated weights for policy 0, policy_version 751 (0.0019) [2024-08-01 15:57:05,261][00147] DAMAGECOUNT value on done: 312.0 [2024-08-01 15:57:05,266][00147] Sum rewards: -3.524, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.015', 'AMMO5': '0.007', 'AMMO2': '0.012', 'AMMO4': '0.061', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'weapon4': '0.188', 'AMMO3': '0.189', 'WEAPON5': '0.200', 'weapon5': '0.236', 'ARMOR': '0.477', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.936', 'FRAGCOUNT': '1.500', 'weapon2': '2.476', 'weapon3': '2.848'} [2024-08-01 15:57:06,601][00138] DAMAGECOUNT value on done: 159.0 [2024-08-01 15:57:06,604][00138] Sum rewards: -2.137, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO5': '0.005', 'AMMO2': '0.025', 'ARMOR': '0.048', 'AMMO3': '0.091', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO4': '0.126', 'DAMAGECOUNT': '0.477', 'WEAPON4': '0.500', 'WEAPON3': '0.500', 'weapon3': '1.128', 'weapon4': '1.610', 'FRAGCOUNT': '2.000', 'weapon2': '2.652'} [2024-08-01 15:57:07,139][00143] DAMAGECOUNT value on done: 180.0 [2024-08-01 15:57:07,146][00143] Sum rewards: -1.889, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO5': '0.005', 'AMMO2': '0.021', 'WEAPON5': '0.100', 'AMMO4': '0.102', 'AMMO3': '0.129', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'weapon4': '0.260', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.644', 'weapon2': '2.690'} [2024-08-01 15:57:08,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 3088384. Throughput: 0: 1519.5. Samples: 1550316. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:57:08,841][00034] Avg episode reward: [(0, '-4.524')] [2024-08-01 15:57:08,867][00136] DAMAGECOUNT value on done: 109.0 [2024-08-01 15:57:09,035][00148] DAMAGECOUNT value on done: 160.0 [2024-08-01 15:57:09,035][00148] Sum rewards: -6.220, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.073', 'AMMO2': '-0.014', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'HITCOUNT': '0.040', 'AMMO3': '0.086', 'WEAPON5': '0.200', 'weapon5': '0.354', 'ARMOR': '0.462', 'DAMAGECOUNT': '0.480', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.214', 'weapon2': '4.144'} [2024-08-01 15:57:09,179][00142] DAMAGECOUNT value on done: 571.0 [2024-08-01 15:57:09,180][00142] Sum rewards: 2.728, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.475', 'AMMO5': '0.005', 'ARMOR': '0.020', 'AMMO2': '0.024', 'weapon5': '0.072', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO4': '0.122', 'AMMO3': '0.127', 'weapon7': '0.162', 'WEAPON7': '0.200', 'WEAPON4': '0.300', 'WEAPON3': '0.700', 'weapon3': '1.260', 'weapon4': '1.300', 'DAMAGECOUNT': '1.413', 'weapon2': '2.068', 'FRAGCOUNT': '3.000'} [2024-08-01 15:57:09,563][00141] DAMAGECOUNT value on done: 99.0 [2024-08-01 15:57:09,568][00141] Sum rewards: -4.434, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'AMMO2': '0.003', 'AMMO5': '0.010', 'AMMO4': '0.014', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'weapon4': '0.120', 'weapon5': '0.132', 'AMMO3': '0.183', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.297', 'ARMOR': '0.489', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.416', 'weapon3': '3.092'} [2024-08-01 15:57:09,912][00133] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:57:09,978][00132] DAMAGECOUNT value on done: 100.0 [2024-08-01 15:57:09,981][00132] Sum rewards: -4.102, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.475', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.009', 'AMMO2': '0.009', 'ARMOR': '0.016', 'AMMO4': '0.045', 'WEAPON5': '0.100', 'weapon5': '0.106', 'HITCOUNT': '0.120', 'AMMO6': '0.160', 'AMMO7': '0.160', 'AMMO3': '0.178', 'weapon7': '0.196', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.300', 'weapon4': '0.616', 'WEAPON3': '1.000', 'weapon3': '2.326', 'weapon2': '2.382'} [2024-08-01 15:57:10,129][00140] DAMAGECOUNT value on done: 552.0 [2024-08-01 15:57:10,136][00140] Sum rewards: -2.758, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO2': '0.005', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'AMMO4': '0.025', 'ARMOR': '0.048', 'HITCOUNT': '0.130', 'WEAPON4': '0.200', 'AMMO3': '0.219', 'WEAPON5': '0.300', 'weapon5': '0.352', 'weapon4': '0.638', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.656', 'weapon3': '1.676', 'weapon2': '3.088', 'FRAGCOUNT': '3.500'} [2024-08-01 15:57:10,443][00137] DAMAGECOUNT value on done: 378.0 [2024-08-01 15:57:10,444][00137] Sum rewards: -4.660, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.195', 'AMMO2': '0.001', 'weapon7': '0.002', 'AMMO4': '0.002', 'AMMO5': '0.021', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.154', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon4': '0.270', 'WEAPON5': '0.400', 'weapon5': '0.420', 'ARMOR': '0.458', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.134', 'weapon3': '2.464', 'weapon2': '2.470'} [2024-08-01 15:57:10,780][00144] DAMAGECOUNT value on done: 315.0 [2024-08-01 15:57:10,781][00144] Sum rewards: -0.342, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.980', 'AMMO5': '0.005', 'AMMO2': '0.011', 'AMMO4': '0.054', 'ARMOR': '0.060', 'AMMO3': '0.149', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'weapon4': '0.640', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.945', 'FRAGCOUNT': '2.000', 'weapon2': '2.412', 'weapon3': '2.552'} [2024-08-01 15:57:11,580][00145] DAMAGECOUNT value on done: 235.0 [2024-08-01 15:57:11,585][00145] Sum rewards: 1.895, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.440', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.008', 'AMMO3': '0.130', 'weapon5': '0.162', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.705', 'weapon2': '2.548', 'weapon3': '2.804', 'FRAGCOUNT': '3.000'} [2024-08-01 15:57:11,921][00135] DAMAGECOUNT value on done: 55.0 [2024-08-01 15:57:11,925][00135] Sum rewards: -5.505, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.830', 'AMMO2': '0.003', 'AMMO5': '0.009', 'AMMO4': '0.013', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.129', 'DAMAGECOUNT': '0.165', 'WEAPON5': '0.200', 'weapon4': '0.206', 'weapon5': '0.244', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.180', 'weapon3': '3.056'} [2024-08-01 15:57:11,976][00146] DAMAGECOUNT value on done: 215.0 [2024-08-01 15:57:13,299][00139] DAMAGECOUNT value on done: 80.0 [2024-08-01 15:57:13,612][00147] DAMAGECOUNT value on done: 118.0 [2024-08-01 15:57:13,618][00147] Sum rewards: -6.114, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.851', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.006', 'AMMO2': '0.040', 'ARMOR': '0.048', 'AMMO3': '0.055', 'HITCOUNT': '0.060', 'AMMO4': '0.199', 'WEAPON5': '0.200', 'weapon5': '0.246', 'WEAPON3': '0.300', 'DAMAGECOUNT': '0.354', 'WEAPON4': '0.600', 'weapon3': '0.644', 'weapon4': '1.116', 'weapon2': '3.368'} [2024-08-01 15:57:13,838][00034] Fps is (10 sec: 2867.5, 60 sec: 3003.8, 300 sec: 3054.6). Total num frames: 3100672. Throughput: 0: 1514.9. Samples: 1554876. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 15:57:13,841][00034] Avg episode reward: [(0, '-4.548')] [2024-08-01 15:57:15,318][00138] DAMAGECOUNT value on done: 345.0 [2024-08-01 15:57:15,318][00138] Sum rewards: -3.338, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.255', 'AMMO4': '-0.071', 'AMMO2': '-0.014', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO3': '0.129', 'HITCOUNT': '0.150', 'WEAPON5': '0.300', 'weapon5': '0.324', 'WEAPON3': '0.500', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '1.035', 'weapon3': '1.176', 'weapon2': '4.108'} [2024-08-01 15:57:15,382][00143] DAMAGECOUNT value on done: 114.0 [2024-08-01 15:57:15,383][00143] Sum rewards: -6.027, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO2': '0.018', 'ARMOR': '0.044', 'AMMO4': '0.092', 'HITCOUNT': '0.110', 'AMMO3': '0.179', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.342', 'weapon4': '0.476', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.108', 'weapon2': '2.964'} [2024-08-01 15:57:16,498][00136] DAMAGECOUNT value on done: 170.0 [2024-08-01 15:57:16,686][00148] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:57:17,220][00142] DAMAGECOUNT value on done: 140.0 [2024-08-01 15:57:17,224][00142] Sum rewards: -1.117, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.125', 'AMMO2': '0.013', 'AMMO4': '0.067', 'AMMO3': '0.106', 'HITCOUNT': '0.150', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.420', 'ARMOR': '0.510', 'weapon4': '0.636', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.768', 'weapon2': '2.838'} [2024-08-01 15:57:17,845][00141] DAMAGECOUNT value on done: 310.0 [2024-08-01 15:57:17,847][00141] Sum rewards: -1.799, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'AMMO3': '0.168', 'HITCOUNT': '0.250', 'weapon5': '0.380', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.930', 'weapon2': '2.168', 'weapon3': '3.034'} [2024-08-01 15:57:17,852][00140] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:57:17,893][00134] Updated weights for policy 0, policy_version 761 (0.0019) [2024-08-01 15:57:18,108][00133] DAMAGECOUNT value on done: 166.0 [2024-08-01 15:57:18,108][00132] DAMAGECOUNT value on done: 80.0 [2024-08-01 15:57:18,444][00144] DAMAGECOUNT value on done: 205.0 [2024-08-01 15:57:18,690][00137] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:57:18,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3140.2, 300 sec: 3082.4). Total num frames: 3121152. Throughput: 0: 1513.3. Samples: 1564104. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:57:18,841][00034] Avg episode reward: [(0, '-4.481')] [2024-08-01 15:57:19,864][00145] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:57:19,876][00145] Sum rewards: -5.158, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO2': '0.008', 'AMMO5': '0.010', 'weapon5': '0.020', 'AMMO4': '0.037', 'HITCOUNT': '0.070', 'AMMO3': '0.191', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.348', 'DAMAGECOUNT': '0.360', 'ARMOR': '0.488', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.532', 'weapon2': '3.038'} [2024-08-01 15:57:19,977][00146] DAMAGECOUNT value on done: 0.0 [2024-08-01 15:57:20,196][00135] DAMAGECOUNT value on done: 205.0 [2024-08-01 15:57:20,199][00135] Sum rewards: -0.143, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.000', 'AMMO5': '0.003', 'AMMO2': '0.014', 'AMMO4': '0.067', 'AMMO3': '0.099', 'WEAPON5': '0.100', 'HITCOUNT': '0.180', 'weapon5': '0.222', 'WEAPON4': '0.300', 'ARMOR': '0.560', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.615', 'weapon4': '0.838', 'weapon3': '1.702', 'FRAGCOUNT': '2.000', 'weapon2': '3.058'} [2024-08-01 15:57:21,805][00147] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:57:21,810][00147] Sum rewards: -4.501, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'HITCOUNT': '0.050', 'weapon5': '0.102', 'AMMO3': '0.148', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.210', 'WEAPON3': '0.900', 'weapon2': '2.842', 'weapon3': '3.010'} [2024-08-01 15:57:22,099][00139] DAMAGECOUNT value on done: 114.0 [2024-08-01 15:57:23,763][00138] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:57:23,767][00138] Sum rewards: -8.444, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.195', 'AMMO3': '0.212', 'weapon4': '0.328', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '2.586', 'weapon2': '2.776'} [2024-08-01 15:57:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3129344. Throughput: 0: 1524.3. Samples: 1573152. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 15:57:23,840][00034] Avg episode reward: [(0, '-4.457')] [2024-08-01 15:57:24,101][00143] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:57:24,175][00136] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:57:24,373][00148] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:57:24,385][00148] Sum rewards: -2.273, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.940', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.005', 'ARMOR': '0.040', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.140', 'AMMO3': '0.168', 'DAMAGECOUNT': '0.210', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.712', 'weapon2': '2.830'} [2024-08-01 15:57:25,137][00142] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:57:25,726][00140] DAMAGECOUNT value on done: 147.0 [2024-08-01 15:57:25,729][00140] Sum rewards: -0.714, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'AMMO2': '0.010', 'ARMOR': '0.044', 'AMMO4': '0.048', 'HITCOUNT': '0.110', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'weapon4': '0.334', 'DAMAGECOUNT': '0.441', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.410', 'weapon3': '3.256'} [2024-08-01 15:57:25,894][00141] DAMAGECOUNT value on done: 70.0 [2024-08-01 15:57:25,895][00141] Sum rewards: -7.507, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.780', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.006', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.031', 'HITCOUNT': '0.070', 'AMMO3': '0.099', 'WEAPON5': '0.100', 'weapon5': '0.124', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.210', 'weapon4': '0.458', 'WEAPON3': '0.600', 'weapon3': '1.928', 'weapon2': '2.918'} [2024-08-01 15:57:25,896][00133] DAMAGECOUNT value on done: 455.0 [2024-08-01 15:57:25,899][00133] Sum rewards: -0.736, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO5': '0.012', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.048', 'weapon4': '0.078', 'AMMO4': '0.082', 'weapon5': '0.134', 'AMMO3': '0.136', 'HITCOUNT': '0.140', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.365', 'weapon3': '2.070', 'weapon2': '3.502', 'FRAGCOUNT': '4.000'} [2024-08-01 15:57:26,171][00144] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:57:26,343][00137] DAMAGECOUNT value on done: 190.0 [2024-08-01 15:57:26,344][00137] Sum rewards: -6.503, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.995', 'AMMO5': '0.008', 'AMMO2': '0.020', 'HITCOUNT': '0.050', 'AMMO4': '0.098', 'WEAPON5': '0.100', 'weapon5': '0.164', 'WEAPON4': '0.200', 'AMMO3': '0.235', 'weapon4': '0.372', 'ARMOR': '0.452', 'DAMAGECOUNT': '0.570', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '2.496', 'weapon2': '2.626'} [2024-08-01 15:57:26,732][00132] DAMAGECOUNT value on done: 30.0 [2024-08-01 15:57:26,732][00132] Sum rewards: -6.939, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.490', 'AMMO2': '0.017', 'WEAPON1': '0.020', 'HITCOUNT': '0.040', 'ARMOR': '0.044', 'AMMO4': '0.086', 'DAMAGECOUNT': '0.090', 'AMMO3': '0.209', 'WEAPON4': '0.300', 'weapon4': '0.426', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.648', 'weapon3': '2.820'} [2024-08-01 15:57:27,823][00146] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:57:27,826][00146] Sum rewards: -4.548, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'AMMO5': '0.005', 'AMMO2': '0.015', 'weapon5': '0.034', 'AMMO4': '0.077', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.160', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.315', 'ARMOR': '0.524', 'WEAPON3': '0.800', 'weapon4': '0.968', 'FRAGCOUNT': '1.000', 'weapon3': '1.958', 'weapon2': '2.656'} [2024-08-01 15:57:28,033][00135] DAMAGECOUNT value on done: 54.0 [2024-08-01 15:57:28,038][00135] Sum rewards: -8.809, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'ARMOR': '0.004', 'weapon4': '0.018', 'HITCOUNT': '0.060', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.162', 'AMMO3': '0.184', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '1.480', 'weapon2': '4.094'} [2024-08-01 15:57:28,446][00145] DAMAGECOUNT value on done: 272.0 [2024-08-01 15:57:28,839][00034] Fps is (10 sec: 2457.7, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3145728. Throughput: 0: 1519.5. Samples: 1577760. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 15:57:28,842][00034] Avg episode reward: [(0, '-4.441')] [2024-08-01 15:57:30,132][00139] DAMAGECOUNT value on done: 114.0 [2024-08-01 15:57:30,138][00139] Sum rewards: -5.242, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.866', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO2': '0.027', 'ARMOR': '0.056', 'HITCOUNT': '0.100', 'AMMO4': '0.136', 'AMMO3': '0.141', 'weapon5': '0.166', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.342', 'weapon4': '0.364', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.926', 'weapon2': '2.788'} [2024-08-01 15:57:31,465][00134] Updated weights for policy 0, policy_version 771 (0.0019) [2024-08-01 15:57:31,706][00136] DAMAGECOUNT value on done: 26.0 [2024-08-01 15:57:31,731][00148] DAMAGECOUNT value on done: 130.0 [2024-08-01 15:57:31,735][00148] Sum rewards: -3.192, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.301', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.060', 'weapon4': '0.118', 'HITCOUNT': '0.120', 'AMMO3': '0.131', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.674', 'weapon3': '2.934'} [2024-08-01 15:57:32,065][00143] DAMAGECOUNT value on done: 183.0 [2024-08-01 15:57:32,361][00138] DAMAGECOUNT value on done: 54.0 [2024-08-01 15:57:32,671][00142] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:57:32,923][00140] DAMAGECOUNT value on done: 25.0 [2024-08-01 15:57:33,363][00144] DAMAGECOUNT value on done: 454.0 [2024-08-01 15:57:33,367][00144] Sum rewards: -0.563, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.113', 'AMMO2': '0.027', 'ARMOR': '0.044', 'AMMO4': '0.133', 'AMMO3': '0.150', 'WEAPON4': '0.300', 'HITCOUNT': '0.350', 'weapon4': '0.532', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.362', 'weapon2': '2.726', 'weapon3': '2.776', 'FRAGCOUNT': '4.000'} [2024-08-01 15:57:33,613][00133] DAMAGECOUNT value on done: 117.0 [2024-08-01 15:57:33,613][00133] Sum rewards: -3.433, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.890', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.111', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.162', 'weapon7': '0.182', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.351', 'weapon4': '0.416', 'WEAPON3': '0.700', 'weapon2': '2.494', 'weapon3': '2.536'} [2024-08-01 15:57:33,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3068.6). Total num frames: 3166208. Throughput: 0: 1528.3. Samples: 1587180. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:57:33,840][00034] Avg episode reward: [(0, '-4.352')] [2024-08-01 15:57:33,994][00137] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:57:33,995][00137] Sum rewards: -10.188, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.500', 'FRAGCOUNT': '-2.000', 'AMMO5': '0.006', 'AMMO2': '0.044', 'HITCOUNT': '0.050', 'DAMAGECOUNT': '0.150', 'weapon4': '0.182', 'AMMO3': '0.195', 'WEAPON5': '0.200', 'AMMO4': '0.219', 'WEAPON4': '0.300', 'weapon5': '0.454', 'WEAPON3': '1.000', 'weapon3': '2.332', 'weapon2': '2.430'} [2024-08-01 15:57:34,279][00141] DAMAGECOUNT value on done: 262.0 [2024-08-01 15:57:34,285][00141] Sum rewards: -3.707, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.210', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.005', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.108', 'AMMO3': '0.115', 'HITCOUNT': '0.130', 'weapon4': '0.404', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.786', 'weapon2': '2.280', 'weapon3': '2.470'} [2024-08-01 15:57:34,997][00132] DAMAGECOUNT value on done: 39.0 [2024-08-01 15:57:35,891][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:57:35,919][00146] DAMAGECOUNT value on done: 255.0 [2024-08-01 15:57:35,931][00146] Sum rewards: -2.264, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.170', 'AMMO5': '0.003', 'ARMOR': '0.004', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.050', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO3': '0.113', 'weapon4': '0.122', 'WEAPON4': '0.200', 'weapon5': '0.278', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.765', 'FRAGCOUNT': '1.000', 'weapon3': '2.144', 'weapon2': '2.906'} [2024-08-01 15:57:36,293][00135] DAMAGECOUNT value on done: 77.0 [2024-08-01 15:57:36,299][00135] Sum rewards: -4.159, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.835', 'AMMO5': '0.009', 'ARMOR': '0.024', 'AMMO2': '0.034', 'HITCOUNT': '0.090', 'AMMO3': '0.139', 'AMMO4': '0.169', 'weapon5': '0.182', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.231', 'WEAPON4': '0.400', 'weapon4': '0.652', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '1.794', 'weapon2': '3.052'} [2024-08-01 15:57:36,416][00145] DAMAGECOUNT value on done: 131.0 [2024-08-01 15:57:38,107][00139] DAMAGECOUNT value on done: 90.0 [2024-08-01 15:57:38,111][00139] Sum rewards: -8.081, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'weapon5': '0.022', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.104', 'AMMO3': '0.190', 'DAMAGECOUNT': '0.270', 'ARMOR': '0.489', 'WEAPON3': '1.100', 'weapon3': '2.690', 'weapon2': '2.976'} [2024-08-01 15:57:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3178496. Throughput: 0: 1531.5. Samples: 1596516. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 15:57:38,840][00034] Avg episode reward: [(0, '-4.327')] [2024-08-01 15:57:39,512][00136] DAMAGECOUNT value on done: 60.0 [2024-08-01 15:57:39,517][00136] Sum rewards: -7.337, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.013', 'HITCOUNT': '0.080', 'DAMAGECOUNT': '0.180', 'AMMO3': '0.212', 'WEAPON5': '0.300', 'weapon5': '0.324', 'ARMOR': '0.432', 'WEAPON3': '1.200', 'weapon2': '2.306', 'weapon3': '2.810'} [2024-08-01 15:57:39,598][00148] DAMAGECOUNT value on done: 50.0 [2024-08-01 15:57:39,602][00148] Sum rewards: -12.891, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.455', 'FRAGCOUNT': '-2.000', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO2': '0.021', 'HITCOUNT': '0.040', 'AMMO4': '0.104', 'weapon4': '0.134', 'DAMAGECOUNT': '0.150', 'weapon5': '0.186', 'AMMO3': '0.194', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'ARMOR': '0.524', 'WEAPON3': '1.100', 'weapon3': '2.244', 'weapon2': '2.940'} [2024-08-01 15:57:40,260][00138] DAMAGECOUNT value on done: 105.0 [2024-08-01 15:57:40,265][00138] Sum rewards: -3.477, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.866', 'AMMO2': '0.008', 'AMMO5': '0.015', 'weapon5': '0.030', 'AMMO4': '0.038', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.152', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.315', 'ARMOR': '0.463', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.514', 'weapon2': '3.404'} [2024-08-01 15:57:40,302][00143] DAMAGECOUNT value on done: 195.0 [2024-08-01 15:57:40,303][00143] Sum rewards: -6.004, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.285', 'AMMO5': '0.004', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.053', 'weapon5': '0.094', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.146', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.810', 'weapon2': '2.988'} [2024-08-01 15:57:40,997][00143] Large shaping reward -2.558 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('ARMOR', -0.008, -8.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 15:57:41,121][00140] DAMAGECOUNT value on done: 120.0 [2024-08-01 15:57:41,583][00142] DAMAGECOUNT value on done: 85.0 [2024-08-01 15:57:42,451][00133] DAMAGECOUNT value on done: 17.0 [2024-08-01 15:57:42,456][00133] Sum rewards: -7.395, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.430', 'AMMO5': '0.010', 'HITCOUNT': '0.020', 'ARMOR': '0.020', 'AMMO2': '0.040', 'DAMAGECOUNT': '0.051', 'weapon5': '0.110', 'AMMO3': '0.115', 'AMMO4': '0.199', 'WEAPON5': '0.200', 'weapon4': '0.448', 'WEAPON4': '0.500', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '1.974', 'weapon2': '2.998'} [2024-08-01 15:57:42,752][00137] DAMAGECOUNT value on done: 295.0 [2024-08-01 15:57:42,756][00137] Sum rewards: -0.898, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.695', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'AMMO4': '0.026', 'AMMO3': '0.138', 'HITCOUNT': '0.200', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.885', 'FRAGCOUNT': '1.000', 'weapon2': '2.038', 'weapon3': '3.534'} [2024-08-01 15:57:42,834][00132] DAMAGECOUNT value on done: 195.0 [2024-08-01 15:57:42,841][00132] Sum rewards: 1.259, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.612', 'AMMO2': '0.008', 'AMMO4': '0.038', 'AMMO3': '0.111', 'HITCOUNT': '0.180', 'WEAPON4': '0.200', 'weapon4': '0.382', 'ARMOR': '0.543', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.600', 'FRAGCOUNT': '2.000', 'weapon3': '2.584', 'weapon2': '2.640'} [2024-08-01 15:57:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3054.8). Total num frames: 3194880. Throughput: 0: 1512.6. Samples: 1600416. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:57:43,841][00034] Avg episode reward: [(0, '-4.464')] [2024-08-01 15:57:44,348][00146] DAMAGECOUNT value on done: 145.0 [2024-08-01 15:57:44,352][00146] Sum rewards: -4.902, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'weapon4': '0.120', 'HITCOUNT': '0.130', 'AMMO3': '0.136', 'weapon5': '0.196', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.435', 'ARMOR': '0.494', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.160', 'weapon2': '3.032'} [2024-08-01 15:57:44,458][00145] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:57:46,066][00139] DAMAGECOUNT value on done: 179.0 [2024-08-01 15:57:46,128][00134] Updated weights for policy 0, policy_version 781 (0.0024) [2024-08-01 15:57:48,244][00138] DAMAGECOUNT value on done: 155.0 [2024-08-01 15:57:48,245][00138] Sum rewards: -4.859, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.215', 'weapon5': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.019', 'ARMOR': '0.028', 'AMMO4': '0.095', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.194', 'WEAPON4': '0.200', 'weapon4': '0.434', 'DAMAGECOUNT': '0.465', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '2.450', 'weapon2': '2.652'} [2024-08-01 15:57:48,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3140.3, 300 sec: 3054.6). Total num frames: 3211264. Throughput: 0: 1511.2. Samples: 1609644. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:57:48,840][00034] Avg episode reward: [(0, '-4.574')] [2024-08-01 15:57:49,308][00142] DAMAGECOUNT value on done: 5.0 [2024-08-01 15:57:50,328][00133] DAMAGECOUNT value on done: 125.0 [2024-08-01 15:57:50,332][00133] Sum rewards: -8.723, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.185', 'AMMO2': '0.012', 'weapon4': '0.056', 'AMMO4': '0.062', 'HITCOUNT': '0.100', 'AMMO3': '0.186', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.375', 'ARMOR': '0.457', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.626', 'weapon3': '3.038'} [2024-08-01 15:57:50,394][00137] DAMAGECOUNT value on done: 361.0 [2024-08-01 15:57:50,397][00137] Sum rewards: -2.659, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.340', 'AMMO5': '0.007', 'AMMO2': '0.022', 'WEAPON5': '0.100', 'AMMO4': '0.110', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.134', 'weapon5': '0.138', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon7': '0.302', 'FRAGCOUNT': '0.500', 'weapon4': '0.746', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.083', 'weapon2': '1.920', 'weapon3': '2.238'} [2024-08-01 15:57:50,870][00132] DAMAGECOUNT value on done: 40.0 [2024-08-01 15:57:50,871][00132] Sum rewards: 2.750, reward structure: {'DEATHCOUNT': '-3.000', 'HEALTH': '-1.130', 'AMMO2': '0.003', 'AMMO5': '0.005', 'weapon5': '0.008', 'AMMO4': '0.016', 'HITCOUNT': '0.050', 'AMMO3': '0.055', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.120', 'weapon4': '0.196', 'WEAPON3': '0.300', 'ARMOR': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '2.052', 'weapon3': '2.374'} [2024-08-01 15:57:51,864][00146] DAMAGECOUNT value on done: 65.0 [2024-08-01 15:57:52,620][00145] DAMAGECOUNT value on done: 224.0 [2024-08-01 15:57:52,621][00145] Sum rewards: -4.556, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.345', 'AMMO5': '0.005', 'AMMO2': '0.009', 'AMMO4': '0.043', 'weapon5': '0.048', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.198', 'WEAPON4': '0.200', 'ARMOR': '0.477', 'weapon4': '0.610', 'DAMAGECOUNT': '0.672', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '2.048', 'weapon2': '2.750'} [2024-08-01 15:57:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3223552. Throughput: 0: 1524.0. Samples: 1618896. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:57:53,841][00034] Avg episode reward: [(0, '-4.467')] [2024-08-01 15:57:56,212][00138] DAMAGECOUNT value on done: 166.0 [2024-08-01 15:57:56,214][00138] Sum rewards: -2.611, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.305', 'AMMO5': '0.005', 'AMMO2': '0.017', 'ARMOR': '0.044', 'AMMO4': '0.086', 'HITCOUNT': '0.120', 'AMMO3': '0.192', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.498', 'weapon4': '0.826', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.068', 'weapon3': '2.688'} [2024-08-01 15:57:56,992][00142] DAMAGECOUNT value on done: 238.0 [2024-08-01 15:57:56,997][00142] Sum rewards: -2.530, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.868', 'ARMOR': '0.004', 'AMMO5': '0.010', 'AMMO2': '0.020', 'AMMO4': '0.099', 'HITCOUNT': '0.140', 'AMMO3': '0.157', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon5': '0.404', 'weapon4': '0.584', 'DAMAGECOUNT': '0.714', 'WEAPON3': '0.900', 'weapon3': '2.176', 'weapon2': '2.380', 'FRAGCOUNT': '3.000'} [2024-08-01 15:57:57,883][00134] Updated weights for policy 0, policy_version 791 (0.0020) [2024-08-01 15:57:58,041][00133] DAMAGECOUNT value on done: 256.0 [2024-08-01 15:57:58,042][00133] Sum rewards: -5.459, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.355', 'AMMO2': '0.009', 'weapon4': '0.020', 'AMMO5': '0.028', 'AMMO4': '0.043', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.179', 'weapon5': '0.438', 'WEAPON5': '0.600', 'DAMAGECOUNT': '0.768', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '1.940', 'weapon2': '3.340'} [2024-08-01 15:57:58,143][00137] DAMAGECOUNT value on done: 95.0 [2024-08-01 15:57:58,147][00137] Sum rewards: -0.118, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.362', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'AMMO2': '0.021', 'ARMOR': '0.072', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO4': '0.103', 'weapon5': '0.104', 'AMMO3': '0.112', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.285', 'weapon4': '0.434', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.246', 'weapon3': '2.752'} [2024-08-01 15:57:58,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3072.1, 300 sec: 3068.5). Total num frames: 3239936. Throughput: 0: 1527.5. Samples: 1623612. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:57:58,841][00034] Avg episode reward: [(0, '-4.375')] [2024-08-01 15:57:59,535][00146] DAMAGECOUNT value on done: 316.0 [2024-08-01 15:57:59,536][00146] Sum rewards: 0.011, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'AMMO5': '0.005', 'AMMO2': '0.007', 'ARMOR': '0.024', 'AMMO4': '0.035', 'weapon5': '0.046', 'WEAPON5': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.135', 'HITCOUNT': '0.170', 'weapon7': '0.172', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.558', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.948', 'FRAGCOUNT': '1.000', 'weapon3': '2.304', 'weapon2': '2.496'} [2024-08-01 15:58:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3054.7). Total num frames: 3256320. Throughput: 0: 1537.1. Samples: 1633272. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:58:03,843][00034] Avg episode reward: [(0, '-4.317')] [2024-08-01 15:58:04,511][00142] DAMAGECOUNT value on done: 144.0 [2024-08-01 15:58:04,516][00142] Sum rewards: -12.981, reward structure: {'DEATHCOUNT': '-15.750', 'HEALTH': '-6.280', 'AMMO5': '0.003', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'AMMO2': '0.020', 'AMMO4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.162', 'weapon5': '0.198', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.432', 'WEAPON3': '0.700', 'weapon4': '0.762', 'FRAGCOUNT': '1.000', 'weapon3': '1.508', 'weapon2': '3.572'} [2024-08-01 15:58:05,885][00137] DAMAGECOUNT value on done: 136.0 [2024-08-01 15:58:05,888][00137] Sum rewards: -7.319, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.825', 'AMMO2': '0.007', 'WEAPON1': '0.020', 'AMMO4': '0.034', 'HITCOUNT': '0.140', 'AMMO3': '0.168', 'WEAPON4': '0.200', 'weapon4': '0.264', 'DAMAGECOUNT': '0.408', 'ARMOR': '0.457', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.808', 'weapon2': '3.000'} [2024-08-01 15:58:05,946][00133] DAMAGECOUNT value on done: 35.0 [2024-08-01 15:58:05,948][00133] Sum rewards: -6.707, reward structure: {'DEATHCOUNT': '-7.500', 'FRAGCOUNT': '-3.000', 'HEALTH': '-2.970', 'AMMO5': '0.007', 'AMMO2': '0.010', 'HITCOUNT': '0.040', 'AMMO4': '0.047', 'AMMO3': '0.094', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.105', 'weapon4': '0.184', 'WEAPON5': '0.200', 'weapon5': '0.318', 'WEAPON3': '0.600', 'weapon3': '1.970', 'weapon2': '3.088'} [2024-08-01 15:58:07,682][00146] DAMAGECOUNT value on done: 20.0 [2024-08-01 15:58:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3268608. Throughput: 0: 1540.8. Samples: 1642488. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:58:08,840][00034] Avg episode reward: [(0, '-4.402')] [2024-08-01 15:58:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000798_3268608.pth... [2024-08-01 15:58:09,014][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000620_2539520.pth [2024-08-01 15:58:11,775][00134] Updated weights for policy 0, policy_version 801 (0.0021) [2024-08-01 15:58:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3284992. Throughput: 0: 1538.1. Samples: 1646976. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 15:58:13,842][00034] Avg episode reward: [(0, '-4.402')] [2024-08-01 15:58:14,317][00142] DAMAGECOUNT value on done: 137.0 [2024-08-01 15:58:14,322][00142] Sum rewards: -3.863, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'HITCOUNT': '0.110', 'AMMO3': '0.179', 'DAMAGECOUNT': '0.411', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.292', 'weapon3': '3.584'} [2024-08-01 15:58:16,028][00137] DAMAGECOUNT value on done: 114.0 [2024-08-01 15:58:16,153][00133] DAMAGECOUNT value on done: 95.0 [2024-08-01 15:58:16,154][00133] Sum rewards: -3.702, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.043', 'AMMO2': '-0.009', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'HITCOUNT': '0.050', 'ARMOR': '0.058', 'WEAPON5': '0.100', 'AMMO3': '0.115', 'weapon5': '0.186', 'DAMAGECOUNT': '0.285', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.498', 'weapon2': '2.838'} [2024-08-01 15:58:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3040.8). Total num frames: 3297280. Throughput: 0: 1521.3. Samples: 1655640. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:58:18,840][00034] Avg episode reward: [(0, '-4.411')] [2024-08-01 15:58:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3054.6). Total num frames: 3317760. Throughput: 0: 1517.3. Samples: 1664796. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 15:58:23,841][00034] Avg episode reward: [(0, '-4.411')] [2024-08-01 15:58:24,499][00133] DAMAGECOUNT value on done: 51.0 [2024-08-01 15:58:25,498][00134] Updated weights for policy 0, policy_version 811 (0.0020) [2024-08-01 15:58:28,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3330048. Throughput: 0: 1534.4. Samples: 1669464. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:58:28,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3346432. Throughput: 0: 1538.7. Samples: 1678884. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:58:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:38,839][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3358720. Throughput: 0: 1537.3. Samples: 1688076. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:58:38,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:39,009][00134] Updated weights for policy 0, policy_version 821 (0.0020) [2024-08-01 15:58:43,842][00034] Fps is (10 sec: 3275.6, 60 sec: 3071.8, 300 sec: 3068.5). Total num frames: 3379200. Throughput: 0: 1534.5. Samples: 1692672. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 15:58:43,846][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:45,581][00145] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:58:48,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3391488. Throughput: 0: 1505.6. Samples: 1701024. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:58:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:52,917][00134] Updated weights for policy 0, policy_version 831 (0.0020) [2024-08-01 15:58:53,838][00034] Fps is (10 sec: 2868.2, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3407872. Throughput: 0: 1504.0. Samples: 1710168. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 15:58:53,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:58:58,242][00142] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:58:58,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3420160. Throughput: 0: 1509.3. Samples: 1714896. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 15:58:58,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:03,759][00143] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:59:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3436544. Throughput: 0: 1521.9. Samples: 1724124. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 15:59:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:05,631][00134] Updated weights for policy 0, policy_version 841 (0.0020) [2024-08-01 15:59:08,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3452928. Throughput: 0: 1522.9. Samples: 1733328. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 15:59:08,844][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:13,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3469312. Throughput: 0: 1522.4. Samples: 1737972. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:59:13,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 3481600. Throughput: 0: 1505.1. Samples: 1746612. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 15:59:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:20,259][00134] Updated weights for policy 0, policy_version 851 (0.0039) [2024-08-01 15:59:23,640][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 15:59:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 3497984. Throughput: 0: 1501.3. Samples: 1755636. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 15:59:23,846][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:28,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.8, 300 sec: 3026.9). Total num frames: 3510272. Throughput: 0: 1507.3. Samples: 1760496. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 15:59:28,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:32,679][00134] Updated weights for policy 0, policy_version 861 (0.0035) [2024-08-01 15:59:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3530752. Throughput: 0: 1526.1. Samples: 1769700. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:59:33,844][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:38,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3543040. Throughput: 0: 1526.1. Samples: 1778844. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 15:59:38,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.6, 300 sec: 3026.9). Total num frames: 3555328. Throughput: 0: 1523.0. Samples: 1783428. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 15:59:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:46,399][00134] Updated weights for policy 0, policy_version 871 (0.0022) [2024-08-01 15:59:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3575808. Throughput: 0: 1523.5. Samples: 1792680. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:59:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:53,841][00034] Fps is (10 sec: 3275.9, 60 sec: 3003.6, 300 sec: 3040.7). Total num frames: 3588096. Throughput: 0: 1511.1. Samples: 1801332. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 15:59:53,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 15:59:58,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3604480. Throughput: 0: 1510.4. Samples: 1805940. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 15:59:58,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:01,177][00134] Updated weights for policy 0, policy_version 881 (0.0021) [2024-08-01 16:00:03,839][00034] Fps is (10 sec: 3277.5, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3620864. Throughput: 0: 1520.5. Samples: 1815036. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:00:03,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:05,743][00137] Large shaping reward -2.536 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:00:08,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3633152. Throughput: 0: 1526.4. Samples: 1824324. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:00:08,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:08,851][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000887_3633152.pth... [2024-08-01 16:00:09,030][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000709_2904064.pth [2024-08-01 16:00:12,423][00134] Updated weights for policy 0, policy_version 891 (0.0021) [2024-08-01 16:00:13,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3649536. Throughput: 0: 1518.4. Samples: 1828824. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:00:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3665920. Throughput: 0: 1518.1. Samples: 1838016. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:00:18,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 3678208. Throughput: 0: 1505.3. Samples: 1846584. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:00:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:26,511][00134] Updated weights for policy 0, policy_version 901 (0.0020) [2024-08-01 16:00:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3054.7). Total num frames: 3694592. Throughput: 0: 1505.3. Samples: 1851168. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:00:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:33,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3710976. Throughput: 0: 1506.4. Samples: 1860468. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:00:33,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:38,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3723264. Throughput: 0: 1515.3. Samples: 1869516. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:00:38,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:40,869][00134] Updated weights for policy 0, policy_version 911 (0.0020) [2024-08-01 16:00:43,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3739648. Throughput: 0: 1515.0. Samples: 1874112. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:00:43,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:48,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 3751936. Throughput: 0: 1517.9. Samples: 1883340. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:00:48,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:53,015][00134] Updated weights for policy 0, policy_version 921 (0.0020) [2024-08-01 16:00:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.1, 300 sec: 3040.8). Total num frames: 3772416. Throughput: 0: 1508.8. Samples: 1892220. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:00:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:00:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.8, 300 sec: 3040.8). Total num frames: 3784704. Throughput: 0: 1502.1. Samples: 1896420. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:00:58,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:01,798][00146] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:01:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 3796992. Throughput: 0: 1504.8. Samples: 1905732. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:01:03,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:07,750][00134] Updated weights for policy 0, policy_version 931 (0.0020) [2024-08-01 16:01:08,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 3813376. Throughput: 0: 1518.1. Samples: 1914900. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:01:08,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:13,839][00034] Fps is (10 sec: 3686.3, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3833856. Throughput: 0: 1519.7. Samples: 1919556. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:01:13,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:18,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3846144. Throughput: 0: 1519.8. Samples: 1928856. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:01:18,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:21,239][00134] Updated weights for policy 0, policy_version 941 (0.0020) [2024-08-01 16:01:23,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3862528. Throughput: 0: 1520.3. Samples: 1937928. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:01:23,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3874816. Throughput: 0: 1509.6. Samples: 1942044. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:01:28,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 3887104. Throughput: 0: 1504.3. Samples: 1951032. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:01:33,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:34,965][00134] Updated weights for policy 0, policy_version 951 (0.0030) [2024-08-01 16:01:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3907584. Throughput: 0: 1512.0. Samples: 1960260. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:01:38,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:43,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 3923968. Throughput: 0: 1524.5. Samples: 1965024. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:01:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:47,712][00134] Updated weights for policy 0, policy_version 961 (0.0020) [2024-08-01 16:01:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 3936256. Throughput: 0: 1519.2. Samples: 1974096. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:01:48,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 3952640. Throughput: 0: 1519.2. Samples: 1983264. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:01:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:01:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 3964928. Throughput: 0: 1519.7. Samples: 1987944. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:01:58,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:02,535][00134] Updated weights for policy 0, policy_version 971 (0.0021) [2024-08-01 16:02:03,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3140.3, 300 sec: 3040.8). Total num frames: 3985408. Throughput: 0: 1502.9. Samples: 1996488. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:02:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 3997696. Throughput: 0: 1506.7. Samples: 2005728. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:02:08,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:08,853][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000976_3997696.pth... [2024-08-01 16:02:09,015][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000798_3268608.pth [2024-08-01 16:02:13,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 4009984. Throughput: 0: 1518.7. Samples: 2010384. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 16:02:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:15,155][00134] Updated weights for policy 0, policy_version 981 (0.0019) [2024-08-01 16:02:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 4026368. Throughput: 0: 1520.0. Samples: 2019432. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:02:18,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:23,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 4046848. Throughput: 0: 1515.2. Samples: 2028444. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:02:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:28,792][00134] Updated weights for policy 0, policy_version 991 (0.0021) [2024-08-01 16:02:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4059136. Throughput: 0: 1513.1. Samples: 2033112. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:02:28,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:33,839][00034] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4071424. Throughput: 0: 1501.1. Samples: 2041644. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:02:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:38,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 4091904. Throughput: 0: 1503.4. Samples: 2050920. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:02:38,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:41,783][00134] Updated weights for policy 0, policy_version 1001 (0.0020) [2024-08-01 16:02:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 4100096. Throughput: 0: 1501.1. Samples: 2055492. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:02:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:48,838][00034] Fps is (10 sec: 2457.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4116480. Throughput: 0: 1510.1. Samples: 2064444. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 16:02:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 4128768. Throughput: 0: 1509.1. Samples: 2073636. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:02:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:02:54,885][00134] Updated weights for policy 0, policy_version 1011 (0.0020) [2024-08-01 16:02:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4149248. Throughput: 0: 1507.5. Samples: 2078220. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:02:58,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:03,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 4165632. Throughput: 0: 1509.1. Samples: 2087340. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 16:03:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4177920. Throughput: 0: 1501.1. Samples: 2095992. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:03:08,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:09,815][00134] Updated weights for policy 0, policy_version 1021 (0.0020) [2024-08-01 16:03:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 4194304. Throughput: 0: 1499.2. Samples: 2100576. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:03:13,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4206592. Throughput: 0: 1512.5. Samples: 2109708. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:03:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:23,045][00134] Updated weights for policy 0, policy_version 1031 (0.0020) [2024-08-01 16:03:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 4227072. Throughput: 0: 1509.4. Samples: 2118840. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:03:23,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:28,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4239360. Throughput: 0: 1512.3. Samples: 2123544. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:03:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 4255744. Throughput: 0: 1521.3. Samples: 2132904. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:03:33,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:35,812][00134] Updated weights for policy 0, policy_version 1041 (0.0020) [2024-08-01 16:03:38,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2867.2, 300 sec: 2999.1). Total num frames: 4263936. Throughput: 0: 1505.6. Samples: 2141388. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:03:38,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4284416. Throughput: 0: 1504.3. Samples: 2145912. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:03:43,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:48,842][00034] Fps is (10 sec: 3685.2, 60 sec: 3071.8, 300 sec: 3026.8). Total num frames: 4300800. Throughput: 0: 1504.1. Samples: 2155032. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:03:48,845][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:50,584][00134] Updated weights for policy 0, policy_version 1051 (0.0020) [2024-08-01 16:03:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4313088. Throughput: 0: 1516.0. Samples: 2164212. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:03:53,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:03:58,838][00034] Fps is (10 sec: 2868.3, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4329472. Throughput: 0: 1516.8. Samples: 2168832. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:03:58,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:03,606][00134] Updated weights for policy 0, policy_version 1061 (0.0019) [2024-08-01 16:04:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4345856. Throughput: 0: 1520.8. Samples: 2178144. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:04:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 4362240. Throughput: 0: 1509.6. Samples: 2186772. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:04:08,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001065_4362240.pth... [2024-08-01 16:04:09,058][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000887_3633152.pth [2024-08-01 16:04:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4374528. Throughput: 0: 1502.1. Samples: 2191140. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:04:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:14,576][00137] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:04:15,656][00146] Large shaping reward -2.548 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('weapon5', 0.002)] [2024-08-01 16:04:16,891][00134] Updated weights for policy 0, policy_version 1071 (0.0020) [2024-08-01 16:04:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4386816. Throughput: 0: 1496.0. Samples: 2200224. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:04:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:23,245][00133] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:04:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 4403200. Throughput: 0: 1509.4. Samples: 2209308. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:04:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4419584. Throughput: 0: 1513.9. Samples: 2214036. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:04:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:30,805][00134] Updated weights for policy 0, policy_version 1081 (0.0020) [2024-08-01 16:04:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4435968. Throughput: 0: 1514.0. Samples: 2223156. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:04:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:35,842][00148] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:04:37,582][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:04:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3040.8). Total num frames: 4452352. Throughput: 0: 1511.5. Samples: 2232228. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:04:38,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:43,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4464640. Throughput: 0: 1496.2. Samples: 2236164. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:04:43,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:44,532][00134] Updated weights for policy 0, policy_version 1091 (0.0031) [2024-08-01 16:04:48,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.7, 300 sec: 3013.0). Total num frames: 4476928. Throughput: 0: 1489.1. Samples: 2245152. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:04:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:53,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4493312. Throughput: 0: 1502.4. Samples: 2254380. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:04:53,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:04:55,756][00139] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:04:57,773][00134] Updated weights for policy 0, policy_version 1101 (0.0030) [2024-08-01 16:04:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4509696. Throughput: 0: 1508.8. Samples: 2259036. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:04:58,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4526080. Throughput: 0: 1508.5. Samples: 2268108. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:05:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:07,785][00145] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:05:08,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4542464. Throughput: 0: 1506.9. Samples: 2277120. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:05:08,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:11,458][00134] Updated weights for policy 0, policy_version 1111 (0.0022) [2024-08-01 16:05:13,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 4550656. Throughput: 0: 1503.2. Samples: 2281680. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:05:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:18,838][00034] Fps is (10 sec: 2457.7, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4567040. Throughput: 0: 1486.9. Samples: 2290068. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:05:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:23,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4583424. Throughput: 0: 1490.4. Samples: 2299296. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:05:23,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:25,560][00134] Updated weights for policy 0, policy_version 1121 (0.0020) [2024-08-01 16:05:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 4595712. Throughput: 0: 1503.2. Samples: 2303808. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:05:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:33,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4616192. Throughput: 0: 1506.7. Samples: 2312952. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:05:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:38,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 4628480. Throughput: 0: 1502.9. Samples: 2322012. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:05:38,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:39,306][00134] Updated weights for policy 0, policy_version 1131 (0.0020) [2024-08-01 16:05:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3026.9). Total num frames: 4644864. Throughput: 0: 1501.3. Samples: 2326596. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 16:05:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:48,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4657152. Throughput: 0: 1486.1. Samples: 2334984. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:05:48,847][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:53,513][00134] Updated weights for policy 0, policy_version 1141 (0.0032) [2024-08-01 16:05:53,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4673536. Throughput: 0: 1488.0. Samples: 2344080. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:05:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:05:58,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 4689920. Throughput: 0: 1488.0. Samples: 2348640. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:05:58,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:03,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2867.2, 300 sec: 2999.1). Total num frames: 4698112. Throughput: 0: 1504.3. Samples: 2357760. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:06:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:06,326][00134] Updated weights for policy 0, policy_version 1151 (0.0020) [2024-08-01 16:06:08,690][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:06:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.8, 300 sec: 3013.0). Total num frames: 4722688. Throughput: 0: 1497.1. Samples: 2366664. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:06:08,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001153_4722688.pth... [2024-08-01 16:06:09,017][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000976_3997696.pth [2024-08-01 16:06:13,839][00034] Fps is (10 sec: 3686.1, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 4734976. Throughput: 0: 1498.4. Samples: 2371236. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 16:06:13,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4747264. Throughput: 0: 1495.7. Samples: 2380260. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:06:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:21,115][00134] Updated weights for policy 0, policy_version 1161 (0.0022) [2024-08-01 16:06:23,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.8, 300 sec: 3013.0). Total num frames: 4763648. Throughput: 0: 1485.6. Samples: 2388864. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 16:06:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:27,759][00145] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:06:28,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4775936. Throughput: 0: 1485.6. Samples: 2393448. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:06:28,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:33,165][00134] Updated weights for policy 0, policy_version 1171 (0.0020) [2024-08-01 16:06:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4796416. Throughput: 0: 1504.5. Samples: 2402688. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:06:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:38,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4808704. Throughput: 0: 1505.1. Samples: 2411808. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:06:38,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 4820992. Throughput: 0: 1506.4. Samples: 2416428. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:06:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:45,281][00141] Large shaping reward -2.538 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28800000000000003, -96.0), ('ARMOR', -0.001, -1.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:06:47,093][00134] Updated weights for policy 0, policy_version 1181 (0.0020) [2024-08-01 16:06:48,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 4841472. Throughput: 0: 1508.5. Samples: 2425644. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:06:48,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4853760. Throughput: 0: 1496.5. Samples: 2434008. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:06:53,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:06:58,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4870144. Throughput: 0: 1497.9. Samples: 2438640. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:06:58,844][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:01,214][00134] Updated weights for policy 0, policy_version 1191 (0.0020) [2024-08-01 16:07:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 4886528. Throughput: 0: 1500.5. Samples: 2447784. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:07:03,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:08,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2999.1). Total num frames: 4894720. Throughput: 0: 1512.5. Samples: 2456928. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:07:08,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:13,338][00147] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:07:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3013.0). Total num frames: 4915200. Throughput: 0: 1517.1. Samples: 2461716. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:07:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:13,874][00134] Updated weights for policy 0, policy_version 1201 (0.0023) [2024-08-01 16:07:18,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 2999.1). Total num frames: 4931584. Throughput: 0: 1513.3. Samples: 2470788. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:07:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4943872. Throughput: 0: 1499.5. Samples: 2479284. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:07:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:28,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.8, 300 sec: 2999.1). Total num frames: 4956160. Throughput: 0: 1496.8. Samples: 2483784. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:07:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:29,408][00134] Updated weights for policy 0, policy_version 1211 (0.0020) [2024-08-01 16:07:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 4976640. Throughput: 0: 1496.8. Samples: 2493000. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:07:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:38,622][00132] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:07:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 4988928. Throughput: 0: 1516.5. Samples: 2502252. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:07:38,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:41,235][00134] Updated weights for policy 0, policy_version 1221 (0.0026) [2024-08-01 16:07:43,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5005312. Throughput: 0: 1515.7. Samples: 2506848. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:07:43,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5021696. Throughput: 0: 1513.6. Samples: 2515896. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:07:48,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:53,785][00146] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:07:53,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5033984. Throughput: 0: 1514.1. Samples: 2525064. Policy #0 lag: (min: 0.0, avg: 3.0, max: 8.0) [2024-08-01 16:07:53,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:07:55,379][00134] Updated weights for policy 0, policy_version 1231 (0.0020) [2024-08-01 16:07:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5050368. Throughput: 0: 1492.5. Samples: 2528880. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:07:58,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5066752. Throughput: 0: 1494.1. Samples: 2538024. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:08:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:06,670][00144] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:08:08,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2999.1). Total num frames: 5079040. Throughput: 0: 1510.7. Samples: 2547264. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:08:08,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001240_5079040.pth... [2024-08-01 16:08:09,030][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001065_4362240.pth [2024-08-01 16:08:09,428][00134] Updated weights for policy 0, policy_version 1241 (0.0020) [2024-08-01 16:08:13,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2935.4, 300 sec: 2999.1). Total num frames: 5091328. Throughput: 0: 1510.9. Samples: 2551776. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:08:13,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5111808. Throughput: 0: 1510.7. Samples: 2560980. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:08:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:22,768][00134] Updated weights for policy 0, policy_version 1251 (0.0020) [2024-08-01 16:08:23,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5124096. Throughput: 0: 1506.1. Samples: 2570028. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:08:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:28,839][00034] Fps is (10 sec: 2866.9, 60 sec: 3072.0, 300 sec: 2999.1). Total num frames: 5140480. Throughput: 0: 1504.0. Samples: 2574528. Policy #0 lag: (min: 1.0, avg: 3.0, max: 7.0) [2024-08-01 16:08:28,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:33,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5156864. Throughput: 0: 1498.9. Samples: 2583348. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:08:33,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:35,536][00134] Updated weights for policy 0, policy_version 1261 (0.0023) [2024-08-01 16:08:38,838][00034] Fps is (10 sec: 2867.5, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5169152. Throughput: 0: 1498.9. Samples: 2592516. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:08:38,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:43,838][00034] Fps is (10 sec: 2867.5, 60 sec: 3003.8, 300 sec: 2999.1). Total num frames: 5185536. Throughput: 0: 1519.5. Samples: 2597256. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:08:43,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:47,898][00142] Large shaping reward -2.502 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.252, -84.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:08:48,790][00134] Updated weights for policy 0, policy_version 1271 (0.0020) [2024-08-01 16:08:48,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 5206016. Throughput: 0: 1525.1. Samples: 2606652. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:08:48,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:49,399][00135] Large shaping reward -2.550 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:08:52,746][00136] Large shaping reward -2.550 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:08:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5218304. Throughput: 0: 1527.7. Samples: 2616012. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:08:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:08:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5234688. Throughput: 0: 1531.7. Samples: 2620704. Policy #0 lag: (min: 0.0, avg: 3.4, max: 9.0) [2024-08-01 16:08:58,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:03,120][00134] Updated weights for policy 0, policy_version 1281 (0.0021) [2024-08-01 16:09:03,839][00034] Fps is (10 sec: 2866.9, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5246976. Throughput: 0: 1525.3. Samples: 2629620. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:09:03,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:06,958][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:09:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5263360. Throughput: 0: 1536.0. Samples: 2639148. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:09:08,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:12,154][00138] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:09:13,838][00034] Fps is (10 sec: 3686.8, 60 sec: 3208.6, 300 sec: 3040.8). Total num frames: 5283840. Throughput: 0: 1542.2. Samples: 2643924. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:09:13,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:16,030][00134] Updated weights for policy 0, policy_version 1291 (0.0030) [2024-08-01 16:09:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5292032. Throughput: 0: 1553.4. Samples: 2653248. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:09:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3026.9). Total num frames: 5312512. Throughput: 0: 1558.4. Samples: 2662644. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:09:23,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:28,693][00134] Updated weights for policy 0, policy_version 1301 (0.0028) [2024-08-01 16:09:28,839][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3026.9). Total num frames: 5328896. Throughput: 0: 1558.1. Samples: 2667372. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:09:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:33,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5341184. Throughput: 0: 1539.4. Samples: 2675928. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:09:33,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:35,947][00135] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:09:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3026.9). Total num frames: 5357568. Throughput: 0: 1528.3. Samples: 2684784. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:09:38,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:43,623][00134] Updated weights for policy 0, policy_version 1311 (0.0024) [2024-08-01 16:09:43,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 5369856. Throughput: 0: 1526.4. Samples: 2689392. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:09:43,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:48,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5386240. Throughput: 0: 1525.6. Samples: 2698272. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:09:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5398528. Throughput: 0: 1518.4. Samples: 2707476. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:09:53,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:09:55,129][00134] Updated weights for policy 0, policy_version 1321 (0.0020) [2024-08-01 16:09:58,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5414912. Throughput: 0: 1513.3. Samples: 2712024. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 16:09:58,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:03,850][00034] Fps is (10 sec: 3682.0, 60 sec: 3139.7, 300 sec: 3026.8). Total num frames: 5435392. Throughput: 0: 1508.9. Samples: 2721168. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 16:10:03,853][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:08,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5443584. Throughput: 0: 1486.9. Samples: 2729556. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:10:08,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001329_5443584.pth... [2024-08-01 16:10:09,016][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001153_4722688.pth [2024-08-01 16:10:10,767][00134] Updated weights for policy 0, policy_version 1331 (0.0027) [2024-08-01 16:10:13,838][00034] Fps is (10 sec: 2460.5, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 5459968. Throughput: 0: 1481.6. Samples: 2734044. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:10:13,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:18,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 5476352. Throughput: 0: 1493.6. Samples: 2743140. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:10:18,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:23,273][00134] Updated weights for policy 0, policy_version 1341 (0.0020) [2024-08-01 16:10:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 5492736. Throughput: 0: 1498.7. Samples: 2752224. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:10:23,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5505024. Throughput: 0: 1497.3. Samples: 2756772. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:10:28,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3026.9). Total num frames: 5521408. Throughput: 0: 1505.4. Samples: 2766012. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:10:33,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:38,618][00134] Updated weights for policy 0, policy_version 1351 (0.0020) [2024-08-01 16:10:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5533696. Throughput: 0: 1483.2. Samples: 2774220. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:10:38,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5550080. Throughput: 0: 1482.4. Samples: 2778732. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:10:43,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:48,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5562368. Throughput: 0: 1483.0. Samples: 2787888. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 16:10:48,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:50,612][00134] Updated weights for policy 0, policy_version 1361 (0.0020) [2024-08-01 16:10:53,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5578752. Throughput: 0: 1496.8. Samples: 2796912. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:10:53,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:10:58,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 5595136. Throughput: 0: 1498.7. Samples: 2801484. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:10:58,844][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:03,839][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.8, 300 sec: 2999.1). Total num frames: 5607424. Throughput: 0: 1500.3. Samples: 2810652. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:11:03,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:05,269][00134] Updated weights for policy 0, policy_version 1371 (0.0020) [2024-08-01 16:11:08,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 5627904. Throughput: 0: 1491.7. Samples: 2819352. Policy #0 lag: (min: 0.0, avg: 3.8, max: 8.0) [2024-08-01 16:11:08,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:09,762][00141] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:11:13,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5636096. Throughput: 0: 1480.8. Samples: 2823408. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:11:13,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:18,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5656576. Throughput: 0: 1481.1. Samples: 2832660. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:11:18,842][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:18,864][00134] Updated weights for policy 0, policy_version 1381 (0.0020) [2024-08-01 16:11:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 5668864. Throughput: 0: 1499.2. Samples: 2841684. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:11:23,841][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:26,840][00133] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:11:28,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 5681152. Throughput: 0: 1502.4. Samples: 2846340. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:11:28,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:32,608][00134] Updated weights for policy 0, policy_version 1391 (0.0031) [2024-08-01 16:11:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5701632. Throughput: 0: 1502.4. Samples: 2855496. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:11:33,843][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:38,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5713920. Throughput: 0: 1505.9. Samples: 2864676. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:11:38,840][00034] Avg episode reward: [(0, '-4.385')] [2024-08-01 16:11:39,332][00147] DAMAGECOUNT value on done: 243.0 [2024-08-01 16:11:39,340][00147] Sum rewards: -4.656, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.702', 'AMMO5': '0.005', 'AMMO2': '0.020', 'ARMOR': '0.072', 'WEAPON5': '0.100', 'AMMO4': '0.100', 'AMMO3': '0.170', 'HITCOUNT': '0.230', 'WEAPON4': '0.500', 'DAMAGECOUNT': '0.684', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.386', 'weapon2': '2.746', 'weapon3': '3.482'} [2024-08-01 16:11:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 5726208. Throughput: 0: 1496.8. Samples: 2868840. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:11:43,840][00034] Avg episode reward: [(0, '-4.392')] [2024-08-01 16:11:46,892][00134] Updated weights for policy 0, policy_version 1401 (0.0023) [2024-08-01 16:11:48,273][00147] DAMAGECOUNT value on done: 299.0 [2024-08-01 16:11:48,278][00147] Sum rewards: -3.395, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.593', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.013', 'AMMO2': '0.017', 'AMMO4': '0.086', 'WEAPON4': '0.100', 'weapon5': '0.146', 'AMMO3': '0.165', 'weapon4': '0.168', 'HITCOUNT': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.810', 'WEAPON3': '0.900', 'weapon2': '2.612', 'weapon3': '4.180'} [2024-08-01 16:11:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 5746688. Throughput: 0: 1489.9. Samples: 2877696. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:11:48,840][00034] Avg episode reward: [(0, '-4.367')] [2024-08-01 16:11:53,013][00144] DAMAGECOUNT value on done: 180.0 [2024-08-01 16:11:53,016][00144] Sum rewards: 3.713, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.935', 'AMMO2': '0.002', 'AMMO4': '0.009', 'ARMOR': '0.105', 'AMMO3': '0.120', 'HITCOUNT': '0.140', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.480', 'weapon4': '0.552', 'WEAPON3': '0.900', 'weapon2': '2.834', 'FRAGCOUNT': '4.000', 'weapon3': '4.056'} [2024-08-01 16:11:53,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 5754880. Throughput: 0: 1496.5. Samples: 2886696. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:11:53,842][00034] Avg episode reward: [(0, '-4.243')] [2024-08-01 16:11:56,093][00147] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:11:56,096][00147] Sum rewards: -8.886, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.920', 'FRAGCOUNT': '-2.000', 'AMMO2': '0.006', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.031', 'ARMOR': '0.064', 'HITCOUNT': '0.100', 'WEAPON4': '0.200', 'weapon5': '0.200', 'AMMO3': '0.206', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.360', 'weapon4': '0.988', 'WEAPON3': '1.300', 'weapon2': '2.596', 'weapon3': '3.650'} [2024-08-01 16:11:58,623][00141] DAMAGECOUNT value on done: 171.0 [2024-08-01 16:11:58,627][00141] Sum rewards: 2.595, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.618', 'AMMO5': '0.009', 'AMMO2': '0.017', 'ARMOR': '0.044', 'AMMO3': '0.073', 'weapon5': '0.082', 'AMMO4': '0.084', 'AMMO6': '0.120', 'AMMO7': '0.120', 'HITCOUNT': '0.130', 'weapon7': '0.132', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.405', 'WEAPON4': '0.500', 'WEAPON3': '0.500', 'weapon4': '1.750', 'weapon3': '1.962', 'FRAGCOUNT': '2.000', 'weapon2': '2.884'} [2024-08-01 16:11:58,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5775360. Throughput: 0: 1507.7. Samples: 2891256. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:11:58,841][00034] Avg episode reward: [(0, '-4.176')] [2024-08-01 16:11:59,976][00134] Updated weights for policy 0, policy_version 1411 (0.0020) [2024-08-01 16:12:02,021][00144] DAMAGECOUNT value on done: 190.0 [2024-08-01 16:12:02,024][00144] Sum rewards: 0.870, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.770', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'ARMOR': '0.044', 'HITCOUNT': '0.110', 'AMMO3': '0.139', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.768', 'weapon3': '4.046'} [2024-08-01 16:12:03,101][00136] DAMAGECOUNT value on done: 130.0 [2024-08-01 16:12:03,102][00136] Sum rewards: -4.781, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.500', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.096', 'AMMO2': '-0.019', 'WEAPON1': '0.020', 'AMMO5': '0.026', 'AMMO3': '0.084', 'HITCOUNT': '0.110', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.152', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.285', 'weapon5': '0.302', 'WEAPON5': '0.500', 'WEAPON3': '0.600', 'weapon3': '2.622', 'weapon2': '4.192'} [2024-08-01 16:12:03,669][00147] DAMAGECOUNT value on done: 428.0 [2024-08-01 16:12:03,675][00147] Sum rewards: -0.147, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.200', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'WEAPON1': '0.020', 'AMMO5': '0.021', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.126', 'weapon4': '0.164', 'HITCOUNT': '0.210', 'weapon5': '0.312', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.699', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.304', 'weapon3': '4.272'} [2024-08-01 16:12:03,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.8, 300 sec: 3026.9). Total num frames: 5787648. Throughput: 0: 1506.4. Samples: 2900448. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:12:03,841][00034] Avg episode reward: [(0, '-4.155')] [2024-08-01 16:12:04,838][00148] DAMAGECOUNT value on done: 45.0 [2024-08-01 16:12:04,840][00148] Sum rewards: -7.545, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'FRAGCOUNT': '-1.500', 'HITCOUNT': '0.020', 'WEAPON1': '0.020', 'AMMO2': '0.022', 'AMMO5': '0.027', 'DAMAGECOUNT': '0.060', 'AMMO4': '0.107', 'AMMO3': '0.119', 'weapon5': '0.210', 'weapon4': '0.232', 'WEAPON4': '0.400', 'WEAPON5': '0.400', 'WEAPON3': '0.700', 'ARMOR': '0.914', 'weapon3': '2.890', 'weapon2': '3.564'} [2024-08-01 16:12:05,344][00141] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:12:05,529][00135] DAMAGECOUNT value on done: 155.0 [2024-08-01 16:12:05,529][00135] Sum rewards: -0.234, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.045', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.014', 'ARMOR': '0.024', 'AMMO3': '0.079', 'HITCOUNT': '0.110', 'weapon5': '0.190', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.300', 'WEAPON5': '0.300', 'WEAPON3': '0.600', 'weapon4': '0.928', 'FRAGCOUNT': '2.000', 'weapon2': '2.512', 'weapon3': '3.066'} [2024-08-01 16:12:06,335][00141] DAMAGECOUNT value on done: 65.0 [2024-08-01 16:12:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5804032. Throughput: 0: 1509.1. Samples: 2909592. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:12:08,840][00034] Avg episode reward: [(0, '-4.131')] [2024-08-01 16:12:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001417_5804032.pth... [2024-08-01 16:12:09,017][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001240_5079040.pth [2024-08-01 16:12:10,340][00144] DAMAGECOUNT value on done: 393.0 [2024-08-01 16:12:10,344][00144] Sum rewards: -3.551, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.560', 'AMMO2': '0.057', 'ARMOR': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.164', 'AMMO4': '0.283', 'DAMAGECOUNT': '0.429', 'WEAPON4': '0.600', 'weapon4': '0.982', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.594', 'weapon3': '3.800'} [2024-08-01 16:12:11,408][00147] DAMAGECOUNT value on done: 89.0 [2024-08-01 16:12:11,415][00136] DAMAGECOUNT value on done: 485.0 [2024-08-01 16:12:11,418][00136] Sum rewards: -0.850, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.610', 'AMMO2': '0.007', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO4': '0.037', 'weapon5': '0.044', 'WEAPON4': '0.100', 'AMMO3': '0.147', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'weapon4': '0.256', 'DAMAGECOUNT': '0.990', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.500', 'weapon2': '2.506', 'weapon3': '3.666'} [2024-08-01 16:12:12,805][00134] Updated weights for policy 0, policy_version 1421 (0.0020) [2024-08-01 16:12:12,956][00148] DAMAGECOUNT value on done: 561.0 [2024-08-01 16:12:12,956][00148] Sum rewards: -1.082, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.600', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'weapon7': '0.052', 'AMMO3': '0.133', 'weapon5': '0.152', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.300', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.238', 'DAMAGECOUNT': '1.326', 'weapon2': '2.164', 'weapon3': '3.322'} [2024-08-01 16:12:13,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5820416. Throughput: 0: 1511.5. Samples: 2914356. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:12:13,841][00034] Avg episode reward: [(0, '-4.073')] [2024-08-01 16:12:14,113][00135] DAMAGECOUNT value on done: 350.0 [2024-08-01 16:12:14,119][00135] Sum rewards: 0.553, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.315', 'AMMO2': '0.007', 'WEAPON1': '0.020', 'AMMO4': '0.034', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'weapon4': '0.144', 'AMMO3': '0.146', 'HITCOUNT': '0.320', 'DAMAGECOUNT': '0.975', 'WEAPON3': '1.000', 'weapon2': '2.840', 'FRAGCOUNT': '3.000', 'weapon3': '3.480'} [2024-08-01 16:12:15,094][00141] DAMAGECOUNT value on done: 522.0 [2024-08-01 16:12:15,098][00141] Sum rewards: 1.108, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO5': '0.012', 'AMMO2': '0.019', 'AMMO4': '0.095', 'weapon7': '0.126', 'weapon5': '0.152', 'AMMO3': '0.176', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.230', 'WEAPON4': '0.400', 'ARMOR': '0.477', 'WEAPON3': '1.100', 'weapon4': '1.226', 'DAMAGECOUNT': '1.461', 'weapon2': '2.188', 'weapon3': '3.306', 'FRAGCOUNT': '4.000'} [2024-08-01 16:12:17,148][00140] DAMAGECOUNT value on done: 736.0 [2024-08-01 16:12:17,149][00140] Sum rewards: 4.039, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.625', 'AMMO2': '0.002', 'AMMO4': '0.009', 'AMMO5': '0.022', 'AMMO3': '0.099', 'weapon5': '0.160', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'WEAPON5': '0.300', 'weapon4': '0.482', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.461', 'weapon2': '2.656', 'FRAGCOUNT': '3.000', 'weapon3': '4.112'} [2024-08-01 16:12:18,723][00144] DAMAGECOUNT value on done: 372.0 [2024-08-01 16:12:18,726][00144] Sum rewards: -3.127, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.566', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.162', 'weapon5': '0.180', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'ARMOR': '0.476', 'weapon4': '0.492', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.711', 'weapon3': '2.840', 'weapon2': '3.304'} [2024-08-01 16:12:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5832704. Throughput: 0: 1491.7. Samples: 2922624. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:12:18,841][00034] Avg episode reward: [(0, '-3.989')] [2024-08-01 16:12:19,884][00136] DAMAGECOUNT value on done: 661.0 [2024-08-01 16:12:19,886][00136] Sum rewards: -4.615, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.431', 'FRAGCOUNT': '0.000', 'AMMO2': '0.003', 'AMMO4': '0.015', 'AMMO5': '0.023', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.119', 'weapon4': '0.198', 'HITCOUNT': '0.250', 'weapon5': '0.394', 'WEAPON5': '0.400', 'ARMOR': '0.487', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.314', 'weapon3': '2.922', 'weapon2': '3.350'} [2024-08-01 16:12:20,077][00147] DAMAGECOUNT value on done: 223.0 [2024-08-01 16:12:20,083][00147] Sum rewards: -2.862, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO5': '0.003', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.047', 'AMMO4': '0.058', 'AMMO3': '0.080', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.132', 'DAMAGECOUNT': '0.324', 'WEAPON4': '0.500', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.442', 'weapon4': '1.768', 'weapon2': '3.612'} [2024-08-01 16:12:21,358][00148] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:12:22,217][00135] DAMAGECOUNT value on done: 327.0 [2024-08-01 16:12:22,234][00143] DAMAGECOUNT value on done: 451.0 [2024-08-01 16:12:22,237][00143] Sum rewards: -8.491, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.685', 'AMMO5': '0.004', 'AMMO2': '0.005', 'AMMO4': '0.024', 'weapon5': '0.074', 'WEAPON5': '0.100', 'HITCOUNT': '0.190', 'AMMO3': '0.197', 'WEAPON4': '0.400', 'FRAGCOUNT': '0.500', 'ARMOR': '0.507', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.179', 'weapon4': '1.630', 'weapon3': '1.762', 'weapon2': '3.322'} [2024-08-01 16:12:22,791][00141] DAMAGECOUNT value on done: 189.0 [2024-08-01 16:12:22,797][00141] Sum rewards: -4.813, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.200', 'AMMO4': '-0.031', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'ARMOR': '0.088', 'WEAPON5': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.172', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.387', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.544', 'weapon3': '1.858', 'weapon2': '3.550'} [2024-08-01 16:12:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5849088. Throughput: 0: 1486.4. Samples: 2931564. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:12:23,841][00034] Avg episode reward: [(0, '-4.005')] [2024-08-01 16:12:25,436][00140] DAMAGECOUNT value on done: 280.0 [2024-08-01 16:12:25,442][00140] Sum rewards: -5.701, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'weapon4': '0.074', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.208', 'ARMOR': '0.507', 'DAMAGECOUNT': '0.705', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '3.454', 'weapon3': '3.572'} [2024-08-01 16:12:26,858][00134] Updated weights for policy 0, policy_version 1431 (0.0020) [2024-08-01 16:12:26,904][00144] DAMAGECOUNT value on done: 260.0 [2024-08-01 16:12:26,909][00144] Sum rewards: -3.205, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.015', 'AMMO2': '0.004', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.021', 'ARMOR': '0.024', 'weapon5': '0.100', 'AMMO3': '0.195', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.424', 'DAMAGECOUNT': '0.750', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.974', 'weapon3': '3.338'} [2024-08-01 16:12:27,542][00147] DAMAGECOUNT value on done: 627.0 [2024-08-01 16:12:27,547][00147] Sum rewards: -7.796, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.450', 'FRAGCOUNT': '-2.000', 'AMMO2': '0.005', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'AMMO4': '0.026', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'weapon4': '0.122', 'WEAPON5': '0.200', 'weapon5': '0.200', 'AMMO3': '0.206', 'DAMAGECOUNT': '0.927', 'WEAPON3': '1.100', 'weapon2': '3.076', 'weapon3': '3.770'} [2024-08-01 16:12:28,101][00136] DAMAGECOUNT value on done: 226.0 [2024-08-01 16:12:28,102][00136] Sum rewards: -8.169, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.360', 'AMMO5': '0.005', 'AMMO2': '0.007', 'WEAPON1': '0.020', 'AMMO4': '0.034', 'weapon5': '0.036', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.180', 'AMMO3': '0.225', 'DAMAGECOUNT': '0.522', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.400', 'weapon2': '3.138', 'weapon3': '3.924'} [2024-08-01 16:12:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 5861376. Throughput: 0: 1494.7. Samples: 2936100. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:12:28,843][00034] Avg episode reward: [(0, '-4.139')] [2024-08-01 16:12:29,454][00148] DAMAGECOUNT value on done: 160.0 [2024-08-01 16:12:30,076][00143] DAMAGECOUNT value on done: 272.0 [2024-08-01 16:12:30,081][00143] Sum rewards: -1.571, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO5': '0.020', 'WEAPON1': '0.020', 'AMMO2': '0.022', 'ARMOR': '0.032', 'weapon5': '0.072', 'AMMO4': '0.108', 'weapon4': '0.148', 'AMMO3': '0.152', 'HITCOUNT': '0.190', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.579', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '3.530', 'weapon2': '3.666'} [2024-08-01 16:12:30,101][00135] DAMAGECOUNT value on done: 195.0 [2024-08-01 16:12:30,106][00135] Sum rewards: -7.862, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.008', 'AMMO2': '0.009', 'AMMO4': '0.047', 'ARMOR': '0.052', 'weapon5': '0.086', 'WEAPON5': '0.100', 'AMMO3': '0.128', 'HITCOUNT': '0.170', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.555', 'weapon4': '0.582', 'WEAPON3': '0.900', 'weapon2': '2.766', 'weapon3': '3.714'} [2024-08-01 16:12:30,589][00141] DAMAGECOUNT value on done: 573.0 [2024-08-01 16:12:30,590][00141] Sum rewards: -1.573, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.212', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.009', 'weapon5': '0.078', 'WEAPON4': '0.100', 'HITCOUNT': '0.180', 'weapon4': '0.186', 'AMMO3': '0.189', 'WEAPON5': '0.200', 'ARMOR': '0.481', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.029', 'FRAGCOUNT': '3.000', 'weapon2': '3.346', 'weapon3': '3.382'} [2024-08-01 16:12:33,101][00140] DAMAGECOUNT value on done: 183.0 [2024-08-01 16:12:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5877760. Throughput: 0: 1501.3. Samples: 2945256. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:12:33,840][00034] Avg episode reward: [(0, '-4.244')] [2024-08-01 16:12:33,874][00139] DAMAGECOUNT value on done: 300.0 [2024-08-01 16:12:33,875][00139] Sum rewards: -5.679, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.766', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'AMMO2': '0.024', 'ARMOR': '0.044', 'AMMO3': '0.114', 'AMMO4': '0.118', 'HITCOUNT': '0.150', 'weapon5': '0.154', 'WEAPON5': '0.300', 'WEAPON4': '0.500', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.144', 'weapon2': '2.794', 'weapon3': '3.218'} [2024-08-01 16:12:34,428][00143] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:12:34,847][00144] DAMAGECOUNT value on done: 215.0 [2024-08-01 16:12:34,859][00144] Sum rewards: -5.291, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.492', 'AMMO5': '0.010', 'AMMO2': '0.010', 'ARMOR': '0.040', 'WEAPON1': '0.040', 'weapon5': '0.040', 'weapon4': '0.050', 'AMMO4': '0.052', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.179', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.600', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.398', 'weapon3': '4.422'} [2024-08-01 16:12:35,535][00147] DAMAGECOUNT value on done: 213.0 [2024-08-01 16:12:35,538][00147] Sum rewards: -0.296, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.662', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.016', 'WEAPON1': '0.040', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.146', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.324', 'weapon5': '0.348', 'ARMOR': '0.480', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.700', 'weapon4': '0.862', 'weapon2': '1.800', 'weapon3': '3.434'} [2024-08-01 16:12:36,274][00136] DAMAGECOUNT value on done: 449.0 [2024-08-01 16:12:36,279][00136] Sum rewards: -10.560, reward structure: {'DEATHCOUNT': '-16.500', 'HEALTH': '-6.605', 'AMMO5': '0.003', 'AMMO2': '0.013', 'ARMOR': '0.052', 'AMMO4': '0.066', 'WEAPON5': '0.100', 'weapon5': '0.144', 'HITCOUNT': '0.210', 'AMMO3': '0.296', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.741', 'weapon4': '1.022', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon2': '3.082', 'weapon3': '3.116'} [2024-08-01 16:12:37,565][00148] DAMAGECOUNT value on done: 428.0 [2024-08-01 16:12:37,569][00148] Sum rewards: -1.039, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO5': '0.009', 'AMMO2': '0.011', 'WEAPON1': '0.040', 'AMMO4': '0.053', 'weapon5': '0.080', 'AMMO3': '0.119', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.270', 'ARMOR': '0.454', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.660', 'FRAGCOUNT': '1.000', 'weapon3': '2.756', 'weapon2': '3.800'} [2024-08-01 16:12:37,686][00132] DAMAGECOUNT value on done: 491.0 [2024-08-01 16:12:37,688][00132] Sum rewards: -0.950, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO5': '0.012', 'AMMO2': '0.018', 'ARMOR': '0.028', 'AMMO4': '0.089', 'HITCOUNT': '0.110', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.130', 'weapon7': '0.154', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon5': '0.284', 'WEAPON4': '0.300', 'weapon4': '0.396', 'DAMAGECOUNT': '0.531', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.224', 'weapon3': '3.864'} [2024-08-01 16:12:37,857][00143] DAMAGECOUNT value on done: 522.0 [2024-08-01 16:12:37,860][00143] Sum rewards: -4.995, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.660', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.003', 'ARMOR': '0.012', 'AMMO5': '0.014', 'AMMO4': '0.016', 'HITCOUNT': '0.120', 'AMMO3': '0.121', 'weapon5': '0.124', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.384', 'WEAPON3': '0.700', 'weapon4': '1.090', 'weapon2': '2.920', 'weapon3': '3.060'} [2024-08-01 16:12:37,895][00135] DAMAGECOUNT value on done: 249.0 [2024-08-01 16:12:37,895][00135] Sum rewards: -1.376, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'WEAPON1': '0.020', 'AMMO2': '0.024', 'AMMO5': '0.025', 'AMMO4': '0.120', 'weapon5': '0.200', 'AMMO3': '0.208', 'HITCOUNT': '0.210', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'weapon4': '0.536', 'DAMAGECOUNT': '0.687', 'WEAPON3': '1.200', 'weapon2': '2.642', 'weapon3': '3.742', 'FRAGCOUNT': '4.000'} [2024-08-01 16:12:38,313][00141] DAMAGECOUNT value on done: 316.0 [2024-08-01 16:12:38,316][00141] Sum rewards: -4.926, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'WEAPON1': '0.020', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'AMMO3': '0.231', 'ARMOR': '0.455', 'weapon4': '0.704', 'DAMAGECOUNT': '0.738', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '2.986', 'weapon2': '3.304'} [2024-08-01 16:12:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5894144. Throughput: 0: 1509.1. Samples: 2954604. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:12:38,843][00034] Avg episode reward: [(0, '-4.220')] [2024-08-01 16:12:40,184][00134] Updated weights for policy 0, policy_version 1441 (0.0020) [2024-08-01 16:12:41,185][00140] DAMAGECOUNT value on done: 134.0 [2024-08-01 16:12:41,462][00139] DAMAGECOUNT value on done: 363.0 [2024-08-01 16:12:42,923][00147] DAMAGECOUNT value on done: 203.0 [2024-08-01 16:12:42,926][00144] DAMAGECOUNT value on done: 447.0 [2024-08-01 16:12:42,927][00147] Sum rewards: -4.607, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.380', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.164', 'weapon4': '0.176', 'weapon5': '0.372', 'WEAPON5': '0.400', 'ARMOR': '0.456', 'DAMAGECOUNT': '0.534', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.864', 'weapon3': '3.892'} [2024-08-01 16:12:42,932][00144] Sum rewards: -3.238, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO5': '0.005', 'AMMO2': '0.006', 'AMMO4': '0.031', 'weapon5': '0.094', 'WEAPON5': '0.100', 'AMMO3': '0.194', 'WEAPON4': '0.300', 'HITCOUNT': '0.320', 'weapon4': '0.916', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.125', 'weapon2': '3.062', 'weapon3': '3.248'} [2024-08-01 16:12:43,019][00145] DAMAGECOUNT value on done: 229.0 [2024-08-01 16:12:43,023][00145] Sum rewards: -3.493, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.872', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'weapon5': '0.082', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.131', 'weapon4': '0.198', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.477', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '3.042', 'weapon3': '3.742'} [2024-08-01 16:12:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5910528. Throughput: 0: 1505.9. Samples: 2959020. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:12:43,840][00034] Avg episode reward: [(0, '-4.231')] [2024-08-01 16:12:44,496][00136] DAMAGECOUNT value on done: 91.0 [2024-08-01 16:12:44,499][00136] Sum rewards: -1.467, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO4': '-0.059', 'AMMO2': '-0.012', 'AMMO5': '0.006', 'WEAPON1': '0.020', 'ARMOR': '0.035', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'weapon5': '0.166', 'AMMO3': '0.178', 'WEAPON5': '0.200', 'weapon4': '0.208', 'DAMAGECOUNT': '0.228', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.850', 'weapon2': '4.212'} [2024-08-01 16:12:45,582][00132] DAMAGECOUNT value on done: 176.0 [2024-08-01 16:12:45,584][00132] Sum rewards: -1.706, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.531', 'AMMO5': '0.005', 'AMMO2': '0.022', 'ARMOR': '0.064', 'AMMO4': '0.112', 'HITCOUNT': '0.150', 'AMMO3': '0.191', 'DAMAGECOUNT': '0.483', 'WEAPON4': '0.600', 'WEAPON3': '1.100', 'weapon4': '2.172', 'weapon3': '2.200', 'weapon2': '2.976', 'FRAGCOUNT': '4.000'} [2024-08-01 16:12:45,764][00135] DAMAGECOUNT value on done: 160.0 [2024-08-01 16:12:45,810][00143] DAMAGECOUNT value on done: 280.0 [2024-08-01 16:12:45,810][00143] Sum rewards: -4.421, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.007', 'AMMO2': '0.009', 'WEAPON1': '0.020', 'AMMO4': '0.047', 'ARMOR': '0.072', 'HITCOUNT': '0.160', 'AMMO3': '0.162', 'WEAPON5': '0.200', 'weapon5': '0.250', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.510', 'weapon4': '0.668', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '2.774', 'weapon2': '3.080'} [2024-08-01 16:12:46,306][00148] DAMAGECOUNT value on done: 373.0 [2024-08-01 16:12:46,307][00148] Sum rewards: -3.766, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.600', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.005', 'AMMO5': '0.006', 'AMMO4': '0.024', 'AMMO3': '0.085', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'weapon5': '0.246', 'WEAPON4': '0.300', 'ARMOR': '0.477', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.759', 'weapon4': '0.774', 'weapon3': '2.478', 'weapon2': '3.310'} [2024-08-01 16:12:46,421][00141] DAMAGECOUNT value on done: 495.0 [2024-08-01 16:12:46,426][00141] Sum rewards: -1.185, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.995', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'AMMO5': '0.008', 'ARMOR': '0.048', 'AMMO3': '0.097', 'HITCOUNT': '0.140', 'weapon5': '0.162', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.700', 'weapon4': '0.804', 'weapon2': '2.738', 'weapon3': '3.120'} [2024-08-01 16:12:48,640][00138] DAMAGECOUNT value on done: 315.0 [2024-08-01 16:12:48,644][00138] Sum rewards: -3.327, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO2': '0.001', 'ARMOR': '0.004', 'AMMO4': '0.007', 'AMMO5': '0.010', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.128', 'WEAPON5': '0.200', 'weapon5': '0.346', 'weapon4': '0.688', 'DAMAGECOUNT': '0.735', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.704', 'weapon3': '3.380'} [2024-08-01 16:12:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 5922816. Throughput: 0: 1486.7. Samples: 2967348. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:12:48,840][00034] Avg episode reward: [(0, '-4.125')] [2024-08-01 16:12:49,787][00139] DAMAGECOUNT value on done: 240.0 [2024-08-01 16:12:49,789][00139] Sum rewards: -1.011, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.940', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'ARMOR': '0.030', 'HITCOUNT': '0.080', 'AMMO3': '0.134', 'weapon5': '0.368', 'DAMAGECOUNT': '0.390', 'WEAPON5': '0.400', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.344', 'weapon3': '3.744'} [2024-08-01 16:12:50,134][00144] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:12:50,489][00140] DAMAGECOUNT value on done: 739.0 [2024-08-01 16:12:50,495][00140] Sum rewards: 1.820, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.742', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.017', 'AMMO3': '0.092', 'ARMOR': '0.100', 'weapon5': '0.208', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.452', 'FRAGCOUNT': '1.500', 'weapon2': '3.186', 'weapon3': '3.544'} [2024-08-01 16:12:51,326][00145] DAMAGECOUNT value on done: 358.0 [2024-08-01 16:12:51,886][00147] DAMAGECOUNT value on done: 95.0 [2024-08-01 16:12:51,889][00147] Sum rewards: -2.664, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.685', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'AMMO5': '0.015', 'ARMOR': '0.024', 'weapon5': '0.086', 'HITCOUNT': '0.090', 'AMMO3': '0.139', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.255', 'weapon4': '0.526', 'WEAPON3': '0.600', 'weapon3': '2.944', 'weapon2': '3.202'} [2024-08-01 16:12:52,016][00144] DAMAGECOUNT value on done: 311.0 [2024-08-01 16:12:52,016][00144] Sum rewards: -1.852, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.180', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'ARMOR': '0.004', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'AMMO3': '0.141', 'weapon5': '0.160', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.768', 'weapon4': '0.998', 'FRAGCOUNT': '1.000', 'weapon2': '2.512', 'weapon3': '2.786'} [2024-08-01 16:12:53,689][00132] DAMAGECOUNT value on done: 325.0 [2024-08-01 16:12:53,693][00132] Sum rewards: 1.414, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO2': '0.018', 'ARMOR': '0.028', 'AMMO5': '0.034', 'AMMO4': '0.087', 'HITCOUNT': '0.100', 'AMMO3': '0.142', 'weapon5': '0.182', 'WEAPON4': '0.300', 'WEAPON5': '0.600', 'DAMAGECOUNT': '0.615', 'weapon4': '0.658', 'WEAPON3': '1.000', 'weapon2': '1.844', 'FRAGCOUNT': '3.000', 'weapon3': '4.296'} [2024-08-01 16:12:53,763][00136] DAMAGECOUNT value on done: 202.0 [2024-08-01 16:12:53,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 5939200. Throughput: 0: 1483.4. Samples: 2976348. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:12:53,842][00034] Avg episode reward: [(0, '-3.967')] [2024-08-01 16:12:53,845][00112] Saving new best policy, reward=-3.967! [2024-08-01 16:12:54,714][00135] DAMAGECOUNT value on done: 158.0 [2024-08-01 16:12:54,717][00135] Sum rewards: -4.380, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.922', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.088', 'AMMO2': '-0.017', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'weapon5': '0.020', 'weapon6': '0.052', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO3': '0.157', 'WEAPON6': '0.200', 'AMMO6': '0.200', 'AMMO7': '0.200', 'DAMAGECOUNT': '0.384', 'ARMOR': '0.479', 'WEAPON3': '1.000', 'weapon3': '3.096', 'weapon2': '3.910'} [2024-08-01 16:12:54,847][00143] DAMAGECOUNT value on done: 342.0 [2024-08-01 16:12:54,854][00143] Sum rewards: -1.942, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.425', 'FRAGCOUNT': '0.000', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.010', 'ARMOR': '0.052', 'AMMO3': '0.082', 'HITCOUNT': '0.160', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon5': '0.306', 'WEAPON3': '0.500', 'weapon4': '0.688', 'DAMAGECOUNT': '1.026', 'weapon3': '1.284', 'weapon2': '5.024'} [2024-08-01 16:12:55,124][00141] DAMAGECOUNT value on done: 411.0 [2024-08-01 16:12:55,131][00141] Sum rewards: -2.584, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.073', 'AMMO3': '0.172', 'weapon4': '0.184', 'HITCOUNT': '0.250', 'WEAPON4': '0.300', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.020', 'FRAGCOUNT': '2.000', 'weapon2': '2.754', 'weapon3': '3.238'} [2024-08-01 16:12:55,317][00134] Updated weights for policy 0, policy_version 1451 (0.0020) [2024-08-01 16:12:55,482][00148] DAMAGECOUNT value on done: 222.0 [2024-08-01 16:12:55,483][00148] Sum rewards: -4.347, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.330', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.064', 'AMMO2': '-0.013', 'ARMOR': '0.004', 'AMMO5': '0.019', 'AMMO3': '0.130', 'HITCOUNT': '0.130', 'weapon5': '0.352', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.546', 'WEAPON3': '0.800', 'weapon2': '3.182', 'weapon3': '3.646'} [2024-08-01 16:12:56,506][00138] DAMAGECOUNT value on done: 460.0 [2024-08-01 16:12:56,511][00138] Sum rewards: -0.463, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.170', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.014', 'weapon5': '0.090', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.340', 'ARMOR': '0.498', 'weapon4': '0.926', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.365', 'weapon2': '2.330', 'FRAGCOUNT': '3.000', 'weapon3': '3.976'} [2024-08-01 16:12:57,576][00139] DAMAGECOUNT value on done: 336.0 [2024-08-01 16:12:57,579][00139] Sum rewards: -1.374, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.009', 'WEAPON1': '0.020', 'AMMO3': '0.145', 'HITCOUNT': '0.150', 'weapon5': '0.182', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.483', 'weapon4': '0.908', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.014', 'weapon3': '3.866'} [2024-08-01 16:12:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5955584. Throughput: 0: 1477.3. Samples: 2980836. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:12:58,841][00034] Avg episode reward: [(0, '-3.715')] [2024-08-01 16:12:58,847][00112] Saving new best policy, reward=-3.715! [2024-08-01 16:12:59,398][00145] DAMAGECOUNT value on done: 507.0 [2024-08-01 16:12:59,401][00145] Sum rewards: 0.223, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.286', 'AMMO4': '-0.096', 'AMMO2': '-0.019', 'AMMO5': '0.013', 'ARMOR': '0.021', 'WEAPON1': '0.060', 'weapon5': '0.140', 'AMMO3': '0.155', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.960', 'FRAGCOUNT': '2.000', 'weapon3': '3.062', 'weapon2': '4.132'} [2024-08-01 16:12:59,426][00140] DAMAGECOUNT value on done: 180.0 [2024-08-01 16:12:59,427][00140] Sum rewards: -1.125, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.300', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'weapon4': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.106', 'HITCOUNT': '0.120', 'weapon5': '0.286', 'WEAPON5': '0.300', 'ARMOR': '0.455', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '3.252', 'weapon3': '3.424'} [2024-08-01 16:12:59,479][00147] DAMAGECOUNT value on done: 440.0 [2024-08-01 16:12:59,482][00147] Sum rewards: 0.788, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.372', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'weapon5': '0.018', 'ARMOR': '0.024', 'WEAPON5': '0.100', 'AMMO3': '0.180', 'WEAPON4': '0.200', 'HITCOUNT': '0.340', 'weapon4': '0.760', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.275', 'weapon2': '2.654', 'weapon3': '4.006', 'FRAGCOUNT': '5.000'} [2024-08-01 16:13:00,638][00144] DAMAGECOUNT value on done: 174.0 [2024-08-01 16:13:00,639][00144] Sum rewards: 0.559, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.047', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.012', 'ARMOR': '0.040', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.149', 'weapon5': '0.198', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.417', 'weapon4': '0.432', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.906', 'weapon3': '3.622'} [2024-08-01 16:13:01,553][00132] DAMAGECOUNT value on done: 86.0 [2024-08-01 16:13:01,558][00132] Sum rewards: -5.048, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO5': '0.023', 'ARMOR': '0.024', 'AMMO2': '0.029', 'HITCOUNT': '0.080', 'AMMO4': '0.143', 'AMMO3': '0.180', 'DAMAGECOUNT': '0.198', 'weapon5': '0.298', 'WEAPON5': '0.400', 'WEAPON4': '0.500', 'weapon4': '0.778', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.950', 'weapon3': '3.080'} [2024-08-01 16:13:02,020][00136] DAMAGECOUNT value on done: 410.0 [2024-08-01 16:13:02,305][00135] DAMAGECOUNT value on done: 190.0 [2024-08-01 16:13:02,308][00135] Sum rewards: -3.196, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.530', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.045', 'AMMO2': '-0.009', 'ARMOR': '0.008', 'AMMO5': '0.017', 'AMMO3': '0.072', 'WEAPON4': '0.100', 'weapon5': '0.168', 'HITCOUNT': '0.170', 'WEAPON5': '0.300', 'weapon4': '0.312', 'DAMAGECOUNT': '0.540', 'WEAPON3': '0.600', 'weapon3': '3.230', 'weapon2': '3.620'} [2024-08-01 16:13:02,524][00143] DAMAGECOUNT value on done: 244.0 [2024-08-01 16:13:02,728][00141] DAMAGECOUNT value on done: 336.0 [2024-08-01 16:13:02,732][00141] Sum rewards: -7.606, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.802', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.003', 'ARMOR': '0.004', 'AMMO4': '0.014', 'AMMO5': '0.021', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'weapon5': '0.176', 'AMMO3': '0.236', 'WEAPON5': '0.400', 'weapon4': '0.536', 'DAMAGECOUNT': '0.900', 'WEAPON3': '1.200', 'weapon2': '2.832', 'weapon3': '3.154'} [2024-08-01 16:13:03,325][00148] DAMAGECOUNT value on done: 300.0 [2024-08-01 16:13:03,328][00148] Sum rewards: -0.417, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.110', 'AMMO2': '0.006', 'AMMO5': '0.012', 'AMMO4': '0.030', 'WEAPON1': '0.060', 'AMMO3': '0.128', 'HITCOUNT': '0.160', 'weapon5': '0.166', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.392', 'ARMOR': '0.457', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.600', 'weapon3': '2.364', 'weapon2': '4.262'} [2024-08-01 16:13:03,839][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 5967872. Throughput: 0: 1496.0. Samples: 2989944. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:13:03,840][00034] Avg episode reward: [(0, '-3.487')] [2024-08-01 16:13:03,842][00112] Saving new best policy, reward=-3.487! [2024-08-01 16:13:04,792][00138] DAMAGECOUNT value on done: 74.0 [2024-08-01 16:13:05,632][00139] DAMAGECOUNT value on done: 159.0 [2024-08-01 16:13:05,636][00139] Sum rewards: -6.557, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.008', 'HITCOUNT': '0.030', 'ARMOR': '0.074', 'WEAPON4': '0.100', 'weapon5': '0.128', 'WEAPON5': '0.200', 'AMMO3': '0.203', 'DAMAGECOUNT': '0.321', 'WEAPON3': '1.200', 'weapon2': '3.328', 'weapon3': '4.036'} [2024-08-01 16:13:06,879][00147] DAMAGECOUNT value on done: 462.0 [2024-08-01 16:13:06,882][00147] Sum rewards: -5.266, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.060', 'AMMO5': '0.012', 'AMMO2': '0.017', 'ARMOR': '0.072', 'AMMO4': '0.084', 'weapon5': '0.126', 'HITCOUNT': '0.190', 'AMMO3': '0.232', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.570', 'weapon4': '0.596', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon3': '3.280', 'weapon2': '3.464'} [2024-08-01 16:13:06,938][00140] DAMAGECOUNT value on done: 478.0 [2024-08-01 16:13:06,943][00140] Sum rewards: -0.420, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.253', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'weapon4': '0.110', 'HITCOUNT': '0.210', 'AMMO3': '0.215', 'WEAPON5': '0.300', 'weapon5': '0.350', 'ARMOR': '0.471', 'DAMAGECOUNT': '1.194', 'WEAPON3': '1.200', 'weapon2': '2.918', 'weapon3': '3.234', 'FRAGCOUNT': '4.000'} [2024-08-01 16:13:07,378][00145] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:13:07,383][00145] Sum rewards: 0.040, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.595', 'AMMO2': '0.012', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'weapon4': '0.054', 'HITCOUNT': '0.060', 'AMMO4': '0.060', 'AMMO3': '0.079', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.210', 'weapon5': '0.296', 'WEAPON5': '0.300', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.866', 'weapon2': '4.060'} [2024-08-01 16:13:07,389][00134] Updated weights for policy 0, policy_version 1461 (0.0020) [2024-08-01 16:13:08,082][00144] DAMAGECOUNT value on done: 1030.0 [2024-08-01 16:13:08,090][00144] Sum rewards: -1.571, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.232', 'AMMO2': '0.001', 'ARMOR': '0.004', 'AMMO4': '0.004', 'AMMO5': '0.007', 'HITCOUNT': '0.050', 'weapon7': '0.102', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.120', 'AMMO3': '0.126', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.356', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.858', 'FRAGCOUNT': '1.000', 'weapon3': '2.452', 'weapon2': '3.290'} [2024-08-01 16:13:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 5984256. Throughput: 0: 1500.3. Samples: 2999076. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:13:08,840][00034] Avg episode reward: [(0, '-3.345')] [2024-08-01 16:13:08,848][00112] Saving new best policy, reward=-3.345! [2024-08-01 16:13:09,577][00136] DAMAGECOUNT value on done: 202.0 [2024-08-01 16:13:09,578][00136] Sum rewards: -4.721, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.940', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.002', 'AMMO4': '0.008', 'WEAPON1': '0.020', 'AMMO5': '0.022', 'ARMOR': '0.024', 'HITCOUNT': '0.100', 'AMMO3': '0.123', 'WEAPON4': '0.200', 'weapon5': '0.214', 'weapon4': '0.266', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.561', 'WEAPON3': '0.800', 'weapon3': '2.852', 'weapon2': '3.778'} [2024-08-01 16:13:09,731][00135] DAMAGECOUNT value on done: 225.0 [2024-08-01 16:13:09,735][00135] Sum rewards: -0.326, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'weapon5': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.018', 'WEAPON1': '0.040', 'ARMOR': '0.056', 'AMMO4': '0.090', 'WEAPON5': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.126', 'HITCOUNT': '0.130', 'AMMO3': '0.194', 'WEAPON7': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.450', 'weapon4': '0.566', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '3.208', 'weapon3': '3.436'} [2024-08-01 16:13:09,928][00132] DAMAGECOUNT value on done: 203.0 [2024-08-01 16:13:10,004][00143] DAMAGECOUNT value on done: 288.0 [2024-08-01 16:13:10,008][00143] Sum rewards: -1.532, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.765', 'AMMO5': '0.015', 'AMMO2': '0.019', 'ARMOR': '0.024', 'WEAPON1': '0.060', 'AMMO4': '0.095', 'HITCOUNT': '0.100', 'weapon4': '0.166', 'AMMO3': '0.175', 'WEAPON4': '0.200', 'WEAPON5': '0.400', 'weapon5': '0.502', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.789', 'weapon3': '1.888', 'FRAGCOUNT': '2.000', 'weapon2': '4.200'} [2024-08-01 16:13:10,336][00141] DAMAGECOUNT value on done: 250.0 [2024-08-01 16:13:10,339][00141] Sum rewards: -4.840, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.750', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'AMMO5': '0.010', 'weapon5': '0.030', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.101', 'AMMO3': '0.202', 'HITCOUNT': '0.220', 'weapon4': '0.254', 'DAMAGECOUNT': '0.750', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.158', 'weapon3': '3.924'} [2024-08-01 16:13:10,912][00148] DAMAGECOUNT value on done: 271.0 [2024-08-01 16:13:10,914][00148] Sum rewards: -7.170, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.370', 'AMMO5': '0.006', 'AMMO2': '0.014', 'ARMOR': '0.052', 'AMMO4': '0.070', 'HITCOUNT': '0.100', 'AMMO3': '0.167', 'WEAPON5': '0.200', 'weapon5': '0.222', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.693', 'weapon4': '0.850', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '2.236', 'weapon2': '3.790'} [2024-08-01 16:13:12,859][00138] DAMAGECOUNT value on done: 354.0 [2024-08-01 16:13:12,862][00138] Sum rewards: -2.430, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.007', 'ARMOR': '0.060', 'HITCOUNT': '0.130', 'AMMO3': '0.166', 'WEAPON5': '0.200', 'weapon5': '0.208', 'DAMAGECOUNT': '0.765', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.822', 'weapon3': '3.930'} [2024-08-01 16:13:13,778][00139] DAMAGECOUNT value on done: 40.0 [2024-08-01 16:13:13,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 5996544. Throughput: 0: 1497.6. Samples: 3003492. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:13:13,840][00034] Avg episode reward: [(0, '-3.420')] [2024-08-01 16:13:14,359][00142] DAMAGECOUNT value on done: 430.0 [2024-08-01 16:13:14,362][00142] Sum rewards: -3.685, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.570', 'AMMO5': '0.010', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'AMMO4': '0.054', 'AMMO3': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.702', 'DAMAGECOUNT': '0.756', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.298', 'weapon3': '4.260'} [2024-08-01 16:13:14,669][00140] DAMAGECOUNT value on done: 348.0 [2024-08-01 16:13:14,675][00140] Sum rewards: -2.238, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'AMMO2': '0.001', 'AMMO4': '0.006', 'weapon5': '0.006', 'AMMO5': '0.025', 'ARMOR': '0.064', 'AMMO3': '0.144', 'HITCOUNT': '0.160', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.648', 'WEAPON3': '0.900', 'weapon4': '1.372', 'FRAGCOUNT': '2.000', 'weapon2': '2.698', 'weapon3': '2.768'} [2024-08-01 16:13:15,163][00147] DAMAGECOUNT value on done: 578.0 [2024-08-01 16:13:15,166][00147] Sum rewards: 1.402, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.000', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.013', 'ARMOR': '0.072', 'AMMO3': '0.130', 'weapon5': '0.152', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.260', 'WEAPON3': '0.800', 'weapon4': '0.870', 'DAMAGECOUNT': '1.404', 'FRAGCOUNT': '1.500', 'weapon2': '2.712', 'weapon3': '3.602'} [2024-08-01 16:13:15,563][00145] DAMAGECOUNT value on done: 442.0 [2024-08-01 16:13:15,569][00145] Sum rewards: -6.107, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.100', 'AMMO2': '0.013', 'AMMO5': '0.025', 'AMMO4': '0.066', 'weapon5': '0.106', 'HITCOUNT': '0.180', 'AMMO3': '0.200', 'WEAPON4': '0.200', 'WEAPON5': '0.400', 'weapon4': '0.628', 'DAMAGECOUNT': '0.735', 'WEAPON3': '1.200', 'FRAGCOUNT': '1.500', 'weapon2': '2.318', 'weapon3': '4.172'} [2024-08-01 16:13:15,871][00144] DAMAGECOUNT value on done: 322.0 [2024-08-01 16:13:15,872][00144] Sum rewards: -1.304, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.022', 'ARMOR': '0.034', 'WEAPON1': '0.040', 'HITCOUNT': '0.110', 'AMMO3': '0.143', 'WEAPON4': '0.200', 'weapon5': '0.324', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.561', 'WEAPON3': '0.700', 'weapon4': '0.938', 'FRAGCOUNT': '1.000', 'weapon2': '2.502', 'weapon3': '3.120'} [2024-08-01 16:13:16,048][00137] DAMAGECOUNT value on done: 170.0 [2024-08-01 16:13:17,238][00146] DAMAGECOUNT value on done: 619.0 [2024-08-01 16:13:17,239][00146] Sum rewards: 0.008, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.214', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'HITCOUNT': '0.100', 'AMMO3': '0.158', 'WEAPON5': '0.200', 'weapon5': '0.306', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.242', 'FRAGCOUNT': '2.000', 'weapon3': '2.702', 'weapon2': '3.304'} [2024-08-01 16:13:17,747][00136] DAMAGECOUNT value on done: 223.0 [2024-08-01 16:13:17,748][00136] Sum rewards: -7.322, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.420', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.015', 'AMMO5': '0.019', 'weapon5': '0.026', 'ARMOR': '0.032', 'AMMO4': '0.072', 'HITCOUNT': '0.080', 'DAMAGECOUNT': '0.177', 'WEAPON5': '0.200', 'AMMO3': '0.215', 'WEAPON4': '0.300', 'weapon4': '0.484', 'WEAPON3': '1.100', 'weapon3': '2.966', 'weapon2': '4.162'} [2024-08-01 16:13:17,821][00132] DAMAGECOUNT value on done: 406.0 [2024-08-01 16:13:17,829][00132] Sum rewards: -1.619, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.595', 'AMMO4': '-0.063', 'AMMO2': '-0.013', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.186', 'DAMAGECOUNT': '0.402', 'weapon4': '0.536', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.038', 'weapon3': '3.532'} [2024-08-01 16:13:18,228][00135] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:13:18,233][00135] Sum rewards: -2.905, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.460', 'weapon5': '0.004', 'AMMO5': '0.010', 'AMMO2': '0.016', 'WEAPON1': '0.020', 'AMMO4': '0.077', 'HITCOUNT': '0.100', 'AMMO3': '0.169', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.262', 'DAMAGECOUNT': '0.315', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.796', 'weapon3': '3.286'} [2024-08-01 16:13:18,685][00143] DAMAGECOUNT value on done: 225.0 [2024-08-01 16:13:18,692][00143] Sum rewards: -3.004, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO2': '0.003', 'ARMOR': '0.004', 'AMMO4': '0.015', 'AMMO5': '0.020', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.127', 'weapon4': '0.262', 'weapon5': '0.322', 'DAMAGECOUNT': '0.375', 'WEAPON5': '0.400', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.684', 'weapon2': '3.404'} [2024-08-01 16:13:18,841][00034] Fps is (10 sec: 2457.1, 60 sec: 2935.4, 300 sec: 2999.1). Total num frames: 6008832. Throughput: 0: 1495.4. Samples: 3012552. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:13:18,842][00034] Avg episode reward: [(0, '-3.098')] [2024-08-01 16:13:18,899][00112] Saving new best policy, reward=-3.098! [2024-08-01 16:13:18,963][00141] DAMAGECOUNT value on done: 308.0 [2024-08-01 16:13:18,971][00141] Sum rewards: -0.928, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.290', 'AMMO2': '0.004', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'AMMO5': '0.025', 'HITCOUNT': '0.110', 'weapon5': '0.150', 'AMMO3': '0.156', 'WEAPON4': '0.200', 'WEAPON5': '0.400', 'weapon4': '0.460', 'ARMOR': '0.520', 'DAMAGECOUNT': '0.624', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '3.014', 'weapon2': '3.110'} [2024-08-01 16:13:19,704][00148] DAMAGECOUNT value on done: 256.0 [2024-08-01 16:13:19,708][00148] Sum rewards: -2.587, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.658', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.047', 'AMMO2': '-0.009', 'AMMO5': '0.013', 'AMMO3': '0.118', 'weapon5': '0.180', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.702', 'weapon2': '2.334', 'weapon3': '4.420'} [2024-08-01 16:13:21,092][00138] DAMAGECOUNT value on done: 624.0 [2024-08-01 16:13:21,094][00138] Sum rewards: 1.282, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.552', 'AMMO4': '-0.079', 'AMMO2': '-0.016', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.129', 'HITCOUNT': '0.180', 'weapon5': '0.348', 'WEAPON5': '0.400', 'ARMOR': '0.455', 'WEAPON3': '0.500', 'weapon4': '0.604', 'DAMAGECOUNT': '1.572', 'weapon3': '2.360', 'FRAGCOUNT': '2.500', 'weapon2': '3.996'} [2024-08-01 16:13:22,053][00139] DAMAGECOUNT value on done: 215.0 [2024-08-01 16:13:22,056][00139] Sum rewards: -2.891, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.641', 'AMMO5': '0.007', 'AMMO2': '0.017', 'ARMOR': '0.064', 'AMMO4': '0.086', 'AMMO3': '0.120', 'HITCOUNT': '0.150', 'weapon5': '0.158', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'WEAPON3': '0.600', 'weapon4': '0.606', 'DAMAGECOUNT': '0.645', 'FRAGCOUNT': '1.000', 'weapon3': '2.592', 'weapon2': '3.204'} [2024-08-01 16:13:22,660][00134] Updated weights for policy 0, policy_version 1471 (0.0020) [2024-08-01 16:13:22,908][00142] DAMAGECOUNT value on done: 151.0 [2024-08-01 16:13:23,284][00147] DAMAGECOUNT value on done: 345.0 [2024-08-01 16:13:23,287][00147] Sum rewards: -1.014, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.030', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.104', 'AMMO3': '0.105', 'HITCOUNT': '0.180', 'weapon4': '0.274', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.660', 'FRAGCOUNT': '2.000', 'weapon3': '2.488', 'weapon2': '3.920'} [2024-08-01 16:13:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 6029312. Throughput: 0: 1469.6. Samples: 3020736. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:13:23,843][00034] Avg episode reward: [(0, '-3.097')] [2024-08-01 16:13:23,845][00112] Saving new best policy, reward=-3.097! [2024-08-01 16:13:23,905][00140] DAMAGECOUNT value on done: 496.0 [2024-08-01 16:13:23,908][00140] Sum rewards: 1.391, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.920', 'AMMO4': '-0.050', 'AMMO2': '-0.010', 'AMMO5': '0.009', 'ARMOR': '0.016', 'weapon5': '0.070', 'AMMO3': '0.116', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.176', 'WEAPON7': '0.200', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.074', 'FRAGCOUNT': '2.000', 'weapon2': '2.416', 'weapon3': '4.254'} [2024-08-01 16:13:24,094][00145] DAMAGECOUNT value on done: 495.0 [2024-08-01 16:13:24,101][00145] Sum rewards: -7.355, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.488', 'FRAGCOUNT': '-2.000', 'AMMO5': '0.007', 'AMMO2': '0.011', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO4': '0.056', 'weapon5': '0.154', 'AMMO3': '0.189', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.266', 'WEAPON4': '0.300', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.915', 'weapon3': '3.428', 'weapon2': '3.700'} [2024-08-01 16:13:24,112][00140] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:13:24,629][00137] DAMAGECOUNT value on done: 669.0 [2024-08-01 16:13:24,632][00137] Sum rewards: -2.345, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.020', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'weapon4': '0.134', 'AMMO3': '0.197', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'HITCOUNT': '0.350', 'weapon5': '0.446', 'ARMOR': '0.449', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.917', 'weapon3': '2.850', 'FRAGCOUNT': '3.500', 'weapon2': '4.040'} [2024-08-01 16:13:24,951][00144] DAMAGECOUNT value on done: 604.0 [2024-08-01 16:13:24,956][00144] Sum rewards: -3.082, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.470', 'ARMOR': '0.008', 'AMMO2': '0.011', 'AMMO5': '0.016', 'WEAPON1': '0.040', 'AMMO4': '0.054', 'AMMO3': '0.143', 'HITCOUNT': '0.160', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon5': '0.382', 'weapon4': '0.442', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.990', 'weapon3': '2.782', 'FRAGCOUNT': '3.000', 'weapon2': '3.310'} [2024-08-01 16:13:25,714][00146] DAMAGECOUNT value on done: 277.0 [2024-08-01 16:13:25,717][00146] Sum rewards: -1.536, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.048', 'AMMO2': '-0.009', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.151', 'weapon4': '0.184', 'WEAPON5': '0.200', 'weapon5': '0.216', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.741', 'ARMOR': '0.944', 'FRAGCOUNT': '1.000', 'weapon3': '2.018', 'weapon2': '3.650'} [2024-08-01 16:13:26,460][00136] DAMAGECOUNT value on done: 202.0 [2024-08-01 16:13:26,465][00136] Sum rewards: -4.074, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'ARMOR': '0.016', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'weapon4': '0.116', 'AMMO3': '0.123', 'DAMAGECOUNT': '0.375', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '3.200', 'weapon3': '3.722'} [2024-08-01 16:13:26,500][00135] DAMAGECOUNT value on done: 94.0 [2024-08-01 16:13:26,502][00135] Sum rewards: -0.032, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.833', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'ARMOR': '0.016', 'AMMO5': '0.019', 'HITCOUNT': '0.070', 'AMMO3': '0.095', 'weapon5': '0.134', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.282', 'WEAPON3': '0.600', 'weapon4': '0.998', 'FRAGCOUNT': '1.000', 'weapon2': '2.780', 'weapon3': '3.188'} [2024-08-01 16:13:26,868][00143] DAMAGECOUNT value on done: 174.0 [2024-08-01 16:13:26,872][00143] Sum rewards: -2.108, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'ARMOR': '0.040', 'HITCOUNT': '0.130', 'AMMO3': '0.162', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.242', 'weapon4': '0.306', 'DAMAGECOUNT': '0.477', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '2.712', 'weapon2': '4.138'} [2024-08-01 16:13:27,011][00132] DAMAGECOUNT value on done: 105.0 [2024-08-01 16:13:27,090][00141] DAMAGECOUNT value on done: 323.0 [2024-08-01 16:13:27,093][00141] Sum rewards: -4.722, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.806', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.021', 'WEAPON1': '0.040', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.255', 'weapon5': '0.290', 'weapon4': '0.306', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.462', 'WEAPON3': '1.100', 'weapon2': '2.770', 'weapon3': '3.416'} [2024-08-01 16:13:27,795][00148] DAMAGECOUNT value on done: 443.0 [2024-08-01 16:13:27,800][00148] Sum rewards: -7.030, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.490', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.007', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'HITCOUNT': '0.130', 'AMMO3': '0.190', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.228', 'DAMAGECOUNT': '0.642', 'weapon4': '0.656', 'WEAPON3': '1.000', 'weapon3': '2.760', 'weapon2': '3.162'} [2024-08-01 16:13:28,838][00034] Fps is (10 sec: 3277.5, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 6041600. Throughput: 0: 1473.6. Samples: 3025332. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:13:28,841][00034] Avg episode reward: [(0, '-3.272')] [2024-08-01 16:13:29,846][00138] DAMAGECOUNT value on done: 450.0 [2024-08-01 16:13:29,849][00138] Sum rewards: -9.421, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.180', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.104', 'AMMO2': '-0.021', 'WEAPON1': '0.020', 'AMMO5': '0.025', 'weapon5': '0.062', 'HITCOUNT': '0.080', 'AMMO3': '0.184', 'DAMAGECOUNT': '0.225', 'WEAPON5': '0.500', 'WEAPON3': '0.800', 'weapon3': '2.504', 'weapon2': '4.734'} [2024-08-01 16:13:30,611][00139] DAMAGECOUNT value on done: 415.0 [2024-08-01 16:13:30,613][00139] Sum rewards: -5.467, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.785', 'AMMO5': '0.010', 'AMMO2': '0.017', 'weapon5': '0.046', 'AMMO4': '0.084', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'AMMO3': '0.240', 'weapon4': '0.408', 'ARMOR': '0.493', 'DAMAGECOUNT': '0.570', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.400', 'weapon2': '2.108', 'weapon3': '4.392'} [2024-08-01 16:13:30,724][00142] DAMAGECOUNT value on done: 268.0 [2024-08-01 16:13:30,727][00142] Sum rewards: -1.836, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.965', 'AMMO2': '0.005', 'weapon5': '0.012', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'AMMO4': '0.023', 'ARMOR': '0.024', 'AMMO3': '0.146', 'HITCOUNT': '0.180', 'weapon4': '0.196', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.714', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '3.032', 'weapon3': '4.012'} [2024-08-01 16:13:31,274][00140] DAMAGECOUNT value on done: 216.0 [2024-08-01 16:13:31,280][00140] Sum rewards: -3.785, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.959', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'WEAPON1': '0.020', 'ARMOR': '0.058', 'HITCOUNT': '0.110', 'AMMO3': '0.157', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.336', 'weapon4': '0.434', 'WEAPON3': '0.700', 'weapon3': '1.760', 'FRAGCOUNT': '2.000', 'weapon2': '4.160'} [2024-08-01 16:13:32,123][00145] DAMAGECOUNT value on done: 140.0 [2024-08-01 16:13:32,146][00147] DAMAGECOUNT value on done: 204.0 [2024-08-01 16:13:32,146][00147] Sum rewards: 0.482, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.640', 'AMMO2': '0.001', 'AMMO5': '0.003', 'AMMO4': '0.006', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'AMMO3': '0.118', 'HITCOUNT': '0.130', 'weapon5': '0.158', 'weapon4': '0.178', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.936', 'weapon2': '3.712'} [2024-08-01 16:13:32,193][00137] DAMAGECOUNT value on done: 250.0 [2024-08-01 16:13:32,197][00137] Sum rewards: -2.523, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.014', 'AMMO2': '0.015', 'ARMOR': '0.020', 'AMMO4': '0.076', 'AMMO3': '0.085', 'HITCOUNT': '0.130', 'weapon5': '0.180', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.600', 'weapon4': '0.722', 'weapon3': '2.636', 'weapon2': '3.394'} [2024-08-01 16:13:32,367][00144] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:13:32,370][00144] Sum rewards: -3.419, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'WEAPON1': '0.020', 'AMMO2': '0.026', 'ARMOR': '0.040', 'HITCOUNT': '0.120', 'AMMO4': '0.131', 'AMMO3': '0.146', 'DAMAGECOUNT': '0.420', 'WEAPON4': '0.500', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon4': '1.816', 'weapon2': '2.512', 'weapon3': '2.590'} [2024-08-01 16:13:33,281][00146] DAMAGECOUNT value on done: 220.0 [2024-08-01 16:13:33,282][00146] Sum rewards: -5.419, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.295', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.010', 'AMMO2': '0.019', 'WEAPON1': '0.040', 'HITCOUNT': '0.090', 'AMMO4': '0.093', 'AMMO3': '0.146', 'WEAPON5': '0.300', 'weapon5': '0.364', 'DAMAGECOUNT': '0.375', 'WEAPON4': '0.400', 'ARMOR': '0.489', 'weapon4': '0.652', 'WEAPON3': '0.800', 'weapon3': '2.772', 'weapon2': '3.326'} [2024-08-01 16:13:33,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 6057984. Throughput: 0: 1494.1. Samples: 3034584. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:13:33,840][00034] Avg episode reward: [(0, '-3.056')] [2024-08-01 16:13:33,843][00112] Saving new best policy, reward=-3.056! [2024-08-01 16:13:33,960][00136] DAMAGECOUNT value on done: 338.0 [2024-08-01 16:13:33,966][00136] Sum rewards: -4.073, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.031', 'AMMO2': '-0.006', 'AMMO5': '0.012', 'WEAPON4': '0.100', 'AMMO3': '0.141', 'HITCOUNT': '0.170', 'weapon5': '0.216', 'WEAPON5': '0.300', 'weapon4': '0.316', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.900', 'weapon3': '2.984', 'weapon2': '3.240'} [2024-08-01 16:13:34,241][00133] DAMAGECOUNT value on done: 94.0 [2024-08-01 16:13:34,427][00132] DAMAGECOUNT value on done: 393.0 [2024-08-01 16:13:34,432][00132] Sum rewards: -0.128, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.592', 'AMMO5': '0.012', 'AMMO2': '0.031', 'ARMOR': '0.060', 'WEAPON1': '0.060', 'AMMO3': '0.064', 'HITCOUNT': '0.120', 'AMMO4': '0.154', 'WEAPON5': '0.400', 'weapon5': '0.456', 'WEAPON4': '0.500', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.699', 'weapon4': '1.384', 'weapon2': '2.366', 'weapon3': '2.658', 'FRAGCOUNT': '3.000'} [2024-08-01 16:13:35,461][00148] DAMAGECOUNT value on done: 73.0 [2024-08-01 16:13:35,620][00135] DAMAGECOUNT value on done: 332.0 [2024-08-01 16:13:35,623][00135] Sum rewards: -4.530, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.970', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'FRAGCOUNT': '0.000', 'ARMOR': '0.004', 'AMMO5': '0.025', 'WEAPON1': '0.040', 'AMMO3': '0.148', 'HITCOUNT': '0.230', 'weapon5': '0.394', 'WEAPON5': '0.500', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.906', 'weapon2': '2.174', 'weapon3': '3.922'} [2024-08-01 16:13:35,944][00143] DAMAGECOUNT value on done: 165.0 [2024-08-01 16:13:36,047][00141] DAMAGECOUNT value on done: 609.0 [2024-08-01 16:13:36,050][00141] Sum rewards: -4.122, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.021', 'HITCOUNT': '0.040', 'AMMO3': '0.147', 'WEAPON4': '0.200', 'weapon5': '0.440', 'ARMOR': '0.480', 'WEAPON5': '0.500', 'weapon4': '0.658', 'DAMAGECOUNT': '0.786', 'WEAPON3': '0.800', 'weapon3': '2.516', 'weapon2': '3.414'} [2024-08-01 16:13:36,415][00134] Updated weights for policy 0, policy_version 1481 (0.0020) [2024-08-01 16:13:37,513][00138] DAMAGECOUNT value on done: 405.0 [2024-08-01 16:13:38,568][00139] DAMAGECOUNT value on done: 539.0 [2024-08-01 16:13:38,572][00139] Sum rewards: 3.865, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.485', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.134', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.212', 'weapon4': '0.338', 'ARMOR': '0.485', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.960', 'weapon2': '2.784', 'FRAGCOUNT': '3.000', 'weapon3': '3.144'} [2024-08-01 16:13:38,608][00142] DAMAGECOUNT value on done: 285.0 [2024-08-01 16:13:38,611][00142] Sum rewards: -0.186, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.420', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.002', 'AMMO4': '0.008', 'AMMO5': '0.010', 'WEAPON1': '0.060', 'ARMOR': '0.076', 'WEAPON4': '0.100', 'AMMO3': '0.120', 'HITCOUNT': '0.120', 'WEAPON5': '0.300', 'weapon5': '0.426', 'DAMAGECOUNT': '0.570', 'weapon4': '0.694', 'WEAPON3': '0.700', 'weapon2': '2.356', 'weapon3': '3.192'} [2024-08-01 16:13:38,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 6074368. Throughput: 0: 1494.7. Samples: 3043608. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:13:38,842][00034] Avg episode reward: [(0, '-2.885')] [2024-08-01 16:13:38,849][00112] Saving new best policy, reward=-2.885! [2024-08-01 16:13:39,212][00140] DAMAGECOUNT value on done: 316.0 [2024-08-01 16:13:39,220][00140] Sum rewards: -2.701, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.715', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.092', 'WEAPON5': '0.100', 'AMMO3': '0.110', 'weapon5': '0.118', 'HITCOUNT': '0.140', 'WEAPON4': '0.300', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.723', 'weapon4': '0.916', 'FRAGCOUNT': '1.000', 'weapon3': '2.118', 'weapon2': '3.770'} [2024-08-01 16:13:40,216][00137] DAMAGECOUNT value on done: 124.0 [2024-08-01 16:13:40,218][00137] Sum rewards: -12.808, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.540', 'FRAGCOUNT': '-3.000', 'WEAPON1': '0.020', 'AMMO2': '0.021', 'AMMO5': '0.033', 'HITCOUNT': '0.080', 'AMMO4': '0.103', 'weapon5': '0.142', 'WEAPON4': '0.200', 'AMMO3': '0.205', 'DAMAGECOUNT': '0.210', 'weapon4': '0.410', 'WEAPON5': '0.500', 'WEAPON3': '1.000', 'weapon3': '2.658', 'weapon2': '3.650'} [2024-08-01 16:13:40,333][00144] DAMAGECOUNT value on done: 376.0 [2024-08-01 16:13:40,336][00144] Sum rewards: 3.978, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.666', 'AMMO4': '-0.080', 'AMMO2': '-0.016', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO3': '0.079', 'HITCOUNT': '0.170', 'WEAPON5': '0.300', 'weapon5': '0.312', 'ARMOR': '0.477', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.801', 'weapon3': '3.098', 'weapon2': '3.622', 'FRAGCOUNT': '4.000'} [2024-08-01 16:13:40,382][00147] DAMAGECOUNT value on done: 434.0 [2024-08-01 16:13:40,383][00147] Sum rewards: -3.328, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.210', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.013', 'AMMO2': '-0.003', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'weapon4': '0.030', 'ARMOR': '0.072', 'WEAPON4': '0.100', 'weapon5': '0.122', 'AMMO3': '0.143', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.804', 'WEAPON3': '1.000', 'weapon2': '2.848', 'weapon3': '4.050'} [2024-08-01 16:13:40,586][00145] DAMAGECOUNT value on done: 155.0 [2024-08-01 16:13:41,239][00146] DAMAGECOUNT value on done: 300.0 [2024-08-01 16:13:41,241][00146] Sum rewards: -2.194, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO2': '0.004', 'AMMO5': '0.011', 'AMMO4': '0.021', 'WEAPON1': '0.040', 'HITCOUNT': '0.090', 'AMMO3': '0.145', 'WEAPON4': '0.200', 'weapon4': '0.278', 'WEAPON5': '0.400', 'FRAGCOUNT': '0.500', 'weapon5': '0.530', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.810', 'weapon3': '2.520', 'weapon2': '2.966'} [2024-08-01 16:13:41,797][00136] DAMAGECOUNT value on done: 74.0 [2024-08-01 16:13:42,117][00133] DAMAGECOUNT value on done: 245.0 [2024-08-01 16:13:42,121][00133] Sum rewards: -5.541, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.110', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.013', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'weapon5': '0.166', 'AMMO3': '0.232', 'weapon4': '0.246', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.615', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.500', 'weapon3': '3.200', 'weapon2': '3.682'} [2024-08-01 16:13:43,109][00132] DAMAGECOUNT value on done: 561.0 [2024-08-01 16:13:43,115][00132] Sum rewards: 1.055, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'AMMO3': '0.177', 'WEAPON5': '0.200', 'weapon5': '0.210', 'DAMAGECOUNT': '1.059', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.292', 'weapon3': '4.438'} [2024-08-01 16:13:43,302][00148] DAMAGECOUNT value on done: 213.0 [2024-08-01 16:13:43,305][00148] Sum rewards: -2.652, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.715', 'AMMO4': '-0.069', 'AMMO2': '-0.014', 'WEAPON1': '0.020', 'AMMO5': '0.021', 'ARMOR': '0.040', 'AMMO3': '0.111', 'HITCOUNT': '0.140', 'weapon5': '0.222', 'DAMAGECOUNT': '0.372', 'WEAPON5': '0.400', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.054', 'weapon2': '5.166'} [2024-08-01 16:13:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6086656. Throughput: 0: 1494.1. Samples: 3048072. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:13:43,840][00034] Avg episode reward: [(0, '-2.861')] [2024-08-01 16:13:43,842][00112] Saving new best policy, reward=-2.861! [2024-08-01 16:13:44,148][00135] DAMAGECOUNT value on done: 336.0 [2024-08-01 16:13:44,148][00135] Sum rewards: -5.482, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'AMMO5': '0.011', 'AMMO2': '0.015', 'ARMOR': '0.020', 'AMMO4': '0.075', 'AMMO3': '0.156', 'HITCOUNT': '0.200', 'weapon5': '0.250', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.900', 'weapon4': '1.112', 'FRAGCOUNT': '1.500', 'weapon2': '2.876', 'weapon3': '2.968'} [2024-08-01 16:13:44,513][00143] DAMAGECOUNT value on done: 215.0 [2024-08-01 16:13:44,545][00141] DAMAGECOUNT value on done: 253.0 [2024-08-01 16:13:46,245][00138] DAMAGECOUNT value on done: 202.0 [2024-08-01 16:13:46,247][00138] Sum rewards: -2.011, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'ARMOR': '0.040', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.125', 'weapon7': '0.176', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.396', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.322', 'weapon2': '2.184', 'weapon3': '3.714'} [2024-08-01 16:13:46,425][00142] DAMAGECOUNT value on done: 192.0 [2024-08-01 16:13:46,434][00142] Sum rewards: -1.784, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.765', 'AMMO2': '0.003', 'AMMO5': '0.014', 'AMMO4': '0.015', 'WEAPON1': '0.040', 'weapon4': '0.092', 'AMMO3': '0.099', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'WEAPON5': '0.300', 'weapon5': '0.408', 'DAMAGECOUNT': '0.546', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon3': '3.154', 'weapon2': '3.350'} [2024-08-01 16:13:47,158][00140] DAMAGECOUNT value on done: 367.0 [2024-08-01 16:13:47,160][00140] Sum rewards: -7.971, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.004', 'AMMO2': '0.006', 'WEAPON1': '0.020', 'AMMO4': '0.027', 'ARMOR': '0.028', 'HITCOUNT': '0.040', 'weapon5': '0.048', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.120', 'AMMO3': '0.160', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon4': '0.210', 'WEAPON3': '1.000', 'weapon2': '2.778', 'weapon3': '4.068'} [2024-08-01 16:13:47,212][00139] DAMAGECOUNT value on done: 191.0 [2024-08-01 16:13:48,062][00137] DAMAGECOUNT value on done: 331.0 [2024-08-01 16:13:48,069][00137] Sum rewards: -3.226, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.005', 'AMMO2': '0.013', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO4': '0.065', 'HITCOUNT': '0.080', 'AMMO3': '0.101', 'WEAPON5': '0.200', 'weapon5': '0.294', 'WEAPON4': '0.400', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.672', 'weapon4': '1.048', 'FRAGCOUNT': '2.000', 'weapon3': '2.912', 'weapon2': '2.992'} [2024-08-01 16:13:48,217][00144] DAMAGECOUNT value on done: 285.0 [2024-08-01 16:13:48,222][00144] Sum rewards: -2.820, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.170', 'AMMO2': '0.016', 'ARMOR': '0.028', 'AMMO5': '0.045', 'WEAPON1': '0.060', 'AMMO4': '0.080', 'HITCOUNT': '0.100', 'AMMO3': '0.262', 'weapon5': '0.330', 'DAMAGECOUNT': '0.390', 'WEAPON5': '0.800', 'weapon2': '1.222', 'WEAPON3': '1.500', 'FRAGCOUNT': '2.000', 'weapon3': '5.016'} [2024-08-01 16:13:48,611][00147] DAMAGECOUNT value on done: 517.0 [2024-08-01 16:13:48,615][00147] Sum rewards: 0.855, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.350', 'AMMO4': '-0.072', 'AMMO2': '-0.014', 'AMMO5': '0.003', 'ARMOR': '0.008', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.143', 'weapon5': '0.166', 'HITCOUNT': '0.250', 'weapon4': '0.590', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.176', 'weapon3': '2.750', 'FRAGCOUNT': '3.000', 'weapon2': '3.636'} [2024-08-01 16:13:48,839][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 6103040. Throughput: 0: 1491.5. Samples: 3057060. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:13:48,843][00034] Avg episode reward: [(0, '-2.938')] [2024-08-01 16:13:48,987][00134] Updated weights for policy 0, policy_version 1491 (0.0020) [2024-08-01 16:13:49,090][00146] DAMAGECOUNT value on done: 225.0 [2024-08-01 16:13:49,093][00146] Sum rewards: -4.001, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.277', 'AMMO4': '-0.067', 'AMMO2': '-0.013', 'AMMO5': '0.007', 'ARMOR': '0.024', 'HITCOUNT': '0.090', 'weapon5': '0.130', 'AMMO3': '0.188', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.510', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.172', 'weapon3': '3.434'} [2024-08-01 16:13:49,343][00145] DAMAGECOUNT value on done: 370.0 [2024-08-01 16:13:49,349][00145] Sum rewards: -0.763, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.010', 'ARMOR': '0.016', 'weapon5': '0.066', 'HITCOUNT': '0.080', 'AMMO3': '0.083', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.264', 'WEAPON4': '0.300', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon4': '1.184', 'weapon3': '2.830', 'weapon2': '3.062'} [2024-08-01 16:13:49,671][00136] DAMAGECOUNT value on done: 350.0 [2024-08-01 16:13:49,675][00136] Sum rewards: -3.859, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.150', 'AMMO2': '0.011', 'AMMO5': '0.015', 'weapon5': '0.026', 'AMMO4': '0.055', 'WEAPON5': '0.100', 'AMMO3': '0.153', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'weapon4': '0.314', 'DAMAGECOUNT': '0.870', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '1.642', 'weapon3': '5.074'} [2024-08-01 16:13:50,427][00133] DAMAGECOUNT value on done: 369.0 [2024-08-01 16:13:50,428][00133] Sum rewards: -5.923, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.680', 'AMMO5': '0.005', 'AMMO2': '0.008', 'weapon4': '0.016', 'WEAPON1': '0.040', 'AMMO4': '0.041', 'HITCOUNT': '0.150', 'AMMO3': '0.192', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.242', 'DAMAGECOUNT': '0.882', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.500', 'weapon2': '2.858', 'weapon3': '3.422'} [2024-08-01 16:13:51,715][00148] DAMAGECOUNT value on done: 405.0 [2024-08-01 16:13:51,753][00148] Sum rewards: 0.809, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.375', 'AMMO2': '0.005', 'AMMO5': '0.015', 'AMMO4': '0.026', 'WEAPON1': '0.040', 'weapon5': '0.080', 'AMMO3': '0.142', 'WEAPON4': '0.200', 'HITCOUNT': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.666', 'DAMAGECOUNT': '0.735', 'WEAPON3': '1.000', 'weapon2': '1.792', 'FRAGCOUNT': '3.000', 'weapon3': '4.232'} [2024-08-01 16:13:52,250][00135] DAMAGECOUNT value on done: 224.0 [2024-08-01 16:13:52,251][00135] Sum rewards: -3.654, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.578', 'AMMO5': '0.017', 'AMMO2': '0.038', 'ARMOR': '0.051', 'HITCOUNT': '0.110', 'AMMO3': '0.171', 'AMMO4': '0.187', 'weapon5': '0.220', 'WEAPON5': '0.300', 'WEAPON4': '0.400', 'weapon4': '0.462', 'DAMAGECOUNT': '0.528', 'WEAPON3': '1.200', 'weapon2': '1.800', 'FRAGCOUNT': '2.000', 'weapon3': '4.690'} [2024-08-01 16:13:52,296][00132] DAMAGECOUNT value on done: 50.0 [2024-08-01 16:13:52,297][00132] Sum rewards: -1.030, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.020', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'HITCOUNT': '0.040', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.105', 'AMMO3': '0.128', 'weapon4': '0.232', 'weapon5': '0.324', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.408', 'weapon3': '3.920'} [2024-08-01 16:13:52,661][00141] DAMAGECOUNT value on done: 184.0 [2024-08-01 16:13:52,662][00141] Sum rewards: -6.016, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'AMMO2': '0.032', 'ARMOR': '0.036', 'AMMO3': '0.100', 'HITCOUNT': '0.120', 'weapon5': '0.144', 'AMMO4': '0.160', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.345', 'WEAPON4': '0.500', 'WEAPON3': '0.700', 'weapon4': '1.484', 'weapon2': '2.356', 'weapon3': '2.908'} [2024-08-01 16:13:52,675][00143] DAMAGECOUNT value on done: 342.0 [2024-08-01 16:13:52,678][00143] Sum rewards: -1.896, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.190', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'AMMO2': '0.036', 'ARMOR': '0.073', 'AMMO3': '0.114', 'HITCOUNT': '0.120', 'weapon5': '0.128', 'AMMO4': '0.179', 'WEAPON5': '0.300', 'WEAPON4': '0.600', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.720', 'weapon4': '1.054', 'weapon3': '2.110', 'FRAGCOUNT': '3.000', 'weapon2': '3.726'} [2024-08-01 16:13:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6115328. Throughput: 0: 1474.9. Samples: 3065448. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:13:53,843][00034] Avg episode reward: [(0, '-3.030')] [2024-08-01 16:13:55,367][00140] DAMAGECOUNT value on done: 210.0 [2024-08-01 16:13:55,414][00138] DAMAGECOUNT value on done: 145.0 [2024-08-01 16:13:55,417][00138] Sum rewards: 0.412, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.765', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'ARMOR': '0.052', 'HITCOUNT': '0.080', 'AMMO3': '0.097', 'weapon5': '0.168', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.270', 'WEAPON5': '0.300', 'weapon4': '0.594', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.978', 'weapon2': '3.568'} [2024-08-01 16:13:55,590][00142] DAMAGECOUNT value on done: 270.0 [2024-08-01 16:13:55,595][00142] Sum rewards: -0.518, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.705', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'ARMOR': '0.008', 'AMMO5': '0.013', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'HITCOUNT': '0.130', 'weapon5': '0.154', 'WEAPON5': '0.200', 'weapon4': '0.248', 'DAMAGECOUNT': '0.780', 'WEAPON3': '0.800', 'weapon2': '3.186', 'weapon3': '3.754'} [2024-08-01 16:13:56,165][00139] DAMAGECOUNT value on done: 280.0 [2024-08-01 16:13:56,389][00147] DAMAGECOUNT value on done: 225.0 [2024-08-01 16:13:56,390][00147] Sum rewards: -4.879, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.350', 'AMMO2': '0.009', 'AMMO5': '0.020', 'WEAPON1': '0.040', 'AMMO4': '0.043', 'HITCOUNT': '0.080', 'AMMO3': '0.151', 'weapon5': '0.234', 'DAMAGECOUNT': '0.345', 'WEAPON5': '0.400', 'ARMOR': '0.467', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.600', 'weapon3': '3.682'} [2024-08-01 16:13:56,551][00144] DAMAGECOUNT value on done: 255.0 [2024-08-01 16:13:57,721][00145] DAMAGECOUNT value on done: 511.0 [2024-08-01 16:13:57,723][00145] Sum rewards: -8.544, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'FRAGCOUNT': '-3.000', 'AMMO5': '0.019', 'ARMOR': '0.024', 'AMMO2': '0.029', 'WEAPON1': '0.060', 'weapon5': '0.074', 'HITCOUNT': '0.090', 'AMMO3': '0.118', 'AMMO4': '0.147', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.315', 'weapon4': '0.330', 'WEAPON3': '0.800', 'weapon3': '3.000', 'weapon2': '3.630'} [2024-08-01 16:13:57,792][00137] DAMAGECOUNT value on done: 556.0 [2024-08-01 16:13:57,798][00137] Sum rewards: 3.669, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.570', 'ARMOR': '0.004', 'AMMO5': '0.005', 'AMMO2': '0.008', 'AMMO4': '0.040', 'weapon5': '0.060', 'AMMO3': '0.080', 'WEAPON5': '0.100', 'HITCOUNT': '0.210', 'AMMO6': '0.240', 'AMMO7': '0.240', 'weapon7': '0.290', 'WEAPON4': '0.400', 'WEAPON7': '0.400', 'WEAPON3': '0.500', 'weapon3': '1.442', 'DAMAGECOUNT': '1.506', 'weapon4': '1.834', 'weapon2': '1.880', 'FRAGCOUNT': '3.000'} [2024-08-01 16:13:57,899][00136] DAMAGECOUNT value on done: 325.0 [2024-08-01 16:13:57,905][00136] Sum rewards: 2.185, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.090', 'AMMO5': '0.010', 'AMMO2': '0.030', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'AMMO4': '0.149', 'AMMO3': '0.179', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.514', 'DAMAGECOUNT': '0.795', 'WEAPON3': '1.000', 'weapon2': '1.382', 'FRAGCOUNT': '3.000', 'weapon3': '4.960'} [2024-08-01 16:13:58,776][00146] DAMAGECOUNT value on done: 280.0 [2024-08-01 16:13:58,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 6131712. Throughput: 0: 1477.3. Samples: 3069972. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:13:58,841][00034] Avg episode reward: [(0, '-2.889')] [2024-08-01 16:13:59,190][00148] DAMAGECOUNT value on done: 246.0 [2024-08-01 16:13:59,192][00148] Sum rewards: -2.604, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'weapon5': '0.072', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.105', 'HITCOUNT': '0.120', 'AMMO3': '0.133', 'DAMAGECOUNT': '0.318', 'weapon4': '0.568', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '3.244', 'weapon3': '3.302'} [2024-08-01 16:13:59,874][00135] DAMAGECOUNT value on done: 170.0 [2024-08-01 16:13:59,898][00133] DAMAGECOUNT value on done: 608.0 [2024-08-01 16:13:59,901][00133] Sum rewards: -1.455, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO4': '-0.052', 'AMMO2': '-0.010', 'AMMO5': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'weapon5': '0.092', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.173', 'WEAPON5': '0.400', 'weapon4': '0.560', 'DAMAGECOUNT': '0.714', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.614', 'weapon3': '3.408'} [2024-08-01 16:14:00,275][00141] DAMAGECOUNT value on done: 243.0 [2024-08-01 16:14:00,279][00141] Sum rewards: -0.135, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.250', 'AMMO2': '0.001', 'AMMO4': '0.005', 'AMMO5': '0.014', 'ARMOR': '0.080', 'weapon5': '0.094', 'AMMO3': '0.173', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.579', 'weapon4': '0.790', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.398', 'weapon3': '3.540'} [2024-08-01 16:14:00,290][00143] DAMAGECOUNT value on done: 204.0 [2024-08-01 16:14:00,293][00143] Sum rewards: -6.651, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.920', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.009', 'AMMO2': '0.020', 'weapon5': '0.034', 'ARMOR': '0.060', 'HITCOUNT': '0.060', 'weapon4': '0.080', 'AMMO4': '0.099', 'AMMO3': '0.186', 'DAMAGECOUNT': '0.195', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON3': '1.000', 'weapon2': '2.406', 'weapon3': '3.970'} [2024-08-01 16:14:00,587][00132] DAMAGECOUNT value on done: 114.0 [2024-08-01 16:14:00,601][00132] Sum rewards: -3.397, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO2': '0.016', 'AMMO5': '0.019', 'ARMOR': '0.044', 'weapon5': '0.076', 'AMMO4': '0.081', 'HITCOUNT': '0.110', 'AMMO3': '0.128', 'DAMAGECOUNT': '0.258', 'WEAPON5': '0.300', 'WEAPON4': '0.500', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon4': '1.568', 'weapon3': '2.490', 'weapon2': '2.802'} [2024-08-01 16:14:02,768][00140] DAMAGECOUNT value on done: 253.0 [2024-08-01 16:14:02,770][00140] Sum rewards: -6.101, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.825', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.003', 'AMMO5': '0.010', 'AMMO4': '0.017', 'ARMOR': '0.040', 'HITCOUNT': '0.070', 'AMMO3': '0.113', 'WEAPON4': '0.200', 'weapon5': '0.222', 'DAMAGECOUNT': '0.294', 'WEAPON5': '0.300', 'WEAPON3': '0.700', 'weapon4': '0.932', 'weapon3': '1.882', 'weapon2': '3.190'} [2024-08-01 16:14:03,369][00134] Updated weights for policy 0, policy_version 1501 (0.0020) [2024-08-01 16:14:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.8, 300 sec: 2999.1). Total num frames: 6148096. Throughput: 0: 1483.8. Samples: 3079320. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:14:03,839][00138] DAMAGECOUNT value on done: 337.0 [2024-08-01 16:14:03,841][00034] Avg episode reward: [(0, '-2.907')] [2024-08-01 16:14:03,842][00138] Sum rewards: -3.329, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.041', 'AMMO2': '-0.008', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'WEAPON4': '0.100', 'AMMO3': '0.145', 'HITCOUNT': '0.230', 'weapon5': '0.284', 'WEAPON5': '0.400', 'weapon4': '0.552', 'DAMAGECOUNT': '0.981', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.956', 'weapon3': '3.654'} [2024-08-01 16:14:03,915][00142] DAMAGECOUNT value on done: 129.0 [2024-08-01 16:14:04,057][00144] DAMAGECOUNT value on done: 239.0 [2024-08-01 16:14:04,061][00144] Sum rewards: -3.621, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO2': '0.015', 'AMMO5': '0.028', 'AMMO4': '0.073', 'HITCOUNT': '0.120', 'AMMO3': '0.148', 'weapon5': '0.206', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.480', 'WEAPON5': '0.500', 'FRAGCOUNT': '0.500', 'weapon4': '0.678', 'WEAPON3': '0.800', 'weapon2': '2.224', 'weapon3': '3.898'} [2024-08-01 16:14:04,143][00147] DAMAGECOUNT value on done: 605.0 [2024-08-01 16:14:04,144][00147] Sum rewards: -1.177, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.077', 'AMMO2': '-0.015', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'weapon5': '0.036', 'ARMOR': '0.060', 'WEAPON5': '0.100', 'AMMO3': '0.225', 'HITCOUNT': '0.320', 'WEAPON3': '1.200', 'DAMAGECOUNT': '1.350', 'FRAGCOUNT': '2.000', 'weapon3': '2.562', 'weapon2': '3.592'} [2024-08-01 16:14:04,819][00139] DAMAGECOUNT value on done: 485.0 [2024-08-01 16:14:04,822][00139] Sum rewards: -3.302, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.006', 'ARMOR': '0.040', 'WEAPON1': '0.040', 'AMMO3': '0.096', 'HITCOUNT': '0.140', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.338', 'WEAPON3': '0.400', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.555', 'weapon4': '0.650', 'weapon3': '1.764', 'weapon2': '4.340'} [2024-08-01 16:14:05,368][00136] DAMAGECOUNT value on done: 197.0 [2024-08-01 16:14:05,564][00137] DAMAGECOUNT value on done: 155.0 [2024-08-01 16:14:06,539][00145] DAMAGECOUNT value on done: 689.0 [2024-08-01 16:14:06,543][00145] Sum rewards: 1.746, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.900', 'AMMO2': '0.013', 'AMMO5': '0.022', 'WEAPON1': '0.040', 'AMMO4': '0.064', 'AMMO3': '0.084', 'HITCOUNT': '0.290', 'WEAPON4': '0.300', 'ARMOR': '0.443', 'weapon5': '0.478', 'WEAPON3': '0.500', 'WEAPON5': '0.500', 'weapon4': '0.692', 'DAMAGECOUNT': '1.353', 'FRAGCOUNT': '2.000', 'weapon2': '2.172', 'weapon3': '3.194'} [2024-08-01 16:14:06,785][00148] DAMAGECOUNT value on done: 272.0 [2024-08-01 16:14:06,789][00148] Sum rewards: -1.607, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.972', 'AMMO2': '0.009', 'AMMO5': '0.024', 'AMMO4': '0.042', 'ARMOR': '0.060', 'HITCOUNT': '0.110', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.136', 'AMMO3': '0.137', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon5': '0.204', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon4': '1.242', 'weapon2': '1.550', 'weapon3': '2.176'} [2024-08-01 16:14:06,810][00146] DAMAGECOUNT value on done: 235.0 [2024-08-01 16:14:06,816][00146] Sum rewards: -6.972, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.080', 'weapon5': '0.008', 'AMMO5': '0.010', 'AMMO2': '0.014', 'AMMO4': '0.069', 'HITCOUNT': '0.080', 'AMMO3': '0.189', 'weapon4': '0.194', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.375', 'ARMOR': '0.487', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '3.080', 'weapon3': '3.752'} [2024-08-01 16:14:07,856][00135] DAMAGECOUNT value on done: 186.0 [2024-08-01 16:14:07,859][00135] Sum rewards: -3.137, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.568', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.015', 'weapon5': '0.036', 'ARMOR': '0.040', 'HITCOUNT': '0.120', 'AMMO3': '0.121', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.363', 'WEAPON3': '0.700', 'weapon4': '0.836', 'FRAGCOUNT': '1.000', 'weapon3': '2.780', 'weapon2': '3.034'} [2024-08-01 16:14:08,247][00141] DAMAGECOUNT value on done: 108.0 [2024-08-01 16:14:08,250][00141] Sum rewards: -8.564, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.060', 'AMMO5': '0.003', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'AMMO4': '0.048', 'HITCOUNT': '0.070', 'weapon5': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.219', 'weapon4': '0.282', 'FRAGCOUNT': '0.500', 'WEAPON3': '1.000', 'weapon3': '2.790', 'weapon2': '3.684'} [2024-08-01 16:14:08,289][00143] DAMAGECOUNT value on done: 308.0 [2024-08-01 16:14:08,290][00143] Sum rewards: 0.615, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.320', 'AMMO5': '0.010', 'AMMO2': '0.020', 'WEAPON1': '0.020', 'weapon5': '0.048', 'ARMOR': '0.072', 'AMMO4': '0.099', 'HITCOUNT': '0.100', 'AMMO3': '0.107', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.351', 'weapon4': '0.500', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.324', 'weapon2': '3.084'} [2024-08-01 16:14:08,599][00133] DAMAGECOUNT value on done: 297.0 [2024-08-01 16:14:08,606][00133] Sum rewards: -7.095, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'FRAGCOUNT': '-1.000', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'ARMOR': '0.004', 'AMMO5': '0.030', 'WEAPON1': '0.060', 'AMMO3': '0.134', 'HITCOUNT': '0.140', 'weapon5': '0.348', 'WEAPON5': '0.600', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.825', 'weapon3': '3.288', 'weapon2': '3.434'} [2024-08-01 16:14:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6164480. Throughput: 0: 1503.5. Samples: 3088392. Policy #0 lag: (min: 0.0, avg: 2.3, max: 6.0) [2024-08-01 16:14:08,842][00034] Avg episode reward: [(0, '-2.933')] [2024-08-01 16:14:08,851][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001505_6164480.pth... [2024-08-01 16:14:08,972][00132] DAMAGECOUNT value on done: 380.0 [2024-08-01 16:14:08,973][00132] Sum rewards: -0.558, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.007', 'ARMOR': '0.024', 'weapon4': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.144', 'WEAPON5': '0.200', 'weapon5': '0.230', 'HITCOUNT': '0.240', 'DAMAGECOUNT': '0.669', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.292', 'weapon3': '4.048'} [2024-08-01 16:14:09,020][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001329_5443584.pth [2024-08-01 16:14:10,287][00140] DAMAGECOUNT value on done: 275.0 [2024-08-01 16:14:10,291][00140] Sum rewards: -4.230, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.573', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.003', 'AMMO5': '0.004', 'AMMO4': '0.015', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'HITCOUNT': '0.120', 'weapon5': '0.138', 'AMMO3': '0.168', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.405', 'ARMOR': '0.535', 'WEAPON3': '0.900', 'weapon4': '1.272', 'weapon3': '2.424', 'weapon2': '2.440'} [2024-08-01 16:14:11,419][00144] DAMAGECOUNT value on done: 198.0 [2024-08-01 16:14:11,422][00144] Sum rewards: -1.275, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.929', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.076', 'AMMO2': '-0.015', 'AMMO5': '0.005', 'ARMOR': '0.008', 'WEAPON1': '0.020', 'weapon5': '0.028', 'WEAPON5': '0.100', 'AMMO3': '0.118', 'HITCOUNT': '0.140', 'DAMAGECOUNT': '0.399', 'WEAPON3': '0.700', 'weapon2': '3.470', 'weapon3': '4.008'} [2024-08-01 16:14:11,820][00138] DAMAGECOUNT value on done: 351.0 [2024-08-01 16:14:11,824][00138] Sum rewards: -7.811, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.020', 'AMMO2': '0.004', 'AMMO4': '0.017', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'HITCOUNT': '0.090', 'weapon5': '0.092', 'AMMO3': '0.218', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.561', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon4': '1.004', 'weapon3': '1.564', 'weapon2': '3.770'} [2024-08-01 16:14:12,012][00147] DAMAGECOUNT value on done: 546.0 [2024-08-01 16:14:12,018][00147] Sum rewards: 2.775, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.011', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.167', 'WEAPON5': '0.200', 'weapon5': '0.208', 'HITCOUNT': '0.340', 'weapon4': '0.552', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.191', 'weapon2': '2.772', 'weapon3': '3.674', 'FRAGCOUNT': '4.000'} [2024-08-01 16:14:12,501][00139] DAMAGECOUNT value on done: 203.0 [2024-08-01 16:14:12,503][00139] Sum rewards: -0.618, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.356', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.004', 'AMMO2': '0.007', 'AMMO4': '0.032', 'HITCOUNT': '0.040', 'weapon5': '0.056', 'AMMO3': '0.081', 'weapon4': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.135', 'WEAPON3': '0.500', 'ARMOR': '0.677', 'weapon3': '2.776', 'weapon2': '2.896'} [2024-08-01 16:14:12,683][00142] DAMAGECOUNT value on done: 400.0 [2024-08-01 16:14:12,688][00142] Sum rewards: -5.626, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.003', 'ARMOR': '0.096', 'WEAPON5': '0.100', 'weapon5': '0.112', 'AMMO3': '0.161', 'HITCOUNT': '0.170', 'WEAPON4': '0.200', 'FRAGCOUNT': '0.500', 'weapon4': '0.524', 'DAMAGECOUNT': '0.774', 'WEAPON3': '0.800', 'weapon3': '2.774', 'weapon2': '3.886'} [2024-08-01 16:14:12,788][00136] DAMAGECOUNT value on done: 522.0 [2024-08-01 16:14:12,793][00136] Sum rewards: -4.135, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.521', 'AMMO5': '0.010', 'AMMO2': '0.016', 'ARMOR': '0.067', 'AMMO4': '0.081', 'WEAPON5': '0.100', 'weapon5': '0.116', 'HITCOUNT': '0.160', 'AMMO3': '0.183', 'WEAPON4': '0.300', 'weapon4': '0.520', 'DAMAGECOUNT': '0.720', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.264', 'weapon3': '3.898'} [2024-08-01 16:14:13,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 6180864. Throughput: 0: 1503.7. Samples: 3093000. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:14:13,840][00034] Avg episode reward: [(0, '-2.948')] [2024-08-01 16:14:14,208][00145] DAMAGECOUNT value on done: 191.0 [2024-08-01 16:14:14,214][00145] Sum rewards: 0.772, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.970', 'AMMO2': '0.016', 'ARMOR': '0.040', 'AMMO4': '0.078', 'AMMO3': '0.129', 'HITCOUNT': '0.160', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.573', 'WEAPON3': '0.700', 'weapon4': '0.884', 'FRAGCOUNT': '2.000', 'weapon2': '2.992', 'weapon3': '3.270'} [2024-08-01 16:14:14,308][00148] DAMAGECOUNT value on done: 316.0 [2024-08-01 16:14:14,309][00148] Sum rewards: -3.519, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.190', 'AMMO5': '0.009', 'AMMO2': '0.018', 'ARMOR': '0.052', 'AMMO4': '0.088', 'AMMO3': '0.145', 'HITCOUNT': '0.160', 'weapon5': '0.178', 'WEAPON5': '0.200', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.540', 'weapon4': '0.796', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.716', 'weapon2': '3.070'} [2024-08-01 16:14:14,516][00137] DAMAGECOUNT value on done: 465.0 [2024-08-01 16:14:14,520][00137] Sum rewards: 3.049, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.580', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.132', 'weapon4': '0.160', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'WEAPON5': '0.300', 'weapon5': '0.412', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.215', 'FRAGCOUNT': '2.000', 'weapon2': '2.492', 'weapon3': '4.002'} [2024-08-01 16:14:15,380][00146] DAMAGECOUNT value on done: 300.0 [2024-08-01 16:14:15,383][00146] Sum rewards: -2.282, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO5': '0.005', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'AMMO4': '0.061', 'WEAPON4': '0.100', 'AMMO3': '0.112', 'WEAPON5': '0.200', 'HITCOUNT': '0.200', 'weapon4': '0.248', 'weapon5': '0.260', 'DAMAGECOUNT': '0.645', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '3.214', 'weapon2': '3.410'} [2024-08-01 16:14:16,506][00132] DAMAGECOUNT value on done: 231.0 [2024-08-01 16:14:16,512][00132] Sum rewards: -1.815, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.355', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO2': '0.028', 'HITCOUNT': '0.100', 'weapon5': '0.116', 'AMMO3': '0.127', 'AMMO4': '0.137', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.381', 'weapon4': '0.656', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '1.728', 'weapon3': '4.090'} [2024-08-01 16:14:16,694][00135] DAMAGECOUNT value on done: 87.0 [2024-08-01 16:14:16,817][00133] DAMAGECOUNT value on done: 602.0 [2024-08-01 16:14:16,823][00133] Sum rewards: -0.246, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.135', 'AMMO5': '0.010', 'AMMO2': '0.019', 'weapon5': '0.062', 'AMMO4': '0.092', 'WEAPON4': '0.100', 'weapon4': '0.118', 'AMMO3': '0.155', 'WEAPON5': '0.200', 'HITCOUNT': '0.320', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.341', 'weapon2': '2.464', 'FRAGCOUNT': '3.000', 'weapon3': '4.658'} [2024-08-01 16:14:16,906][00134] Updated weights for policy 0, policy_version 1511 (0.0019) [2024-08-01 16:14:17,158][00141] DAMAGECOUNT value on done: 307.0 [2024-08-01 16:14:17,163][00141] Sum rewards: -2.131, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.175', 'AMMO2': '0.013', 'AMMO4': '0.062', 'ARMOR': '0.064', 'AMMO3': '0.099', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.482', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.666', 'weapon3': '2.642', 'FRAGCOUNT': '3.000', 'weapon2': '4.596'} [2024-08-01 16:14:17,242][00143] DAMAGECOUNT value on done: 264.0 [2024-08-01 16:14:18,453][00140] DAMAGECOUNT value on done: 424.0 [2024-08-01 16:14:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.1, 300 sec: 2985.2). Total num frames: 6193152. Throughput: 0: 1499.5. Samples: 3102060. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:14:18,840][00034] Avg episode reward: [(0, '-2.883')] [2024-08-01 16:14:19,517][00138] DAMAGECOUNT value on done: 494.0 [2024-08-01 16:14:19,520][00138] Sum rewards: 0.657, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.104', 'AMMO4': '-0.039', 'AMMO2': '-0.008', 'ARMOR': '0.008', 'AMMO5': '0.012', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'weapon5': '0.122', 'AMMO3': '0.165', 'WEAPON5': '0.200', 'HITCOUNT': '0.290', 'weapon4': '0.376', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.284', 'weapon2': '3.006', 'weapon3': '3.854', 'FRAGCOUNT': '4.000'} [2024-08-01 16:14:19,553][00144] DAMAGECOUNT value on done: 275.0 [2024-08-01 16:14:19,558][00144] Sum rewards: -0.909, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.830', 'weapon4': '0.012', 'AMMO2': '0.013', 'AMMO4': '0.064', 'WEAPON4': '0.100', 'AMMO3': '0.221', 'HITCOUNT': '0.230', 'DAMAGECOUNT': '0.765', 'WEAPON3': '1.100', 'weapon2': '1.994', 'FRAGCOUNT': '3.000', 'weapon3': '5.172'} [2024-08-01 16:14:20,102][00139] DAMAGECOUNT value on done: 164.0 [2024-08-01 16:14:20,104][00139] Sum rewards: -3.437, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.115', 'AMMO5': '0.019', 'AMMO2': '0.029', 'HITCOUNT': '0.130', 'AMMO4': '0.147', 'AMMO3': '0.171', 'weapon5': '0.184', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.420', 'weapon4': '0.870', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.176', 'weapon3': '3.582'} [2024-08-01 16:14:20,506][00147] DAMAGECOUNT value on done: 415.0 [2024-08-01 16:14:20,513][00147] Sum rewards: 2.819, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.930', 'AMMO5': '0.010', 'AMMO2': '0.015', 'weapon5': '0.042', 'AMMO4': '0.075', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.156', 'HITCOUNT': '0.200', 'AMMO6': '0.240', 'AMMO7': '0.240', 'weapon7': '0.322', 'WEAPON7': '0.400', 'weapon4': '0.790', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.215', 'weapon2': '1.720', 'FRAGCOUNT': '3.000', 'weapon3': '3.074'} [2024-08-01 16:14:20,601][00142] DAMAGECOUNT value on done: 579.0 [2024-08-01 16:14:20,606][00142] Sum rewards: -3.474, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-5.078', 'AMMO2': '0.001', 'AMMO4': '0.007', 'ARMOR': '0.020', 'AMMO5': '0.022', 'weapon5': '0.172', 'AMMO3': '0.210', 'HITCOUNT': '0.240', 'WEAPON5': '0.500', 'DAMAGECOUNT': '1.071', 'WEAPON3': '1.300', 'weapon2': '2.184', 'FRAGCOUNT': '3.000', 'weapon3': '4.876'} [2024-08-01 16:14:21,355][00136] DAMAGECOUNT value on done: 456.0 [2024-08-01 16:14:21,362][00136] Sum rewards: -2.281, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.759', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.169', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'weapon5': '0.332', 'DAMAGECOUNT': '0.642', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '1.910', 'weapon3': '4.870'} [2024-08-01 16:14:21,772][00145] DAMAGECOUNT value on done: 221.0 [2024-08-01 16:14:21,775][00145] Sum rewards: -2.407, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.006', 'AMMO5': '0.011', 'WEAPON1': '0.020', 'AMMO4': '0.029', 'HITCOUNT': '0.080', 'AMMO3': '0.091', 'DAMAGECOUNT': '0.252', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'weapon5': '0.320', 'ARMOR': '0.492', 'WEAPON3': '0.600', 'weapon4': '0.838', 'weapon3': '2.092', 'weapon2': '3.092'} [2024-08-01 16:14:22,582][00137] DAMAGECOUNT value on done: 416.0 [2024-08-01 16:14:22,583][00137] Sum rewards: -4.328, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.015', 'weapon5': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.133', 'WEAPON5': '0.300', 'HITCOUNT': '0.310', 'weapon4': '0.314', 'ARMOR': '0.433', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.158', 'weapon3': '3.424', 'weapon2': '3.448'} [2024-08-01 16:14:22,987][00148] DAMAGECOUNT value on done: 475.0 [2024-08-01 16:14:22,990][00148] Sum rewards: 4.243, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.470', 'AMMO4': '-0.069', 'AMMO2': '-0.014', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'AMMO3': '0.148', 'WEAPON5': '0.200', 'HITCOUNT': '0.240', 'weapon5': '0.258', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.335', 'FRAGCOUNT': '3.000', 'weapon2': '3.002', 'weapon3': '3.880'} [2024-08-01 16:14:23,763][00146] DAMAGECOUNT value on done: 180.0 [2024-08-01 16:14:23,763][00146] Sum rewards: -7.139, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.004', 'ARMOR': '0.052', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'weapon5': '0.112', 'AMMO3': '0.152', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.495', 'FRAGCOUNT': '0.500', 'weapon4': '0.680', 'WEAPON3': '0.900', 'weapon3': '3.154', 'weapon2': '3.182'} [2024-08-01 16:14:23,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 6205440. Throughput: 0: 1488.6. Samples: 3110592. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:14:23,843][00034] Avg episode reward: [(0, '-2.608')] [2024-08-01 16:14:23,845][00112] Saving new best policy, reward=-2.608! [2024-08-01 16:14:24,763][00132] DAMAGECOUNT value on done: 377.0 [2024-08-01 16:14:24,766][00132] Sum rewards: -4.932, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO5': '0.003', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'AMMO4': '0.076', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.102', 'AMMO3': '0.125', 'DAMAGECOUNT': '0.165', 'weapon4': '0.396', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.392', 'weapon2': '4.454'} [2024-08-01 16:14:25,351][00135] DAMAGECOUNT value on done: 644.0 [2024-08-01 16:14:25,354][00135] Sum rewards: -2.141, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.540', 'AMMO2': '0.004', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'AMMO4': '0.021', 'weapon5': '0.026', 'ARMOR': '0.044', 'weapon4': '0.116', 'AMMO3': '0.185', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'WEAPON5': '0.400', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.209', 'FRAGCOUNT': '3.000', 'weapon2': '3.338', 'weapon3': '3.796'} [2024-08-01 16:14:25,517][00133] DAMAGECOUNT value on done: 164.0 [2024-08-01 16:14:25,518][00133] Sum rewards: -0.386, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.010', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.013', 'HITCOUNT': '0.070', 'weapon5': '0.132', 'AMMO3': '0.140', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.426', 'ARMOR': '0.464', 'weapon4': '0.680', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.968', 'weapon2': '3.042'} [2024-08-01 16:14:25,884][00141] DAMAGECOUNT value on done: 129.0 [2024-08-01 16:14:26,033][00143] DAMAGECOUNT value on done: 247.0 [2024-08-01 16:14:26,033][00143] Sum rewards: -4.409, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.100', 'AMMO2': '0.017', 'AMMO5': '0.017', 'ARMOR': '0.040', 'AMMO4': '0.086', 'AMMO3': '0.111', 'weapon5': '0.154', 'HITCOUNT': '0.170', 'WEAPON5': '0.400', 'WEAPON4': '0.500', 'DAMAGECOUNT': '0.621', 'WEAPON3': '0.700', 'weapon4': '1.556', 'weapon3': '2.006', 'weapon2': '3.062', 'FRAGCOUNT': '4.000'} [2024-08-01 16:14:27,071][00140] DAMAGECOUNT value on done: 338.0 [2024-08-01 16:14:27,076][00140] Sum rewards: -2.181, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.904', 'AMMO2': '0.005', 'AMMO5': '0.007', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO4': '0.024', 'HITCOUNT': '0.140', 'AMMO3': '0.173', 'WEAPON5': '0.200', 'weapon5': '0.220', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.744', 'weapon4': '0.818', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '2.154', 'weapon2': '3.752'} [2024-08-01 16:14:27,725][00138] DAMAGECOUNT value on done: 678.0 [2024-08-01 16:14:27,729][00138] Sum rewards: -1.518, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.695', 'AMMO2': '0.007', 'AMMO5': '0.013', 'AMMO4': '0.033', 'WEAPON4': '0.100', 'AMMO3': '0.130', 'weapon4': '0.146', 'weapon5': '0.206', 'HITCOUNT': '0.210', 'WEAPON5': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.909', 'FRAGCOUNT': '1.500', 'weapon2': '3.084', 'weapon3': '3.740'} [2024-08-01 16:14:28,138][00144] DAMAGECOUNT value on done: 222.0 [2024-08-01 16:14:28,141][00144] Sum rewards: -6.482, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.930', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.007', 'AMMO5': '0.014', 'ARMOR': '0.028', 'AMMO4': '0.036', 'weapon5': '0.066', 'WEAPON5': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.171', 'WEAPON4': '0.200', 'weapon4': '0.214', 'DAMAGECOUNT': '0.576', 'WEAPON3': '0.800', 'weapon2': '2.766', 'weapon3': '3.550'} [2024-08-01 16:14:28,230][00139] DAMAGECOUNT value on done: 299.0 [2024-08-01 16:14:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6221824. Throughput: 0: 1485.6. Samples: 3114924. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:14:28,840][00034] Avg episode reward: [(0, '-2.635')] [2024-08-01 16:14:29,014][00142] DAMAGECOUNT value on done: 205.0 [2024-08-01 16:14:29,016][00142] Sum rewards: -3.138, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.013', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.155', 'weapon5': '0.158', 'WEAPON5': '0.200', 'weapon4': '0.256', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.900', 'weapon2': '3.192', 'weapon3': '3.272'} [2024-08-01 16:14:29,586][00136] DAMAGECOUNT value on done: 558.0 [2024-08-01 16:14:29,589][00136] Sum rewards: -5.332, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.760', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'WEAPON1': '0.020', 'AMMO5': '0.021', 'AMMO3': '0.116', 'HITCOUNT': '0.190', 'weapon5': '0.270', 'WEAPON5': '0.400', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.074', 'weapon3': '3.106', 'weapon2': '3.562'} [2024-08-01 16:14:29,662][00147] DAMAGECOUNT value on done: 448.0 [2024-08-01 16:14:29,662][00147] Sum rewards: -5.623, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.465', 'ARMOR': '0.008', 'AMMO2': '0.009', 'WEAPON1': '0.020', 'AMMO4': '0.042', 'HITCOUNT': '0.100', 'AMMO3': '0.127', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.408', 'weapon4': '0.484', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '3.142', 'weapon2': '3.652'} [2024-08-01 16:14:29,932][00145] DAMAGECOUNT value on done: 325.0 [2024-08-01 16:14:29,938][00145] Sum rewards: -6.903, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'FRAGCOUNT': '-1.000', 'AMMO2': '0.017', 'AMMO5': '0.021', 'ARMOR': '0.040', 'AMMO4': '0.084', 'WEAPON1': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.187', 'weapon4': '0.232', 'weapon5': '0.248', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.546', 'WEAPON3': '1.200', 'weapon2': '2.628', 'weapon3': '3.754'} [2024-08-01 16:14:30,739][00137] DAMAGECOUNT value on done: 63.0 [2024-08-01 16:14:30,744][00137] Sum rewards: -3.432, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'ARMOR': '0.028', 'HITCOUNT': '0.070', 'AMMO3': '0.084', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.189', 'WEAPON3': '0.400', 'weapon4': '0.620', 'FRAGCOUNT': '1.000', 'weapon3': '1.082', 'weapon2': '4.520'} [2024-08-01 16:14:31,014][00148] DAMAGECOUNT value on done: 418.0 [2024-08-01 16:14:31,024][00148] Sum rewards: -2.046, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.480', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'weapon4': '0.054', 'WEAPON4': '0.100', 'AMMO3': '0.129', 'weapon5': '0.140', 'HITCOUNT': '0.150', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.774', 'weapon3': '3.696'} [2024-08-01 16:14:31,035][00134] Updated weights for policy 0, policy_version 1521 (0.0020) [2024-08-01 16:14:31,598][00146] DAMAGECOUNT value on done: 315.0 [2024-08-01 16:14:31,603][00146] Sum rewards: -0.645, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.075', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'AMMO2': '0.025', 'ARMOR': '0.044', 'HITCOUNT': '0.090', 'weapon5': '0.096', 'WEAPON5': '0.100', 'AMMO4': '0.126', 'AMMO3': '0.148', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.210', 'weapon4': '0.372', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.588', 'weapon3': '4.006'} [2024-08-01 16:14:32,601][00132] DAMAGECOUNT value on done: 584.0 [2024-08-01 16:14:32,609][00132] Sum rewards: -3.388, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.065', 'AMMO5': '0.005', 'AMMO2': '0.005', 'AMMO4': '0.023', 'weapon5': '0.030', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.164', 'HITCOUNT': '0.180', 'weapon4': '0.298', 'DAMAGECOUNT': '0.582', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.500', 'weapon2': '2.872', 'weapon3': '3.768'} [2024-08-01 16:14:33,535][00133] DAMAGECOUNT value on done: 289.0 [2024-08-01 16:14:33,539][00133] Sum rewards: -7.900, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.470', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.008', 'ARMOR': '0.036', 'weapon7': '0.104', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.134', 'HITCOUNT': '0.160', 'weapon5': '0.194', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.507', 'weapon4': '0.772', 'WEAPON3': '0.800', 'weapon2': '2.430', 'weapon3': '3.330'} [2024-08-01 16:14:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6238208. Throughput: 0: 1489.4. Samples: 3124080. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:14:33,842][00034] Avg episode reward: [(0, '-2.821')] [2024-08-01 16:14:33,922][00135] DAMAGECOUNT value on done: 354.0 [2024-08-01 16:14:34,461][00141] DAMAGECOUNT value on done: 230.0 [2024-08-01 16:14:34,799][00140] DAMAGECOUNT value on done: 309.0 [2024-08-01 16:14:34,804][00143] DAMAGECOUNT value on done: 441.0 [2024-08-01 16:14:34,808][00143] Sum rewards: -4.439, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.385', 'AMMO5': '0.007', 'AMMO2': '0.016', 'WEAPON1': '0.040', 'ARMOR': '0.068', 'AMMO4': '0.078', 'weapon4': '0.102', 'AMMO3': '0.125', 'weapon5': '0.184', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.915', 'weapon2': '3.144', 'weapon3': '3.836'} [2024-08-01 16:14:35,998][00144] DAMAGECOUNT value on done: 455.0 [2024-08-01 16:14:35,999][00144] Sum rewards: -3.279, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.014', 'AMMO5': '0.018', 'WEAPON1': '0.040', 'AMMO4': '0.067', 'AMMO3': '0.093', 'weapon7': '0.100', 'HITCOUNT': '0.110', 'AMMO6': '0.160', 'AMMO7': '0.160', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon5': '0.226', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.420', 'ARMOR': '0.437', 'weapon4': '0.532', 'WEAPON3': '0.700', 'weapon2': '2.520', 'weapon3': '3.504'} [2024-08-01 16:14:36,522][00138] DAMAGECOUNT value on done: 320.0 [2024-08-01 16:14:36,526][00138] Sum rewards: -1.555, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO2': '0.010', 'AMMO5': '0.015', 'AMMO4': '0.051', 'HITCOUNT': '0.060', 'ARMOR': '0.101', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.150', 'weapon5': '0.160', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'AMMO3': '0.213', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.345', 'weapon4': '0.412', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '3.160', 'weapon2': '3.268'} [2024-08-01 16:14:37,034][00139] DAMAGECOUNT value on done: 331.0 [2024-08-01 16:14:37,038][00139] Sum rewards: -4.642, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.040', 'weapon5': '0.002', 'ARMOR': '0.004', 'AMMO2': '0.009', 'AMMO5': '0.015', 'AMMO4': '0.047', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.176', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'AMMO3': '0.214', 'HITCOUNT': '0.270', 'DAMAGECOUNT': '0.723', 'weapon4': '0.842', 'WEAPON3': '1.100', 'weapon2': '2.560', 'FRAGCOUNT': '3.000', 'weapon3': '3.346'} [2024-08-01 16:14:37,412][00136] DAMAGECOUNT value on done: 442.0 [2024-08-01 16:14:37,415][00136] Sum rewards: 1.749, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'AMMO2': '0.001', 'AMMO4': '0.007', 'AMMO5': '0.024', 'ARMOR': '0.040', 'WEAPON1': '0.040', 'AMMO3': '0.200', 'weapon5': '0.230', 'HITCOUNT': '0.290', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.999', 'WEAPON3': '1.200', 'weapon2': '2.282', 'weapon3': '4.666', 'FRAGCOUNT': '5.000'} [2024-08-01 16:14:37,640][00142] DAMAGECOUNT value on done: 370.0 [2024-08-01 16:14:37,641][00142] Sum rewards: -4.721, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.545', 'AMMO4': '-0.047', 'AMMO2': '-0.009', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'weapon5': '0.030', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.243', 'ARMOR': '0.463', 'DAMAGECOUNT': '0.585', 'weapon4': '0.762', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.340', 'weapon3': '4.152'} [2024-08-01 16:14:37,875][00147] DAMAGECOUNT value on done: 387.0 [2024-08-01 16:14:37,878][00147] Sum rewards: -6.668, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.800', 'AMMO4': '-0.033', 'AMMO2': '-0.006', 'ARMOR': '0.023', 'AMMO3': '0.107', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.486', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.807', 'FRAGCOUNT': '1.000', 'weapon3': '2.396', 'weapon2': '4.332'} [2024-08-01 16:14:38,761][00145] DAMAGECOUNT value on done: 377.0 [2024-08-01 16:14:38,768][00145] Sum rewards: -0.972, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.070', 'AMMO2': '-0.014', 'AMMO5': '0.004', 'ARMOR': '0.004', 'WEAPON1': '0.020', 'weapon5': '0.080', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.115', 'FRAGCOUNT': '0.500', 'weapon4': '0.616', 'DAMAGECOUNT': '0.675', 'WEAPON3': '0.800', 'weapon3': '3.044', 'weapon2': '3.424'} [2024-08-01 16:14:38,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6250496. Throughput: 0: 1496.3. Samples: 3132780. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:14:38,840][00034] Avg episode reward: [(0, '-2.888')] [2024-08-01 16:14:39,029][00148] DAMAGECOUNT value on done: 414.0 [2024-08-01 16:14:39,030][00148] Sum rewards: -9.891, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.680', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.016', 'AMMO2': '0.022', 'WEAPON1': '0.040', 'AMMO4': '0.107', 'HITCOUNT': '0.130', 'AMMO3': '0.223', 'weapon5': '0.224', 'WEAPON5': '0.300', 'WEAPON4': '0.400', 'ARMOR': '0.475', 'weapon4': '0.642', 'DAMAGECOUNT': '0.762', 'WEAPON3': '1.100', 'weapon3': '3.020', 'weapon2': '3.078'} [2024-08-01 16:14:39,595][00137] DAMAGECOUNT value on done: 263.0 [2024-08-01 16:14:39,596][00137] Sum rewards: -5.721, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.700', 'AMMO5': '0.005', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'AMMO4': '0.056', 'AMMO3': '0.170', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.202', 'HITCOUNT': '0.210', 'weapon5': '0.268', 'FRAGCOUNT': '0.500', 'ARMOR': '0.508', 'DAMAGECOUNT': '0.789', 'WEAPON3': '1.000', 'weapon3': '3.366', 'weapon2': '3.474'} [2024-08-01 16:14:40,598][00146] DAMAGECOUNT value on done: 324.0 [2024-08-01 16:14:40,602][00146] Sum rewards: -8.219, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.310', 'AMMO2': '0.002', 'AMMO4': '0.011', 'ARMOR': '0.020', 'AMMO5': '0.029', 'HITCOUNT': '0.130', 'weapon4': '0.142', 'AMMO3': '0.199', 'WEAPON4': '0.200', 'WEAPON5': '0.400', 'weapon5': '0.452', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.771', 'WEAPON3': '1.000', 'weapon3': '2.850', 'weapon2': '3.884'} [2024-08-01 16:14:41,051][00132] DAMAGECOUNT value on done: 547.0 [2024-08-01 16:14:41,055][00132] Sum rewards: -3.577, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.700', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.027', 'AMMO3': '0.140', 'weapon5': '0.152', 'WEAPON4': '0.200', 'HITCOUNT': '0.280', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.948', 'weapon4': '0.952', 'weapon3': '2.864', 'FRAGCOUNT': '3.000', 'weapon2': '3.398'} [2024-08-01 16:14:42,107][00135] DAMAGECOUNT value on done: 436.0 [2024-08-01 16:14:42,112][00135] Sum rewards: -1.815, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.780', 'AMMO4': '-0.031', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'ARMOR': '0.060', 'AMMO3': '0.137', 'WEAPON5': '0.200', 'weapon5': '0.268', 'HITCOUNT': '0.290', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.248', 'FRAGCOUNT': '2.000', 'weapon3': '2.848', 'weapon2': '3.896'} [2024-08-01 16:14:42,547][00141] DAMAGECOUNT value on done: 259.0 [2024-08-01 16:14:42,714][00143] DAMAGECOUNT value on done: 273.0 [2024-08-01 16:14:42,718][00143] Sum rewards: -6.099, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'AMMO2': '0.023', 'WEAPON5': '0.100', 'AMMO4': '0.115', 'weapon5': '0.122', 'HITCOUNT': '0.140', 'AMMO3': '0.168', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.444', 'weapon4': '0.492', 'ARMOR': '0.496', 'WEAPON3': '1.000', 'weapon2': '2.992', 'weapon3': '3.646'} [2024-08-01 16:14:42,720][00140] DAMAGECOUNT value on done: 159.0 [2024-08-01 16:14:42,726][00140] Sum rewards: -3.160, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.795', 'AMMO5': '0.005', 'AMMO2': '0.005', 'ARMOR': '0.012', 'weapon5': '0.024', 'AMMO4': '0.027', 'WEAPON1': '0.080', 'AMMO3': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.130', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.387', 'WEAPON3': '0.600', 'weapon4': '0.738', 'FRAGCOUNT': '1.000', 'weapon3': '2.934', 'weapon2': '3.292'} [2024-08-01 16:14:43,090][00133] DAMAGECOUNT value on done: 199.0 [2024-08-01 16:14:43,735][00144] DAMAGECOUNT value on done: 532.0 [2024-08-01 16:14:43,738][00144] Sum rewards: -2.253, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.327', 'AMMO2': '0.003', 'AMMO5': '0.004', 'AMMO4': '0.014', 'ARMOR': '0.049', 'weapon5': '0.068', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'AMMO3': '0.243', 'HITCOUNT': '0.250', 'weapon4': '0.672', 'DAMAGECOUNT': '0.981', 'WEAPON3': '1.400', 'FRAGCOUNT': '2.000', 'weapon2': '2.742', 'weapon3': '3.848'} [2024-08-01 16:14:43,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6266880. Throughput: 0: 1496.0. Samples: 3137292. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:14:43,840][00034] Avg episode reward: [(0, '-3.074')] [2024-08-01 16:14:44,270][00138] DAMAGECOUNT value on done: 568.0 [2024-08-01 16:14:44,280][00138] Sum rewards: -1.638, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.440', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'ARMOR': '0.080', 'AMMO3': '0.152', 'HITCOUNT': '0.160', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.699', 'WEAPON3': '0.900', 'weapon4': '0.906', 'FRAGCOUNT': '1.000', 'weapon2': '2.460', 'weapon3': '3.508'} [2024-08-01 16:14:44,780][00139] DAMAGECOUNT value on done: 344.0 [2024-08-01 16:14:44,784][00139] Sum rewards: 1.816, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.501', 'ARMOR': '0.004', 'AMMO2': '0.005', 'AMMO5': '0.007', 'AMMO4': '0.024', 'AMMO3': '0.080', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.120', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon7': '0.234', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.852', 'weapon4': '0.988', 'weapon2': '1.650', 'FRAGCOUNT': '2.000', 'weapon3': '2.792'} [2024-08-01 16:14:45,244][00134] Updated weights for policy 0, policy_version 1531 (0.0021) [2024-08-01 16:14:45,358][00136] DAMAGECOUNT value on done: 385.0 [2024-08-01 16:14:45,361][00136] Sum rewards: -1.585, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.679', 'AMMO4': '-0.052', 'AMMO2': '-0.010', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'weapon7': '0.116', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.177', 'HITCOUNT': '0.180', 'WEAPON7': '0.200', 'weapon4': '0.236', 'DAMAGECOUNT': '0.645', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '2.616', 'weapon2': '3.610'} [2024-08-01 16:14:45,692][00147] DAMAGECOUNT value on done: 133.0 [2024-08-01 16:14:45,698][00147] Sum rewards: -5.904, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'weapon5': '0.184', 'DAMAGECOUNT': '0.189', 'WEAPON5': '0.200', 'AMMO3': '0.215', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '3.164', 'weapon2': '3.718'} [2024-08-01 16:14:46,469][00145] DAMAGECOUNT value on done: 479.0 [2024-08-01 16:14:46,471][00145] Sum rewards: -7.253, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.080', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'AMMO5': '0.012', 'AMMO3': '0.173', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.216', 'HITCOUNT': '0.320', 'FRAGCOUNT': '0.500', 'weapon4': '0.876', 'DAMAGECOUNT': '1.017', 'WEAPON3': '1.100', 'weapon3': '2.932', 'weapon2': '3.060'} [2024-08-01 16:14:46,782][00148] DAMAGECOUNT value on done: 31.0 [2024-08-01 16:14:47,291][00142] DAMAGECOUNT value on done: 211.0 [2024-08-01 16:14:47,292][00142] Sum rewards: -3.186, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.028', 'AMMO2': '-0.006', 'AMMO5': '0.014', 'ARMOR': '0.016', 'HITCOUNT': '0.120', 'weapon5': '0.170', 'AMMO3': '0.233', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.453', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon3': '3.476', 'weapon2': '3.516'} [2024-08-01 16:14:48,746][00132] DAMAGECOUNT value on done: 30.0 [2024-08-01 16:14:48,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.8, 300 sec: 2999.1). Total num frames: 6283264. Throughput: 0: 1485.1. Samples: 3146148. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 16:14:48,840][00034] Avg episode reward: [(0, '-3.116')] [2024-08-01 16:14:49,255][00137] DAMAGECOUNT value on done: 273.0 [2024-08-01 16:14:49,260][00137] Sum rewards: -2.417, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.250', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.008', 'AMMO5': '0.014', 'ARMOR': '0.038', 'AMMO4': '0.038', 'WEAPON1': '0.040', 'AMMO3': '0.101', 'weapon5': '0.116', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.240', 'weapon4': '0.544', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.804', 'weapon3': '2.934', 'weapon2': '3.606'} [2024-08-01 16:14:49,984][00146] DAMAGECOUNT value on done: 344.0 [2024-08-01 16:14:49,988][00146] Sum rewards: -5.630, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.001', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'weapon5': '0.020', 'ARMOR': '0.061', 'WEAPON5': '0.100', 'AMMO3': '0.157', 'HITCOUNT': '0.200', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.717', 'WEAPON3': '0.900', 'weapon4': '1.234', 'weapon3': '2.916', 'weapon2': '2.942'} [2024-08-01 16:14:50,582][00135] DAMAGECOUNT value on done: 240.0 [2024-08-01 16:14:50,584][00135] Sum rewards: 2.771, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.785', 'AMMO4': '-0.074', 'AMMO2': '-0.015', 'WEAPON1': '0.020', 'AMMO3': '0.079', 'HITCOUNT': '0.140', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.555', 'FRAGCOUNT': '2.000', 'weapon3': '2.642', 'weapon2': '3.208'} [2024-08-01 16:14:50,743][00140] DAMAGECOUNT value on done: 770.0 [2024-08-01 16:14:50,746][00140] Sum rewards: 0.235, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.261', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.013', 'weapon5': '0.072', 'ARMOR': '0.109', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.134', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon7': '0.232', 'weapon4': '0.544', 'DAMAGECOUNT': '0.654', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon2': '2.960', 'weapon3': '3.334'} [2024-08-01 16:14:50,977][00141] DAMAGECOUNT value on done: 375.0 [2024-08-01 16:14:50,982][00141] Sum rewards: -9.196, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.770', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.006', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'AMMO4': '0.030', 'HITCOUNT': '0.080', 'weapon5': '0.132', 'AMMO3': '0.178', 'DAMAGECOUNT': '0.195', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.528', 'WEAPON3': '0.800', 'weapon3': '3.032', 'weapon2': '3.658'} [2024-08-01 16:14:51,179][00143] DAMAGECOUNT value on done: 293.0 [2024-08-01 16:14:51,180][00143] Sum rewards: -5.240, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.060', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'weapon5': '0.036', 'weapon7': '0.058', 'WEAPON5': '0.100', 'AMMO3': '0.114', 'WEAPON4': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.270', 'ARMOR': '0.457', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.840', 'weapon4': '0.854', 'FRAGCOUNT': '2.000', 'weapon2': '2.930', 'weapon3': '3.298'} [2024-08-01 16:14:51,391][00144] DAMAGECOUNT value on done: 379.0 [2024-08-01 16:14:51,395][00144] Sum rewards: 2.520, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.985', 'AMMO5': '0.003', 'AMMO2': '0.008', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.039', 'WEAPON5': '0.100', 'AMMO3': '0.121', 'weapon5': '0.140', 'WEAPON4': '0.200', 'HITCOUNT': '0.240', 'WEAPON3': '0.800', 'weapon4': '1.006', 'DAMAGECOUNT': '1.032', 'weapon2': '2.226', 'FRAGCOUNT': '3.000', 'weapon3': '4.058'} [2024-08-01 16:14:51,951][00138] DAMAGECOUNT value on done: 280.0 [2024-08-01 16:14:51,955][00138] Sum rewards: -8.191, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.380', 'AMMO5': '0.005', 'weapon5': '0.022', 'AMMO2': '0.025', 'WEAPON5': '0.100', 'AMMO4': '0.126', 'ARMOR': '0.148', 'HITCOUNT': '0.150', 'AMMO3': '0.166', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.375', 'weapon4': '0.382', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.476', 'weapon2': '4.514'} [2024-08-01 16:14:52,432][00139] DAMAGECOUNT value on done: 270.0 [2024-08-01 16:14:52,437][00139] Sum rewards: -1.557, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO2': '0.014', 'AMMO5': '0.015', 'weapon5': '0.046', 'AMMO4': '0.071', 'AMMO3': '0.104', 'HITCOUNT': '0.170', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'weapon4': '0.520', 'ARMOR': '0.558', 'DAMAGECOUNT': '0.645', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon2': '2.634', 'weapon3': '3.856'} [2024-08-01 16:14:52,530][00133] DAMAGECOUNT value on done: 268.0 [2024-08-01 16:14:52,534][00133] Sum rewards: -5.273, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.903', 'AMMO2': '0.003', 'weapon7': '0.006', 'AMMO5': '0.009', 'AMMO4': '0.013', 'weapon5': '0.068', 'HITCOUNT': '0.140', 'AMMO3': '0.176', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.300', 'ARMOR': '0.494', 'DAMAGECOUNT': '0.564', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon4': '1.382', 'weapon2': '2.526', 'weapon3': '3.148'} [2024-08-01 16:14:52,806][00136] DAMAGECOUNT value on done: 237.0 [2024-08-01 16:14:52,809][00136] Sum rewards: -1.966, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.975', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.011', 'AMMO5': '0.022', 'ARMOR': '0.024', 'AMMO4': '0.056', 'AMMO3': '0.119', 'HITCOUNT': '0.130', 'WEAPON4': '0.200', 'weapon5': '0.308', 'WEAPON3': '0.500', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.651', 'weapon4': '0.692', 'weapon2': '2.304', 'weapon3': '3.492'} [2024-08-01 16:14:53,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 6291456. Throughput: 0: 1485.3. Samples: 3155232. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 16:14:53,840][00034] Avg episode reward: [(0, '-3.194')] [2024-08-01 16:14:54,275][00148] DAMAGECOUNT value on done: 433.0 [2024-08-01 16:14:54,278][00148] Sum rewards: -2.174, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.810', 'AMMO2': '0.004', 'AMMO4': '0.020', 'AMMO5': '0.024', 'WEAPON1': '0.040', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.132', 'AMMO3': '0.156', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.240', 'WEAPON5': '0.300', 'weapon5': '0.304', 'weapon4': '0.364', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.089', 'weapon2': '2.886', 'weapon3': '3.388'} [2024-08-01 16:14:54,312][00145] DAMAGECOUNT value on done: 345.0 [2024-08-01 16:14:54,313][00145] Sum rewards: 2.751, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.660', 'AMMO2': '0.002', 'AMMO4': '0.012', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.046', 'AMMO3': '0.078', 'WEAPON5': '0.100', 'WEAPON4': '0.300', 'HITCOUNT': '0.310', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.020', 'weapon4': '1.454', 'weapon2': '2.516', 'weapon3': '2.688', 'FRAGCOUNT': '3.000'} [2024-08-01 16:14:56,242][00142] DAMAGECOUNT value on done: 261.0 [2024-08-01 16:14:57,396][00132] DAMAGECOUNT value on done: 428.0 [2024-08-01 16:14:57,402][00132] Sum rewards: -1.808, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.235', 'AMMO4': '-0.088', 'AMMO2': '-0.017', 'AMMO5': '0.005', 'weapon5': '0.010', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'AMMO3': '0.161', 'HITCOUNT': '0.300', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.254', 'weapon3': '2.324', 'FRAGCOUNT': '4.000', 'weapon2': '4.150'} [2024-08-01 16:14:58,109][00137] DAMAGECOUNT value on done: 203.0 [2024-08-01 16:14:58,360][00134] Updated weights for policy 0, policy_version 1541 (0.0025) [2024-08-01 16:14:58,757][00135] DAMAGECOUNT value on done: 457.0 [2024-08-01 16:14:58,761][00135] Sum rewards: -3.023, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.550', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.024', 'WEAPON1': '0.040', 'ARMOR': '0.052', 'weapon4': '0.056', 'AMMO3': '0.090', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'weapon5': '0.422', 'WEAPON5': '0.500', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.756', 'weapon3': '2.238', 'weapon2': '4.050'} [2024-08-01 16:14:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2971.5). Total num frames: 6311936. Throughput: 0: 1469.9. Samples: 3159144. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 16:14:58,840][00034] Avg episode reward: [(0, '-3.225')] [2024-08-01 16:14:58,847][00146] DAMAGECOUNT value on done: 294.0 [2024-08-01 16:14:58,848][00146] Sum rewards: -9.130, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.660', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.013', 'ARMOR': '0.068', 'HITCOUNT': '0.110', 'weapon5': '0.150', 'AMMO3': '0.186', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.450', 'weapon4': '0.754', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.622', 'weapon3': '3.726'} [2024-08-01 16:14:59,145][00141] DAMAGECOUNT value on done: 565.0 [2024-08-01 16:14:59,146][00141] Sum rewards: -1.063, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.016', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO3': '0.186', 'WEAPON5': '0.300', 'weapon5': '0.300', 'HITCOUNT': '0.410', 'ARMOR': '0.461', 'WEAPON3': '1.200', 'DAMAGECOUNT': '1.485', 'weapon2': '3.090', 'FRAGCOUNT': '3.500', 'weapon3': '3.704'} [2024-08-01 16:14:59,350][00143] DAMAGECOUNT value on done: 285.0 [2024-08-01 16:14:59,351][00143] Sum rewards: -2.813, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.574', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'HITCOUNT': '0.070', 'ARMOR': '0.090', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.189', 'DAMAGECOUNT': '0.315', 'weapon4': '0.740', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.408', 'weapon3': '3.794'} [2024-08-01 16:14:59,505][00140] DAMAGECOUNT value on done: 120.0 [2024-08-01 16:14:59,506][00140] Sum rewards: -4.841, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.009', 'AMMO5': '0.010', 'AMMO4': '0.047', 'HITCOUNT': '0.060', 'ARMOR': '0.074', 'weapon5': '0.080', 'weapon7': '0.132', 'AMMO3': '0.138', 'AMMO6': '0.160', 'AMMO7': '0.160', 'DAMAGECOUNT': '0.165', 'WEAPON7': '0.200', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.404', 'WEAPON3': '1.000', 'weapon2': '1.748', 'weapon3': '4.432'} [2024-08-01 16:15:00,142][00144] DAMAGECOUNT value on done: 708.0 [2024-08-01 16:15:00,142][00144] Sum rewards: -0.413, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.305', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.003', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.184', 'weapon5': '0.188', 'weapon4': '0.256', 'DAMAGECOUNT': '0.762', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.782', 'weapon3': '3.626'} [2024-08-01 16:15:00,717][00138] DAMAGECOUNT value on done: 199.0 [2024-08-01 16:15:00,721][00138] Sum rewards: -7.946, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.760', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.005', 'AMMO2': '0.016', 'weapon5': '0.022', 'AMMO4': '0.079', 'WEAPON5': '0.100', 'ARMOR': '0.100', 'HITCOUNT': '0.180', 'AMMO3': '0.225', 'WEAPON4': '0.500', 'DAMAGECOUNT': '0.510', 'WEAPON3': '1.100', 'weapon4': '1.360', 'weapon3': '2.178', 'weapon2': '3.940'} [2024-08-01 16:15:00,928][00133] DAMAGECOUNT value on done: 366.0 [2024-08-01 16:15:00,930][00133] Sum rewards: -2.476, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.790', 'AMMO2': '0.010', 'AMMO5': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.048', 'AMMO4': '0.051', 'HITCOUNT': '0.090', 'weapon5': '0.110', 'AMMO3': '0.114', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.800', 'weapon4': '0.906', 'FRAGCOUNT': '1.000', 'weapon2': '2.652', 'weapon3': '3.358'} [2024-08-01 16:15:01,172][00139] DAMAGECOUNT value on done: 177.0 [2024-08-01 16:15:01,852][00136] DAMAGECOUNT value on done: 291.0 [2024-08-01 16:15:01,855][00136] Sum rewards: -1.724, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.130', 'AMMO5': '0.003', 'AMMO2': '0.009', 'ARMOR': '0.026', 'WEAPON1': '0.040', 'AMMO4': '0.045', 'weapon5': '0.096', 'WEAPON5': '0.100', 'AMMO3': '0.151', 'HITCOUNT': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.340', 'DAMAGECOUNT': '0.795', 'WEAPON3': '1.000', 'FRAGCOUNT': '3.000', 'weapon3': '3.104', 'weapon2': '3.698'} [2024-08-01 16:15:02,891][00145] DAMAGECOUNT value on done: 611.0 [2024-08-01 16:15:02,893][00145] Sum rewards: -1.476, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.490', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'AMMO3': '0.076', 'HITCOUNT': '0.230', 'WEAPON4': '0.300', 'WEAPON3': '0.400', 'ARMOR': '0.454', 'weapon4': '0.704', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.053', 'weapon3': '1.684', 'weapon2': '4.360'} [2024-08-01 16:15:03,541][00148] DAMAGECOUNT value on done: 315.0 [2024-08-01 16:15:03,547][00148] Sum rewards: -1.311, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.020', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.020', 'AMMO2': '0.029', 'ARMOR': '0.032', 'WEAPON1': '0.060', 'AMMO3': '0.084', 'HITCOUNT': '0.120', 'AMMO4': '0.143', 'AMMO6': '0.160', 'AMMO7': '0.160', 'weapon7': '0.188', 'WEAPON7': '0.200', 'weapon5': '0.256', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.555', 'weapon4': '1.012', 'weapon3': '2.486', 'weapon2': '3.004'} [2024-08-01 16:15:03,839][00034] Fps is (10 sec: 3276.6, 60 sec: 2935.4, 300 sec: 2985.2). Total num frames: 6324224. Throughput: 0: 1469.0. Samples: 3168168. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:15:03,841][00034] Avg episode reward: [(0, '-3.294')] [2024-08-01 16:15:04,270][00142] DAMAGECOUNT value on done: 176.0 [2024-08-01 16:15:05,080][00132] DAMAGECOUNT value on done: 270.0 [2024-08-01 16:15:05,081][00132] Sum rewards: -2.101, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.200', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.162', 'WEAPON5': '0.200', 'weapon5': '0.246', 'weapon4': '0.354', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.520', 'weapon2': '3.252'} [2024-08-01 16:15:05,939][00137] DAMAGECOUNT value on done: 295.0 [2024-08-01 16:15:06,664][00146] DAMAGECOUNT value on done: 162.0 [2024-08-01 16:15:07,472][00135] DAMAGECOUNT value on done: 453.0 [2024-08-01 16:15:07,475][00135] Sum rewards: 1.780, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.200', 'AMMO2': '0.002', 'AMMO4': '0.012', 'ARMOR': '0.040', 'AMMO3': '0.132', 'WEAPON4': '0.300', 'HITCOUNT': '0.320', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.197', 'weapon4': '1.272', 'weapon2': '2.870', 'FRAGCOUNT': '3.000', 'weapon3': '3.184'} [2024-08-01 16:15:07,841][00141] DAMAGECOUNT value on done: 398.0 [2024-08-01 16:15:08,044][00140] DAMAGECOUNT value on done: 367.0 [2024-08-01 16:15:08,046][00140] Sum rewards: 0.939, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.865', 'WEAPON1': '0.020', 'AMMO2': '0.025', 'AMMO3': '0.079', 'AMMO4': '0.122', 'HITCOUNT': '0.220', 'WEAPON4': '0.400', 'ARMOR': '0.448', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.660', 'weapon4': '0.992', 'FRAGCOUNT': '1.000', 'weapon3': '2.828', 'weapon2': '3.260'} [2024-08-01 16:15:08,120][00143] DAMAGECOUNT value on done: 256.0 [2024-08-01 16:15:08,633][00138] DAMAGECOUNT value on done: 201.0 [2024-08-01 16:15:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6340608. Throughput: 0: 1477.3. Samples: 3177072. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:15:08,840][00034] Avg episode reward: [(0, '-3.294')] [2024-08-01 16:15:09,140][00139] DAMAGECOUNT value on done: 227.0 [2024-08-01 16:15:09,226][00133] DAMAGECOUNT value on done: 265.0 [2024-08-01 16:15:09,227][00133] Sum rewards: -6.875, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.170', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'weapon5': '0.006', 'AMMO5': '0.010', 'ARMOR': '0.052', 'weapon7': '0.104', 'AMMO6': '0.120', 'AMMO7': '0.120', 'HITCOUNT': '0.140', 'weapon4': '0.184', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'AMMO3': '0.227', 'DAMAGECOUNT': '0.615', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon3': '2.448', 'weapon2': '4.224'} [2024-08-01 16:15:09,728][00136] DAMAGECOUNT value on done: 143.0 [2024-08-01 16:15:09,735][00136] Sum rewards: -2.546, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.420', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.007', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'HITCOUNT': '0.050', 'WEAPON4': '0.100', 'AMMO3': '0.129', 'weapon7': '0.130', 'weapon5': '0.134', 'AMMO6': '0.160', 'AMMO7': '0.160', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.249', 'FRAGCOUNT': '0.500', 'weapon4': '0.518', 'WEAPON3': '0.800', 'weapon3': '2.188', 'weapon2': '3.572'} [2024-08-01 16:15:10,798][00145] DAMAGECOUNT value on done: 349.0 [2024-08-01 16:15:10,804][00145] Sum rewards: 1.836, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.380', 'AMMO2': '0.011', 'AMMO5': '0.019', 'AMMO4': '0.057', 'HITCOUNT': '0.080', 'AMMO3': '0.133', 'weapon5': '0.214', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.342', 'weapon4': '0.570', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.654', 'weapon3': '3.736'} [2024-08-01 16:15:11,257][00148] DAMAGECOUNT value on done: 190.0 [2024-08-01 16:15:11,263][00148] Sum rewards: -4.827, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.009', 'weapon5': '0.026', 'WEAPON5': '0.100', 'AMMO3': '0.119', 'HITCOUNT': '0.120', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.132', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.420', 'ARMOR': '0.495', 'WEAPON3': '0.600', 'weapon3': '2.542', 'weapon2': '4.282'} [2024-08-01 16:15:12,404][00134] Updated weights for policy 0, policy_version 1551 (0.0023) [2024-08-01 16:15:12,559][00142] DAMAGECOUNT value on done: 329.0 [2024-08-01 16:15:12,884][00132] DAMAGECOUNT value on done: 250.0 [2024-08-01 16:15:12,886][00132] Sum rewards: -7.582, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.500', 'FRAGCOUNT': '-1.000', 'AMMO2': '0.008', 'AMMO5': '0.024', 'ARMOR': '0.032', 'AMMO4': '0.039', 'HITCOUNT': '0.130', 'AMMO3': '0.153', 'weapon5': '0.276', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.900', 'weapon2': '2.936', 'weapon3': '3.760'} [2024-08-01 16:15:13,838][00034] Fps is (10 sec: 3277.0, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6356992. Throughput: 0: 1484.0. Samples: 3181704. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:15:13,840][00034] Avg episode reward: [(0, '-3.376')] [2024-08-01 16:15:14,688][00137] DAMAGECOUNT value on done: 137.0 [2024-08-01 16:15:14,691][00137] Sum rewards: -4.511, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO5': '0.005', 'weapon5': '0.014', 'AMMO2': '0.018', 'HITCOUNT': '0.070', 'AMMO4': '0.087', 'ARMOR': '0.088', 'WEAPON5': '0.100', 'AMMO3': '0.173', 'DAMAGECOUNT': '0.246', 'WEAPON4': '0.300', 'weapon4': '0.450', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '3.006', 'weapon2': '3.692'} [2024-08-01 16:15:15,468][00146] DAMAGECOUNT value on done: 134.0 [2024-08-01 16:15:15,473][00146] Sum rewards: -4.620, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.290', 'AMMO2': '0.003', 'AMMO4': '0.014', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.028', 'ARMOR': '0.040', 'HITCOUNT': '0.050', 'DAMAGECOUNT': '0.117', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.418', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.992', 'weapon3': '3.710'} [2024-08-01 16:15:15,740][00135] DAMAGECOUNT value on done: 173.0 [2024-08-01 16:15:15,741][00135] Sum rewards: -7.133, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.178', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.288', 'weapon5': '0.296', 'weapon4': '0.390', 'WEAPON3': '1.100', 'weapon3': '2.906', 'weapon2': '3.424'} [2024-08-01 16:15:15,935][00140] DAMAGECOUNT value on done: 125.0 [2024-08-01 16:15:16,430][00143] DAMAGECOUNT value on done: 567.0 [2024-08-01 16:15:16,433][00143] Sum rewards: -0.007, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'AMMO2': '0.033', 'ARMOR': '0.044', 'AMMO3': '0.148', 'AMMO4': '0.165', 'HITCOUNT': '0.210', 'weapon5': '0.212', 'WEAPON5': '0.400', 'WEAPON4': '0.500', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.500', 'DAMAGECOUNT': '1.626', 'weapon2': '1.694', 'weapon4': '1.718', 'weapon3': '3.346'} [2024-08-01 16:15:16,856][00138] DAMAGECOUNT value on done: 630.0 [2024-08-01 16:15:16,862][00138] Sum rewards: -3.307, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.010', 'weapon4': '0.040', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.155', 'WEAPON5': '0.200', 'weapon5': '0.322', 'DAMAGECOUNT': '0.855', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '3.014', 'weapon2': '3.692'} [2024-08-01 16:15:17,493][00139] DAMAGECOUNT value on done: 184.0 [2024-08-01 16:15:17,777][00133] DAMAGECOUNT value on done: 361.0 [2024-08-01 16:15:17,780][00133] Sum rewards: -3.753, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.395', 'AMMO4': '-0.045', 'AMMO2': '-0.009', 'ARMOR': '0.068', 'WEAPON4': '0.100', 'weapon4': '0.122', 'AMMO3': '0.167', 'HITCOUNT': '0.170', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'DAMAGECOUNT': '0.585', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '3.508', 'weapon2': '3.876'} [2024-08-01 16:15:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 6365184. Throughput: 0: 1478.7. Samples: 3190620. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:15:18,841][00034] Avg episode reward: [(0, '-3.592')] [2024-08-01 16:15:19,584][00145] DAMAGECOUNT value on done: 385.0 [2024-08-01 16:15:19,587][00145] Sum rewards: 1.196, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.528', 'AMMO5': '0.005', 'ARMOR': '0.008', 'AMMO2': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.040', 'WEAPON5': '0.100', 'weapon5': '0.104', 'AMMO6': '0.160', 'AMMO7': '0.160', 'AMMO3': '0.176', 'weapon7': '0.198', 'WEAPON7': '0.200', 'HITCOUNT': '0.210', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.795', 'WEAPON3': '0.900', 'weapon4': '1.032', 'weapon2': '2.506', 'FRAGCOUNT': '3.000', 'weapon3': '3.052'} [2024-08-01 16:15:20,716][00142] DAMAGECOUNT value on done: 676.0 [2024-08-01 16:15:20,717][00142] Sum rewards: -6.821, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO5': '0.007', 'AMMO2': '0.018', 'WEAPON1': '0.020', 'ARMOR': '0.076', 'AMMO4': '0.090', 'HITCOUNT': '0.090', 'AMMO3': '0.091', 'WEAPON5': '0.200', 'weapon5': '0.214', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon4': '1.202', 'weapon3': '2.044', 'weapon2': '3.652'} [2024-08-01 16:15:21,738][00132] DAMAGECOUNT value on done: 130.0 [2024-08-01 16:15:21,741][00132] Sum rewards: -2.980, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.500', 'AMMO2': '0.004', 'AMMO5': '0.006', 'AMMO4': '0.018', 'HITCOUNT': '0.090', 'AMMO3': '0.092', 'ARMOR': '0.094', 'WEAPON5': '0.200', 'weapon5': '0.216', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.300', 'WEAPON3': '0.500', 'weapon4': '0.510', 'FRAGCOUNT': '1.000', 'weapon3': '1.950', 'weapon2': '4.240'} [2024-08-01 16:15:22,754][00137] DAMAGECOUNT value on done: 559.0 [2024-08-01 16:15:22,757][00137] Sum rewards: 0.499, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.445', 'AMMO5': '0.005', 'AMMO2': '0.009', 'AMMO4': '0.046', 'WEAPON5': '0.100', 'weapon5': '0.102', 'AMMO3': '0.146', 'HITCOUNT': '0.220', 'WEAPON4': '0.300', 'ARMOR': '0.517', 'DAMAGECOUNT': '0.543', 'weapon4': '0.656', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.810', 'weapon3': '3.740'} [2024-08-01 16:15:23,677][00146] DAMAGECOUNT value on done: 70.0 [2024-08-01 16:15:23,813][00140] DAMAGECOUNT value on done: 421.0 [2024-08-01 16:15:23,819][00140] Sum rewards: -3.674, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.000', 'AMMO4': '-0.052', 'AMMO2': '-0.010', 'AMMO5': '0.029', 'WEAPON4': '0.100', 'AMMO3': '0.131', 'weapon4': '0.176', 'weapon5': '0.192', 'HITCOUNT': '0.220', 'WEAPON5': '0.400', 'ARMOR': '0.480', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.903', 'weapon3': '2.380', 'weapon2': '4.028'} [2024-08-01 16:15:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6385664. Throughput: 0: 1488.5. Samples: 3199764. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:15:23,840][00034] Avg episode reward: [(0, '-3.469')] [2024-08-01 16:15:24,341][00143] DAMAGECOUNT value on done: 309.0 [2024-08-01 16:15:24,347][00143] Sum rewards: -0.782, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.165', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.137', 'weapon5': '0.248', 'WEAPON5': '0.300', 'weapon4': '0.350', 'DAMAGECOUNT': '0.378', 'ARMOR': '0.479', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.214', 'weapon3': '3.650'} [2024-08-01 16:15:25,227][00138] DAMAGECOUNT value on done: 170.0 [2024-08-01 16:15:25,231][00138] Sum rewards: -3.305, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO2': '0.002', 'AMMO4': '0.012', 'AMMO5': '0.020', 'ARMOR': '0.035', 'WEAPON1': '0.040', 'weapon5': '0.106', 'HITCOUNT': '0.130', 'AMMO3': '0.143', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.315', 'WEAPON3': '0.900', 'weapon4': '0.962', 'FRAGCOUNT': '1.000', 'weapon2': '2.012', 'weapon3': '3.078'} [2024-08-01 16:15:25,700][00139] DAMAGECOUNT value on done: 327.0 [2024-08-01 16:15:25,708][00139] Sum rewards: -2.237, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'weapon4': '0.120', 'AMMO3': '0.128', 'HITCOUNT': '0.140', 'WEAPON5': '0.300', 'weapon5': '0.380', 'DAMAGECOUNT': '0.639', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.222', 'weapon2': '4.532'} [2024-08-01 16:15:26,949][00133] DAMAGECOUNT value on done: 508.0 [2024-08-01 16:15:26,954][00133] Sum rewards: 1.527, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO2': '0.002', 'ARMOR': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.012', 'AMMO3': '0.107', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.268', 'weapon4': '0.624', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.209', 'weapon3': '2.418', 'FRAGCOUNT': '3.000', 'weapon2': '4.058'} [2024-08-01 16:15:27,731][00134] Updated weights for policy 0, policy_version 1561 (0.0020) [2024-08-01 16:15:27,744][00145] DAMAGECOUNT value on done: 569.0 [2024-08-01 16:15:27,745][00145] Sum rewards: -0.632, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.500', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.162', 'HITCOUNT': '0.190', 'weapon5': '0.298', 'WEAPON5': '0.300', 'weapon4': '0.500', 'DAMAGECOUNT': '0.891', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.130', 'weapon3': '4.158'} [2024-08-01 16:15:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 6397952. Throughput: 0: 1487.5. Samples: 3204228. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:15:28,840][00034] Avg episode reward: [(0, '-3.323')] [2024-08-01 16:15:30,265][00132] DAMAGECOUNT value on done: 285.0 [2024-08-01 16:15:30,266][00132] Sum rewards: 0.758, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.840', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'ARMOR': '0.004', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.146', 'HITCOUNT': '0.150', 'WEAPON7': '0.200', 'weapon7': '0.234', 'DAMAGECOUNT': '0.738', 'weapon4': '0.786', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.118', 'weapon2': '2.842'} [2024-08-01 16:15:30,497][00142] DAMAGECOUNT value on done: 419.0 [2024-08-01 16:15:30,501][00142] Sum rewards: -9.537, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.370', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO2': '0.020', 'ARMOR': '0.040', 'AMMO4': '0.100', 'AMMO3': '0.176', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'weapon5': '0.206', 'WEAPON4': '0.300', 'weapon4': '0.480', 'DAMAGECOUNT': '0.837', 'WEAPON3': '0.900', 'weapon3': '3.098', 'weapon2': '3.268'} [2024-08-01 16:15:32,352][00137] DAMAGECOUNT value on done: 108.0 [2024-08-01 16:15:32,709][00143] DAMAGECOUNT value on done: 431.0 [2024-08-01 16:15:32,715][00143] Sum rewards: -4.270, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.585', 'FRAGCOUNT': '-1.500', 'AMMO5': '0.003', 'AMMO2': '0.015', 'ARMOR': '0.016', 'AMMO4': '0.077', 'WEAPON5': '0.100', 'AMMO3': '0.130', 'weapon5': '0.172', 'HITCOUNT': '0.210', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.708', 'weapon4': '0.794', 'WEAPON3': '0.900', 'weapon2': '3.130', 'weapon3': '3.160'} [2024-08-01 16:15:32,988][00146] DAMAGECOUNT value on done: 510.0 [2024-08-01 16:15:32,991][00146] Sum rewards: -0.320, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.038', 'AMMO2': '-0.008', 'AMMO5': '0.010', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.109', 'HITCOUNT': '0.150', 'weapon5': '0.192', 'WEAPON5': '0.200', 'weapon4': '0.436', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.885', 'FRAGCOUNT': '1.000', 'weapon2': '2.688', 'weapon3': '3.576'} [2024-08-01 16:15:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6414336. Throughput: 0: 1475.7. Samples: 3212556. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:15:33,840][00034] Avg episode reward: [(0, '-3.257')] [2024-08-01 16:15:34,564][00138] DAMAGECOUNT value on done: 164.0 [2024-08-01 16:15:34,571][00138] Sum rewards: 0.068, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.296', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'weapon5': '0.004', 'AMMO5': '0.010', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.144', 'DAMAGECOUNT': '0.330', 'weapon4': '0.352', 'ARMOR': '0.464', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '1.982', 'weapon3': '2.976'} [2024-08-01 16:15:34,996][00139] DAMAGECOUNT value on done: 170.0 [2024-08-01 16:15:35,000][00139] Sum rewards: -3.970, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.115', 'AMMO2': '0.004', 'AMMO5': '0.015', 'AMMO4': '0.020', 'WEAPON1': '0.040', 'HITCOUNT': '0.090', 'weapon5': '0.096', 'AMMO3': '0.169', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.240', 'WEAPON5': '0.300', 'weapon4': '0.332', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.908', 'weapon3': '3.682'} [2024-08-01 16:15:35,730][00133] DAMAGECOUNT value on done: 70.0 [2024-08-01 16:15:35,731][00133] Sum rewards: -2.372, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.530', 'AMMO2': '0.004', 'AMMO5': '0.010', 'AMMO4': '0.018', 'weapon5': '0.026', 'HITCOUNT': '0.030', 'AMMO3': '0.072', 'ARMOR': '0.116', 'DAMAGECOUNT': '0.150', 'WEAPON5': '0.200', 'WEAPON4': '0.400', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon4': '1.546', 'weapon3': '1.906', 'weapon2': '3.430'} [2024-08-01 16:15:36,800][00145] DAMAGECOUNT value on done: 266.0 [2024-08-01 16:15:36,807][00145] Sum rewards: -3.981, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.185', 'AMMO5': '0.007', 'ARMOR': '0.008', 'AMMO2': '0.015', 'AMMO4': '0.077', 'weapon5': '0.098', 'HITCOUNT': '0.120', 'AMMO3': '0.173', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.405', 'weapon4': '0.650', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '3.160', 'weapon2': '3.590'} [2024-08-01 16:15:38,356][00142] DAMAGECOUNT value on done: 212.0 [2024-08-01 16:15:38,358][00142] Sum rewards: -1.985, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.270', 'AMMO5': '0.005', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.036', 'AMMO4': '0.073', 'AMMO3': '0.090', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'ARMOR': '0.116', 'HITCOUNT': '0.130', 'weapon4': '0.134', 'DAMAGECOUNT': '0.486', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '3.094', 'weapon3': '3.436'} [2024-08-01 16:15:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6430720. Throughput: 0: 1471.5. Samples: 3221448. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:15:38,843][00034] Avg episode reward: [(0, '-3.140')] [2024-08-01 16:15:39,148][00132] DAMAGECOUNT value on done: 505.0 [2024-08-01 16:15:39,149][00132] Sum rewards: 1.042, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.518', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.013', 'ARMOR': '0.032', 'weapon4': '0.056', 'WEAPON4': '0.100', 'AMMO3': '0.143', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.238', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.930', 'FRAGCOUNT': '3.000', 'weapon2': '3.232', 'weapon3': '3.792'} [2024-08-01 16:15:39,626][00134] Updated weights for policy 0, policy_version 1571 (0.0021) [2024-08-01 16:15:40,308][00137] DAMAGECOUNT value on done: 443.0 [2024-08-01 16:15:40,309][00137] Sum rewards: -2.013, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO2': '0.018', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'weapon5': '0.058', 'ARMOR': '0.068', 'AMMO4': '0.088', 'AMMO3': '0.124', 'HITCOUNT': '0.190', 'WEAPON5': '0.300', 'WEAPON4': '0.400', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.759', 'weapon4': '1.110', 'FRAGCOUNT': '1.500', 'weapon3': '2.364', 'weapon2': '3.878'} [2024-08-01 16:15:40,893][00146] DAMAGECOUNT value on done: 108.0 [2024-08-01 16:15:43,689][00133] DAMAGECOUNT value on done: 676.0 [2024-08-01 16:15:43,696][00133] Sum rewards: -2.452, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.018', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'weapon5': '0.158', 'AMMO3': '0.159', 'weapon4': '0.218', 'HITCOUNT': '0.290', 'WEAPON5': '0.300', 'FRAGCOUNT': '0.500', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.530', 'weapon2': '2.588', 'weapon3': '4.214'} [2024-08-01 16:15:43,828][00138] DAMAGECOUNT value on done: 215.0 [2024-08-01 16:15:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2971.3). Total num frames: 6438912. Throughput: 0: 1485.1. Samples: 3225972. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:15:43,842][00034] Avg episode reward: [(0, '-3.057')] [2024-08-01 16:15:44,133][00139] DAMAGECOUNT value on done: 794.0 [2024-08-01 16:15:44,135][00139] Sum rewards: 4.174, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO2': '0.008', 'WEAPON1': '0.020', 'AMMO5': '0.025', 'AMMO4': '0.040', 'ARMOR': '0.048', 'weapon5': '0.068', 'AMMO3': '0.166', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'HITCOUNT': '0.470', 'weapon4': '0.608', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.845', 'weapon2': '3.100', 'weapon3': '3.646', 'FRAGCOUNT': '4.000'} [2024-08-01 16:15:45,985][00145] DAMAGECOUNT value on done: 322.0 [2024-08-01 16:15:45,991][00145] Sum rewards: 3.589, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-1.980', 'AMMO2': '0.006', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.028', 'AMMO3': '0.034', 'WEAPON4': '0.100', 'HITCOUNT': '0.170', 'weapon5': '0.230', 'weapon4': '0.238', 'WEAPON3': '0.300', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.861', 'weapon3': '1.998', 'FRAGCOUNT': '2.000', 'weapon2': '4.522'} [2024-08-01 16:15:46,892][00142] DAMAGECOUNT value on done: 288.0 [2024-08-01 16:15:46,893][00142] Sum rewards: -0.417, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.930', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'weapon7': '0.002', 'AMMO5': '0.004', 'weapon4': '0.012', 'ARMOR': '0.024', 'weapon5': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.123', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.220', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.849', 'weapon2': '2.676', 'weapon3': '3.926'} [2024-08-01 16:15:47,796][00132] DAMAGECOUNT value on done: 306.0 [2024-08-01 16:15:47,805][00132] Sum rewards: -0.852, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'AMMO2': '0.004', 'WEAPON1': '0.020', 'AMMO4': '0.021', 'AMMO5': '0.022', 'AMMO3': '0.088', 'HITCOUNT': '0.200', 'WEAPON4': '0.200', 'WEAPON5': '0.500', 'weapon5': '0.522', 'WEAPON3': '0.600', 'weapon4': '0.674', 'DAMAGECOUNT': '0.798', 'weapon3': '2.512', 'FRAGCOUNT': '3.000', 'weapon2': '3.616'} [2024-08-01 16:15:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6459392. Throughput: 0: 1483.0. Samples: 3234900. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:15:48,840][00034] Avg episode reward: [(0, '-2.863')] [2024-08-01 16:15:48,922][00137] DAMAGECOUNT value on done: 329.0 [2024-08-01 16:15:48,928][00137] Sum rewards: -2.355, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.041', 'AMMO2': '-0.008', 'AMMO5': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.148', 'HITCOUNT': '0.150', 'weapon4': '0.172', 'WEAPON5': '0.400', 'weapon5': '0.492', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.837', 'FRAGCOUNT': '1.000', 'weapon3': '2.328', 'weapon2': '3.764'} [2024-08-01 16:15:49,509][00146] DAMAGECOUNT value on done: 362.0 [2024-08-01 16:15:49,514][00146] Sum rewards: -3.187, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.700', 'AMMO2': '0.016', 'AMMO5': '0.017', 'ARMOR': '0.028', 'AMMO4': '0.078', 'weapon4': '0.092', 'HITCOUNT': '0.180', 'AMMO3': '0.181', 'WEAPON4': '0.200', 'weapon5': '0.230', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.771', 'WEAPON3': '1.100', 'FRAGCOUNT': '3.000', 'weapon2': '3.142', 'weapon3': '4.078'} [2024-08-01 16:15:51,406][00138] DAMAGECOUNT value on done: 445.0 [2024-08-01 16:15:51,410][00138] Sum rewards: 0.041, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.190', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.005', 'weapon5': '0.056', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.159', 'weapon4': '0.248', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '0.870', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.060', 'weapon3': '4.610'} [2024-08-01 16:15:52,300][00133] DAMAGECOUNT value on done: 612.0 [2024-08-01 16:15:52,303][00133] Sum rewards: -2.504, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-4.125', 'AMMO5': '0.022', 'AMMO2': '0.030', 'HITCOUNT': '0.060', 'AMMO3': '0.143', 'AMMO4': '0.148', 'weapon5': '0.166', 'WEAPON5': '0.400', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.471', 'ARMOR': '0.482', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon4': '1.568', 'weapon2': '2.746', 'weapon3': '2.834'} [2024-08-01 16:15:53,749][00134] Updated weights for policy 0, policy_version 1581 (0.0021) [2024-08-01 16:15:53,839][00034] Fps is (10 sec: 3686.3, 60 sec: 3072.0, 300 sec: 2985.2). Total num frames: 6475776. Throughput: 0: 1482.7. Samples: 3243792. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:15:53,840][00034] Avg episode reward: [(0, '-2.669')] [2024-08-01 16:15:54,433][00145] DAMAGECOUNT value on done: 380.0 [2024-08-01 16:15:54,434][00145] Sum rewards: 2.277, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.320', 'AMMO2': '0.007', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'AMMO4': '0.037', 'weapon5': '0.056', 'AMMO3': '0.077', 'WEAPON5': '0.100', 'weapon7': '0.106', 'HITCOUNT': '0.120', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.468', 'WEAPON3': '0.600', 'weapon4': '0.754', 'FRAGCOUNT': '2.000', 'weapon2': '2.588', 'weapon3': '3.014'} [2024-08-01 16:15:54,798][00142] DAMAGECOUNT value on done: 309.0 [2024-08-01 16:15:54,803][00142] Sum rewards: -6.273, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.340', 'AMMO5': '0.010', 'AMMO2': '0.018', 'weapon5': '0.018', 'ARMOR': '0.024', 'AMMO4': '0.087', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.136', 'HITCOUNT': '0.170', 'AMMO3': '0.264', 'DAMAGECOUNT': '0.672', 'WEAPON3': '1.600', 'FRAGCOUNT': '2.000', 'weapon2': '2.564', 'weapon3': '4.804'} [2024-08-01 16:15:56,705][00137] DAMAGECOUNT value on done: 424.0 [2024-08-01 16:15:56,715][00137] Sum rewards: -2.041, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.136', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.009', 'weapon5': '0.044', 'HITCOUNT': '0.080', 'WEAPON5': '0.100', 'AMMO3': '0.122', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.387', 'ARMOR': '0.553', 'WEAPON3': '0.800', 'weapon4': '1.308', 'weapon3': '2.620', 'weapon2': '2.770'} [2024-08-01 16:15:57,341][00146] DAMAGECOUNT value on done: 420.0 [2024-08-01 16:15:57,344][00146] Sum rewards: -7.057, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.051', 'AMMO2': '-0.010', 'AMMO5': '0.006', 'WEAPON1': '0.020', 'weapon4': '0.096', 'WEAPON4': '0.100', 'HITCOUNT': '0.100', 'AMMO3': '0.177', 'weapon5': '0.192', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.900', 'weapon3': '2.678', 'weapon2': '4.250'} [2024-08-01 16:15:58,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2867.2, 300 sec: 2971.3). Total num frames: 6483968. Throughput: 0: 1480.0. Samples: 3248304. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:15:58,843][00034] Avg episode reward: [(0, '-2.636')] [2024-08-01 16:16:00,868][00133] DAMAGECOUNT value on done: 277.0 [2024-08-01 16:16:00,872][00133] Sum rewards: -0.946, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.737', 'AMMO2': '0.006', 'AMMO4': '0.032', 'ARMOR': '0.072', 'HITCOUNT': '0.120', 'AMMO3': '0.205', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.480', 'weapon4': '0.672', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '3.350', 'weapon2': '3.454'} [2024-08-01 16:16:01,628][00138] DAMAGECOUNT value on done: 415.0 [2024-08-01 16:16:01,631][00138] Sum rewards: -2.340, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.630', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'ARMOR': '0.020', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.140', 'HITCOUNT': '0.190', 'weapon4': '0.218', 'DAMAGECOUNT': '0.747', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.606', 'weapon3': '4.252'} [2024-08-01 16:16:03,439][00142] DAMAGECOUNT value on done: 135.0 [2024-08-01 16:16:03,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.8, 300 sec: 2971.3). Total num frames: 6504448. Throughput: 0: 1462.9. Samples: 3256452. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:16:03,841][00034] Avg episode reward: [(0, '-2.664')] [2024-08-01 16:16:05,430][00137] DAMAGECOUNT value on done: 531.0 [2024-08-01 16:16:05,433][00137] Sum rewards: -11.496, reward structure: {'DEATHCOUNT': '-15.000', 'HEALTH': '-5.980', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.004', 'weapon7': '0.010', 'AMMO5': '0.016', 'AMMO4': '0.020', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'AMMO3': '0.226', 'weapon5': '0.394', 'WEAPON5': '0.400', 'ARMOR': '0.456', 'weapon4': '0.460', 'DAMAGECOUNT': '0.510', 'WEAPON3': '1.300', 'weapon2': '2.798', 'weapon3': '3.530'} [2024-08-01 16:16:06,007][00146] DAMAGECOUNT value on done: 187.0 [2024-08-01 16:16:08,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2867.2, 300 sec: 2971.3). Total num frames: 6512640. Throughput: 0: 1456.8. Samples: 3265320. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:16:08,840][00034] Avg episode reward: [(0, '-2.878')] [2024-08-01 16:16:08,851][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001590_6512640.pth... [2024-08-01 16:16:09,033][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001417_5804032.pth [2024-08-01 16:16:09,146][00134] Updated weights for policy 0, policy_version 1591 (0.0020) [2024-08-01 16:16:09,167][00133] DAMAGECOUNT value on done: 212.0 [2024-08-01 16:16:09,168][00133] Sum rewards: -4.068, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.015', 'AMMO2': '0.015', 'weapon5': '0.054', 'AMMO4': '0.075', 'ARMOR': '0.096', 'AMMO3': '0.131', 'HITCOUNT': '0.150', 'WEAPON5': '0.300', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.800', 'weapon4': '0.960', 'FRAGCOUNT': '1.000', 'weapon2': '2.810', 'weapon3': '3.220'} [2024-08-01 16:16:11,426][00142] DAMAGECOUNT value on done: 433.0 [2024-08-01 16:16:11,427][00142] Sum rewards: 1.944, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.680', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'weapon5': '0.026', 'AMMO3': '0.100', 'HITCOUNT': '0.140', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'ARMOR': '0.553', 'DAMAGECOUNT': '0.585', 'WEAPON3': '0.700', 'weapon4': '0.700', 'FRAGCOUNT': '2.000', 'weapon2': '2.888', 'weapon3': '3.286'} [2024-08-01 16:16:13,504][00137] DAMAGECOUNT value on done: 160.0 [2024-08-01 16:16:13,507][00137] Sum rewards: -2.936, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'AMMO5': '0.010', 'HITCOUNT': '0.070', 'WEAPON4': '0.100', 'AMMO3': '0.164', 'DAMAGECOUNT': '0.195', 'WEAPON5': '0.200', 'weapon5': '0.312', 'weapon4': '0.324', 'ARMOR': '0.453', 'WEAPON3': '0.800', 'weapon3': '2.550', 'weapon2': '3.982'} [2024-08-01 16:16:13,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 6529024. Throughput: 0: 1456.0. Samples: 3269748. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:16:13,842][00034] Avg episode reward: [(0, '-2.795')] [2024-08-01 16:16:14,040][00146] DAMAGECOUNT value on done: 267.0 [2024-08-01 16:16:14,049][00146] Sum rewards: -6.753, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.420', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.013', 'AMMO2': '0.020', 'ARMOR': '0.044', 'AMMO4': '0.097', 'AMMO3': '0.132', 'HITCOUNT': '0.160', 'weapon5': '0.196', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon4': '0.392', 'DAMAGECOUNT': '0.606', 'WEAPON3': '0.700', 'weapon2': '3.204', 'weapon3': '3.354'} [2024-08-01 16:16:17,069][00133] DAMAGECOUNT value on done: 700.0 [2024-08-01 16:16:17,072][00133] Sum rewards: 2.734, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.184', 'AMMO5': '0.003', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'AMMO4': '0.023', 'ARMOR': '0.054', 'weapon4': '0.088', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.134', 'AMMO3': '0.177', 'HITCOUNT': '0.270', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.725', 'FRAGCOUNT': '3.000', 'weapon2': '3.378', 'weapon3': '3.992'} [2024-08-01 16:16:18,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 2985.2). Total num frames: 6549504. Throughput: 0: 1476.0. Samples: 3278976. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:16:18,840][00034] Avg episode reward: [(0, '-2.745')] [2024-08-01 16:16:19,640][00142] DAMAGECOUNT value on done: 154.0 [2024-08-01 16:16:19,641][00142] Sum rewards: -6.353, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.007', 'HITCOUNT': '0.020', 'DAMAGECOUNT': '0.030', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'AMMO3': '0.146', 'WEAPON5': '0.200', 'weapon5': '0.346', 'weapon4': '0.376', 'WEAPON3': '0.900', 'weapon2': '3.132', 'weapon3': '3.462'} [2024-08-01 16:16:21,899][00137] DAMAGECOUNT value on done: 346.0 [2024-08-01 16:16:21,904][00137] Sum rewards: -0.709, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'ARMOR': '0.005', 'AMMO5': '0.010', 'weapon5': '0.016', 'weapon4': '0.054', 'WEAPON4': '0.100', 'AMMO3': '0.188', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.630', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.576', 'weapon3': '4.766'} [2024-08-01 16:16:22,102][00134] Updated weights for policy 0, policy_version 1601 (0.0021) [2024-08-01 16:16:22,473][00146] DAMAGECOUNT value on done: 471.0 [2024-08-01 16:16:22,476][00146] Sum rewards: 0.522, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO4': '-0.013', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.056', 'WEAPON5': '0.100', 'weapon5': '0.116', 'HITCOUNT': '0.140', 'AMMO3': '0.162', 'DAMAGECOUNT': '0.465', 'WEAPON3': '1.000', 'weapon2': '2.864', 'FRAGCOUNT': '3.000', 'weapon3': '4.140'} [2024-08-01 16:16:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2971.3). Total num frames: 6557696. Throughput: 0: 1477.9. Samples: 3287952. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:16:23,843][00034] Avg episode reward: [(0, '-2.757')] [2024-08-01 16:16:25,518][00133] DAMAGECOUNT value on done: 391.0 [2024-08-01 16:16:25,523][00133] Sum rewards: -1.355, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.375', 'AMMO5': '0.010', 'weapon5': '0.018', 'ARMOR': '0.032', 'AMMO2': '0.032', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'AMMO3': '0.155', 'AMMO4': '0.161', 'WEAPON5': '0.200', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.405', 'weapon4': '0.516', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '2.916', 'weapon3': '3.504'} [2024-08-01 16:16:27,555][00142] DAMAGECOUNT value on done: 350.0 [2024-08-01 16:16:27,559][00142] Sum rewards: -1.450, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO2': '0.012', 'AMMO5': '0.015', 'ARMOR': '0.036', 'AMMO4': '0.061', 'HITCOUNT': '0.080', 'AMMO3': '0.169', 'weapon5': '0.266', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon4': '0.382', 'DAMAGECOUNT': '0.639', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.094', 'weapon3': '3.706'} [2024-08-01 16:16:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2971.3). Total num frames: 6578176. Throughput: 0: 1479.2. Samples: 3292536. Policy #0 lag: (min: 0.0, avg: 3.8, max: 6.0) [2024-08-01 16:16:28,841][00034] Avg episode reward: [(0, '-2.696')] [2024-08-01 16:16:29,676][00137] DAMAGECOUNT value on done: 379.0 [2024-08-01 16:16:29,679][00137] Sum rewards: -0.701, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.910', 'AMMO2': '0.005', 'AMMO5': '0.012', 'AMMO4': '0.024', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.121', 'weapon4': '0.146', 'HITCOUNT': '0.210', 'weapon5': '0.272', 'WEAPON5': '0.300', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.795', 'FRAGCOUNT': '1.000', 'weapon3': '2.848', 'weapon2': '3.136'} [2024-08-01 16:16:30,231][00146] DAMAGECOUNT value on done: 150.0 [2024-08-01 16:16:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 6590464. Throughput: 0: 1480.5. Samples: 3301524. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:16:33,840][00034] Avg episode reward: [(0, '-2.707')] [2024-08-01 16:16:34,043][00133] DAMAGECOUNT value on done: 290.0 [2024-08-01 16:16:34,044][00133] Sum rewards: -5.865, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'AMMO5': '0.005', 'AMMO2': '0.014', 'AMMO4': '0.068', 'AMMO3': '0.165', 'HITCOUNT': '0.190', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.765', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon4': '1.026', 'weapon2': '2.796', 'weapon3': '3.626'} [2024-08-01 16:16:35,036][00134] Updated weights for policy 0, policy_version 1611 (0.0020) [2024-08-01 16:16:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6606848. Throughput: 0: 1478.7. Samples: 3310332. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:16:38,840][00034] Avg episode reward: [(0, '-2.684')] [2024-08-01 16:16:42,041][00133] DAMAGECOUNT value on done: 148.0 [2024-08-01 16:16:42,048][00133] Sum rewards: -5.548, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.497', 'AMMO2': '0.002', 'AMMO4': '0.008', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.056', 'HITCOUNT': '0.070', 'DAMAGECOUNT': '0.159', 'AMMO3': '0.182', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon5': '0.318', 'weapon4': '0.720', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.098', 'weapon3': '3.952'} [2024-08-01 16:16:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2971.3). Total num frames: 6623232. Throughput: 0: 1482.1. Samples: 3315000. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:16:43,840][00034] Avg episode reward: [(0, '-2.723')] [2024-08-01 16:16:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6635520. Throughput: 0: 1509.9. Samples: 3324396. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:16:48,840][00034] Avg episode reward: [(0, '-2.723')] [2024-08-01 16:16:49,373][00134] Updated weights for policy 0, policy_version 1621 (0.0019) [2024-08-01 16:16:49,838][00133] DAMAGECOUNT value on done: 201.0 [2024-08-01 16:16:49,841][00133] Sum rewards: -1.538, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.290', 'AMMO5': '0.008', 'AMMO2': '0.027', 'WEAPON1': '0.040', 'HITCOUNT': '0.080', 'AMMO3': '0.106', 'AMMO4': '0.133', 'weapon5': '0.168', 'WEAPON5': '0.200', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.450', 'WEAPON3': '0.600', 'weapon4': '0.696', 'FRAGCOUNT': '1.000', 'weapon3': '2.634', 'weapon2': '3.460'} [2024-08-01 16:16:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 6651904. Throughput: 0: 1519.2. Samples: 3333684. Policy #0 lag: (min: 0.0, avg: 3.9, max: 8.0) [2024-08-01 16:16:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:16:58,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2999.1). Total num frames: 6672384. Throughput: 0: 1526.7. Samples: 3338448. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:16:58,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:02,413][00134] Updated weights for policy 0, policy_version 1631 (0.0019) [2024-08-01 16:17:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6684672. Throughput: 0: 1530.4. Samples: 3347844. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:17:03,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:08,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3072.0, 300 sec: 2971.3). Total num frames: 6696960. Throughput: 0: 1522.4. Samples: 3356460. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:17:08,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2985.2). Total num frames: 6713344. Throughput: 0: 1526.1. Samples: 3361212. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:17:13,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:15,242][00134] Updated weights for policy 0, policy_version 1641 (0.0028) [2024-08-01 16:17:18,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6729728. Throughput: 0: 1532.8. Samples: 3370500. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:17:18,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 2999.1). Total num frames: 6746112. Throughput: 0: 1542.1. Samples: 3379728. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:17:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:28,479][00132] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:17:28,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6758400. Throughput: 0: 1543.7. Samples: 3384468. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:17:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:29,237][00134] Updated weights for policy 0, policy_version 1651 (0.0019) [2024-08-01 16:17:33,839][00034] Fps is (10 sec: 2866.9, 60 sec: 3072.0, 300 sec: 2985.2). Total num frames: 6774784. Throughput: 0: 1543.2. Samples: 3393840. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:17:33,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:38,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2985.2). Total num frames: 6791168. Throughput: 0: 1528.3. Samples: 3402456. Policy #0 lag: (min: 0.0, avg: 2.3, max: 6.0) [2024-08-01 16:17:38,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:42,947][00134] Updated weights for policy 0, policy_version 1661 (0.0041) [2024-08-01 16:17:43,839][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 2985.2). Total num frames: 6803456. Throughput: 0: 1525.3. Samples: 3407088. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:17:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:48,841][00034] Fps is (10 sec: 3275.9, 60 sec: 3140.1, 300 sec: 2999.1). Total num frames: 6823936. Throughput: 0: 1523.1. Samples: 3416388. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:17:48,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:53,840][00034] Fps is (10 sec: 3685.7, 60 sec: 3140.2, 300 sec: 2999.1). Total num frames: 6840320. Throughput: 0: 1539.9. Samples: 3425760. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:17:53,845][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:17:54,707][00134] Updated weights for policy 0, policy_version 1671 (0.0021) [2024-08-01 16:17:58,838][00034] Fps is (10 sec: 2458.3, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 6848512. Throughput: 0: 1537.1. Samples: 3430380. Policy #0 lag: (min: 0.0, avg: 3.4, max: 6.0) [2024-08-01 16:17:58,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:03,029][00140] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:18:03,838][00034] Fps is (10 sec: 3277.4, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 6873088. Throughput: 0: 1539.8. Samples: 3439788. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:18:03,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:08,558][00134] Updated weights for policy 0, policy_version 1681 (0.0019) [2024-08-01 16:18:08,839][00034] Fps is (10 sec: 3686.3, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 6885376. Throughput: 0: 1545.9. Samples: 3449292. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:18:08,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:08,852][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001681_6885376.pth... [2024-08-01 16:18:09,019][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001505_6164480.pth [2024-08-01 16:18:13,839][00034] Fps is (10 sec: 2457.4, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 6897664. Throughput: 0: 1526.9. Samples: 3453180. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:18:13,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 2999.1). Total num frames: 6914048. Throughput: 0: 1527.2. Samples: 3462564. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:18:18,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:23,484][00134] Updated weights for policy 0, policy_version 1691 (0.0019) [2024-08-01 16:18:23,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 6926336. Throughput: 0: 1543.2. Samples: 3471900. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:18:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 6946816. Throughput: 0: 1539.5. Samples: 3476364. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:18:28,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:33,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 6963200. Throughput: 0: 1544.9. Samples: 3485904. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:18:33,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:34,538][00134] Updated weights for policy 0, policy_version 1701 (0.0020) [2024-08-01 16:18:37,409][00137] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:18:38,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 6971392. Throughput: 0: 1544.6. Samples: 3495264. Policy #0 lag: (min: 0.0, avg: 3.9, max: 6.0) [2024-08-01 16:18:38,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3013.0). Total num frames: 6991872. Throughput: 0: 1542.9. Samples: 3499812. Policy #0 lag: (min: 0.0, avg: 3.5, max: 6.0) [2024-08-01 16:18:43,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.9, 300 sec: 3013.0). Total num frames: 7004160. Throughput: 0: 1527.2. Samples: 3508512. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:18:48,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:48,922][00134] Updated weights for policy 0, policy_version 1711 (0.0019) [2024-08-01 16:18:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3013.0). Total num frames: 7020544. Throughput: 0: 1523.7. Samples: 3517860. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 16:18:53,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:18:58,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 3026.9). Total num frames: 7041024. Throughput: 0: 1541.1. Samples: 3522528. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:18:58,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:03,055][00134] Updated weights for policy 0, policy_version 1721 (0.0019) [2024-08-01 16:19:03,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7053312. Throughput: 0: 1548.8. Samples: 3532260. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 16:19:03,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 7069696. Throughput: 0: 1544.0. Samples: 3541380. Policy #0 lag: (min: 0.0, avg: 3.5, max: 6.0) [2024-08-01 16:19:08,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:13,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3140.3, 300 sec: 3026.9). Total num frames: 7086080. Throughput: 0: 1548.2. Samples: 3546036. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:19:13,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:14,923][00134] Updated weights for policy 0, policy_version 1731 (0.0020) [2024-08-01 16:19:17,676][00137] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:19:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7094272. Throughput: 0: 1522.7. Samples: 3554424. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:19:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:21,986][00139] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:19:23,838][00034] Fps is (10 sec: 2867.5, 60 sec: 3140.3, 300 sec: 3026.9). Total num frames: 7114752. Throughput: 0: 1514.7. Samples: 3563424. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:19:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7127040. Throughput: 0: 1517.9. Samples: 3568116. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:19:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:29,107][00134] Updated weights for policy 0, policy_version 1741 (0.0021) [2024-08-01 16:19:33,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 7143424. Throughput: 0: 1529.1. Samples: 3577320. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 16:19:33,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3013.0). Total num frames: 7155712. Throughput: 0: 1522.4. Samples: 3586368. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:19:38,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:42,765][00133] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:19:43,133][00134] Updated weights for policy 0, policy_version 1751 (0.0020) [2024-08-01 16:19:43,838][00034] Fps is (10 sec: 2867.3, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7172096. Throughput: 0: 1521.1. Samples: 3590976. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:19:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 7188480. Throughput: 0: 1493.9. Samples: 3599484. Policy #0 lag: (min: 0.0, avg: 3.5, max: 8.0) [2024-08-01 16:19:48,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 7204864. Throughput: 0: 1493.9. Samples: 3608604. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:19:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:19:56,107][00134] Updated weights for policy 0, policy_version 1761 (0.0020) [2024-08-01 16:19:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7217152. Throughput: 0: 1496.0. Samples: 3613356. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 16:19:58,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 3026.9). Total num frames: 7233536. Throughput: 0: 1512.5. Samples: 3622488. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:20:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:08,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2935.4, 300 sec: 3013.0). Total num frames: 7245824. Throughput: 0: 1514.1. Samples: 3631560. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:20:08,844][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:08,876][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001770_7249920.pth... [2024-08-01 16:20:09,054][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001590_6512640.pth [2024-08-01 16:20:09,642][00134] Updated weights for policy 0, policy_version 1771 (0.0020) [2024-08-01 16:20:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3040.8). Total num frames: 7262208. Throughput: 0: 1510.9. Samples: 3636108. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:20:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:18,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 7278592. Throughput: 0: 1510.4. Samples: 3645288. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:20:18,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7290880. Throughput: 0: 1498.9. Samples: 3653820. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:20:23,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:24,319][00134] Updated weights for policy 0, policy_version 1781 (0.0020) [2024-08-01 16:20:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 7311360. Throughput: 0: 1496.5. Samples: 3658320. Policy #0 lag: (min: 0.0, avg: 3.6, max: 8.0) [2024-08-01 16:20:28,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:33,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 7323648. Throughput: 0: 1510.9. Samples: 3667476. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:20:33,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:36,993][00134] Updated weights for policy 0, policy_version 1791 (0.0020) [2024-08-01 16:20:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 7340032. Throughput: 0: 1512.8. Samples: 3676680. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:20:38,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:43,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 7352320. Throughput: 0: 1510.7. Samples: 3681336. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:20:43,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 7372800. Throughput: 0: 1510.7. Samples: 3690468. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:20:48,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:50,818][00134] Updated weights for policy 0, policy_version 1801 (0.0023) [2024-08-01 16:20:53,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3040.8). Total num frames: 7380992. Throughput: 0: 1501.6. Samples: 3699132. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:20:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:20:58,838][00034] Fps is (10 sec: 2457.6, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 7397376. Throughput: 0: 1500.8. Samples: 3703644. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:20:58,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 7413760. Throughput: 0: 1503.2. Samples: 3712932. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:21:03,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:03,900][00134] Updated weights for policy 0, policy_version 1811 (0.0023) [2024-08-01 16:21:08,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3054.6). Total num frames: 7430144. Throughput: 0: 1516.8. Samples: 3722076. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:21:08,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:13,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 7446528. Throughput: 0: 1516.5. Samples: 3726564. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:21:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:18,150][00134] Updated weights for policy 0, policy_version 1821 (0.0020) [2024-08-01 16:21:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3068.5). Total num frames: 7462912. Throughput: 0: 1520.6. Samples: 3735900. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:21:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3040.8). Total num frames: 7475200. Throughput: 0: 1510.4. Samples: 3744648. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:21:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3054.6). Total num frames: 7491584. Throughput: 0: 1498.1. Samples: 3748752. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:21:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:31,121][00134] Updated weights for policy 0, policy_version 1831 (0.0020) [2024-08-01 16:21:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7499776. Throughput: 0: 1493.3. Samples: 3757668. Policy #0 lag: (min: 0.0, avg: 3.6, max: 9.0) [2024-08-01 16:21:33,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:38,839][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 7520256. Throughput: 0: 1499.2. Samples: 3766596. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:21:38,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 7532544. Throughput: 0: 1498.4. Samples: 3771072. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:21:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:44,699][00134] Updated weights for policy 0, policy_version 1841 (0.0020) [2024-08-01 16:21:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3040.8). Total num frames: 7548928. Throughput: 0: 1492.3. Samples: 3780084. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:21:48,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 3026.9). Total num frames: 7565312. Throughput: 0: 1486.4. Samples: 3788964. Policy #0 lag: (min: 0.0, avg: 2.2, max: 7.0) [2024-08-01 16:21:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:21:56,303][00141] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:21:58,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 3026.9). Total num frames: 7577600. Throughput: 0: 1478.1. Samples: 3793080. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:21:58,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:00,154][00134] Updated weights for policy 0, policy_version 1851 (0.0020) [2024-08-01 16:22:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3040.8). Total num frames: 7593984. Throughput: 0: 1466.9. Samples: 3801912. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:22:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:08,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7606272. Throughput: 0: 1472.5. Samples: 3810912. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:22:08,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001857_7606272.pth... [2024-08-01 16:22:09,018][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001681_6885376.pth [2024-08-01 16:22:12,559][00134] Updated weights for policy 0, policy_version 1861 (0.0023) [2024-08-01 16:22:13,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2935.4, 300 sec: 3026.9). Total num frames: 7622656. Throughput: 0: 1482.1. Samples: 3815448. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:22:13,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:16,428][00137] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:22:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7639040. Throughput: 0: 1485.1. Samples: 3824496. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:22:18,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:23,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7651328. Throughput: 0: 1486.4. Samples: 3833484. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 16:22:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:25,630][00134] Updated weights for policy 0, policy_version 1871 (0.0028) [2024-08-01 16:22:28,842][00034] Fps is (10 sec: 2866.1, 60 sec: 2935.3, 300 sec: 3026.8). Total num frames: 7667712. Throughput: 0: 1486.3. Samples: 3837960. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:22:28,847][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7680000. Throughput: 0: 1474.7. Samples: 3846444. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:22:33,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:34,155][00144] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:22:38,838][00034] Fps is (10 sec: 2868.3, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7696384. Throughput: 0: 1476.0. Samples: 3855384. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:22:38,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:41,507][00134] Updated weights for policy 0, policy_version 1881 (0.0021) [2024-08-01 16:22:43,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7712768. Throughput: 0: 1488.5. Samples: 3860064. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:22:43,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 7725056. Throughput: 0: 1487.7. Samples: 3868860. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:22:48,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:53,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 3026.9). Total num frames: 7741440. Throughput: 0: 1487.5. Samples: 3877848. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:22:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:22:53,956][00137] Large shaping reward 2.642 for [('FRAGCOUNT', 2.0, 2.0), ('HITCOUNT', 0.04, 4.0), ('DAMAGECOUNT', 0.6, 200), ('weapon7', 0.002)] [2024-08-01 16:22:55,097][00134] Updated weights for policy 0, policy_version 1891 (0.0021) [2024-08-01 16:22:57,990][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:22:58,840][00034] Fps is (10 sec: 3276.3, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 7757824. Throughput: 0: 1485.8. Samples: 3882312. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:22:58,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:03,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2867.2, 300 sec: 2985.2). Total num frames: 7766016. Throughput: 0: 1469.6. Samples: 3890628. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:23:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:06,638][00146] Large shaping reward -2.536 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:23:08,229][00134] Updated weights for policy 0, policy_version 1901 (0.0038) [2024-08-01 16:23:08,838][00034] Fps is (10 sec: 2867.6, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7786496. Throughput: 0: 1469.1. Samples: 3899592. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:23:08,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:13,838][00034] Fps is (10 sec: 3276.9, 60 sec: 2935.5, 300 sec: 2999.1). Total num frames: 7798784. Throughput: 0: 1468.9. Samples: 3904056. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:23:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 3013.0). Total num frames: 7815168. Throughput: 0: 1476.3. Samples: 3912876. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:23:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:20,464][00145] Large shaping reward -2.518 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('weapon5', 0.002)] [2024-08-01 16:23:22,597][00134] Updated weights for policy 0, policy_version 1911 (0.0021) [2024-08-01 16:23:23,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 2985.2). Total num frames: 7827456. Throughput: 0: 1474.4. Samples: 3921732. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 16:23:23,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.7, 300 sec: 2985.2). Total num frames: 7843840. Throughput: 0: 1471.2. Samples: 3926268. Policy #0 lag: (min: 0.0, avg: 3.4, max: 8.0) [2024-08-01 16:23:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:31,608][00135] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:23:31,978][00135] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:23:33,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3003.7, 300 sec: 3013.0). Total num frames: 7860224. Throughput: 0: 1476.0. Samples: 3935280. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:23:33,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:36,391][00134] Updated weights for policy 0, policy_version 1921 (0.0021) [2024-08-01 16:23:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 7872512. Throughput: 0: 1474.7. Samples: 3944208. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:23:38,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:43,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2867.2, 300 sec: 2985.2). Total num frames: 7884800. Throughput: 0: 1471.8. Samples: 3948540. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:23:43,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:48,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2999.1). Total num frames: 7905280. Throughput: 0: 1478.9. Samples: 3957180. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:23:48,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:49,930][00134] Updated weights for policy 0, policy_version 1931 (0.0023) [2024-08-01 16:23:53,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 7913472. Throughput: 0: 1470.4. Samples: 3965760. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:23:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:23:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 7933952. Throughput: 0: 1468.0. Samples: 3970116. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:23:58,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2971.3). Total num frames: 7946240. Throughput: 0: 1470.1. Samples: 3979032. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:24:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:04,461][00134] Updated weights for policy 0, policy_version 1941 (0.0020) [2024-08-01 16:24:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 7962624. Throughput: 0: 1463.5. Samples: 3987588. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:24:08,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001944_7962624.pth... [2024-08-01 16:24:09,015][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001770_7249920.pth [2024-08-01 16:24:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 7974912. Throughput: 0: 1460.3. Samples: 3991980. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:24:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 7987200. Throughput: 0: 1453.1. Samples: 4000668. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:24:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:19,594][00134] Updated weights for policy 0, policy_version 1951 (0.0025) [2024-08-01 16:24:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 8003584. Throughput: 0: 1445.6. Samples: 4009260. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:24:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:28,839][00034] Fps is (10 sec: 3276.6, 60 sec: 2935.4, 300 sec: 2971.3). Total num frames: 8019968. Throughput: 0: 1445.6. Samples: 4013592. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:24:28,844][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:32,714][00134] Updated weights for policy 0, policy_version 1961 (0.0036) [2024-08-01 16:24:33,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2935.5, 300 sec: 2985.2). Total num frames: 8036352. Throughput: 0: 1450.4. Samples: 4022448. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:24:33,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:38,714][00136] Large shaping reward -2.536 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:24:38,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 8048640. Throughput: 0: 1451.7. Samples: 4031088. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:24:38,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:43,839][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2957.4). Total num frames: 8060928. Throughput: 0: 1450.4. Samples: 4035384. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:24:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:46,370][00134] Updated weights for policy 0, policy_version 1971 (0.0020) [2024-08-01 16:24:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2957.4). Total num frames: 8077312. Throughput: 0: 1443.2. Samples: 4043976. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:24:48,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:53,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3003.7, 300 sec: 2971.3). Total num frames: 8093696. Throughput: 0: 1444.2. Samples: 4052580. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:24:53,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:24:57,603][00144] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:24:58,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 8105984. Throughput: 0: 1446.9. Samples: 4057092. Policy #0 lag: (min: 0.0, avg: 3.3, max: 9.0) [2024-08-01 16:24:58,845][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:02,059][00134] Updated weights for policy 0, policy_version 1981 (0.0020) [2024-08-01 16:25:03,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2935.5, 300 sec: 2971.3). Total num frames: 8122368. Throughput: 0: 1449.6. Samples: 4065900. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:25:03,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2957.5). Total num frames: 8134656. Throughput: 0: 1451.7. Samples: 4074588. Policy #0 lag: (min: 0.0, avg: 3.4, max: 9.0) [2024-08-01 16:25:08,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2957.5). Total num frames: 8151040. Throughput: 0: 1453.1. Samples: 4078980. Policy #0 lag: (min: 0.0, avg: 2.8, max: 8.0) [2024-08-01 16:25:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:15,340][00134] Updated weights for policy 0, policy_version 1991 (0.0020) [2024-08-01 16:25:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2957.5). Total num frames: 8163328. Throughput: 0: 1450.4. Samples: 4087716. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 16:25:18,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2943.6). Total num frames: 8179712. Throughput: 0: 1449.6. Samples: 4096320. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:25:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2943.6). Total num frames: 8192000. Throughput: 0: 1455.5. Samples: 4100880. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:25:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:29,184][00134] Updated weights for policy 0, policy_version 2001 (0.0031) [2024-08-01 16:25:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2943.6). Total num frames: 8208384. Throughput: 0: 1459.5. Samples: 4109652. Policy #0 lag: (min: 0.0, avg: 3.3, max: 8.0) [2024-08-01 16:25:33,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:38,646][00147] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:25:38,839][00034] Fps is (10 sec: 3276.5, 60 sec: 2935.4, 300 sec: 2957.4). Total num frames: 8224768. Throughput: 0: 1458.9. Samples: 4118232. Policy #0 lag: (min: 0.0, avg: 3.4, max: 6.0) [2024-08-01 16:25:38,844][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:43,525][00134] Updated weights for policy 0, policy_version 2011 (0.0021) [2024-08-01 16:25:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8237056. Throughput: 0: 1455.2. Samples: 4122576. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:25:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:48,838][00034] Fps is (10 sec: 2867.5, 60 sec: 2935.5, 300 sec: 2957.5). Total num frames: 8253440. Throughput: 0: 1453.6. Samples: 4131312. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:25:48,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:53,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2867.2, 300 sec: 2943.6). Total num frames: 8265728. Throughput: 0: 1458.9. Samples: 4140240. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:25:53,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:25:56,785][00134] Updated weights for policy 0, policy_version 2021 (0.0020) [2024-08-01 16:25:58,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2929.7). Total num frames: 8278016. Throughput: 0: 1456.3. Samples: 4144512. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:25:58,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:03,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2867.2, 300 sec: 2929.7). Total num frames: 8294400. Throughput: 0: 1458.4. Samples: 4153344. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:26:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8306688. Throughput: 0: 1461.6. Samples: 4162092. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:26:08,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:08,850][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002028_8306688.pth... [2024-08-01 16:26:09,020][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001857_7606272.pth [2024-08-01 16:26:11,197][00134] Updated weights for policy 0, policy_version 2031 (0.0021) [2024-08-01 16:26:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8323072. Throughput: 0: 1455.5. Samples: 4166376. Policy #0 lag: (min: 0.0, avg: 3.1, max: 8.0) [2024-08-01 16:26:13,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:18,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8339456. Throughput: 0: 1453.9. Samples: 4175076. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:26:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8355840. Throughput: 0: 1457.6. Samples: 4183824. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:26:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:25,780][00134] Updated weights for policy 0, policy_version 2041 (0.0021) [2024-08-01 16:26:28,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3003.7, 300 sec: 2957.5). Total num frames: 8372224. Throughput: 0: 1460.5. Samples: 4188300. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:26:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8380416. Throughput: 0: 1458.9. Samples: 4196964. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:26:33,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:38,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2867.2, 300 sec: 2929.7). Total num frames: 8396800. Throughput: 0: 1451.5. Samples: 4205556. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:26:38,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:40,309][00134] Updated weights for policy 0, policy_version 2051 (0.0021) [2024-08-01 16:26:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8409088. Throughput: 0: 1453.9. Samples: 4209936. Policy #0 lag: (min: 0.0, avg: 3.2, max: 8.0) [2024-08-01 16:26:43,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:48,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8425472. Throughput: 0: 1454.6. Samples: 4218804. Policy #0 lag: (min: 0.0, avg: 2.9, max: 8.0) [2024-08-01 16:26:48,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:52,995][00134] Updated weights for policy 0, policy_version 2061 (0.0027) [2024-08-01 16:26:53,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3003.8, 300 sec: 2943.6). Total num frames: 8445952. Throughput: 0: 1450.4. Samples: 4227360. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:26:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:26:58,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8454144. Throughput: 0: 1455.5. Samples: 4231872. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:26:58,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8470528. Throughput: 0: 1458.7. Samples: 4240716. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:27:03,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:08,587][00134] Updated weights for policy 0, policy_version 2071 (0.0020) [2024-08-01 16:27:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8482816. Throughput: 0: 1457.3. Samples: 4249404. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:27:08,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:11,265][00137] Large shaping reward -2.510 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.261, -87.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:27:13,492][00144] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:27:13,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8495104. Throughput: 0: 1454.1. Samples: 4253736. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:27:13,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8515584. Throughput: 0: 1457.6. Samples: 4262556. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:27:18,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:19,425][00142] Large shaping reward -2.558 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('ARMOR', -0.009000000000000001, -9.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:27:22,391][00134] Updated weights for policy 0, policy_version 2081 (0.0021) [2024-08-01 16:27:23,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8527872. Throughput: 0: 1457.3. Samples: 4271136. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:27:23,843][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2929.7). Total num frames: 8544256. Throughput: 0: 1454.9. Samples: 4275408. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:27:28,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8556544. Throughput: 0: 1452.3. Samples: 4284156. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:27:33,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:35,688][00134] Updated weights for policy 0, policy_version 2091 (0.0022) [2024-08-01 16:27:38,235][00137] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:27:38,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8568832. Throughput: 0: 1457.1. Samples: 4292928. Policy #0 lag: (min: 0.0, avg: 2.7, max: 7.0) [2024-08-01 16:27:38,845][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8585216. Throughput: 0: 1455.5. Samples: 4297368. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:27:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:45,104][00143] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:27:48,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8601600. Throughput: 0: 1450.1. Samples: 4305972. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:27:48,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:49,833][00134] Updated weights for policy 0, policy_version 2101 (0.0021) [2024-08-01 16:27:53,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8617984. Throughput: 0: 1450.7. Samples: 4314684. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:27:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:27:58,839][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 8630272. Throughput: 0: 1452.8. Samples: 4319112. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:27:58,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:03,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8642560. Throughput: 0: 1451.5. Samples: 4327872. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:28:03,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:04,013][00134] Updated weights for policy 0, policy_version 2111 (0.0020) [2024-08-01 16:28:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8658944. Throughput: 0: 1454.9. Samples: 4336608. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:28:08,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002114_8658944.pth... [2024-08-01 16:28:09,019][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000001944_7962624.pth [2024-08-01 16:28:13,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 2901.9). Total num frames: 8671232. Throughput: 0: 1447.4. Samples: 4340544. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:28:13,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:18,408][00134] Updated weights for policy 0, policy_version 2121 (0.0020) [2024-08-01 16:28:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8687616. Throughput: 0: 1441.9. Samples: 4349040. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:28:18,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:23,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8699904. Throughput: 0: 1438.1. Samples: 4357644. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:28:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8720384. Throughput: 0: 1437.6. Samples: 4362060. Policy #0 lag: (min: 0.0, avg: 2.1, max: 7.0) [2024-08-01 16:28:28,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2798.9, 300 sec: 2888.0). Total num frames: 8724480. Throughput: 0: 1441.6. Samples: 4370844. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:28:33,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:34,204][00134] Updated weights for policy 0, policy_version 2131 (0.0020) [2024-08-01 16:28:38,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8744960. Throughput: 0: 1442.1. Samples: 4379580. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:28:38,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:43,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 8757248. Throughput: 0: 1440.8. Samples: 4383948. Policy #0 lag: (min: 0.0, avg: 1.9, max: 7.0) [2024-08-01 16:28:43,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:46,416][00134] Updated weights for policy 0, policy_version 2141 (0.0021) [2024-08-01 16:28:48,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 8773632. Throughput: 0: 1422.4. Samples: 4391880. Policy #0 lag: (min: 0.0, avg: 3.8, max: 10.0) [2024-08-01 16:28:48,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8790016. Throughput: 0: 1422.1. Samples: 4400604. Policy #0 lag: (min: 0.0, avg: 2.1, max: 7.0) [2024-08-01 16:28:53,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:28:58,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2798.9, 300 sec: 2888.0). Total num frames: 8798208. Throughput: 0: 1431.0. Samples: 4404936. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:28:58,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:01,125][00134] Updated weights for policy 0, policy_version 2151 (0.0020) [2024-08-01 16:29:03,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2901.9). Total num frames: 8818688. Throughput: 0: 1436.0. Samples: 4413660. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 16:29:03,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:08,839][00034] Fps is (10 sec: 2866.9, 60 sec: 2798.9, 300 sec: 2888.0). Total num frames: 8826880. Throughput: 0: 1442.4. Samples: 4422552. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:29:08,841][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:13,839][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8847360. Throughput: 0: 1442.9. Samples: 4426992. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:29:13,842][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:16,828][00134] Updated weights for policy 0, policy_version 2161 (0.0020) [2024-08-01 16:29:18,838][00034] Fps is (10 sec: 3277.1, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8859648. Throughput: 0: 1426.1. Samples: 4435020. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:29:18,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:23,839][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 8871936. Throughput: 0: 1422.1. Samples: 4443576. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:29:23,840][00034] Avg episode reward: [(0, '-2.686')] [2024-08-01 16:29:24,682][00147] DAMAGECOUNT value on done: 780.0 [2024-08-01 16:29:24,690][00147] Sum rewards: -0.781, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.850', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.030', 'AMMO3': '0.141', 'AMMO6': '0.160', 'AMMO7': '0.160', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon7': '0.220', 'weapon5': '0.252', 'HITCOUNT': '0.290', 'WEAPON5': '0.300', 'weapon4': '0.820', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.500', 'DAMAGECOUNT': '1.611', 'weapon2': '2.322', 'weapon3': '3.588'} [2024-08-01 16:29:28,629][00134] Updated weights for policy 0, policy_version 2171 (0.0025) [2024-08-01 16:29:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 8892416. Throughput: 0: 1423.5. Samples: 4448004. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 16:29:28,842][00034] Avg episode reward: [(0, '-2.674')] [2024-08-01 16:29:33,071][00147] DAMAGECOUNT value on done: 792.0 [2024-08-01 16:29:33,073][00147] Sum rewards: 2.690, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.920', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.133', 'weapon5': '0.138', 'WEAPON5': '0.200', 'HITCOUNT': '0.320', 'ARMOR': '0.514', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.479', 'FRAGCOUNT': '2.500', 'weapon2': '3.096', 'weapon3': '3.930'} [2024-08-01 16:29:33,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 8900608. Throughput: 0: 1444.8. Samples: 4456896. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 16:29:33,840][00034] Avg episode reward: [(0, '-2.626')] [2024-08-01 16:29:38,503][00144] DAMAGECOUNT value on done: 515.0 [2024-08-01 16:29:38,508][00144] Sum rewards: 1.557, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO5': '0.009', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.048', 'weapon4': '0.052', 'WEAPON4': '0.100', 'AMMO3': '0.145', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'weapon5': '0.510', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.005', 'weapon2': '2.214', 'FRAGCOUNT': '3.000', 'weapon3': '3.834'} [2024-08-01 16:29:38,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8921088. Throughput: 0: 1445.9. Samples: 4465668. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:29:38,842][00034] Avg episode reward: [(0, '-2.638')] [2024-08-01 16:29:40,965][00147] DAMAGECOUNT value on done: 481.0 [2024-08-01 16:29:40,966][00147] Sum rewards: -6.845, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.392', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.025', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.186', 'HITCOUNT': '0.210', 'weapon5': '0.334', 'weapon4': '0.462', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.828', 'WEAPON3': '1.100', 'weapon2': '2.972', 'weapon3': '3.326'} [2024-08-01 16:29:43,139][00134] Updated weights for policy 0, policy_version 2181 (0.0020) [2024-08-01 16:29:43,839][00034] Fps is (10 sec: 3276.5, 60 sec: 2935.4, 300 sec: 2901.9). Total num frames: 8933376. Throughput: 0: 1450.6. Samples: 4470216. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 16:29:43,841][00034] Avg episode reward: [(0, '-2.607')] [2024-08-01 16:29:46,100][00144] DAMAGECOUNT value on done: 340.0 [2024-08-01 16:29:48,026][00136] DAMAGECOUNT value on done: 378.0 [2024-08-01 16:29:48,029][00136] Sum rewards: -3.847, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.855', 'AMMO5': '0.003', 'AMMO2': '0.018', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'AMMO4': '0.091', 'WEAPON5': '0.100', 'weapon4': '0.102', 'weapon5': '0.118', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.128', 'AMMO3': '0.184', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.744', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon3': '3.384', 'weapon2': '4.030'} [2024-08-01 16:29:48,838][00034] Fps is (10 sec: 2457.7, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 8945664. Throughput: 0: 1450.9. Samples: 4478952. Policy #0 lag: (min: 0.0, avg: 2.4, max: 6.0) [2024-08-01 16:29:48,843][00034] Avg episode reward: [(0, '-2.634')] [2024-08-01 16:29:49,469][00147] DAMAGECOUNT value on done: 535.0 [2024-08-01 16:29:49,469][00147] Sum rewards: -2.027, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.056', 'ARMOR': '0.092', 'weapon4': '0.092', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.176', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.321', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '3.068', 'weapon3': '4.214'} [2024-08-01 16:29:51,264][00148] DAMAGECOUNT value on done: 549.0 [2024-08-01 16:29:51,269][00148] Sum rewards: -2.716, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon5': '0.186', 'WEAPON5': '0.200', 'AMMO3': '0.254', 'HITCOUNT': '0.360', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.512', 'FRAGCOUNT': '2.000', 'weapon2': '3.026', 'weapon3': '4.114'} [2024-08-01 16:29:53,839][00034] Fps is (10 sec: 2457.6, 60 sec: 2798.9, 300 sec: 2888.0). Total num frames: 8957952. Throughput: 0: 1438.9. Samples: 4487304. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:29:53,843][00034] Avg episode reward: [(0, '-2.560')] [2024-08-01 16:29:53,846][00112] Saving new best policy, reward=-2.560! [2024-08-01 16:29:54,574][00144] DAMAGECOUNT value on done: 393.0 [2024-08-01 16:29:54,578][00144] Sum rewards: -1.320, reward structure: {'DEATHCOUNT': '-3.750', 'FRAGCOUNT': '-3.000', 'HEALTH': '-1.330', 'AMMO4': '-0.059', 'AMMO2': '-0.012', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.081', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.166', 'weapon7': '0.170', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'WEAPON3': '0.400', 'ARMOR': '0.668', 'weapon2': '2.326', 'weapon3': '2.352'} [2024-08-01 16:29:56,663][00136] DAMAGECOUNT value on done: 631.0 [2024-08-01 16:29:56,664][00136] Sum rewards: 3.444, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.920', 'AMMO5': '0.005', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO2': '0.024', 'AMMO3': '0.063', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'AMMO4': '0.118', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'WEAPON4': '0.200', 'weapon7': '0.240', 'DAMAGECOUNT': '0.438', 'WEAPON3': '0.500', 'weapon4': '0.516', 'FRAGCOUNT': '2.000', 'weapon2': '2.146', 'weapon3': '2.948'} [2024-08-01 16:29:57,588][00147] DAMAGECOUNT value on done: 113.0 [2024-08-01 16:29:58,277][00141] DAMAGECOUNT value on done: 403.0 [2024-08-01 16:29:58,296][00141] Sum rewards: -2.504, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO4': '-0.108', 'AMMO2': '-0.022', 'AMMO5': '0.015', 'WEAPON1': '0.040', 'ARMOR': '0.048', 'HITCOUNT': '0.080', 'AMMO3': '0.101', 'weapon5': '0.284', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.696', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon3': '2.624', 'weapon2': '4.248'} [2024-08-01 16:29:58,385][00134] Updated weights for policy 0, policy_version 2191 (0.0020) [2024-08-01 16:29:58,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2935.4, 300 sec: 2888.0). Total num frames: 8974336. Throughput: 0: 1437.8. Samples: 4491696. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:29:58,844][00034] Avg episode reward: [(0, '-2.517')] [2024-08-01 16:29:58,851][00112] Saving new best policy, reward=-2.517! [2024-08-01 16:29:59,686][00148] DAMAGECOUNT value on done: 875.0 [2024-08-01 16:29:59,691][00148] Sum rewards: -1.810, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.504', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'FRAGCOUNT': '0.000', 'AMMO5': '0.012', 'ARMOR': '0.023', 'WEAPON1': '0.040', 'weapon7': '0.104', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.161', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.230', 'weapon5': '0.248', 'WEAPON5': '0.300', 'weapon4': '0.652', 'DAMAGECOUNT': '0.942', 'WEAPON3': '1.100', 'weapon2': '2.608', 'weapon3': '3.648'} [2024-08-01 16:30:03,726][00144] DAMAGECOUNT value on done: 731.0 [2024-08-01 16:30:03,727][00144] Sum rewards: 1.329, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.657', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.100', 'AMMO3': '0.133', 'HITCOUNT': '0.300', 'weapon4': '0.436', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.077', 'weapon3': '2.976', 'weapon2': '3.948', 'FRAGCOUNT': '4.000'} [2024-08-01 16:30:03,838][00034] Fps is (10 sec: 3686.7, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 8994816. Throughput: 0: 1462.4. Samples: 4500828. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:30:03,840][00034] Avg episode reward: [(0, '-2.456')] [2024-08-01 16:30:03,844][00112] Saving new best policy, reward=-2.456! [2024-08-01 16:30:04,158][00140] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:30:05,036][00135] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:30:05,522][00136] DAMAGECOUNT value on done: 847.0 [2024-08-01 16:30:05,524][00136] Sum rewards: 5.810, reward structure: {'DEATHCOUNT': '-2.250', 'HEALTH': '-0.933', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'AMMO3': '0.068', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'WEAPON3': '0.300', 'weapon5': '0.390', 'ARMOR': '0.470', 'DAMAGECOUNT': '0.558', 'weapon4': '0.788', 'weapon2': '1.912', 'weapon3': '1.914', 'FRAGCOUNT': '2.000'} [2024-08-01 16:30:05,743][00135] DAMAGECOUNT value on done: 290.0 [2024-08-01 16:30:05,750][00135] Sum rewards: -0.620, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.735', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'AMMO5': '0.012', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'weapon4': '0.108', 'HITCOUNT': '0.120', 'AMMO3': '0.147', 'weapon5': '0.154', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.405', 'WEAPON3': '0.900', 'FRAGCOUNT': '3.000', 'weapon2': '3.440', 'weapon3': '3.444'} [2024-08-01 16:30:05,815][00147] DAMAGECOUNT value on done: 530.0 [2024-08-01 16:30:05,816][00147] Sum rewards: -4.147, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.420', 'AMMO2': '0.003', 'AMMO5': '0.010', 'AMMO4': '0.016', 'weapon5': '0.062', 'AMMO3': '0.156', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'weapon4': '0.480', 'ARMOR': '0.504', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.921', 'FRAGCOUNT': '1.000', 'weapon3': '2.630', 'weapon2': '4.310'} [2024-08-01 16:30:06,805][00141] DAMAGECOUNT value on done: 230.0 [2024-08-01 16:30:06,810][00141] Sum rewards: -2.830, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'FRAGCOUNT': '-1.000', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'weapon7': '0.102', 'AMMO3': '0.112', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.322', 'DAMAGECOUNT': '0.495', 'weapon4': '0.666', 'WEAPON3': '0.800', 'weapon2': '2.778', 'weapon3': '3.218'} [2024-08-01 16:30:08,531][00148] DAMAGECOUNT value on done: 464.0 [2024-08-01 16:30:08,532][00148] Sum rewards: 2.275, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.620', 'AMMO2': '0.014', 'ARMOR': '0.016', 'AMMO5': '0.030', 'WEAPON1': '0.040', 'AMMO4': '0.068', 'AMMO3': '0.110', 'HITCOUNT': '0.220', 'weapon5': '0.422', 'WEAPON5': '0.600', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.777', 'FRAGCOUNT': '2.000', 'weapon3': '3.308', 'weapon2': '3.340'} [2024-08-01 16:30:08,839][00034] Fps is (10 sec: 3277.0, 60 sec: 3003.8, 300 sec: 2901.9). Total num frames: 9007104. Throughput: 0: 1466.9. Samples: 4509588. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:30:08,843][00034] Avg episode reward: [(0, '-2.280')] [2024-08-01 16:30:08,853][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002199_9007104.pth... [2024-08-01 16:30:09,032][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002028_8306688.pth [2024-08-01 16:30:09,043][00112] Saving new best policy, reward=-2.280! [2024-08-01 16:30:11,545][00134] Updated weights for policy 0, policy_version 2201 (0.0021) [2024-08-01 16:30:11,692][00144] DAMAGECOUNT value on done: 454.0 [2024-08-01 16:30:11,697][00144] Sum rewards: -3.183, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.420', 'AMMO4': '-0.058', 'AMMO2': '-0.012', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'weapon5': '0.052', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon7': '0.102', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'HITCOUNT': '0.210', 'AMMO3': '0.223', 'weapon4': '0.312', 'DAMAGECOUNT': '0.582', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon2': '3.526', 'weapon3': '3.552'} [2024-08-01 16:30:13,489][00146] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:30:13,605][00147] DAMAGECOUNT value on done: 1063.0 [2024-08-01 16:30:13,607][00147] Sum rewards: 1.390, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.550', 'AMMO5': '0.007', 'AMMO2': '0.012', 'AMMO4': '0.058', 'AMMO3': '0.152', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'HITCOUNT': '0.340', 'weapon5': '0.342', 'ARMOR': '0.457', 'WEAPON3': '0.900', 'weapon4': '1.022', 'DAMAGECOUNT': '1.308', 'weapon3': '2.714', 'FRAGCOUNT': '3.000', 'weapon2': '3.128'} [2024-08-01 16:30:13,687][00135] DAMAGECOUNT value on done: 525.0 [2024-08-01 16:30:13,690][00135] Sum rewards: -0.580, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.400', 'FRAGCOUNT': '-1.000', 'AMMO2': '0.007', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO4': '0.037', 'WEAPON4': '0.100', 'AMMO3': '0.135', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'weapon5': '0.244', 'ARMOR': '0.487', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.800', 'weapon2': '2.592', 'weapon3': '3.512'} [2024-08-01 16:30:13,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 9019392. Throughput: 0: 1465.9. Samples: 4513968. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:30:13,840][00034] Avg episode reward: [(0, '-2.200')] [2024-08-01 16:30:13,841][00112] Saving new best policy, reward=-2.200! [2024-08-01 16:30:14,005][00136] DAMAGECOUNT value on done: 416.0 [2024-08-01 16:30:14,694][00141] DAMAGECOUNT value on done: 739.0 [2024-08-01 16:30:14,698][00141] Sum rewards: -0.775, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.199', 'AMMO4': '-0.102', 'AMMO2': '-0.020', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.102', 'weapon5': '0.120', 'HITCOUNT': '0.170', 'weapon4': '0.428', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.651', 'FRAGCOUNT': '1.000', 'weapon3': '2.048', 'weapon2': '4.668'} [2024-08-01 16:30:17,291][00148] DAMAGECOUNT value on done: 529.0 [2024-08-01 16:30:17,298][00148] Sum rewards: -2.949, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.950', 'AMMO2': '0.005', 'AMMO5': '0.011', 'AMMO4': '0.026', 'WEAPON1': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.135', 'weapon4': '0.216', 'weapon5': '0.224', 'HITCOUNT': '0.280', 'WEAPON5': '0.300', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.107', 'weapon2': '2.432', 'weapon3': '3.934'} [2024-08-01 16:30:18,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9031680. Throughput: 0: 1464.0. Samples: 4522776. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:30:18,840][00034] Avg episode reward: [(0, '-2.280')] [2024-08-01 16:30:20,749][00144] DAMAGECOUNT value on done: 693.0 [2024-08-01 16:30:20,764][00144] Sum rewards: 0.532, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.115', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'AMMO3': '0.193', 'WEAPON4': '0.200', 'HITCOUNT': '0.290', 'weapon4': '0.352', 'weapon5': '0.380', 'WEAPON5': '0.400', 'ARMOR': '0.505', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.434', 'weapon3': '2.814', 'weapon2': '3.548', 'FRAGCOUNT': '4.000'} [2024-08-01 16:30:21,860][00147] DAMAGECOUNT value on done: 559.0 [2024-08-01 16:30:21,862][00147] Sum rewards: 6.807, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.919', 'AMMO2': '0.015', 'AMMO5': '0.028', 'ARMOR': '0.040', 'AMMO3': '0.057', 'WEAPON1': '0.060', 'AMMO4': '0.076', 'WEAPON4': '0.100', 'HITCOUNT': '0.180', 'weapon4': '0.278', 'weapon5': '0.482', 'WEAPON3': '0.500', 'WEAPON5': '0.500', 'DAMAGECOUNT': '1.038', 'weapon2': '2.618', 'weapon3': '3.254', 'FRAGCOUNT': '4.000'} [2024-08-01 16:30:22,083][00135] DAMAGECOUNT value on done: 546.0 [2024-08-01 16:30:22,084][00135] Sum rewards: -7.117, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.016', 'weapon4': '0.024', 'ARMOR': '0.040', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.181', 'HITCOUNT': '0.200', 'weapon5': '0.332', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.657', 'WEAPON3': '1.100', 'weapon2': '3.128', 'weapon3': '3.896'} [2024-08-01 16:30:22,709][00140] DAMAGECOUNT value on done: 1116.0 [2024-08-01 16:30:22,715][00140] Sum rewards: 3.114, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.175', 'AMMO2': '0.006', 'AMMO5': '0.008', 'AMMO4': '0.029', 'ARMOR': '0.064', 'weapon7': '0.074', 'AMMO3': '0.142', 'AMMO6': '0.160', 'AMMO7': '0.160', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'weapon5': '0.360', 'WEAPON3': '1.000', 'weapon4': '1.086', 'DAMAGECOUNT': '1.140', 'weapon2': '1.906', 'FRAGCOUNT': '3.000', 'weapon3': '3.824'} [2024-08-01 16:30:23,126][00136] DAMAGECOUNT value on done: 825.0 [2024-08-01 16:30:23,127][00136] Sum rewards: 2.342, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.880', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.005', 'weapon5': '0.030', 'AMMO3': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'HITCOUNT': '0.320', 'weapon4': '0.428', 'ARMOR': '0.489', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.128', 'FRAGCOUNT': '2.000', 'weapon3': '3.250', 'weapon2': '4.026'} [2024-08-01 16:30:23,434][00141] DAMAGECOUNT value on done: 504.0 [2024-08-01 16:30:23,434][00141] Sum rewards: -0.995, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.128', 'weapon4': '0.182', 'HITCOUNT': '0.190', 'AMMO3': '0.208', 'ARMOR': '0.458', 'DAMAGECOUNT': '0.945', 'WEAPON3': '1.200', 'FRAGCOUNT': '3.000', 'weapon3': '3.168', 'weapon2': '3.994'} [2024-08-01 16:30:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2901.9). Total num frames: 9048064. Throughput: 0: 1450.7. Samples: 4530948. Policy #0 lag: (min: 0.0, avg: 2.5, max: 6.0) [2024-08-01 16:30:23,840][00034] Avg episode reward: [(0, '-2.105')] [2024-08-01 16:30:23,842][00112] Saving new best policy, reward=-2.105! [2024-08-01 16:30:25,454][00134] Updated weights for policy 0, policy_version 2211 (0.0020) [2024-08-01 16:30:26,236][00148] DAMAGECOUNT value on done: 600.0 [2024-08-01 16:30:28,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 9064448. Throughput: 0: 1448.6. Samples: 4535400. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:30:28,840][00034] Avg episode reward: [(0, '-2.073')] [2024-08-01 16:30:28,848][00112] Saving new best policy, reward=-2.073! [2024-08-01 16:30:29,321][00144] DAMAGECOUNT value on done: 507.0 [2024-08-01 16:30:29,671][00143] DAMAGECOUNT value on done: 619.0 [2024-08-01 16:30:29,677][00143] Sum rewards: -2.272, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.196', 'weapon5': '0.246', 'WEAPON5': '0.300', 'ARMOR': '0.413', 'DAMAGECOUNT': '0.504', 'weapon4': '0.596', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.684', 'weapon3': '3.958'} [2024-08-01 16:30:30,310][00147] DAMAGECOUNT value on done: 466.0 [2024-08-01 16:30:30,579][00135] DAMAGECOUNT value on done: 428.0 [2024-08-01 16:30:30,584][00135] Sum rewards: 0.708, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.928', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.007', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.132', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'FRAGCOUNT': '0.500', 'ARMOR': '0.560', 'weapon4': '0.576', 'DAMAGECOUNT': '0.699', 'WEAPON3': '1.000', 'weapon3': '3.180', 'weapon2': '3.200'} [2024-08-01 16:30:31,147][00140] DAMAGECOUNT value on done: 1030.0 [2024-08-01 16:30:31,153][00140] Sum rewards: -2.680, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.041', 'AMMO2': '-0.008', 'AMMO5': '0.034', 'WEAPON1': '0.040', 'AMMO3': '0.256', 'HITCOUNT': '0.400', 'weapon5': '0.402', 'WEAPON5': '0.700', 'WEAPON3': '1.400', 'FRAGCOUNT': '1.500', 'weapon2': '1.980', 'DAMAGECOUNT': '2.250', 'weapon3': '5.146'} [2024-08-01 16:30:31,408][00136] DAMAGECOUNT value on done: 291.0 [2024-08-01 16:30:31,409][00136] Sum rewards: 0.098, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.075', 'AMMO2': '-0.015', 'AMMO5': '0.005', 'weapon5': '0.006', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.133', 'HITCOUNT': '0.140', 'weapon4': '0.304', 'ARMOR': '0.558', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.928', 'weapon2': '3.874'} [2024-08-01 16:30:31,683][00141] DAMAGECOUNT value on done: 743.0 [2024-08-01 16:30:31,689][00141] Sum rewards: -2.558, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.277', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'ARMOR': '0.004', 'AMMO5': '0.005', 'weapon5': '0.012', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon7': '0.106', 'AMMO3': '0.118', 'AMMO6': '0.120', 'AMMO7': '0.120', 'HITCOUNT': '0.150', 'WEAPON7': '0.200', 'weapon4': '0.492', 'DAMAGECOUNT': '0.510', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.578', 'weapon3': '2.702'} [2024-08-01 16:30:33,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2901.9). Total num frames: 9080832. Throughput: 0: 1445.9. Samples: 4544016. Policy #0 lag: (min: 0.0, avg: 2.3, max: 6.0) [2024-08-01 16:30:33,840][00034] Avg episode reward: [(0, '-1.954')] [2024-08-01 16:30:33,842][00112] Saving new best policy, reward=-1.954! [2024-08-01 16:30:34,742][00148] DAMAGECOUNT value on done: 567.0 [2024-08-01 16:30:34,748][00148] Sum rewards: 0.323, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.980', 'AMMO5': '0.007', 'AMMO2': '0.008', 'WEAPON1': '0.020', 'AMMO4': '0.041', 'AMMO3': '0.110', 'weapon5': '0.120', 'ARMOR': '0.122', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon4': '0.372', 'DAMAGECOUNT': '0.582', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.874', 'weapon2': '3.126'} [2024-08-01 16:30:35,045][00135] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:30:37,666][00144] DAMAGECOUNT value on done: 516.0 [2024-08-01 16:30:37,671][00144] Sum rewards: -0.546, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.220', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'weapon5': '0.168', 'HITCOUNT': '0.180', 'AMMO3': '0.187', 'weapon4': '0.204', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.615', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.230', 'weapon3': '4.678'} [2024-08-01 16:30:38,093][00143] DAMAGECOUNT value on done: 532.0 [2024-08-01 16:30:38,099][00143] Sum rewards: -5.624, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.890', 'AMMO2': '0.016', 'AMMO5': '0.017', 'weapon4': '0.032', 'WEAPON1': '0.040', 'AMMO4': '0.079', 'weapon5': '0.122', 'HITCOUNT': '0.180', 'WEAPON4': '0.200', 'AMMO3': '0.231', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.780', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.874', 'weapon3': '4.094'} [2024-08-01 16:30:38,624][00147] DAMAGECOUNT value on done: 416.0 [2024-08-01 16:30:38,627][00147] Sum rewards: -2.503, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.067', 'AMMO2': '-0.013', 'AMMO5': '0.004', 'ARMOR': '0.004', 'WEAPON5': '0.100', 'weapon5': '0.100', 'AMMO3': '0.246', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.963', 'WEAPON3': '1.400', 'FRAGCOUNT': '2.000', 'weapon2': '2.904', 'weapon3': '4.246'} [2024-08-01 16:30:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 9093120. Throughput: 0: 1450.4. Samples: 4552572. Policy #0 lag: (min: 0.0, avg: 3.1, max: 6.0) [2024-08-01 16:30:38,840][00034] Avg episode reward: [(0, '-1.882')] [2024-08-01 16:30:38,847][00112] Saving new best policy, reward=-1.882! [2024-08-01 16:30:39,052][00135] DAMAGECOUNT value on done: 525.0 [2024-08-01 16:30:39,056][00135] Sum rewards: -7.202, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.674', 'AMMO5': '0.009', 'AMMO2': '0.023', 'weapon4': '0.030', 'WEAPON4': '0.100', 'weapon5': '0.102', 'AMMO4': '0.114', 'HITCOUNT': '0.130', 'WEAPON5': '0.200', 'AMMO3': '0.229', 'ARMOR': '0.473', 'DAMAGECOUNT': '0.828', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '3.366', 'weapon3': '4.068'} [2024-08-01 16:30:39,478][00140] DAMAGECOUNT value on done: 422.0 [2024-08-01 16:30:39,481][00140] Sum rewards: 3.452, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.065', 'AMMO4': '-0.086', 'AMMO2': '-0.017', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.092', 'HITCOUNT': '0.100', 'WEAPON5': '0.200', 'weapon5': '0.248', 'ARMOR': '0.450', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.717', 'FRAGCOUNT': '1.000', 'weapon2': '3.354', 'weapon3': '4.082'} [2024-08-01 16:30:39,634][00136] DAMAGECOUNT value on done: 476.0 [2024-08-01 16:30:39,640][00136] Sum rewards: -0.605, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.211', 'AMMO5': '0.003', 'AMMO2': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.037', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.103', 'weapon5': '0.150', 'HITCOUNT': '0.180', 'weapon4': '0.452', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.822', 'FRAGCOUNT': '2.000', 'weapon3': '2.158', 'weapon2': '3.242'} [2024-08-01 16:30:40,151][00141] DAMAGECOUNT value on done: 525.0 [2024-08-01 16:30:40,161][00141] Sum rewards: -2.343, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.009', 'AMMO2': '0.030', 'ARMOR': '0.040', 'weapon5': '0.044', 'WEAPON5': '0.100', 'AMMO4': '0.148', 'HITCOUNT': '0.160', 'AMMO3': '0.177', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.400', 'DAMAGECOUNT': '0.627', 'weapon4': '0.858', 'WEAPON3': '1.000', 'weapon2': '2.478', 'weapon3': '4.006'} [2024-08-01 16:30:40,781][00134] Updated weights for policy 0, policy_version 2221 (0.0021) [2024-08-01 16:30:42,961][00148] DAMAGECOUNT value on done: 492.0 [2024-08-01 16:30:42,963][00148] Sum rewards: 5.186, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.162', 'AMMO4': '-0.066', 'AMMO2': '-0.013', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.107', 'HITCOUNT': '0.160', 'weapon5': '0.182', 'WEAPON5': '0.200', 'ARMOR': '0.509', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.810', 'weapon2': '2.616', 'FRAGCOUNT': '3.000', 'weapon3': '4.266'} [2024-08-01 16:30:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9105408. Throughput: 0: 1447.8. Samples: 4556844. Policy #0 lag: (min: 0.0, avg: 2.6, max: 6.0) [2024-08-01 16:30:43,840][00034] Avg episode reward: [(0, '-1.782')] [2024-08-01 16:30:43,842][00112] Saving new best policy, reward=-1.782! [2024-08-01 16:30:46,118][00144] DAMAGECOUNT value on done: 544.0 [2024-08-01 16:30:46,122][00144] Sum rewards: -1.959, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.272', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.007', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'weapon4': '0.052', 'WEAPON4': '0.100', 'AMMO3': '0.149', 'WEAPON5': '0.200', 'HITCOUNT': '0.360', 'weapon5': '0.410', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.110', 'FRAGCOUNT': '3.000', 'weapon2': '3.074', 'weapon3': '3.454'} [2024-08-01 16:30:47,779][00143] DAMAGECOUNT value on done: 632.0 [2024-08-01 16:30:47,783][00143] Sum rewards: -1.851, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.225', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'WEAPON1': '0.020', 'ARMOR': '0.076', 'HITCOUNT': '0.110', 'AMMO3': '0.150', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.330', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon4': '1.110', 'weapon2': '2.696', 'weapon3': '2.934'} [2024-08-01 16:30:48,016][00147] DAMAGECOUNT value on done: 567.0 [2024-08-01 16:30:48,017][00147] Sum rewards: -3.638, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.300', 'AMMO2': '0.009', 'AMMO5': '0.035', 'AMMO4': '0.046', 'ARMOR': '0.048', 'HITCOUNT': '0.100', 'AMMO3': '0.179', 'weapon5': '0.204', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.381', 'WEAPON5': '0.500', 'weapon4': '0.814', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.660', 'weapon3': '3.786'} [2024-08-01 16:30:48,355][00136] DAMAGECOUNT value on done: 872.0 [2024-08-01 16:30:48,356][00136] Sum rewards: 2.429, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.604', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.003', 'ARMOR': '0.032', 'weapon4': '0.098', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.149', 'weapon5': '0.164', 'HITCOUNT': '0.230', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.386', 'FRAGCOUNT': '1.500', 'weapon2': '2.488', 'weapon3': '4.646'} [2024-08-01 16:30:48,402][00140] DAMAGECOUNT value on done: 459.0 [2024-08-01 16:30:48,403][00140] Sum rewards: -3.995, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.496', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.008', 'ARMOR': '0.024', 'WEAPON1': '0.040', 'weapon4': '0.070', 'WEAPON4': '0.100', 'weapon5': '0.134', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'AMMO3': '0.220', 'DAMAGECOUNT': '0.975', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.710', 'weapon3': '4.838'} [2024-08-01 16:30:48,616][00135] DAMAGECOUNT value on done: 770.0 [2024-08-01 16:30:48,618][00135] Sum rewards: 1.868, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.946', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.088', 'AMMO3': '0.119', 'HITCOUNT': '0.310', 'WEAPON5': '0.400', 'weapon5': '0.502', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.500', 'DAMAGECOUNT': '1.830', 'weapon2': '2.968', 'weapon3': '3.788'} [2024-08-01 16:30:48,839][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9117696. Throughput: 0: 1421.6. Samples: 4564800. Policy #0 lag: (min: 0.0, avg: 3.0, max: 6.0) [2024-08-01 16:30:48,840][00034] Avg episode reward: [(0, '-1.807')] [2024-08-01 16:30:49,722][00141] DAMAGECOUNT value on done: 787.0 [2024-08-01 16:30:49,728][00141] Sum rewards: -3.093, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.100', 'AMMO4': '-0.084', 'AMMO2': '-0.017', 'AMMO5': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO3': '0.121', 'HITCOUNT': '0.150', 'weapon5': '0.192', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.876', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '3.296', 'weapon3': '3.604'} [2024-08-01 16:30:51,946][00148] DAMAGECOUNT value on done: 533.0 [2024-08-01 16:30:51,949][00148] Sum rewards: -3.856, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.745', 'FRAGCOUNT': '-1.000', 'AMMO5': '0.016', 'AMMO2': '0.016', 'ARMOR': '0.036', 'WEAPON1': '0.060', 'AMMO4': '0.081', 'AMMO3': '0.159', 'HITCOUNT': '0.160', 'WEAPON4': '0.200', 'weapon4': '0.348', 'WEAPON5': '0.400', 'weapon5': '0.522', 'DAMAGECOUNT': '0.699', 'WEAPON3': '1.100', 'weapon2': '1.966', 'weapon3': '4.126'} [2024-08-01 16:30:53,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9129984. Throughput: 0: 1392.0. Samples: 4572228. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:30:53,840][00034] Avg episode reward: [(0, '-1.747')] [2024-08-01 16:30:53,844][00112] Saving new best policy, reward=-1.747! [2024-08-01 16:30:55,242][00144] DAMAGECOUNT value on done: 1174.0 [2024-08-01 16:30:55,248][00144] Sum rewards: -0.752, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.765', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'HITCOUNT': '0.070', 'AMMO3': '0.109', 'weapon7': '0.112', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'WEAPON4': '0.200', 'weapon4': '0.244', 'weapon5': '0.274', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.432', 'WEAPON3': '0.700', 'weapon3': '2.942', 'weapon2': '3.384'} [2024-08-01 16:30:56,472][00134] Updated weights for policy 0, policy_version 2231 (0.0023) [2024-08-01 16:30:56,598][00139] DAMAGECOUNT value on done: 424.0 [2024-08-01 16:30:56,602][00139] Sum rewards: -0.055, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.660', 'AMMO4': '-0.043', 'AMMO2': '-0.008', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO3': '0.091', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.176', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.372', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '3.068', 'weapon2': '3.644'} [2024-08-01 16:30:57,219][00136] DAMAGECOUNT value on done: 538.0 [2024-08-01 16:30:57,225][00143] DAMAGECOUNT value on done: 573.0 [2024-08-01 16:30:57,224][00136] Sum rewards: -2.297, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO4': '-0.084', 'AMMO2': '-0.017', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'weapon5': '0.150', 'AMMO3': '0.175', 'HITCOUNT': '0.180', 'ARMOR': '0.492', 'DAMAGECOUNT': '1.008', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.406', 'weapon3': '3.850'} [2024-08-01 16:30:57,227][00143] Sum rewards: -3.020, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.299', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'AMMO5': '0.022', 'WEAPON1': '0.040', 'ARMOR': '0.080', 'WEAPON4': '0.100', 'weapon5': '0.148', 'weapon4': '0.170', 'HITCOUNT': '0.200', 'AMMO3': '0.202', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.879', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '2.402', 'weapon2': '4.048'} [2024-08-01 16:30:57,359][00140] DAMAGECOUNT value on done: 744.0 [2024-08-01 16:30:57,377][00147] DAMAGECOUNT value on done: 782.0 [2024-08-01 16:30:57,378][00147] Sum rewards: -2.976, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.610', 'FRAGCOUNT': '-1.000', 'AMMO4': '-0.018', 'AMMO2': '-0.003', 'AMMO5': '0.023', 'ARMOR': '0.108', 'WEAPON4': '0.200', 'AMMO3': '0.208', 'weapon5': '0.222', 'HITCOUNT': '0.230', 'WEAPON5': '0.400', 'weapon4': '0.556', 'DAMAGECOUNT': '0.960', 'WEAPON3': '1.100', 'weapon3': '3.284', 'weapon2': '3.364'} [2024-08-01 16:30:58,077][00135] DAMAGECOUNT value on done: 408.0 [2024-08-01 16:30:58,078][00135] Sum rewards: -1.315, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO4': '-0.017', 'AMMO2': '-0.003', 'AMMO5': '0.015', 'WEAPON1': '0.040', 'AMMO3': '0.198', 'HITCOUNT': '0.220', 'weapon5': '0.360', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.750', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.884', 'weapon3': '4.158'} [2024-08-01 16:30:58,839][00034] Fps is (10 sec: 2457.5, 60 sec: 2799.0, 300 sec: 2874.1). Total num frames: 9142272. Throughput: 0: 1382.1. Samples: 4576164. Policy #0 lag: (min: 0.0, avg: 2.9, max: 6.0) [2024-08-01 16:30:58,842][00034] Avg episode reward: [(0, '-1.700')] [2024-08-01 16:30:58,851][00112] Saving new best policy, reward=-1.700! [2024-08-01 16:30:59,213][00141] DAMAGECOUNT value on done: 506.0 [2024-08-01 16:30:59,215][00141] Sum rewards: -3.032, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.190', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.003', 'AMMO2': '-0.001', 'AMMO5': '0.017', 'WEAPON1': '0.060', 'HITCOUNT': '0.080', 'AMMO3': '0.161', 'DAMAGECOUNT': '0.285', 'WEAPON5': '0.300', 'weapon5': '0.456', 'WEAPON3': '1.000', 'weapon2': '2.262', 'weapon3': '4.290'} [2024-08-01 16:31:00,694][00148] DAMAGECOUNT value on done: 443.0 [2024-08-01 16:31:01,661][00132] DAMAGECOUNT value on done: 776.0 [2024-08-01 16:31:01,665][00132] Sum rewards: -1.054, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.180', 'AMMO4': '-0.009', 'AMMO2': '-0.002', 'AMMO5': '0.012', 'ARMOR': '0.052', 'weapon5': '0.104', 'AMMO3': '0.135', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.240', 'FRAGCOUNT': '0.500', 'weapon4': '0.526', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.855', 'weapon2': '2.940', 'weapon3': '3.922'} [2024-08-01 16:31:03,761][00144] DAMAGECOUNT value on done: 402.0 [2024-08-01 16:31:03,764][00144] Sum rewards: -1.585, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'HITCOUNT': '0.080', 'AMMO3': '0.139', 'weapon5': '0.160', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'DAMAGECOUNT': '0.240', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.650', 'weapon3': '4.850'} [2024-08-01 16:31:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2662.4, 300 sec: 2874.1). Total num frames: 9154560. Throughput: 0: 1368.5. Samples: 4584360. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:31:03,841][00034] Avg episode reward: [(0, '-1.733')] [2024-08-01 16:31:05,182][00139] DAMAGECOUNT value on done: 528.0 [2024-08-01 16:31:05,191][00139] Sum rewards: 0.537, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.930', 'AMMO4': '-0.101', 'AMMO2': '-0.020', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'AMMO3': '0.105', 'weapon5': '0.122', 'ARMOR': '0.136', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.495', 'WEAPON3': '0.700', 'FRAGCOUNT': '2.000', 'weapon3': '3.244', 'weapon2': '3.894'} [2024-08-01 16:31:05,675][00136] DAMAGECOUNT value on done: 458.0 [2024-08-01 16:31:05,679][00136] Sum rewards: -4.080, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'WEAPON1': '0.020', 'ARMOR': '0.029', 'AMMO5': '0.029', 'HITCOUNT': '0.080', 'AMMO3': '0.156', 'WEAPON4': '0.200', 'weapon5': '0.520', 'WEAPON5': '0.600', 'DAMAGECOUNT': '0.705', 'weapon4': '0.730', 'WEAPON3': '0.900', 'weapon2': '2.356', 'weapon3': '3.108'} [2024-08-01 16:31:05,922][00140] DAMAGECOUNT value on done: 455.0 [2024-08-01 16:31:05,929][00140] Sum rewards: -6.915, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'AMMO5': '0.007', 'AMMO2': '0.008', 'AMMO4': '0.037', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'weapon5': '0.128', 'AMMO3': '0.198', 'WEAPON4': '0.200', 'HITCOUNT': '0.240', 'weapon4': '0.336', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.825', 'WEAPON3': '1.000', 'weapon3': '2.602', 'weapon2': '3.584'} [2024-08-01 16:31:06,955][00143] DAMAGECOUNT value on done: 537.0 [2024-08-01 16:31:06,960][00143] Sum rewards: -7.311, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.105', 'AMMO4': '-0.060', 'AMMO2': '-0.012', 'AMMO5': '0.033', 'ARMOR': '0.040', 'HITCOUNT': '0.220', 'AMMO3': '0.257', 'weapon5': '0.290', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.585', 'WEAPON5': '0.600', 'WEAPON3': '1.300', 'weapon2': '2.554', 'weapon3': '4.238'} [2024-08-01 16:31:06,965][00147] DAMAGECOUNT value on done: 672.0 [2024-08-01 16:31:07,758][00135] DAMAGECOUNT value on done: 641.0 [2024-08-01 16:31:07,760][00135] Sum rewards: -0.965, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.995', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'WEAPON1': '0.060', 'WEAPON4': '0.200', 'AMMO3': '0.203', 'HITCOUNT': '0.240', 'weapon5': '0.298', 'WEAPON5': '0.400', 'weapon4': '0.506', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.353', 'FRAGCOUNT': '2.000', 'weapon3': '2.376', 'weapon2': '4.072'} [2024-08-01 16:31:08,807][00141] DAMAGECOUNT value on done: 462.0 [2024-08-01 16:31:08,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2730.7, 300 sec: 2874.1). Total num frames: 9170944. Throughput: 0: 1371.5. Samples: 4592664. Policy #0 lag: (min: 0.0, avg: 2.7, max: 6.0) [2024-08-01 16:31:08,840][00034] Avg episode reward: [(0, '-1.952')] [2024-08-01 16:31:09,125][00148] DAMAGECOUNT value on done: 798.0 [2024-08-01 16:31:09,130][00148] Sum rewards: -0.835, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.400', 'AMMO5': '0.005', 'AMMO2': '0.014', 'WEAPON1': '0.020', 'weapon5': '0.036', 'AMMO4': '0.071', 'WEAPON5': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.182', 'AMMO3': '0.186', 'WEAPON7': '0.200', 'WEAPON4': '0.300', 'HITCOUNT': '0.400', 'ARMOR': '0.477', 'weapon4': '0.722', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.626', 'FRAGCOUNT': '2.500', 'weapon2': '3.054', 'weapon3': '3.582'} [2024-08-01 16:31:10,200][00132] DAMAGECOUNT value on done: 470.0 [2024-08-01 16:31:10,207][00132] Sum rewards: 2.127, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.043', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.090', 'AMMO2': '-0.018', 'AMMO5': '0.008', 'weapon5': '0.090', 'ARMOR': '0.091', 'AMMO3': '0.099', 'WEAPON5': '0.100', 'weapon7': '0.108', 'AMMO6': '0.120', 'AMMO7': '0.120', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.882', 'weapon2': '3.582', 'weapon3': '3.708'} [2024-08-01 16:31:10,307][00145] DAMAGECOUNT value on done: 393.0 [2024-08-01 16:31:10,311][00145] Sum rewards: -2.386, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.900', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'ARMOR': '0.060', 'HITCOUNT': '0.120', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.152', 'AMMO3': '0.188', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.492', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '3.624', 'weapon3': '4.138'} [2024-08-01 16:31:11,085][00134] Updated weights for policy 0, policy_version 2241 (0.0021) [2024-08-01 16:31:12,328][00144] DAMAGECOUNT value on done: 794.0 [2024-08-01 16:31:12,329][00144] Sum rewards: -4.344, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.545', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.095', 'AMMO2': '-0.019', 'AMMO5': '0.021', 'AMMO3': '0.143', 'weapon5': '0.208', 'HITCOUNT': '0.210', 'WEAPON5': '0.400', 'ARMOR': '0.455', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.800', 'weapon3': '3.180', 'weapon2': '3.828'} [2024-08-01 16:31:13,776][00139] DAMAGECOUNT value on done: 380.0 [2024-08-01 16:31:13,778][00139] Sum rewards: 2.615, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.490', 'AMMO2': '0.002', 'AMMO4': '0.009', 'AMMO5': '0.010', 'ARMOR': '0.032', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.144', 'DAMAGECOUNT': '0.420', 'weapon4': '0.426', 'WEAPON3': '0.900', 'weapon2': '1.558', 'FRAGCOUNT': '2.000', 'weapon3': '5.304'} [2024-08-01 16:31:13,839][00034] Fps is (10 sec: 2867.1, 60 sec: 2730.6, 300 sec: 2860.3). Total num frames: 9183232. Throughput: 0: 1370.9. Samples: 4597092. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:31:13,842][00034] Avg episode reward: [(0, '-1.976')] [2024-08-01 16:31:14,267][00136] DAMAGECOUNT value on done: 474.0 [2024-08-01 16:31:14,270][00136] Sum rewards: -2.537, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.530', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'weapon4': '0.002', 'AMMO5': '0.015', 'ARMOR': '0.020', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.130', 'HITCOUNT': '0.190', 'WEAPON5': '0.300', 'weapon5': '0.342', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.816', 'FRAGCOUNT': '1.000', 'weapon2': '3.074', 'weapon3': '3.174'} [2024-08-01 16:31:14,617][00140] DAMAGECOUNT value on done: 768.0 [2024-08-01 16:31:15,041][00147] DAMAGECOUNT value on done: 615.0 [2024-08-01 16:31:15,044][00147] Sum rewards: -2.218, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'WEAPON1': '0.020', 'ARMOR': '0.064', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.188', 'HITCOUNT': '0.200', 'WEAPON7': '0.200', 'AMMO3': '0.209', 'weapon4': '0.512', 'DAMAGECOUNT': '0.810', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.132', 'weapon3': '4.432'} [2024-08-01 16:31:15,210][00143] DAMAGECOUNT value on done: 820.0 [2024-08-01 16:31:15,212][00143] Sum rewards: 2.739, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.895', 'AMMO2': '0.004', 'AMMO5': '0.011', 'AMMO4': '0.017', 'WEAPON1': '0.020', 'ARMOR': '0.048', 'AMMO3': '0.096', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'HITCOUNT': '0.300', 'weapon4': '0.376', 'weapon5': '0.548', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.500', 'DAMAGECOUNT': '1.728', 'weapon3': '2.694', 'weapon2': '3.942'} [2024-08-01 16:31:15,849][00135] DAMAGECOUNT value on done: 417.0 [2024-08-01 16:31:15,853][00135] Sum rewards: -4.279, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.028', 'AMMO2': '-0.006', 'AMMO5': '0.010', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.133', 'HITCOUNT': '0.160', 'weapon4': '0.184', 'DAMAGECOUNT': '0.576', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.778', 'weapon3': '4.326'} [2024-08-01 16:31:16,860][00141] DAMAGECOUNT value on done: 690.0 [2024-08-01 16:31:16,863][00141] Sum rewards: -1.068, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.970', 'AMMO2': '0.004', 'AMMO5': '0.006', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'AMMO3': '0.136', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.296', 'HITCOUNT': '0.320', 'weapon4': '0.684', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.320', 'weapon2': '2.156', 'FRAGCOUNT': '2.500', 'weapon3': '3.770'} [2024-08-01 16:31:17,458][00148] DAMAGECOUNT value on done: 643.0 [2024-08-01 16:31:18,839][00034] Fps is (10 sec: 2867.2, 60 sec: 2798.9, 300 sec: 2860.3). Total num frames: 9199616. Throughput: 0: 1374.7. Samples: 4605876. Policy #0 lag: (min: 0.0, avg: 2.8, max: 6.0) [2024-08-01 16:31:18,842][00034] Avg episode reward: [(0, '-1.676')] [2024-08-01 16:31:18,853][00112] Saving new best policy, reward=-1.676! [2024-08-01 16:31:19,863][00132] DAMAGECOUNT value on done: 649.0 [2024-08-01 16:31:19,866][00132] Sum rewards: -1.116, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.003', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'weapon5': '0.106', 'HITCOUNT': '0.200', 'AMMO3': '0.214', 'DAMAGECOUNT': '0.972', 'WEAPON3': '1.400', 'weapon2': '2.768', 'weapon3': '3.740', 'FRAGCOUNT': '4.000'} [2024-08-01 16:31:20,014][00145] DAMAGECOUNT value on done: 438.0 [2024-08-01 16:31:20,190][00144] DAMAGECOUNT value on done: 415.0 [2024-08-01 16:31:20,195][00144] Sum rewards: -3.662, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.100', 'AMMO2': '0.006', 'WEAPON1': '0.020', 'AMMO4': '0.032', 'ARMOR': '0.048', 'HITCOUNT': '0.160', 'AMMO3': '0.184', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.630', 'weapon4': '0.742', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.282', 'weapon3': '4.334'} [2024-08-01 16:31:20,788][00138] DAMAGECOUNT value on done: 570.0 [2024-08-01 16:31:20,791][00138] Sum rewards: 5.615, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.030', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.107', 'HITCOUNT': '0.140', 'weapon5': '0.228', 'WEAPON5': '0.300', 'weapon4': '0.322', 'ARMOR': '0.568', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.765', 'FRAGCOUNT': '3.000', 'weapon3': '3.218', 'weapon2': '3.412'} [2024-08-01 16:31:21,909][00136] DAMAGECOUNT value on done: 483.0 [2024-08-01 16:31:21,913][00136] Sum rewards: 0.561, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.625', 'AMMO4': '-0.024', 'AMMO2': '-0.005', 'ARMOR': '0.008', 'WEAPON1': '0.020', 'HITCOUNT': '0.090', 'AMMO3': '0.099', 'WEAPON4': '0.100', 'weapon4': '0.426', 'DAMAGECOUNT': '0.435', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '3.462', 'weapon3': '3.624'} [2024-08-01 16:31:22,409][00140] DAMAGECOUNT value on done: 713.0 [2024-08-01 16:31:22,410][00140] Sum rewards: -1.865, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.470', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.007', 'ARMOR': '0.032', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'weapon5': '0.128', 'WEAPON5': '0.200', 'AMMO3': '0.209', 'HITCOUNT': '0.240', 'weapon4': '0.254', 'DAMAGECOUNT': '1.095', 'WEAPON3': '1.400', 'weapon2': '2.766', 'FRAGCOUNT': '3.000', 'weapon3': '4.406'} [2024-08-01 16:31:22,524][00147] DAMAGECOUNT value on done: 839.0 [2024-08-01 16:31:22,525][00147] Sum rewards: 1.530, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.230', 'AMMO4': '-0.038', 'AMMO2': '-0.008', 'AMMO5': '0.003', 'ARMOR': '0.024', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.108', 'AMMO3': '0.112', 'weapon4': '0.128', 'HITCOUNT': '0.410', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.905', 'FRAGCOUNT': '2.000', 'weapon2': '3.276', 'weapon3': '3.990'} [2024-08-01 16:31:22,818][00143] DAMAGECOUNT value on done: 770.0 [2024-08-01 16:31:22,821][00143] Sum rewards: 3.090, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.545', 'AMMO4': '-0.043', 'AMMO2': '-0.009', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO3': '0.096', 'WEAPON4': '0.100', 'weapon5': '0.140', 'WEAPON5': '0.200', 'HITCOUNT': '0.280', 'weapon4': '0.454', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.446', 'weapon3': '2.584', 'weapon2': '3.964', 'FRAGCOUNT': '5.000'} [2024-08-01 16:31:23,221][00139] DAMAGECOUNT value on done: 563.0 [2024-08-01 16:31:23,224][00139] Sum rewards: 0.814, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.206', 'AMMO4': '-0.098', 'AMMO2': '-0.020', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'AMMO3': '0.127', 'weapon5': '0.154', 'WEAPON5': '0.200', 'HITCOUNT': '0.200', 'ARMOR': '0.584', 'DAMAGECOUNT': '0.681', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '3.076', 'weapon2': '3.788'} [2024-08-01 16:31:23,594][00135] DAMAGECOUNT value on done: 493.0 [2024-08-01 16:31:23,598][00135] Sum rewards: 0.933, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.920', 'AMMO2': '0.004', 'AMMO4': '0.020', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'weapon4': '0.136', 'AMMO3': '0.176', 'HITCOUNT': '0.230', 'ARMOR': '0.499', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.864', 'FRAGCOUNT': '2.000', 'weapon2': '2.876', 'weapon3': '3.728'} [2024-08-01 16:31:23,838][00034] Fps is (10 sec: 3276.9, 60 sec: 2798.9, 300 sec: 2860.3). Total num frames: 9216000. Throughput: 0: 1385.6. Samples: 4614924. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:31:23,840][00034] Avg episode reward: [(0, '-1.468')] [2024-08-01 16:31:23,843][00112] Saving new best policy, reward=-1.468! [2024-08-01 16:31:24,602][00141] DAMAGECOUNT value on done: 512.0 [2024-08-01 16:31:24,605][00141] Sum rewards: -7.181, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.830', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.073', 'AMMO2': '-0.014', 'AMMO5': '0.013', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'weapon5': '0.116', 'HITCOUNT': '0.120', 'AMMO3': '0.143', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.612', 'WEAPON3': '0.800', 'weapon2': '3.064', 'weapon3': '3.246'} [2024-08-01 16:31:24,769][00134] Updated weights for policy 0, policy_version 2251 (0.0020) [2024-08-01 16:31:25,215][00148] DAMAGECOUNT value on done: 413.0 [2024-08-01 16:31:25,222][00148] Sum rewards: -7.464, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.040', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.007', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'weapon5': '0.146', 'WEAPON4': '0.200', 'AMMO3': '0.215', 'HITCOUNT': '0.260', 'weapon4': '0.496', 'DAMAGECOUNT': '1.020', 'WEAPON3': '1.400', 'weapon2': '3.034', 'weapon3': '3.916'} [2024-08-01 16:31:28,558][00144] DAMAGECOUNT value on done: 534.0 [2024-08-01 16:31:28,562][00144] Sum rewards: -0.525, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.200', 'AMMO2': '0.007', 'AMMO5': '0.010', 'weapon4': '0.022', 'AMMO4': '0.033', 'ARMOR': '0.056', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.179', 'WEAPON5': '0.200', 'weapon5': '0.274', 'DAMAGECOUNT': '0.474', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.728', 'weapon3': '3.622'} [2024-08-01 16:31:28,613][00132] DAMAGECOUNT value on done: 209.0 [2024-08-01 16:31:28,783][00145] DAMAGECOUNT value on done: 842.0 [2024-08-01 16:31:28,786][00145] Sum rewards: -2.213, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO2': '0.001', 'AMMO4': '0.005', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.176', 'weapon4': '0.254', 'WEAPON5': '0.300', 'weapon5': '0.332', 'DAMAGECOUNT': '1.005', 'WEAPON3': '1.100', 'weapon2': '2.982', 'FRAGCOUNT': '3.000', 'weapon3': '4.002'} [2024-08-01 16:31:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2730.7, 300 sec: 2874.1). Total num frames: 9228288. Throughput: 0: 1370.9. Samples: 4618536. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:31:28,840][00034] Avg episode reward: [(0, '-1.465')] [2024-08-01 16:31:28,847][00112] Saving new best policy, reward=-1.465! [2024-08-01 16:31:29,591][00138] DAMAGECOUNT value on done: 972.0 [2024-08-01 16:31:29,601][00138] Sum rewards: 2.767, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.434', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'weapon4': '0.048', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'AMMO3': '0.123', 'weapon5': '0.172', 'WEAPON5': '0.300', 'HITCOUNT': '0.410', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.536', 'FRAGCOUNT': '3.500', 'weapon3': '3.614', 'weapon2': '3.712'} [2024-08-01 16:31:30,874][00136] DAMAGECOUNT value on done: 314.0 [2024-08-01 16:31:30,880][00136] Sum rewards: -2.512, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO2': '0.029', 'AMMO4': '0.145', 'HITCOUNT': '0.150', 'AMMO3': '0.193', 'WEAPON4': '0.200', 'weapon5': '0.250', 'weapon4': '0.388', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '3.152', 'weapon2': '3.488'} [2024-08-01 16:31:31,103][00147] DAMAGECOUNT value on done: 639.0 [2024-08-01 16:31:31,109][00147] Sum rewards: -1.152, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.759', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.018', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.116', 'HITCOUNT': '0.150', 'weapon4': '0.254', 'weapon5': '0.276', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon2': '2.718', 'weapon3': '4.160'} [2024-08-01 16:31:31,559][00140] DAMAGECOUNT value on done: 695.0 [2024-08-01 16:31:31,628][00143] DAMAGECOUNT value on done: 409.0 [2024-08-01 16:31:31,632][00143] Sum rewards: -4.363, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.021', 'ARMOR': '0.090', 'HITCOUNT': '0.140', 'AMMO3': '0.183', 'WEAPON4': '0.200', 'weapon5': '0.222', 'weapon4': '0.272', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.552', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon3': '3.534', 'weapon2': '3.630'} [2024-08-01 16:31:32,189][00139] DAMAGECOUNT value on done: 405.0 [2024-08-01 16:31:32,190][00139] Sum rewards: -2.237, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.100', 'AMMO4': '-0.054', 'AMMO2': '-0.011', 'WEAPON4': '0.100', 'AMMO3': '0.126', 'HITCOUNT': '0.190', 'weapon4': '0.482', 'ARMOR': '0.543', 'DAMAGECOUNT': '0.738', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '2.984', 'weapon2': '4.464'} [2024-08-01 16:31:32,264][00135] DAMAGECOUNT value on done: 499.0 [2024-08-01 16:31:32,267][00135] Sum rewards: -0.871, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.470', 'AMMO2': '0.007', 'AMMO5': '0.007', 'AMMO4': '0.037', 'ARMOR': '0.044', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.170', 'AMMO3': '0.172', 'weapon7': '0.196', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.320', 'weapon4': '0.394', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.215', 'weapon2': '2.250', 'FRAGCOUNT': '4.000', 'weapon3': '4.196'} [2024-08-01 16:31:33,096][00141] DAMAGECOUNT value on done: 377.0 [2024-08-01 16:31:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2730.7, 300 sec: 2874.1). Total num frames: 9244672. Throughput: 0: 1391.7. Samples: 4627428. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:31:33,841][00034] Avg episode reward: [(0, '-1.419')] [2024-08-01 16:31:33,844][00112] Saving new best policy, reward=-1.419! [2024-08-01 16:31:34,248][00148] DAMAGECOUNT value on done: 438.0 [2024-08-01 16:31:34,253][00148] Sum rewards: -2.253, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.845', 'AMMO4': '-0.008', 'AMMO2': '-0.002', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'HITCOUNT': '0.110', 'AMMO3': '0.153', 'WEAPON4': '0.200', 'weapon4': '0.252', 'weapon5': '0.370', 'WEAPON5': '0.400', 'ARMOR': '0.492', 'DAMAGECOUNT': '0.675', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '3.188', 'weapon2': '3.574'} [2024-08-01 16:31:36,931][00144] DAMAGECOUNT value on done: 726.0 [2024-08-01 16:31:36,937][00144] Sum rewards: -1.745, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.840', 'AMMO2': '0.002', 'AMMO4': '0.011', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.052', 'AMMO3': '0.099', 'weapon5': '0.174', 'WEAPON4': '0.300', 'HITCOUNT': '0.340', 'WEAPON5': '0.400', 'WEAPON3': '0.700', 'weapon4': '0.800', 'DAMAGECOUNT': '1.323', 'FRAGCOUNT': '1.500', 'weapon3': '2.672', 'weapon2': '3.432'} [2024-08-01 16:31:36,950][00146] DAMAGECOUNT value on done: 829.0 [2024-08-01 16:31:36,952][00146] Sum rewards: -6.667, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.780', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.011', 'AMMO5': '0.014', 'weapon5': '0.022', 'AMMO4': '0.054', 'HITCOUNT': '0.140', 'ARMOR': '0.144', 'AMMO3': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.268', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.630', 'WEAPON3': '1.300', 'weapon2': '3.532', 'weapon3': '3.798'} [2024-08-01 16:31:37,452][00142] DAMAGECOUNT value on done: 690.0 [2024-08-01 16:31:37,454][00142] Sum rewards: 3.644, reward structure: {'DEATHCOUNT': '-3.750', 'HEALTH': '-1.628', 'AMMO5': '0.005', 'AMMO2': '0.017', 'WEAPON1': '0.040', 'HITCOUNT': '0.050', 'AMMO3': '0.063', 'ARMOR': '0.072', 'AMMO4': '0.086', 'WEAPON5': '0.100', 'weapon5': '0.238', 'WEAPON4': '0.300', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.780', 'weapon4': '0.790', 'FRAGCOUNT': '1.500', 'weapon2': '1.862', 'weapon3': '2.618'} [2024-08-01 16:31:37,721][00132] DAMAGECOUNT value on done: 488.0 [2024-08-01 16:31:37,725][00132] Sum rewards: -2.390, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.275', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'ARMOR': '0.004', 'AMMO5': '0.010', 'weapon5': '0.014', 'WEAPON1': '0.040', 'WEAPON5': '0.100', 'HITCOUNT': '0.170', 'AMMO3': '0.228', 'DAMAGECOUNT': '0.855', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon2': '3.204', 'weapon3': '4.490'} [2024-08-01 16:31:37,990][00145] DAMAGECOUNT value on done: 390.0 [2024-08-01 16:31:37,991][00145] Sum rewards: -1.232, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.155', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.050', 'AMMO2': '-0.010', 'AMMO5': '0.006', 'WEAPON1': '0.040', 'weapon4': '0.084', 'WEAPON4': '0.100', 'AMMO3': '0.108', 'HITCOUNT': '0.130', 'WEAPON5': '0.200', 'weapon5': '0.200', 'DAMAGECOUNT': '0.555', 'WEAPON3': '0.700', 'ARMOR': '0.984', 'weapon3': '3.108', 'weapon2': '3.768'} [2024-08-01 16:31:38,696][00136] DAMAGECOUNT value on done: 624.0 [2024-08-01 16:31:38,699][00136] Sum rewards: -0.146, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.405', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'weapon5': '0.056', 'weapon4': '0.088', 'WEAPON4': '0.100', 'AMMO3': '0.163', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'ARMOR': '0.477', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.822', 'FRAGCOUNT': '2.000', 'weapon2': '3.282', 'weapon3': '3.318'} [2024-08-01 16:31:38,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2662.4, 300 sec: 2860.3). Total num frames: 9252864. Throughput: 0: 1424.3. Samples: 4636320. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:31:38,840][00034] Avg episode reward: [(0, '-1.539')] [2024-08-01 16:31:39,003][00147] DAMAGECOUNT value on done: 677.0 [2024-08-01 16:31:39,091][00138] DAMAGECOUNT value on done: 547.0 [2024-08-01 16:31:39,095][00138] Sum rewards: -0.713, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.865', 'AMMO4': '-0.101', 'AMMO2': '-0.020', 'AMMO5': '0.017', 'WEAPON1': '0.040', 'weapon5': '0.148', 'AMMO3': '0.157', 'WEAPON5': '0.300', 'HITCOUNT': '0.350', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.419', 'weapon3': '2.626', 'FRAGCOUNT': '3.000', 'weapon2': '4.066'} [2024-08-01 16:31:39,536][00140] DAMAGECOUNT value on done: 650.0 [2024-08-01 16:31:39,538][00140] Sum rewards: -2.096, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO4': '-0.029', 'AMMO2': '-0.006', 'AMMO5': '0.009', 'weapon5': '0.046', 'ARMOR': '0.061', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.214', 'HITCOUNT': '0.260', 'weapon4': '0.320', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.302', 'FRAGCOUNT': '2.000', 'weapon2': '2.598', 'weapon3': '4.288'} [2024-08-01 16:31:39,676][00143] DAMAGECOUNT value on done: 399.0 [2024-08-01 16:31:39,679][00143] Sum rewards: -4.387, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.150', 'AMMO2': '0.006', 'AMMO5': '0.011', 'AMMO4': '0.031', 'ARMOR': '0.040', 'WEAPON1': '0.080', 'AMMO3': '0.149', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'weapon5': '0.276', 'WEAPON5': '0.300', 'weapon4': '0.502', 'DAMAGECOUNT': '0.675', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.252', 'weapon2': '3.730'} [2024-08-01 16:31:40,218][00135] DAMAGECOUNT value on done: 599.0 [2024-08-01 16:31:40,225][00135] Sum rewards: 0.200, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.000', 'AMMO4': '-0.063', 'AMMO2': '-0.012', 'ARMOR': '0.076', 'WEAPON4': '0.100', 'AMMO3': '0.102', 'HITCOUNT': '0.190', 'weapon4': '0.456', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.801', 'FRAGCOUNT': '2.000', 'weapon2': '2.818', 'weapon3': '3.432'} [2024-08-01 16:31:40,394][00134] Updated weights for policy 0, policy_version 2261 (0.0021) [2024-08-01 16:31:41,086][00141] DAMAGECOUNT value on done: 674.0 [2024-08-01 16:31:41,742][00137] DAMAGECOUNT value on done: 318.0 [2024-08-01 16:31:41,742][00137] Sum rewards: -1.067, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.955', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.060', 'HITCOUNT': '0.090', 'AMMO3': '0.108', 'weapon5': '0.174', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.444', 'weapon4': '0.568', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.206', 'weapon3': '2.856'} [2024-08-01 16:31:41,923][00148] DAMAGECOUNT value on done: 610.0 [2024-08-01 16:31:41,926][00148] Sum rewards: -2.438, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.570', 'AMMO4': '-0.046', 'AMMO2': '-0.009', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.060', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.128', 'weapon7': '0.136', 'AMMO3': '0.152', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.254', 'DAMAGECOUNT': '0.615', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon3': '2.988', 'weapon2': '3.126'} [2024-08-01 16:31:41,954][00139] DAMAGECOUNT value on done: 541.0 [2024-08-01 16:31:41,960][00139] Sum rewards: 1.264, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.910', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO5': '0.032', 'AMMO4': '0.075', 'AMMO3': '0.116', 'HITCOUNT': '0.250', 'weapon5': '0.364', 'WEAPON4': '0.400', 'FRAGCOUNT': '0.500', 'WEAPON5': '0.600', 'WEAPON3': '0.700', 'weapon4': '1.328', 'DAMAGECOUNT': '1.503', 'weapon2': '2.816', 'weapon3': '2.928'} [2024-08-01 16:31:43,839][00034] Fps is (10 sec: 2867.0, 60 sec: 2798.9, 300 sec: 2874.1). Total num frames: 9273344. Throughput: 0: 1435.2. Samples: 4640748. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:31:43,841][00034] Avg episode reward: [(0, '-1.471')] [2024-08-01 16:31:44,127][00148] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:31:44,775][00144] DAMAGECOUNT value on done: 490.0 [2024-08-01 16:31:44,781][00144] Sum rewards: -2.803, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.890', 'AMMO2': '0.006', 'AMMO4': '0.030', 'AMMO3': '0.163', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'weapon4': '0.232', 'DAMAGECOUNT': '0.705', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.482', 'weapon3': '4.688'} [2024-08-01 16:31:44,997][00146] DAMAGECOUNT value on done: 402.0 [2024-08-01 16:31:45,000][00146] Sum rewards: -1.471, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO4': '-0.038', 'AMMO2': '-0.008', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.090', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.153', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.375', 'weapon4': '0.538', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.842', 'weapon2': '3.782'} [2024-08-01 16:31:45,569][00142] DAMAGECOUNT value on done: 381.0 [2024-08-01 16:31:45,573][00142] Sum rewards: -3.591, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.640', 'FRAGCOUNT': '-1.000', 'AMMO4': '-0.004', 'AMMO2': '-0.001', 'AMMO5': '0.009', 'ARMOR': '0.035', 'weapon5': '0.068', 'weapon4': '0.078', 'WEAPON4': '0.100', 'AMMO3': '0.112', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'weapon2': '3.792', 'weapon3': '3.950'} [2024-08-01 16:31:46,715][00147] DAMAGECOUNT value on done: 429.0 [2024-08-01 16:31:46,720][00147] Sum rewards: -4.421, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.690', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'AMMO5': '0.006', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.147', 'weapon5': '0.186', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'ARMOR': '0.520', 'weapon4': '0.544', 'DAMAGECOUNT': '0.612', 'WEAPON3': '1.000', 'weapon2': '1.772', 'weapon3': '4.500'} [2024-08-01 16:31:46,746][00136] DAMAGECOUNT value on done: 600.0 [2024-08-01 16:31:46,749][00136] Sum rewards: -1.191, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.110', 'AMMO2': '0.018', 'AMMO5': '0.022', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'weapon4': '0.044', 'AMMO4': '0.090', 'weapon5': '0.190', 'WEAPON4': '0.200', 'AMMO3': '0.207', 'HITCOUNT': '0.230', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.825', 'WEAPON3': '1.100', 'weapon2': '2.454', 'FRAGCOUNT': '3.000', 'weapon3': '4.470'} [2024-08-01 16:31:47,050][00132] DAMAGECOUNT value on done: 688.0 [2024-08-01 16:31:47,052][00132] Sum rewards: -3.972, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.424', 'AMMO4': '-0.095', 'AMMO2': '-0.019', 'AMMO5': '0.005', 'weapon5': '0.024', 'WEAPON5': '0.100', 'HITCOUNT': '0.220', 'AMMO3': '0.221', 'FRAGCOUNT': '0.500', 'ARMOR': '0.604', 'DAMAGECOUNT': '0.846', 'WEAPON3': '1.200', 'weapon3': '3.514', 'weapon2': '3.832'} [2024-08-01 16:31:47,347][00145] DAMAGECOUNT value on done: 630.0 [2024-08-01 16:31:47,353][00145] Sum rewards: -1.283, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.204', 'AMMO2': '0.007', 'AMMO5': '0.017', 'AMMO4': '0.033', 'WEAPON1': '0.040', 'ARMOR': '0.060', 'AMMO3': '0.116', 'HITCOUNT': '0.200', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'weapon5': '0.312', 'weapon4': '0.430', 'DAMAGECOUNT': '0.564', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.792', 'weapon2': '3.400'} [2024-08-01 16:31:47,550][00143] DAMAGECOUNT value on done: 400.0 [2024-08-01 16:31:47,735][00140] DAMAGECOUNT value on done: 811.0 [2024-08-01 16:31:47,738][00140] Sum rewards: 1.666, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.550', 'AMMO5': '0.012', 'AMMO2': '0.019', 'WEAPON1': '0.060', 'AMMO4': '0.093', 'WEAPON4': '0.100', 'AMMO3': '0.131', 'weapon4': '0.170', 'weapon5': '0.268', 'WEAPON5': '0.300', 'HITCOUNT': '0.370', 'ARMOR': '0.474', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.485', 'weapon2': '2.436', 'FRAGCOUNT': '3.000', 'weapon3': '4.298'} [2024-08-01 16:31:48,029][00135] DAMAGECOUNT value on done: 535.0 [2024-08-01 16:31:48,030][00135] Sum rewards: 0.620, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.940', 'AMMO2': '0.005', 'AMMO5': '0.021', 'AMMO4': '0.022', 'WEAPON1': '0.040', 'HITCOUNT': '0.060', 'AMMO3': '0.118', 'weapon5': '0.276', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.597', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.500', 'weapon2': '3.134', 'weapon3': '3.988'} [2024-08-01 16:31:48,526][00138] DAMAGECOUNT value on done: 579.0 [2024-08-01 16:31:48,527][00138] Sum rewards: -2.225, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.270', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.004', 'ARMOR': '0.042', 'weapon5': '0.042', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.170', 'HITCOUNT': '0.180', 'weapon4': '0.208', 'DAMAGECOUNT': '0.675', 'WEAPON3': '1.100', 'weapon2': '1.858', 'weapon3': '5.332'} [2024-08-01 16:31:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2730.7, 300 sec: 2832.5). Total num frames: 9281536. Throughput: 0: 1447.2. Samples: 4649484. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:31:48,840][00034] Avg episode reward: [(0, '-1.625')] [2024-08-01 16:31:49,105][00141] DAMAGECOUNT value on done: 451.0 [2024-08-01 16:31:49,107][00141] Sum rewards: -2.823, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.491', 'AMMO2': '0.003', 'AMMO5': '0.005', 'AMMO4': '0.016', 'weapon5': '0.022', 'ARMOR': '0.072', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.190', 'AMMO3': '0.250', 'DAMAGECOUNT': '0.594', 'WEAPON3': '1.300', 'FRAGCOUNT': '3.000', 'weapon2': '3.394', 'weapon3': '3.872'} [2024-08-01 16:31:49,350][00132] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:31:49,972][00148] DAMAGECOUNT value on done: 446.0 [2024-08-01 16:31:49,973][00148] Sum rewards: -1.384, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.945', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.014', 'weapon5': '0.042', 'ARMOR': '0.056', 'WEAPON5': '0.100', 'AMMO3': '0.145', 'HITCOUNT': '0.150', 'WEAPON4': '0.200', 'weapon4': '0.350', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'weapon2': '3.504', 'weapon3': '3.506'} [2024-08-01 16:31:50,299][00137] DAMAGECOUNT value on done: 1121.0 [2024-08-01 16:31:50,302][00137] Sum rewards: 3.421, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.340', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.024', 'ARMOR': '0.024', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.102', 'HITCOUNT': '0.130', 'weapon5': '0.462', 'weapon4': '0.484', 'WEAPON5': '0.500', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.356', 'weapon3': '2.344', 'weapon2': '2.636', 'FRAGCOUNT': '3.000'} [2024-08-01 16:31:50,670][00139] DAMAGECOUNT value on done: 605.0 [2024-08-01 16:31:50,671][00139] Sum rewards: 2.291, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.264', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'weapon5': '0.024', 'ARMOR': '0.055', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.121', 'weapon4': '0.296', 'WEAPON5': '0.300', 'HITCOUNT': '0.320', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.170', 'weapon2': '2.768', 'weapon3': '3.818', 'FRAGCOUNT': '4.000'} [2024-08-01 16:31:52,262][00134] Updated weights for policy 0, policy_version 2271 (0.0020) [2024-08-01 16:31:52,710][00144] DAMAGECOUNT value on done: 524.0 [2024-08-01 16:31:52,714][00144] Sum rewards: 1.001, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.250', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'weapon5': '0.074', 'WEAPON5': '0.100', 'AMMO3': '0.133', 'HITCOUNT': '0.220', 'WEAPON4': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.855', 'weapon4': '0.956', 'weapon3': '2.766', 'FRAGCOUNT': '3.000', 'weapon2': '3.218'} [2024-08-01 16:31:53,122][00146] DAMAGECOUNT value on done: 460.0 [2024-08-01 16:31:53,130][00146] Sum rewards: -3.013, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO2': '0.022', 'weapon5': '0.038', 'AMMO4': '0.111', 'AMMO3': '0.173', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.652', 'DAMAGECOUNT': '0.720', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '2.260', 'weapon3': '4.010'} [2024-08-01 16:31:53,824][00142] DAMAGECOUNT value on done: 458.0 [2024-08-01 16:31:53,828][00142] Sum rewards: -4.577, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO2': '0.010', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'AMMO4': '0.047', 'ARMOR': '0.060', 'weapon5': '0.188', 'HITCOUNT': '0.200', 'AMMO3': '0.201', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.570', 'weapon4': '0.580', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.638', 'weapon3': '3.834'} [2024-08-01 16:31:53,838][00034] Fps is (10 sec: 2867.4, 60 sec: 2867.2, 300 sec: 2874.1). Total num frames: 9302016. Throughput: 0: 1459.7. Samples: 4658352. Policy #0 lag: (min: 0.0, avg: 3.8, max: 7.0) [2024-08-01 16:31:53,840][00034] Avg episode reward: [(0, '-1.521')] [2024-08-01 16:31:54,614][00136] DAMAGECOUNT value on done: 382.0 [2024-08-01 16:31:55,428][00132] DAMAGECOUNT value on done: 480.0 [2024-08-01 16:31:55,431][00132] Sum rewards: -4.346, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.770', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'AMMO5': '0.004', 'ARMOR': '0.004', 'WEAPON1': '0.020', 'weapon5': '0.092', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon4': '0.144', 'AMMO3': '0.254', 'HITCOUNT': '0.290', 'DAMAGECOUNT': '1.125', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '3.098', 'weapon3': '4.036'} [2024-08-01 16:31:55,476][00147] DAMAGECOUNT value on done: 735.0 [2024-08-01 16:31:55,476][00147] Sum rewards: -6.513, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'FRAGCOUNT': '-3.500', 'AMMO2': '0.003', 'ARMOR': '0.012', 'AMMO4': '0.015', 'AMMO5': '0.015', 'weapon4': '0.096', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.132', 'weapon5': '0.246', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.900', 'weapon2': '3.132', 'weapon3': '4.056'} [2024-08-01 16:31:55,688][00145] DAMAGECOUNT value on done: 659.0 [2024-08-01 16:31:55,696][00145] Sum rewards: 0.759, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.896', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.025', 'AMMO3': '0.123', 'HITCOUNT': '0.150', 'WEAPON5': '0.400', 'ARMOR': '0.462', 'DAMAGECOUNT': '0.492', 'weapon5': '0.524', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '2.680', 'weapon3': '3.866'} [2024-08-01 16:31:55,720][00140] DAMAGECOUNT value on done: 727.0 [2024-08-01 16:31:55,737][00140] Sum rewards: 3.990, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.360', 'AMMO5': '0.003', 'AMMO2': '0.004', 'AMMO4': '0.022', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO3': '0.085', 'WEAPON5': '0.100', 'weapon5': '0.170', 'WEAPON4': '0.200', 'HITCOUNT': '0.270', 'WEAPON3': '0.700', 'weapon4': '0.722', 'DAMAGECOUNT': '1.080', 'weapon2': '2.180', 'FRAGCOUNT': '3.000', 'weapon3': '3.742'} [2024-08-01 16:31:56,432][00143] DAMAGECOUNT value on done: 321.0 [2024-08-01 16:31:56,435][00143] Sum rewards: -5.342, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.535', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.094', 'AMMO2': '-0.019', 'AMMO5': '0.007', 'ARMOR': '0.008', 'WEAPON1': '0.020', 'HITCOUNT': '0.120', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.134', 'AMMO3': '0.135', 'weapon5': '0.170', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'DAMAGECOUNT': '0.318', 'WEAPON3': '0.800', 'weapon3': '2.542', 'weapon2': '3.662'} [2024-08-01 16:31:56,553][00138] DAMAGECOUNT value on done: 774.0 [2024-08-01 16:31:56,868][00135] DAMAGECOUNT value on done: 483.0 [2024-08-01 16:31:56,874][00135] Sum rewards: 0.846, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.127', 'AMMO4': '-0.043', 'AMMO2': '-0.009', 'AMMO5': '0.006', 'WEAPON1': '0.060', 'AMMO3': '0.098', 'WEAPON4': '0.100', 'WEAPON5': '0.200', 'HITCOUNT': '0.220', 'weapon5': '0.302', 'weapon4': '0.390', 'ARMOR': '0.539', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.777', 'FRAGCOUNT': '2.000', 'weapon3': '2.976', 'weapon2': '3.156'} [2024-08-01 16:31:58,112][00141] DAMAGECOUNT value on done: 324.0 [2024-08-01 16:31:58,118][00141] Sum rewards: -3.214, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.200', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.004', 'AMMO5': '0.016', 'AMMO4': '0.020', 'WEAPON1': '0.040', 'weapon7': '0.042', 'ARMOR': '0.108', 'HITCOUNT': '0.110', 'AMMO3': '0.121', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.362', 'WEAPON5': '0.400', 'weapon4': '0.408', 'DAMAGECOUNT': '0.420', 'WEAPON3': '0.600', 'weapon3': '2.858', 'weapon2': '3.426'} [2024-08-01 16:31:58,838][00034] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2860.3). Total num frames: 9314304. Throughput: 0: 1462.7. Samples: 4662912. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:31:58,840][00034] Avg episode reward: [(0, '-1.649')] [2024-08-01 16:31:58,909][00148] DAMAGECOUNT value on done: 476.0 [2024-08-01 16:31:58,946][00137] DAMAGECOUNT value on done: 395.0 [2024-08-01 16:31:58,949][00137] Sum rewards: -4.660, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.920', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.080', 'AMMO2': '-0.016', 'AMMO5': '0.004', 'ARMOR': '0.040', 'weapon5': '0.064', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.187', 'DAMAGECOUNT': '0.435', 'weapon4': '0.454', 'WEAPON3': '1.100', 'weapon3': '3.234', 'weapon2': '3.728'} [2024-08-01 16:31:59,005][00139] DAMAGECOUNT value on done: 495.0 [2024-08-01 16:32:01,538][00144] DAMAGECOUNT value on done: 287.0 [2024-08-01 16:32:01,543][00144] Sum rewards: 4.450, reward structure: {'DEATHCOUNT': '-3.750', 'HEALTH': '-1.480', 'AMMO4': '-0.013', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'weapon5': '0.068', 'HITCOUNT': '0.080', 'AMMO3': '0.092', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'DAMAGECOUNT': '0.267', 'weapon4': '0.468', 'WEAPON3': '0.500', 'ARMOR': '0.522', 'FRAGCOUNT': '2.000', 'weapon2': '2.722', 'weapon3': '2.772'} [2024-08-01 16:32:01,929][00146] DAMAGECOUNT value on done: 451.0 [2024-08-01 16:32:01,930][00146] Sum rewards: 3.287, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.750', 'AMMO4': '-0.076', 'AMMO2': '-0.015', 'AMMO5': '0.008', 'HITCOUNT': '0.040', 'AMMO3': '0.099', 'weapon5': '0.102', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.453', 'ARMOR': '0.570', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '2.920', 'weapon3': '3.636'} [2024-08-01 16:32:02,572][00142] DAMAGECOUNT value on done: 440.0 [2024-08-01 16:32:02,574][00142] Sum rewards: -6.598, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.145', 'AMMO4': '-0.099', 'AMMO2': '-0.020', 'AMMO5': '0.005', 'ARMOR': '0.024', 'weapon5': '0.066', 'weapon7': '0.080', 'WEAPON5': '0.100', 'AMMO6': '0.160', 'AMMO7': '0.160', 'HITCOUNT': '0.180', 'WEAPON7': '0.200', 'AMMO3': '0.204', 'DAMAGECOUNT': '0.465', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon3': '3.598', 'weapon2': '3.974'} [2024-08-01 16:32:03,422][00136] DAMAGECOUNT value on done: 922.0 [2024-08-01 16:32:03,427][00136] Sum rewards: -1.597, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO4': '-0.047', 'AMMO2': '-0.009', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO5': '0.025', 'weapon5': '0.072', 'WEAPON4': '0.100', 'AMMO3': '0.240', 'WEAPON5': '0.300', 'HITCOUNT': '0.320', 'weapon4': '0.578', 'DAMAGECOUNT': '1.200', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon2': '2.186', 'weapon3': '4.782'} [2024-08-01 16:32:03,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2860.3). Total num frames: 9326592. Throughput: 0: 1450.7. Samples: 4671156. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:32:03,840][00034] Avg episode reward: [(0, '-1.605')] [2024-08-01 16:32:04,190][00147] DAMAGECOUNT value on done: 664.0 [2024-08-01 16:32:04,202][00147] Sum rewards: -0.849, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.880', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.009', 'WEAPON1': '0.060', 'HITCOUNT': '0.080', 'AMMO3': '0.132', 'WEAPON5': '0.300', 'weapon5': '0.308', 'DAMAGECOUNT': '0.354', 'ARMOR': '0.499', 'WEAPON3': '0.900', 'weapon2': '3.582', 'weapon3': '3.856'} [2024-08-01 16:32:04,236][00132] DAMAGECOUNT value on done: 893.0 [2024-08-01 16:32:04,238][00132] Sum rewards: -0.606, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'AMMO4': '-0.056', 'AMMO2': '-0.011', 'AMMO5': '0.018', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO3': '0.215', 'weapon5': '0.270', 'WEAPON5': '0.300', 'HITCOUNT': '0.310', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.500', 'weapon2': '2.484', 'FRAGCOUNT': '2.500', 'weapon3': '4.334'} [2024-08-01 16:32:04,504][00140] DAMAGECOUNT value on done: 323.0 [2024-08-01 16:32:04,568][00145] DAMAGECOUNT value on done: 612.0 [2024-08-01 16:32:04,574][00145] Sum rewards: 2.534, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.940', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'AMMO5': '0.033', 'AMMO4': '0.053', 'AMMO3': '0.124', 'HITCOUNT': '0.200', 'WEAPON4': '0.300', 'weapon5': '0.442', 'WEAPON5': '0.500', 'weapon4': '0.548', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.416', 'FRAGCOUNT': '2.500', 'weapon2': '2.530', 'weapon3': '3.472'} [2024-08-01 16:32:05,450][00138] DAMAGECOUNT value on done: 616.0 [2024-08-01 16:32:05,451][00138] Sum rewards: 0.517, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.580', 'AMMO5': '0.005', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'weapon5': '0.054', 'AMMO4': '0.061', 'AMMO3': '0.098', 'WEAPON5': '0.100', 'HITCOUNT': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.498', 'WEAPON3': '0.600', 'weapon4': '0.846', 'FRAGCOUNT': '1.000', 'weapon3': '2.948', 'weapon2': '3.176'} [2024-08-01 16:32:05,705][00143] DAMAGECOUNT value on done: 617.0 [2024-08-01 16:32:05,713][00143] Sum rewards: -1.964, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.680', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.137', 'weapon4': '0.178', 'weapon5': '0.180', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.825', 'WEAPON3': '0.900', 'weapon2': '3.628', 'weapon3': '3.684', 'FRAGCOUNT': '4.000'} [2024-08-01 16:32:06,205][00135] DAMAGECOUNT value on done: 376.0 [2024-08-01 16:32:06,208][00135] Sum rewards: -5.463, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.012', 'weapon5': '0.168', 'AMMO3': '0.169', 'HITCOUNT': '0.170', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'ARMOR': '0.492', 'weapon4': '0.604', 'DAMAGECOUNT': '0.618', 'WEAPON3': '0.900', 'weapon2': '3.066', 'weapon3': '3.154'} [2024-08-01 16:32:06,487][00148] DAMAGECOUNT value on done: 481.0 [2024-08-01 16:32:06,490][00148] Sum rewards: 5.393, reward structure: {'DEATHCOUNT': '-3.000', 'HEALTH': '-1.110', 'AMMO4': '-0.070', 'AMMO2': '-0.014', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO3': '0.083', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'weapon5': '0.212', 'WEAPON3': '0.400', 'DAMAGECOUNT': '0.495', 'FRAGCOUNT': '2.000', 'weapon2': '2.718', 'weapon3': '3.242'} [2024-08-01 16:32:06,797][00137] DAMAGECOUNT value on done: 634.0 [2024-08-01 16:32:06,800][00137] Sum rewards: -1.642, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.714', 'AMMO4': '-0.053', 'AMMO2': '-0.010', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.062', 'AMMO3': '0.217', 'WEAPON5': '0.300', 'HITCOUNT': '0.340', 'WEAPON3': '1.400', 'DAMAGECOUNT': '1.530', 'weapon2': '2.396', 'FRAGCOUNT': '4.000', 'weapon3': '4.856'} [2024-08-01 16:32:07,247][00134] Updated weights for policy 0, policy_version 2281 (0.0020) [2024-08-01 16:32:07,463][00141] DAMAGECOUNT value on done: 468.0 [2024-08-01 16:32:07,466][00141] Sum rewards: -6.077, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.895', 'AMMO4': '-0.073', 'AMMO2': '-0.015', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'HITCOUNT': '0.200', 'AMMO3': '0.225', 'DAMAGECOUNT': '0.675', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.500', 'weapon2': '2.992', 'weapon3': '4.278'} [2024-08-01 16:32:07,633][00139] DAMAGECOUNT value on done: 974.0 [2024-08-01 16:32:07,635][00139] Sum rewards: 5.582, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.931', 'AMMO4': '-0.018', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'weapon7': '0.062', 'AMMO3': '0.144', 'AMMO6': '0.160', 'AMMO7': '0.160', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'weapon5': '0.256', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.305', 'weapon2': '2.720', 'weapon3': '4.530', 'FRAGCOUNT': '5.000'} [2024-08-01 16:32:08,839][00034] Fps is (10 sec: 3276.7, 60 sec: 2935.4, 300 sec: 2888.0). Total num frames: 9347072. Throughput: 0: 1444.3. Samples: 4679916. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:32:08,842][00034] Avg episode reward: [(0, '-1.429')] [2024-08-01 16:32:08,849][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002282_9347072.pth... [2024-08-01 16:32:09,019][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002114_8658944.pth [2024-08-01 16:32:09,626][00146] DAMAGECOUNT value on done: 498.0 [2024-08-01 16:32:09,628][00146] Sum rewards: 0.995, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.175', 'AMMO2': '0.007', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'AMMO4': '0.033', 'ARMOR': '0.100', 'AMMO3': '0.107', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon5': '0.134', 'weapon7': '0.190', 'WEAPON7': '0.200', 'HITCOUNT': '0.220', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon4': '0.534', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.819', 'FRAGCOUNT': '1.000', 'weapon2': '3.222', 'weapon3': '3.432'} [2024-08-01 16:32:09,934][00144] DAMAGECOUNT value on done: 847.0 [2024-08-01 16:32:09,938][00144] Sum rewards: -4.948, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.680', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'ARMOR': '0.024', 'AMMO5': '0.029', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'weapon5': '0.160', 'AMMO3': '0.269', 'weapon4': '0.310', 'HITCOUNT': '0.340', 'WEAPON5': '0.500', 'WEAPON3': '1.600', 'DAMAGECOUNT': '1.716', 'weapon2': '2.442', 'FRAGCOUNT': '3.000', 'weapon3': '4.484'} [2024-08-01 16:32:10,343][00142] DAMAGECOUNT value on done: 364.0 [2024-08-01 16:32:10,347][00142] Sum rewards: -5.486, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.152', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.028', 'AMMO2': '-0.006', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'weapon4': '0.112', 'HITCOUNT': '0.160', 'AMMO3': '0.178', 'weapon5': '0.354', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.516', 'ARMOR': '0.957', 'WEAPON3': '1.200', 'weapon2': '2.962', 'weapon3': '3.726'} [2024-08-01 16:32:11,722][00133] DAMAGECOUNT value on done: 316.0 [2024-08-01 16:32:11,726][00133] Sum rewards: -8.605, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.437', 'AMMO4': '-0.083', 'AMMO2': '-0.016', 'AMMO5': '0.008', 'ARMOR': '0.056', 'WEAPON1': '0.060', 'HITCOUNT': '0.230', 'AMMO3': '0.253', 'WEAPON5': '0.300', 'weapon5': '0.372', 'DAMAGECOUNT': '0.666', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.400', 'weapon3': '2.582', 'weapon2': '3.504'} [2024-08-01 16:32:12,192][00132] DAMAGECOUNT value on done: 871.0 [2024-08-01 16:32:12,194][00132] Sum rewards: -7.843, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.640', 'AMMO4': '-0.018', 'AMMO2': '-0.004', 'weapon4': '0.002', 'AMMO5': '0.020', 'weapon5': '0.036', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'AMMO3': '0.243', 'HITCOUNT': '0.280', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.930', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.500', 'weapon2': '2.920', 'weapon3': '4.686'} [2024-08-01 16:32:12,447][00136] DAMAGECOUNT value on done: 863.0 [2024-08-01 16:32:12,450][00136] Sum rewards: -4.188, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO4': '-0.081', 'AMMO2': '-0.016', 'AMMO5': '0.003', 'WEAPON1': '0.040', 'WEAPON5': '0.100', 'weapon5': '0.164', 'AMMO3': '0.230', 'HITCOUNT': '0.260', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.221', 'WEAPON3': '1.300', 'weapon2': '3.360', 'weapon3': '3.942'} [2024-08-01 16:32:12,532][00145] DAMAGECOUNT value on done: 355.0 [2024-08-01 16:32:12,533][00145] Sum rewards: -6.417, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.810', 'AMMO4': '-0.104', 'AMMO2': '-0.021', 'AMMO5': '0.010', 'ARMOR': '0.112', 'weapon5': '0.148', 'AMMO3': '0.174', 'HITCOUNT': '0.180', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.998', 'weapon2': '4.196'} [2024-08-01 16:32:12,592][00147] DAMAGECOUNT value on done: 669.0 [2024-08-01 16:32:12,593][00147] Sum rewards: 2.287, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.280', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'WEAPON5': '0.100', 'AMMO3': '0.115', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '0.762', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.420', 'weapon3': '4.012'} [2024-08-01 16:32:13,495][00138] DAMAGECOUNT value on done: 525.0 [2024-08-01 16:32:13,496][00138] Sum rewards: -2.998, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.895', 'AMMO2': '0.002', 'AMMO5': '0.010', 'AMMO4': '0.011', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'weapon5': '0.050', 'HITCOUNT': '0.100', 'AMMO3': '0.186', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.360', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '1.788', 'weapon3': '5.672'} [2024-08-01 16:32:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2846.4). Total num frames: 9355264. Throughput: 0: 1463.5. Samples: 4684392. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:32:13,840][00034] Avg episode reward: [(0, '-1.610')] [2024-08-01 16:32:13,853][00140] DAMAGECOUNT value on done: 462.0 [2024-08-01 16:32:13,858][00140] Sum rewards: 0.402, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'ARMOR': '0.004', 'AMMO5': '0.030', 'WEAPON1': '0.060', 'AMMO3': '0.098', 'HITCOUNT': '0.140', 'WEAPON4': '0.200', 'weapon5': '0.316', 'weapon4': '0.468', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.627', 'WEAPON3': '0.700', 'weapon3': '2.632', 'weapon2': '3.160', 'FRAGCOUNT': '4.000'} [2024-08-01 16:32:13,871][00143] DAMAGECOUNT value on done: 476.0 [2024-08-01 16:32:13,874][00143] Sum rewards: 1.369, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO4': '-0.087', 'AMMO2': '-0.017', 'AMMO5': '0.005', 'weapon5': '0.008', 'WEAPON5': '0.100', 'AMMO3': '0.149', 'weapon7': '0.158', 'HITCOUNT': '0.230', 'AMMO6': '0.320', 'AMMO7': '0.320', 'WEAPON7': '0.400', 'ARMOR': '0.511', 'DAMAGECOUNT': '0.816', 'WEAPON3': '1.000', 'weapon3': '3.280', 'weapon2': '3.786', 'FRAGCOUNT': '4.000'} [2024-08-01 16:32:14,272][00135] DAMAGECOUNT value on done: 522.0 [2024-08-01 16:32:14,274][00135] Sum rewards: 3.151, reward structure: {'DEATHCOUNT': '-3.000', 'HEALTH': '-1.235', 'FRAGCOUNT': '-0.500', 'AMMO5': '0.007', 'AMMO2': '0.007', 'AMMO4': '0.035', 'AMMO3': '0.050', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.136', 'HITCOUNT': '0.170', 'weapon5': '0.194', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'WEAPON3': '0.400', 'DAMAGECOUNT': '1.008', 'weapon4': '1.018', 'weapon2': '1.250', 'weapon3': '2.770'} [2024-08-01 16:32:15,048][00137] DAMAGECOUNT value on done: 682.0 [2024-08-01 16:32:15,055][00137] Sum rewards: -2.121, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO4': '-0.085', 'AMMO2': '-0.017', 'ARMOR': '0.016', 'AMMO5': '0.022', 'AMMO3': '0.138', 'weapon5': '0.230', 'HITCOUNT': '0.340', 'WEAPON5': '0.500', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.053', 'FRAGCOUNT': '2.000', 'weapon2': '3.462', 'weapon3': '3.880'} [2024-08-01 16:32:15,261][00141] DAMAGECOUNT value on done: 359.0 [2024-08-01 16:32:15,264][00141] Sum rewards: -2.020, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.371', 'AMMO4': '-0.067', 'AMMO2': '-0.013', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'AMMO3': '0.158', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'weapon5': '0.276', 'ARMOR': '0.468', 'DAMAGECOUNT': '0.753', 'WEAPON3': '1.100', 'weapon2': '2.816', 'FRAGCOUNT': '3.000', 'weapon3': '3.962'} [2024-08-01 16:32:15,499][00139] DAMAGECOUNT value on done: 318.0 [2024-08-01 16:32:15,500][00139] Sum rewards: 5.819, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.700', 'AMMO2': '0.002', 'AMMO5': '0.007', 'AMMO4': '0.011', 'AMMO3': '0.118', 'weapon5': '0.128', 'HITCOUNT': '0.130', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.381', 'weapon4': '0.442', 'ARMOR': '0.595', 'WEAPON3': '0.600', 'weapon2': '2.618', 'FRAGCOUNT': '3.000', 'weapon3': '3.586'} [2024-08-01 16:32:15,782][00148] DAMAGECOUNT value on done: 884.0 [2024-08-01 16:32:15,783][00148] Sum rewards: 1.223, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.530', 'AMMO2': '0.001', 'AMMO4': '0.004', 'AMMO5': '0.010', 'weapon5': '0.010', 'ARMOR': '0.028', 'WEAPON5': '0.100', 'AMMO3': '0.155', 'WEAPON4': '0.200', 'HITCOUNT': '0.300', 'weapon4': '0.574', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.227', 'weapon2': '1.956', 'FRAGCOUNT': '4.000', 'weapon3': '4.088'} [2024-08-01 16:32:17,836][00146] DAMAGECOUNT value on done: 459.0 [2024-08-01 16:32:17,838][00146] Sum rewards: -5.765, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.855', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'weapon5': '0.162', 'AMMO3': '0.174', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'WEAPON5': '0.300', 'ARMOR': '0.505', 'DAMAGECOUNT': '0.537', 'weapon4': '0.624', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon3': '2.864', 'weapon2': '3.594'} [2024-08-01 16:32:18,386][00144] DAMAGECOUNT value on done: 590.0 [2024-08-01 16:32:18,387][00144] Sum rewards: 0.497, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.280', 'AMMO2': '0.009', 'AMMO5': '0.029', 'WEAPON1': '0.040', 'AMMO4': '0.043', 'WEAPON4': '0.100', 'weapon5': '0.130', 'AMMO3': '0.206', 'weapon4': '0.286', 'HITCOUNT': '0.360', 'WEAPON5': '0.500', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.104', 'FRAGCOUNT': '1.500', 'weapon2': '1.684', 'weapon3': '4.936'} [2024-08-01 16:32:18,606][00142] DAMAGECOUNT value on done: 573.0 [2024-08-01 16:32:18,609][00142] Sum rewards: 5.933, reward structure: {'DEATHCOUNT': '-3.000', 'HEALTH': '-1.060', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'AMMO3': '0.050', 'WEAPON4': '0.100', 'HITCOUNT': '0.230', 'weapon4': '0.254', 'WEAPON3': '0.300', 'ARMOR': '0.470', 'DAMAGECOUNT': '0.909', 'weapon2': '2.060', 'weapon3': '2.646', 'FRAGCOUNT': '3.000'} [2024-08-01 16:32:18,838][00034] Fps is (10 sec: 2867.3, 60 sec: 2935.5, 300 sec: 2874.1). Total num frames: 9375744. Throughput: 0: 1464.5. Samples: 4693332. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:32:18,841][00034] Avg episode reward: [(0, '-1.322')] [2024-08-01 16:32:18,848][00112] Saving new best policy, reward=-1.322! [2024-08-01 16:32:20,062][00133] DAMAGECOUNT value on done: 451.0 [2024-08-01 16:32:20,066][00133] Sum rewards: -3.572, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.860', 'AMMO4': '-0.101', 'AMMO2': '-0.020', 'WEAPON1': '0.020', 'AMMO5': '0.031', 'ARMOR': '0.064', 'HITCOUNT': '0.140', 'AMMO3': '0.178', 'weapon5': '0.290', 'WEAPON5': '0.500', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.618', 'WEAPON3': '1.000', 'weapon3': '2.942', 'weapon2': '3.876'} [2024-08-01 16:32:20,466][00136] DAMAGECOUNT value on done: 1065.0 [2024-08-01 16:32:20,467][00136] Sum rewards: 2.398, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.962', 'AMMO4': '-0.059', 'AMMO2': '-0.012', 'AMMO5': '0.003', 'ARMOR': '0.035', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.102', 'AMMO3': '0.154', 'HITCOUNT': '0.250', 'weapon4': '0.392', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.521', 'FRAGCOUNT': '2.500', 'weapon2': '2.860', 'weapon3': '3.914'} [2024-08-01 16:32:20,510][00132] DAMAGECOUNT value on done: 359.0 [2024-08-01 16:32:20,511][00132] Sum rewards: 2.934, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.600', 'AMMO4': '-0.068', 'AMMO2': '-0.014', 'AMMO5': '0.012', 'ARMOR': '0.052', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.179', 'weapon5': '0.230', 'WEAPON5': '0.300', 'weapon4': '0.450', 'DAMAGECOUNT': '0.927', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '3.240', 'weapon3': '3.686'} [2024-08-01 16:32:20,752][00147] DAMAGECOUNT value on done: 532.0 [2024-08-01 16:32:20,758][00147] Sum rewards: -9.820, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.030', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.008', 'AMMO5': '0.012', 'AMMO4': '0.039', 'WEAPON1': '0.040', 'HITCOUNT': '0.100', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.252', 'weapon5': '0.262', 'AMMO3': '0.279', 'WEAPON4': '0.300', 'weapon4': '0.338', 'WEAPON3': '1.400', 'weapon3': '2.832', 'weapon2': '3.398'} [2024-08-01 16:32:20,950][00145] DAMAGECOUNT value on done: 515.0 [2024-08-01 16:32:20,953][00145] Sum rewards: -4.785, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.080', 'AMMO4': '-0.032', 'AMMO2': '-0.006', 'AMMO5': '0.014', 'ARMOR': '0.020', 'WEAPON1': '0.020', 'HITCOUNT': '0.120', 'AMMO3': '0.165', 'WEAPON5': '0.400', 'weapon5': '0.406', 'DAMAGECOUNT': '0.435', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.700', 'weapon2': '3.468', 'weapon3': '3.584'} [2024-08-01 16:32:21,704][00140] DAMAGECOUNT value on done: 957.0 [2024-08-01 16:32:21,704][00140] Sum rewards: 1.000, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.003', 'AMMO2': '0.012', 'WEAPON1': '0.040', 'ARMOR': '0.040', 'AMMO4': '0.058', 'WEAPON5': '0.100', 'weapon5': '0.142', 'AMMO3': '0.172', 'WEAPON4': '0.300', 'weapon4': '0.310', 'HITCOUNT': '0.340', 'WEAPON3': '1.100', 'DAMAGECOUNT': '2.046', 'weapon2': '2.762', 'FRAGCOUNT': '4.000', 'weapon3': '4.256'} [2024-08-01 16:32:22,097][00134] Updated weights for policy 0, policy_version 2291 (0.0023) [2024-08-01 16:32:22,132][00138] DAMAGECOUNT value on done: 592.0 [2024-08-01 16:32:22,132][00138] Sum rewards: -8.597, reward structure: {'DEATHCOUNT': '-14.250', 'HEALTH': '-5.812', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'weapon4': '0.098', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.201', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '1.170', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.764', 'weapon3': '3.520'} [2024-08-01 16:32:22,142][00143] DAMAGECOUNT value on done: 837.0 [2024-08-01 16:32:22,145][00143] Sum rewards: -1.632, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.410', 'AMMO4': '-0.063', 'AMMO2': '-0.013', 'AMMO5': '0.008', 'WEAPON5': '0.200', 'AMMO3': '0.227', 'HITCOUNT': '0.340', 'weapon5': '0.420', 'WEAPON3': '1.400', 'DAMAGECOUNT': '1.587', 'weapon2': '2.722', 'FRAGCOUNT': '3.000', 'weapon3': '4.200'} [2024-08-01 16:32:22,451][00135] DAMAGECOUNT value on done: 497.0 [2024-08-01 16:32:22,452][00135] Sum rewards: -1.433, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.910', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'WEAPON1': '0.020', 'AMMO5': '0.029', 'AMMO3': '0.141', 'HITCOUNT': '0.150', 'weapon5': '0.460', 'WEAPON3': '0.700', 'WEAPON5': '0.700', 'DAMAGECOUNT': '1.230', 'FRAGCOUNT': '2.500', 'weapon3': '3.044', 'weapon2': '3.288'} [2024-08-01 16:32:22,806][00137] DAMAGECOUNT value on done: 696.0 [2024-08-01 16:32:22,807][00137] Sum rewards: -2.131, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.570', 'AMMO4': '-0.092', 'AMMO2': '-0.018', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.064', 'HITCOUNT': '0.140', 'AMMO3': '0.181', 'weapon5': '0.284', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.420', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon3': '3.354', 'weapon2': '3.776'} [2024-08-01 16:32:23,458][00141] DAMAGECOUNT value on done: 327.0 [2024-08-01 16:32:23,839][00034] Fps is (10 sec: 3276.6, 60 sec: 2867.2, 300 sec: 2860.3). Total num frames: 9388032. Throughput: 0: 1464.2. Samples: 4702212. Policy #0 lag: (min: 0.0, avg: 2.8, max: 7.0) [2024-08-01 16:32:23,841][00034] Avg episode reward: [(0, '-1.533')] [2024-08-01 16:32:23,967][00148] DAMAGECOUNT value on done: 610.0 [2024-08-01 16:32:23,971][00148] Sum rewards: 0.549, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.715', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'HITCOUNT': '0.050', 'AMMO3': '0.076', 'WEAPON5': '0.300', 'weapon5': '0.378', 'DAMAGECOUNT': '0.576', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '2.780', 'weapon2': '4.192'} [2024-08-01 16:32:24,166][00139] DAMAGECOUNT value on done: 653.0 [2024-08-01 16:32:24,172][00139] Sum rewards: 0.469, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.570', 'AMMO4': '-0.059', 'AMMO2': '-0.012', 'weapon4': '0.002', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'AMMO3': '0.094', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.184', 'HITCOUNT': '0.190', 'WEAPON7': '0.200', 'weapon5': '0.244', 'WEAPON5': '0.300', 'ARMOR': '0.504', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.119', 'FRAGCOUNT': '2.000', 'weapon3': '2.986', 'weapon2': '4.316'} [2024-08-01 16:32:25,635][00146] DAMAGECOUNT value on done: 537.0 [2024-08-01 16:32:25,649][00146] Sum rewards: -4.434, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.000', 'AMMO4': '-0.063', 'AMMO2': '-0.013', 'AMMO5': '0.030', 'ARMOR': '0.050', 'WEAPON1': '0.060', 'HITCOUNT': '0.200', 'AMMO3': '0.205', 'weapon5': '0.254', 'WEAPON5': '0.600', 'DAMAGECOUNT': '0.906', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.500', 'weapon2': '2.720', 'weapon3': '4.566'} [2024-08-01 16:32:26,095][00141] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:32:26,597][00144] DAMAGECOUNT value on done: 831.0 [2024-08-01 16:32:26,603][00144] Sum rewards: 1.577, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.252', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.011', 'WEAPON1': '0.020', 'ARMOR': '0.072', 'AMMO3': '0.164', 'WEAPON4': '0.200', 'weapon5': '0.210', 'HITCOUNT': '0.240', 'WEAPON5': '0.300', 'weapon4': '0.820', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.128', 'weapon2': '1.686', 'FRAGCOUNT': '2.500', 'weapon3': '4.634'} [2024-08-01 16:32:26,764][00142] DAMAGECOUNT value on done: 313.0 [2024-08-01 16:32:26,768][00142] Sum rewards: 1.215, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.284', 'AMMO4': '-0.054', 'AMMO2': '-0.011', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'ARMOR': '0.064', 'AMMO3': '0.137', 'HITCOUNT': '0.140', 'weapon5': '0.196', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.552', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon3': '2.490', 'weapon2': '4.038'} [2024-08-01 16:32:28,293][00133] DAMAGECOUNT value on done: 446.0 [2024-08-01 16:32:28,336][00147] DAMAGECOUNT value on done: 502.0 [2024-08-01 16:32:28,342][00147] Sum rewards: -5.211, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.870', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.045', 'AMMO2': '-0.009', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon4': '0.024', 'weapon5': '0.048', 'ARMOR': '0.057', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'AMMO3': '0.175', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.345', 'WEAPON3': '1.100', 'weapon2': '3.596', 'weapon3': '4.054'} [2024-08-01 16:32:28,545][00136] DAMAGECOUNT value on done: 599.0 [2024-08-01 16:32:28,548][00136] Sum rewards: -4.661, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.672', 'AMMO4': '-0.016', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'weapon5': '0.022', 'ARMOR': '0.044', 'HITCOUNT': '0.100', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'AMMO3': '0.201', 'DAMAGECOUNT': '0.471', 'weapon4': '0.648', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.792', 'weapon3': '3.478'} [2024-08-01 16:32:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2874.1). Total num frames: 9404416. Throughput: 0: 1465.4. Samples: 4706688. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:32:28,840][00034] Avg episode reward: [(0, '-1.543')] [2024-08-01 16:32:29,162][00132] DAMAGECOUNT value on done: 539.0 [2024-08-01 16:32:29,167][00132] Sum rewards: -1.199, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.580', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'WEAPON1': '0.020', 'AMMO5': '0.021', 'ARMOR': '0.032', 'AMMO3': '0.121', 'weapon5': '0.192', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'WEAPON5': '0.300', 'weapon4': '0.514', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.275', 'FRAGCOUNT': '1.500', 'weapon2': '2.666', 'weapon3': '3.438'} [2024-08-01 16:32:29,758][00145] DAMAGECOUNT value on done: 640.0 [2024-08-01 16:32:30,091][00140] DAMAGECOUNT value on done: 714.0 [2024-08-01 16:32:30,092][00140] Sum rewards: -4.171, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.520', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon5': '0.092', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'weapon4': '0.178', 'WEAPON5': '0.200', 'AMMO3': '0.302', 'DAMAGECOUNT': '0.870', 'WEAPON3': '1.700', 'weapon2': '2.548', 'FRAGCOUNT': '4.000', 'weapon3': '4.686'} [2024-08-01 16:32:30,178][00143] DAMAGECOUNT value on done: 368.0 [2024-08-01 16:32:30,180][00143] Sum rewards: 1.629, reward structure: {'DEATHCOUNT': '-5.250', 'HEALTH': '-2.030', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.010', 'weapon4': '0.040', 'HITCOUNT': '0.080', 'AMMO3': '0.088', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.156', 'DAMAGECOUNT': '0.312', 'WEAPON3': '0.500', 'ARMOR': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '2.614', 'weapon3': '3.432'} [2024-08-01 16:32:30,478][00135] DAMAGECOUNT value on done: 729.0 [2024-08-01 16:32:30,638][00138] DAMAGECOUNT value on done: 649.0 [2024-08-01 16:32:30,640][00138] Sum rewards: -2.343, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.450', 'AMMO4': '-0.018', 'AMMO2': '-0.003', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO3': '0.192', 'weapon5': '0.206', 'WEAPON5': '0.300', 'HITCOUNT': '0.300', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.512', 'FRAGCOUNT': '2.500', 'weapon2': '3.012', 'weapon3': '4.192'} [2024-08-01 16:32:31,449][00141] DAMAGECOUNT value on done: 299.0 [2024-08-01 16:32:31,872][00137] DAMAGECOUNT value on done: 892.0 [2024-08-01 16:32:31,874][00137] Sum rewards: -1.833, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.356', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'AMMO2': '0.024', 'weapon5': '0.096', 'WEAPON5': '0.100', 'ARMOR': '0.112', 'AMMO4': '0.119', 'AMMO3': '0.228', 'WEAPON4': '0.300', 'weapon4': '0.482', 'HITCOUNT': '0.660', 'WEAPON3': '1.500', 'weapon2': '2.044', 'DAMAGECOUNT': '2.211', 'FRAGCOUNT': '4.500', 'weapon3': '4.624'} [2024-08-01 16:32:32,578][00148] DAMAGECOUNT value on done: 648.0 [2024-08-01 16:32:32,582][00148] Sum rewards: 3.038, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.740', 'AMMO2': '0.015', 'AMMO5': '0.018', 'ARMOR': '0.044', 'AMMO4': '0.073', 'AMMO3': '0.115', 'WEAPON4': '0.200', 'HITCOUNT': '0.210', 'WEAPON5': '0.300', 'weapon5': '0.362', 'weapon4': '0.502', 'DAMAGECOUNT': '0.702', 'WEAPON3': '0.900', 'weapon2': '1.544', 'FRAGCOUNT': '3.000', 'weapon3': '4.544'} [2024-08-01 16:32:32,689][00139] DAMAGECOUNT value on done: 1025.0 [2024-08-01 16:32:32,691][00139] Sum rewards: 2.803, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.560', 'AMMO4': '-0.083', 'AMMO2': '-0.017', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'AMMO3': '0.089', 'HITCOUNT': '0.160', 'WEAPON5': '0.300', 'weapon5': '0.440', 'ARMOR': '0.472', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.620', 'FRAGCOUNT': '2.000', 'weapon3': '3.218', 'weapon2': '3.266'} [2024-08-01 16:32:33,808][00139] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:32:33,838][00034] Fps is (10 sec: 3277.0, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 9420800. Throughput: 0: 1461.1. Samples: 4715232. Policy #0 lag: (min: 0.0, avg: 3.0, max: 7.0) [2024-08-01 16:32:33,841][00034] Avg episode reward: [(0, '-1.552')] [2024-08-01 16:32:34,084][00134] Updated weights for policy 0, policy_version 2301 (0.0019) [2024-08-01 16:32:34,636][00146] DAMAGECOUNT value on done: 760.0 [2024-08-01 16:32:34,641][00146] Sum rewards: 0.189, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO5': '0.013', 'AMMO2': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.065', 'AMMO3': '0.109', 'weapon4': '0.144', 'weapon5': '0.152', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.230', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.380', 'weapon2': '3.196', 'weapon3': '3.374', 'FRAGCOUNT': '5.000'} [2024-08-01 16:32:35,228][00144] DAMAGECOUNT value on done: 726.0 [2024-08-01 16:32:35,229][00144] Sum rewards: -2.666, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.013', 'AMMO2': '-0.003', 'AMMO5': '0.016', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'WEAPON4': '0.100', 'HITCOUNT': '0.180', 'AMMO3': '0.182', 'weapon5': '0.240', 'WEAPON5': '0.400', 'weapon4': '0.402', 'DAMAGECOUNT': '0.582', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '3.358', 'weapon3': '3.482'} [2024-08-01 16:32:35,970][00142] DAMAGECOUNT value on done: 660.0 [2024-08-01 16:32:35,983][00142] Sum rewards: -0.177, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.965', 'AMMO4': '-0.053', 'AMMO2': '-0.010', 'AMMO5': '0.005', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'AMMO3': '0.084', 'HITCOUNT': '0.130', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.272', 'WEAPON3': '0.600', 'weapon4': '0.640', 'DAMAGECOUNT': '0.780', 'FRAGCOUNT': '1.000', 'weapon3': '2.238', 'weapon2': '4.126'} [2024-08-01 16:32:36,049][00147] DAMAGECOUNT value on done: 418.0 [2024-08-01 16:32:36,052][00147] Sum rewards: -1.221, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.550', 'AMMO2': '0.008', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'AMMO4': '0.041', 'weapon4': '0.054', 'WEAPON4': '0.100', 'AMMO3': '0.103', 'HITCOUNT': '0.200', 'weapon5': '0.316', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.855', 'FRAGCOUNT': '2.000', 'weapon2': '2.352', 'weapon3': '4.062'} [2024-08-01 16:32:37,229][00132] DAMAGECOUNT value on done: 885.0 [2024-08-01 16:32:37,232][00132] Sum rewards: 2.314, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.830', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'ARMOR': '0.059', 'WEAPON4': '0.100', 'AMMO3': '0.194', 'weapon5': '0.216', 'HITCOUNT': '0.300', 'weapon4': '0.394', 'WEAPON5': '0.400', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.515', 'weapon2': '2.222', 'weapon3': '4.188', 'FRAGCOUNT': '5.000'} [2024-08-01 16:32:37,279][00136] DAMAGECOUNT value on done: 595.0 [2024-08-01 16:32:37,284][00136] Sum rewards: -4.576, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.172', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'AMMO3': '0.216', 'ARMOR': '0.454', 'DAMAGECOUNT': '0.630', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.872', 'weapon3': '4.370'} [2024-08-01 16:32:37,676][00143] DAMAGECOUNT value on done: 467.0 [2024-08-01 16:32:37,680][00145] DAMAGECOUNT value on done: 1183.0 [2024-08-01 16:32:37,686][00145] Sum rewards: 3.550, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.782', 'AMMO2': '0.004', 'AMMO4': '0.018', 'WEAPON1': '0.020', 'AMMO5': '0.029', 'ARMOR': '0.032', 'weapon4': '0.058', 'AMMO3': '0.131', 'weapon5': '0.150', 'WEAPON4': '0.200', 'HITCOUNT': '0.290', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.482', 'FRAGCOUNT': '2.000', 'weapon2': '3.146', 'weapon3': '4.322'} [2024-08-01 16:32:37,855][00133] DAMAGECOUNT value on done: 807.0 [2024-08-01 16:32:37,856][00133] Sum rewards: -2.888, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.100', 'AMMO4': '-0.039', 'AMMO2': '-0.008', 'AMMO5': '0.014', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.165', 'HITCOUNT': '0.180', 'weapon5': '0.304', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.597', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon3': '3.160', 'weapon2': '3.778'} [2024-08-01 16:32:37,971][00135] DAMAGECOUNT value on done: 550.0 [2024-08-01 16:32:37,972][00135] Sum rewards: -3.807, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.097', 'AMMO2': '-0.019', 'ARMOR': '0.024', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'HITCOUNT': '0.180', 'AMMO3': '0.227', 'weapon4': '0.492', 'DAMAGECOUNT': '0.588', 'WEAPON3': '1.200', 'FRAGCOUNT': '3.000', 'weapon3': '3.190', 'weapon2': '4.008'} [2024-08-01 16:32:37,989][00136] Large shaping reward -2.549 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:32:38,534][00138] DAMAGECOUNT value on done: 517.0 [2024-08-01 16:32:38,540][00140] DAMAGECOUNT value on done: 593.0 [2024-08-01 16:32:38,537][00138] Sum rewards: -4.795, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.845', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'ARMOR': '0.060', 'WEAPON5': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.197', 'WEAPON4': '0.200', 'weapon4': '0.360', 'DAMAGECOUNT': '0.540', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '3.558', 'weapon3': '3.712'} [2024-08-01 16:32:38,542][00140] Sum rewards: -7.349, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.320', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon5': '0.044', 'weapon4': '0.058', 'WEAPON4': '0.100', 'AMMO3': '0.184', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.765', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.936', 'weapon3': '4.642'} [2024-08-01 16:32:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2874.1). Total num frames: 9433088. Throughput: 0: 1466.7. Samples: 4724352. Policy #0 lag: (min: 0.0, avg: 3.5, max: 6.0) [2024-08-01 16:32:38,840][00034] Avg episode reward: [(0, '-1.577')] [2024-08-01 16:32:38,946][00141] DAMAGECOUNT value on done: 377.0 [2024-08-01 16:32:38,950][00141] Sum rewards: -0.620, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.665', 'AMMO2': '0.014', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'AMMO4': '0.068', 'weapon5': '0.074', 'AMMO3': '0.117', 'HITCOUNT': '0.150', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.441', 'weapon4': '0.622', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '3.198', 'weapon3': '3.798'} [2024-08-01 16:32:40,172][00148] DAMAGECOUNT value on done: 166.0 [2024-08-01 16:32:40,180][00148] Sum rewards: -0.138, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO2': '0.009', 'AMMO5': '0.014', 'AMMO4': '0.044', 'weapon5': '0.076', 'HITCOUNT': '0.120', 'AMMO3': '0.122', 'WEAPON5': '0.200', 'weapon4': '0.244', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.405', 'ARMOR': '0.507', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon3': '3.258', 'weapon2': '3.422'} [2024-08-01 16:32:40,436][00139] DAMAGECOUNT value on done: 677.0 [2024-08-01 16:32:40,440][00139] Sum rewards: -3.257, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO4': '-0.080', 'AMMO2': '-0.016', 'AMMO5': '0.022', 'AMMO3': '0.215', 'weapon5': '0.224', 'HITCOUNT': '0.300', 'WEAPON5': '0.300', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.422', 'FRAGCOUNT': '1.500', 'weapon2': '3.286', 'weapon3': '3.960'} [2024-08-01 16:32:41,359][00137] DAMAGECOUNT value on done: 685.0 [2024-08-01 16:32:41,360][00137] Sum rewards: -2.841, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'AMMO5': '0.006', 'WEAPON1': '0.040', 'ARMOR': '0.092', 'HITCOUNT': '0.110', 'AMMO3': '0.140', 'WEAPON5': '0.200', 'weapon5': '0.220', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.660', 'WEAPON3': '1.000', 'weapon2': '2.996', 'weapon3': '3.784'} [2024-08-01 16:32:42,667][00144] DAMAGECOUNT value on done: 622.0 [2024-08-01 16:32:42,676][00144] Sum rewards: 2.987, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.350', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.012', 'ARMOR': '0.016', 'WEAPON1': '0.020', 'AMMO3': '0.079', 'WEAPON5': '0.200', 'weapon5': '0.204', 'HITCOUNT': '0.230', 'WEAPON3': '0.500', 'DAMAGECOUNT': '0.729', 'weapon3': '2.744', 'FRAGCOUNT': '3.000', 'weapon2': '3.598'} [2024-08-01 16:32:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2874.1). Total num frames: 9449472. Throughput: 0: 1465.3. Samples: 4728852. Policy #0 lag: (min: 0.0, avg: 3.7, max: 8.0) [2024-08-01 16:32:43,841][00034] Avg episode reward: [(0, '-1.536')] [2024-08-01 16:32:44,831][00136] DAMAGECOUNT value on done: 638.0 [2024-08-01 16:32:44,835][00132] DAMAGECOUNT value on done: 272.0 [2024-08-01 16:32:44,836][00136] Sum rewards: 1.582, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'ARMOR': '0.004', 'AMMO5': '0.013', 'WEAPON1': '0.040', 'AMMO3': '0.083', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.128', 'weapon4': '0.144', 'HITCOUNT': '0.180', 'WEAPON7': '0.200', 'WEAPON5': '0.400', 'weapon5': '0.570', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.203', 'FRAGCOUNT': '1.500', 'weapon2': '3.002', 'weapon3': '3.574'} [2024-08-01 16:32:44,886][00146] DAMAGECOUNT value on done: 316.0 [2024-08-01 16:32:45,337][00145] DAMAGECOUNT value on done: 246.0 [2024-08-01 16:32:45,711][00143] DAMAGECOUNT value on done: 752.0 [2024-08-01 16:32:45,715][00143] Sum rewards: -2.594, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.170', 'AMMO4': '-0.010', 'AMMO2': '-0.002', 'weapon4': '0.030', 'WEAPON1': '0.040', 'ARMOR': '0.044', 'WEAPON4': '0.100', 'AMMO3': '0.162', 'HITCOUNT': '0.280', 'DAMAGECOUNT': '0.933', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.748', 'weapon3': '4.550'} [2024-08-01 16:32:45,952][00135] DAMAGECOUNT value on done: 519.0 [2024-08-01 16:32:46,162][00138] DAMAGECOUNT value on done: 679.0 [2024-08-01 16:32:46,163][00138] Sum rewards: -1.569, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.245', 'AMMO2': '0.004', 'AMMO5': '0.005', 'AMMO4': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'weapon4': '0.114', 'WEAPON5': '0.200', 'weapon5': '0.208', 'AMMO3': '0.222', 'HITCOUNT': '0.370', 'DAMAGECOUNT': '0.984', 'WEAPON3': '1.100', 'FRAGCOUNT': '3.000', 'weapon2': '3.212', 'weapon3': '3.578'} [2024-08-01 16:32:46,228][00140] DAMAGECOUNT value on done: 561.0 [2024-08-01 16:32:46,231][00140] Sum rewards: 4.503, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.740', 'AMMO4': '-0.039', 'AMMO2': '-0.008', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'HITCOUNT': '0.090', 'WEAPON4': '0.100', 'AMMO3': '0.108', 'weapon5': '0.132', 'WEAPON5': '0.200', 'ARMOR': '0.492', 'weapon4': '0.568', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.756', 'weapon2': '1.654', 'weapon3': '2.942', 'FRAGCOUNT': '3.000'} [2024-08-01 16:32:46,332][00142] DAMAGECOUNT value on done: 757.0 [2024-08-01 16:32:46,790][00141] DAMAGECOUNT value on done: 520.0 [2024-08-01 16:32:46,794][00141] Sum rewards: -0.873, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO2': '0.006', 'AMMO5': '0.010', 'AMMO4': '0.031', 'weapon5': '0.038', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'AMMO3': '0.203', 'HITCOUNT': '0.230', 'weapon4': '0.414', 'ARMOR': '0.520', 'DAMAGECOUNT': '0.783', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.200', 'weapon2': '2.006', 'weapon3': '4.926'} [2024-08-01 16:32:47,723][00148] DAMAGECOUNT value on done: 832.0 [2024-08-01 16:32:47,724][00148] Sum rewards: -0.137, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO5': '0.007', 'AMMO2': '0.009', 'WEAPON1': '0.020', 'AMMO4': '0.043', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'weapon4': '0.128', 'weapon5': '0.150', 'AMMO3': '0.183', 'WEAPON5': '0.200', 'HITCOUNT': '0.260', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.197', 'weapon2': '2.416', 'weapon3': '4.728', 'FRAGCOUNT': '5.000'} [2024-08-01 16:32:47,917][00133] DAMAGECOUNT value on done: 602.0 [2024-08-01 16:32:47,918][00133] Sum rewards: -3.488, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.130', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.009', 'weapon5': '0.028', 'weapon7': '0.114', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.185', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'HITCOUNT': '0.250', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.915', 'WEAPON3': '1.100', 'weapon2': '3.110', 'weapon3': '4.322'} [2024-08-01 16:32:47,992][00139] DAMAGECOUNT value on done: 206.0 [2024-08-01 16:32:48,384][00134] Updated weights for policy 0, policy_version 2311 (0.0027) [2024-08-01 16:32:48,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3072.0, 300 sec: 2874.1). Total num frames: 9465856. Throughput: 0: 1483.7. Samples: 4737924. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:32:48,840][00034] Avg episode reward: [(0, '-1.598')] [2024-08-01 16:32:50,110][00144] DAMAGECOUNT value on done: 881.0 [2024-08-01 16:32:50,111][00144] Sum rewards: -5.958, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.690', 'AMMO4': '-0.055', 'AMMO2': '-0.011', 'AMMO5': '0.014', 'WEAPON1': '0.040', 'ARMOR': '0.044', 'WEAPON4': '0.100', 'HITCOUNT': '0.130', 'weapon5': '0.166', 'AMMO3': '0.229', 'WEAPON5': '0.300', 'weapon4': '0.316', 'DAMAGECOUNT': '0.519', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '3.134', 'weapon3': '3.506'} [2024-08-01 16:32:50,496][00137] DAMAGECOUNT value on done: 581.0 [2024-08-01 16:32:50,497][00137] Sum rewards: 2.189, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.700', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'ARMOR': '0.044', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.127', 'weapon7': '0.136', 'weapon5': '0.158', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.495', 'weapon4': '0.520', 'WEAPON3': '0.600', 'weapon3': '1.880', 'FRAGCOUNT': '3.000', 'weapon2': '3.842'} [2024-08-01 16:32:52,250][00136] DAMAGECOUNT value on done: 561.0 [2024-08-01 16:32:52,251][00136] Sum rewards: -1.262, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO2': '0.007', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.033', 'weapon5': '0.156', 'AMMO3': '0.199', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '0.810', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.854', 'weapon3': '4.590'} [2024-08-01 16:32:52,300][00132] DAMAGECOUNT value on done: 748.0 [2024-08-01 16:32:52,302][00132] Sum rewards: -0.830, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.205', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'weapon5': '0.152', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'AMMO3': '0.214', 'HITCOUNT': '0.340', 'weapon4': '0.478', 'DAMAGECOUNT': '1.113', 'WEAPON3': '1.200', 'FRAGCOUNT': '3.000', 'weapon2': '3.146', 'weapon3': '3.794'} [2024-08-01 16:32:52,742][00145] DAMAGECOUNT value on done: 521.0 [2024-08-01 16:32:52,745][00145] Sum rewards: -2.288, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO2': '0.001', 'AMMO4': '0.007', 'AMMO5': '0.010', 'weapon5': '0.048', 'weapon4': '0.126', 'AMMO3': '0.156', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.260', 'DAMAGECOUNT': '0.900', 'WEAPON3': '1.100', 'FRAGCOUNT': '3.000', 'weapon2': '3.406', 'weapon3': '4.008'} [2024-08-01 16:32:53,692][00140] DAMAGECOUNT value on done: 337.0 [2024-08-01 16:32:53,692][00138] DAMAGECOUNT value on done: 923.0 [2024-08-01 16:32:53,695][00138] Sum rewards: 0.938, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.023', 'AMMO2': '-0.004', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'weapon5': '0.146', 'AMMO3': '0.148', 'HITCOUNT': '0.300', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.287', 'FRAGCOUNT': '2.000', 'weapon2': '3.002', 'weapon3': '4.370'} [2024-08-01 16:32:53,698][00146] DAMAGECOUNT value on done: 625.0 [2024-08-01 16:32:53,698][00146] Sum rewards: -0.166, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'AMMO2': '0.005', 'WEAPON1': '0.020', 'AMMO4': '0.027', 'AMMO5': '0.030', 'ARMOR': '0.044', 'AMMO3': '0.152', 'WEAPON4': '0.200', 'HITCOUNT': '0.260', 'weapon5': '0.270', 'weapon4': '0.412', 'WEAPON5': '0.500', 'DAMAGECOUNT': '0.930', 'WEAPON3': '1.100', 'weapon2': '1.720', 'FRAGCOUNT': '3.000', 'weapon3': '4.734'} [2024-08-01 16:32:53,846][00034] Fps is (10 sec: 2865.1, 60 sec: 2935.1, 300 sec: 2874.1). Total num frames: 9478144. Throughput: 0: 1494.7. Samples: 4747188. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 16:32:53,847][00034] Avg episode reward: [(0, '-1.512')] [2024-08-01 16:32:54,044][00143] DAMAGECOUNT value on done: 482.0 [2024-08-01 16:32:54,047][00143] Sum rewards: -5.811, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.810', 'FRAGCOUNT': '-2.000', 'AMMO4': '-0.086', 'AMMO2': '-0.017', 'AMMO5': '0.024', 'weapon5': '0.046', 'AMMO3': '0.123', 'HITCOUNT': '0.150', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.627', 'WEAPON3': '0.900', 'weapon3': '3.432', 'weapon2': '3.500'} [2024-08-01 16:32:54,263][00135] DAMAGECOUNT value on done: 344.0 [2024-08-01 16:32:54,265][00135] Sum rewards: -0.035, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.995', 'AMMO4': '-0.091', 'AMMO2': '-0.018', 'AMMO5': '0.003', 'WEAPON1': '0.040', 'ARMOR': '0.092', 'WEAPON5': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.121', 'weapon5': '0.122', 'DAMAGECOUNT': '0.312', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon3': '3.240', 'weapon2': '3.630'} [2024-08-01 16:32:54,866][00142] DAMAGECOUNT value on done: 605.0 [2024-08-01 16:32:54,869][00142] Sum rewards: -3.579, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.645', 'AMMO2': '0.001', 'AMMO4': '0.006', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'weapon4': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.221', 'weapon5': '0.238', 'HITCOUNT': '0.280', 'WEAPON5': '0.300', 'DAMAGECOUNT': '1.200', 'WEAPON3': '1.400', 'FRAGCOUNT': '1.500', 'weapon2': '2.014', 'weapon3': '5.002'} [2024-08-01 16:32:55,181][00141] DAMAGECOUNT value on done: 474.0 [2024-08-01 16:32:55,184][00141] Sum rewards: -0.815, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.300', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'AMMO5': '0.008', 'weapon4': '0.010', 'WEAPON1': '0.040', 'weapon5': '0.066', 'ARMOR': '0.088', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'AMMO3': '0.105', 'HITCOUNT': '0.120', 'DAMAGECOUNT': '0.297', 'WEAPON3': '0.800', 'weapon2': '2.944', 'weapon3': '3.334'} [2024-08-01 16:32:55,199][00148] DAMAGECOUNT value on done: 465.0 [2024-08-01 16:32:55,202][00148] Sum rewards: -4.689, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.550', 'AMMO4': '-0.007', 'AMMO2': '-0.001', 'AMMO5': '0.020', 'weapon5': '0.040', 'HITCOUNT': '0.120', 'AMMO3': '0.137', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'weapon4': '0.378', 'DAMAGECOUNT': '0.450', 'ARMOR': '0.501', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '3.440', 'weapon3': '3.634'} [2024-08-01 16:32:56,107][00139] DAMAGECOUNT value on done: 424.0 [2024-08-01 16:32:56,113][00139] Sum rewards: -0.228, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.186', 'AMMO5': '0.010', 'AMMO2': '0.016', 'WEAPON1': '0.040', 'AMMO4': '0.080', 'weapon4': '0.080', 'weapon5': '0.096', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.190', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.375', 'ARMOR': '0.499', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.908', 'weapon3': '4.394'} [2024-08-01 16:32:56,303][00133] DAMAGECOUNT value on done: 617.0 [2024-08-01 16:32:58,728][00137] DAMAGECOUNT value on done: 753.0 [2024-08-01 16:32:58,731][00137] Sum rewards: 5.793, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.945', 'AMMO4': '-0.020', 'AMMO2': '-0.004', 'ARMOR': '0.004', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.132', 'HITCOUNT': '0.190', 'WEAPON7': '0.200', 'weapon5': '0.234', 'weapon7': '0.236', 'weapon4': '0.272', 'WEAPON5': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.785', 'weapon3': '2.994', 'weapon2': '3.744', 'FRAGCOUNT': '5.000'} [2024-08-01 16:32:58,838][00034] Fps is (10 sec: 3276.9, 60 sec: 3072.0, 300 sec: 2901.9). Total num frames: 9498624. Throughput: 0: 1494.9. Samples: 4751664. Policy #0 lag: (min: 0.0, avg: 3.6, max: 7.0) [2024-08-01 16:32:58,840][00034] Avg episode reward: [(0, '-1.634')] [2024-08-01 16:32:59,769][00136] DAMAGECOUNT value on done: 661.0 [2024-08-01 16:32:59,773][00136] Sum rewards: -1.869, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO2': '0.000', 'AMMO4': '0.000', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.152', 'AMMO3': '0.194', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'weapon5': '0.206', 'HITCOUNT': '0.260', 'weapon4': '0.538', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.554', 'weapon2': '2.478', 'FRAGCOUNT': '2.500', 'weapon3': '3.908'} [2024-08-01 16:33:00,758][00132] DAMAGECOUNT value on done: 774.0 [2024-08-01 16:33:00,761][00132] Sum rewards: -0.201, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.345', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'ARMOR': '0.008', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'weapon5': '0.110', 'AMMO6': '0.120', 'AMMO7': '0.120', 'HITCOUNT': '0.130', 'weapon7': '0.168', 'AMMO3': '0.175', 'WEAPON7': '0.200', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.570', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.518', 'weapon3': '4.010'} [2024-08-01 16:33:01,142][00145] DAMAGECOUNT value on done: 638.0 [2024-08-01 16:33:01,146][00145] Sum rewards: -5.447, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.800', 'AMMO2': '0.001', 'AMMO5': '0.004', 'AMMO4': '0.005', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'WEAPON5': '0.100', 'WEAPON4': '0.200', 'AMMO3': '0.219', 'weapon5': '0.224', 'HITCOUNT': '0.270', 'weapon4': '0.440', 'DAMAGECOUNT': '0.939', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.374', 'weapon3': '4.208'} [2024-08-01 16:33:01,179][00146] DAMAGECOUNT value on done: 454.0 [2024-08-01 16:33:01,180][00140] DAMAGECOUNT value on done: 940.0 [2024-08-01 16:33:01,184][00140] Sum rewards: 1.497, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.693', 'AMMO4': '-0.068', 'AMMO2': '-0.013', 'AMMO5': '0.013', 'weapon5': '0.152', 'AMMO3': '0.166', 'HITCOUNT': '0.170', 'WEAPON5': '0.300', 'ARMOR': '0.503', 'DAMAGECOUNT': '0.510', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.774', 'weapon3': '4.434'} [2024-08-01 16:33:01,183][00146] Sum rewards: -0.820, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.715', 'AMMO2': '0.004', 'AMMO5': '0.012', 'AMMO4': '0.021', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'AMMO3': '0.097', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'DAMAGECOUNT': '0.390', 'WEAPON5': '0.400', 'weapon5': '0.456', 'WEAPON3': '0.500', 'FRAGCOUNT': '0.500', 'weapon4': '0.560', 'weapon3': '2.388', 'weapon2': '3.040'} [2024-08-01 16:33:02,067][00138] DAMAGECOUNT value on done: 1050.0 [2024-08-01 16:33:02,073][00138] Sum rewards: -5.134, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.042', 'AMMO2': '-0.008', 'weapon5': '0.006', 'AMMO5': '0.010', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon4': '0.128', 'AMMO3': '0.192', 'HITCOUNT': '0.340', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.116', 'WEAPON3': '1.300', 'weapon2': '3.468', 'weapon3': '3.896'} [2024-08-01 16:33:02,836][00148] DAMAGECOUNT value on done: 681.0 [2024-08-01 16:33:02,840][00148] Sum rewards: 2.035, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO4': '-0.058', 'AMMO2': '-0.011', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'WEAPON4': '0.100', 'AMMO3': '0.179', 'weapon5': '0.212', 'WEAPON5': '0.300', 'HITCOUNT': '0.360', 'weapon4': '0.500', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.473', 'weapon2': '2.530', 'FRAGCOUNT': '4.000', 'weapon3': '4.020'} [2024-08-01 16:33:03,334][00134] Updated weights for policy 0, policy_version 2321 (0.0020) [2024-08-01 16:33:03,529][00142] DAMAGECOUNT value on done: 624.0 [2024-08-01 16:33:03,550][00142] Sum rewards: -1.875, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.800', 'AMMO4': '-0.050', 'AMMO2': '-0.010', 'weapon5': '0.018', 'AMMO5': '0.020', 'WEAPON1': '0.020', 'ARMOR': '0.052', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.190', 'WEAPON5': '0.300', 'weapon4': '0.440', 'DAMAGECOUNT': '0.762', 'WEAPON3': '1.200', 'weapon2': '2.636', 'weapon3': '2.836', 'FRAGCOUNT': '3.000'} [2024-08-01 16:33:03,601][00143] DAMAGECOUNT value on done: 563.0 [2024-08-01 16:33:03,601][00143] Sum rewards: -6.116, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.820', 'AMMO5': '0.009', 'AMMO2': '0.025', 'ARMOR': '0.040', 'weapon5': '0.112', 'AMMO4': '0.123', 'AMMO3': '0.153', 'HITCOUNT': '0.170', 'WEAPON5': '0.200', 'WEAPON4': '0.300', 'weapon4': '0.460', 'DAMAGECOUNT': '0.810', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.040', 'weapon3': '4.162'} [2024-08-01 16:33:03,763][00135] DAMAGECOUNT value on done: 509.0 [2024-08-01 16:33:03,838][00034] Fps is (10 sec: 2869.3, 60 sec: 3003.7, 300 sec: 2874.1). Total num frames: 9506816. Throughput: 0: 1493.1. Samples: 4760520. Policy #0 lag: (min: 0.0, avg: 3.4, max: 7.0) [2024-08-01 16:33:03,840][00034] Avg episode reward: [(0, '-1.624')] [2024-08-01 16:33:04,391][00139] DAMAGECOUNT value on done: 417.0 [2024-08-01 16:33:04,394][00139] Sum rewards: -4.401, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'weapon4': '0.084', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'HITCOUNT': '0.140', 'AMMO3': '0.160', 'DAMAGECOUNT': '0.258', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon2': '2.614', 'weapon3': '4.606'} [2024-08-01 16:33:04,673][00141] DAMAGECOUNT value on done: 695.0 [2024-08-01 16:33:04,679][00141] Sum rewards: -1.092, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.700', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.004', 'weapon5': '0.064', 'HITCOUNT': '0.090', 'AMMO3': '0.096', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'ARMOR': '0.158', 'weapon4': '0.164', 'DAMAGECOUNT': '0.390', 'WEAPON3': '0.600', 'weapon3': '2.550', 'weapon2': '4.584'} [2024-08-01 16:33:05,293][00133] DAMAGECOUNT value on done: 444.0 [2024-08-01 16:33:05,298][00133] Sum rewards: 1.088, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.270', 'AMMO4': '-0.085', 'AMMO2': '-0.017', 'ARMOR': '0.016', 'AMMO5': '0.019', 'WEAPON1': '0.040', 'AMMO3': '0.146', 'HITCOUNT': '0.150', 'WEAPON5': '0.400', 'weapon5': '0.462', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.840', 'FRAGCOUNT': '3.000', 'weapon2': '3.244', 'weapon3': '3.592'} [2024-08-01 16:33:08,187][00137] DAMAGECOUNT value on done: 618.0 [2024-08-01 16:33:08,190][00137] Sum rewards: -4.772, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.460', 'AMMO2': '0.000', 'AMMO4': '0.001', 'AMMO5': '0.012', 'ARMOR': '0.020', 'WEAPON1': '0.020', 'AMMO3': '0.184', 'WEAPON4': '0.200', 'HITCOUNT': '0.240', 'WEAPON5': '0.300', 'weapon4': '0.324', 'weapon5': '0.376', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '1.065', 'WEAPON3': '1.100', 'weapon2': '3.064', 'weapon3': '3.532'} [2024-08-01 16:33:08,811][00132] DAMAGECOUNT value on done: 857.0 [2024-08-01 16:33:08,814][00132] Sum rewards: -5.715, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.150', 'FRAGCOUNT': '-1.500', 'AMMO2': '0.001', 'AMMO4': '0.003', 'AMMO5': '0.011', 'WEAPON1': '0.040', 'ARMOR': '0.072', 'WEAPON4': '0.100', 'weapon4': '0.192', 'AMMO3': '0.203', 'weapon5': '0.224', 'HITCOUNT': '0.250', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.930', 'WEAPON3': '1.300', 'weapon2': '2.004', 'weapon3': '4.804'} [2024-08-01 16:33:08,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 9523200. Throughput: 0: 1495.0. Samples: 4769484. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:33:08,841][00034] Avg episode reward: [(0, '-1.496')] [2024-08-01 16:33:08,977][00140] DAMAGECOUNT value on done: 260.0 [2024-08-01 16:33:08,978][00140] Sum rewards: -4.704, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.131', 'AMMO4': '-0.054', 'AMMO2': '-0.011', 'weapon4': '0.014', 'AMMO5': '0.024', 'WEAPON1': '0.040', 'ARMOR': '0.042', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.154', 'weapon5': '0.232', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.420', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.900', 'weapon3': '3.036', 'weapon2': '4.010'} [2024-08-01 16:33:09,172][00145] DAMAGECOUNT value on done: 939.0 [2024-08-01 16:33:09,177][00145] Sum rewards: 0.312, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.780', 'AMMO5': '0.005', 'AMMO2': '0.015', 'WEAPON1': '0.020', 'ARMOR': '0.028', 'AMMO4': '0.076', 'WEAPON4': '0.100', 'AMMO3': '0.109', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'weapon5': '0.228', 'weapon4': '0.278', 'WEAPON3': '0.800', 'DAMAGECOUNT': '1.662', 'weapon2': '2.726', 'weapon3': '3.434', 'FRAGCOUNT': '4.000'} [2024-08-01 16:33:10,021][00138] DAMAGECOUNT value on done: 665.0 [2024-08-01 16:33:10,033][00138] Sum rewards: 1.026, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.965', 'AMMO4': '-0.015', 'AMMO2': '-0.003', 'AMMO5': '0.005', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'AMMO3': '0.132', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.240', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.035', 'FRAGCOUNT': '2.000', 'weapon2': '2.696', 'weapon3': '3.932'} [2024-08-01 16:33:10,605][00146] DAMAGECOUNT value on done: 609.0 [2024-08-01 16:33:11,150][00143] DAMAGECOUNT value on done: 710.0 [2024-08-01 16:33:11,153][00143] Sum rewards: -5.208, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.420', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.017', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.135', 'weapon4': '0.164', 'WEAPON5': '0.300', 'HITCOUNT': '0.350', 'weapon5': '0.354', 'ARMOR': '0.491', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.095', 'weapon2': '2.760', 'weapon3': '4.212'} [2024-08-01 16:33:11,288][00135] DAMAGECOUNT value on done: 626.0 [2024-08-01 16:33:11,293][00135] Sum rewards: -6.163, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.225', 'AMMO4': '-0.090', 'AMMO2': '-0.018', 'AMMO5': '0.007', 'ARMOR': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.124', 'WEAPON5': '0.200', 'weapon5': '0.276', 'WEAPON3': '0.400', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.519', 'weapon4': '0.522', 'weapon3': '2.250', 'weapon2': '3.642'} [2024-08-01 16:33:12,014][00142] DAMAGECOUNT value on done: 506.0 [2024-08-01 16:33:12,018][00142] Sum rewards: -3.315, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.080', 'AMMO4': '-0.067', 'AMMO2': '-0.013', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.056', 'weapon5': '0.128', 'WEAPON5': '0.200', 'HITCOUNT': '0.240', 'AMMO3': '0.243', 'DAMAGECOUNT': '0.885', 'WEAPON3': '1.400', 'weapon2': '2.882', 'FRAGCOUNT': '4.000', 'weapon3': '4.528'} [2024-08-01 16:33:12,231][00141] DAMAGECOUNT value on done: 766.0 [2024-08-01 16:33:12,232][00141] Sum rewards: -5.552, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.310', 'AMMO4': '-0.051', 'AMMO2': '-0.010', 'AMMO5': '0.022', 'ARMOR': '0.042', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.261', 'weapon4': '0.320', 'weapon5': '0.322', 'WEAPON5': '0.500', 'DAMAGECOUNT': '1.104', 'WEAPON3': '1.500', 'FRAGCOUNT': '2.000', 'weapon2': '3.206', 'weapon3': '3.772'} [2024-08-01 16:33:12,493][00139] DAMAGECOUNT value on done: 742.0 [2024-08-01 16:33:12,494][00139] Sum rewards: 5.076, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.668', 'AMMO5': '0.010', 'AMMO2': '0.011', 'WEAPON1': '0.020', 'weapon5': '0.038', 'AMMO4': '0.057', 'WEAPON5': '0.100', 'AMMO3': '0.138', 'weapon4': '0.174', 'WEAPON4': '0.200', 'HITCOUNT': '0.300', 'ARMOR': '0.472', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.194', 'weapon2': '1.744', 'FRAGCOUNT': '4.000', 'weapon3': '5.136'} [2024-08-01 16:33:13,662][00133] DAMAGECOUNT value on done: 464.0 [2024-08-01 16:33:13,670][00133] Sum rewards: -1.683, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.853', 'AMMO5': '0.007', 'AMMO2': '0.013', 'weapon4': '0.026', 'AMMO4': '0.064', 'ARMOR': '0.084', 'WEAPON4': '0.100', 'weapon5': '0.114', 'AMMO3': '0.133', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.525', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '3.488', 'weapon3': '4.106'} [2024-08-01 16:33:13,839][00034] Fps is (10 sec: 3276.6, 60 sec: 3072.0, 300 sec: 2888.0). Total num frames: 9539584. Throughput: 0: 1498.4. Samples: 4774116. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:33:13,842][00034] Avg episode reward: [(0, '-1.879')] [2024-08-01 16:33:15,011][00134] Updated weights for policy 0, policy_version 2331 (0.0030) [2024-08-01 16:33:16,602][00137] DAMAGECOUNT value on done: 623.0 [2024-08-01 16:33:16,603][00137] Sum rewards: 0.269, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.545', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'weapon5': '0.026', 'WEAPON5': '0.100', 'AMMO3': '0.121', 'HITCOUNT': '0.290', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.050', 'FRAGCOUNT': '2.000', 'weapon2': '2.964', 'weapon3': '4.594'} [2024-08-01 16:33:17,125][00140] DAMAGECOUNT value on done: 690.0 [2024-08-01 16:33:17,128][00140] Sum rewards: -6.414, reward structure: {'DEATHCOUNT': '-12.750', 'HEALTH': '-5.080', 'AMMO4': '-0.097', 'AMMO2': '-0.019', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'weapon5': '0.078', 'HITCOUNT': '0.180', 'AMMO3': '0.218', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.969', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon3': '3.580', 'weapon2': '3.842'} [2024-08-01 16:33:17,273][00132] DAMAGECOUNT value on done: 355.0 [2024-08-01 16:33:17,274][00132] Sum rewards: -1.171, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO2': '0.019', 'weapon4': '0.028', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO5': '0.041', 'AMMO4': '0.094', 'HITCOUNT': '0.110', 'AMMO3': '0.176', 'WEAPON4': '0.200', 'weapon5': '0.358', 'WEAPON5': '0.700', 'DAMAGECOUNT': '0.975', 'WEAPON3': '1.100', 'weapon2': '2.326', 'FRAGCOUNT': '3.000', 'weapon3': '4.270'} [2024-08-01 16:33:17,660][00145] DAMAGECOUNT value on done: 823.0 [2024-08-01 16:33:17,663][00145] Sum rewards: 1.234, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.553', 'AMMO4': '-0.003', 'AMMO2': '-0.000', 'AMMO5': '0.018', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.176', 'HITCOUNT': '0.250', 'WEAPON5': '0.300', 'weapon5': '0.410', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.032', 'weapon2': '2.214', 'FRAGCOUNT': '4.000', 'weapon3': '4.250'} [2024-08-01 16:33:18,431][00138] DAMAGECOUNT value on done: 758.0 [2024-08-01 16:33:18,437][00138] Sum rewards: -2.010, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.915', 'AMMO4': '-0.050', 'AMMO2': '-0.010', 'AMMO5': '0.007', 'ARMOR': '0.104', 'AMMO3': '0.148', 'weapon5': '0.150', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.570', 'weapon4': '0.774', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '3.166', 'weapon2': '3.306'} [2024-08-01 16:33:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 9551872. Throughput: 0: 1504.5. Samples: 4782936. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:33:18,841][00034] Avg episode reward: [(0, '-1.832')] [2024-08-01 16:33:19,175][00146] DAMAGECOUNT value on done: 389.0 [2024-08-01 16:33:19,177][00146] Sum rewards: -2.471, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO2': '0.003', 'AMMO5': '0.007', 'AMMO4': '0.015', 'WEAPON1': '0.040', 'ARMOR': '0.048', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'weapon4': '0.142', 'AMMO3': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.236', 'DAMAGECOUNT': '0.285', 'WEAPON3': '0.900', 'FRAGCOUNT': '1.000', 'weapon2': '3.022', 'weapon3': '3.740'} [2024-08-01 16:33:19,794][00143] DAMAGECOUNT value on done: 376.0 [2024-08-01 16:33:19,794][00143] Sum rewards: 2.240, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.720', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'weapon5': '0.040', 'AMMO3': '0.074', 'WEAPON5': '0.100', 'HITCOUNT': '0.120', 'ARMOR': '0.139', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.360', 'WEAPON3': '0.600', 'weapon4': '0.694', 'FRAGCOUNT': '1.000', 'weapon2': '2.298', 'weapon3': '2.844'} [2024-08-01 16:33:19,844][00135] DAMAGECOUNT value on done: 288.0 [2024-08-01 16:33:19,844][00135] Sum rewards: 1.266, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.863', 'AMMO5': '0.005', 'AMMO2': '0.012', 'WEAPON1': '0.020', 'HITCOUNT': '0.060', 'AMMO4': '0.061', 'AMMO3': '0.134', 'WEAPON5': '0.200', 'weapon5': '0.204', 'DAMAGECOUNT': '0.345', 'WEAPON3': '0.500', 'FRAGCOUNT': '1.000', 'weapon3': '1.594', 'weapon2': '3.494'} [2024-08-01 16:33:20,424][00139] DAMAGECOUNT value on done: 444.0 [2024-08-01 16:33:20,425][00139] Sum rewards: -2.640, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.575', 'AMMO2': '0.001', 'AMMO5': '0.005', 'AMMO4': '0.006', 'weapon5': '0.034', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.199', 'weapon4': '0.412', 'ARMOR': '0.477', 'DAMAGECOUNT': '0.522', 'WEAPON3': '1.000', 'FRAGCOUNT': '1.000', 'weapon2': '2.398', 'weapon3': '3.530'} [2024-08-01 16:33:20,700][00142] DAMAGECOUNT value on done: 793.0 [2024-08-01 16:33:20,703][00142] Sum rewards: -0.188, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO4': '-0.011', 'AMMO2': '-0.002', 'AMMO5': '0.013', 'ARMOR': '0.030', 'WEAPON1': '0.040', 'AMMO3': '0.136', 'weapon5': '0.168', 'HITCOUNT': '0.170', 'WEAPON4': '0.300', 'WEAPON5': '0.300', 'weapon4': '0.874', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.596', 'weapon3': '2.642', 'weapon2': '3.316', 'FRAGCOUNT': '4.000'} [2024-08-01 16:33:22,289][00133] DAMAGECOUNT value on done: 639.0 [2024-08-01 16:33:22,290][00133] Sum rewards: -3.601, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'AMMO4': '-0.117', 'AMMO2': '-0.023', 'AMMO5': '0.005', 'WEAPON1': '0.040', 'ARMOR': '0.048', 'WEAPON5': '0.100', 'AMMO3': '0.170', 'HITCOUNT': '0.360', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.320', 'weapon3': '2.760', 'FRAGCOUNT': '3.000', 'weapon2': '4.456'} [2024-08-01 16:33:23,838][00034] Fps is (10 sec: 3277.0, 60 sec: 3072.0, 300 sec: 2888.0). Total num frames: 9572352. Throughput: 0: 1500.8. Samples: 4791888. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:33:23,841][00034] Avg episode reward: [(0, '-1.751')] [2024-08-01 16:33:24,772][00137] DAMAGECOUNT value on done: 393.0 [2024-08-01 16:33:24,778][00137] Sum rewards: -3.233, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.895', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'WEAPON1': '0.020', 'AMMO5': '0.020', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.161', 'weapon5': '0.208', 'WEAPON5': '0.300', 'weapon4': '0.454', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.570', 'WEAPON3': '1.000', 'weapon3': '3.320', 'weapon2': '3.640'} [2024-08-01 16:33:25,134][00140] DAMAGECOUNT value on done: 287.0 [2024-08-01 16:33:25,934][00132] DAMAGECOUNT value on done: 628.0 [2024-08-01 16:33:25,940][00132] Sum rewards: 1.457, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.300', 'AMMO4': '-0.030', 'AMMO2': '-0.006', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'weapon4': '0.036', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.128', 'weapon5': '0.146', 'HITCOUNT': '0.150', 'AMMO3': '0.167', 'WEAPON5': '0.200', 'WEAPON7': '0.200', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.800', 'weapon2': '3.016', 'weapon3': '3.442'} [2024-08-01 16:33:26,378][00145] DAMAGECOUNT value on done: 490.0 [2024-08-01 16:33:26,384][00145] Sum rewards: -1.538, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.260', 'AMMO4': '-0.060', 'AMMO2': '-0.012', 'AMMO5': '0.018', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'weapon5': '0.140', 'HITCOUNT': '0.150', 'AMMO3': '0.170', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.435', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '2.524', 'weapon3': '4.136'} [2024-08-01 16:33:26,986][00146] DAMAGECOUNT value on done: 450.0 [2024-08-01 16:33:26,989][00146] Sum rewards: -3.965, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO5': '0.005', 'AMMO2': '0.008', 'weapon4': '0.022', 'AMMO4': '0.042', 'HITCOUNT': '0.150', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'weapon5': '0.214', 'AMMO3': '0.242', 'DAMAGECOUNT': '0.864', 'WEAPON3': '1.200', 'FRAGCOUNT': '1.500', 'weapon2': '2.564', 'weapon3': '4.514'} [2024-08-01 16:33:27,093][00138] DAMAGECOUNT value on done: 548.0 [2024-08-01 16:33:27,094][00138] Sum rewards: -4.328, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'AMMO4': '-0.077', 'AMMO2': '-0.015', 'AMMO5': '0.021', 'ARMOR': '0.036', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'HITCOUNT': '0.150', 'AMMO3': '0.191', 'weapon5': '0.220', 'weapon4': '0.264', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.804', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '2.984', 'weapon2': '4.174'} [2024-08-01 16:33:28,402][00143] DAMAGECOUNT value on done: 712.0 [2024-08-01 16:33:28,690][00142] DAMAGECOUNT value on done: 484.0 [2024-08-01 16:33:28,694][00142] Sum rewards: -0.898, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'AMMO2': '0.025', 'ARMOR': '0.056', 'AMMO3': '0.123', 'AMMO4': '0.127', 'HITCOUNT': '0.200', 'weapon5': '0.206', 'WEAPON5': '0.300', 'WEAPON4': '0.300', 'weapon4': '0.474', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.924', 'FRAGCOUNT': '2.000', 'weapon2': '2.412', 'weapon3': '3.542'} [2024-08-01 16:33:28,839][00034] Fps is (10 sec: 3276.7, 60 sec: 3003.7, 300 sec: 2915.8). Total num frames: 9584640. Throughput: 0: 1502.9. Samples: 4796484. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:33:28,840][00034] Avg episode reward: [(0, '-1.797')] [2024-08-01 16:33:28,856][00139] DAMAGECOUNT value on done: 396.0 [2024-08-01 16:33:28,857][00139] Sum rewards: -6.443, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.170', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.064', 'AMMO2': '-0.013', 'AMMO5': '0.009', 'ARMOR': '0.048', 'weapon5': '0.054', 'WEAPON4': '0.100', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'AMMO3': '0.220', 'weapon4': '0.304', 'DAMAGECOUNT': '0.657', 'WEAPON3': '1.200', 'weapon3': '3.402', 'weapon2': '3.420'} [2024-08-01 16:33:29,352][00134] Updated weights for policy 0, policy_version 2341 (0.0020) [2024-08-01 16:33:30,255][00133] DAMAGECOUNT value on done: 353.0 [2024-08-01 16:33:30,260][00133] Sum rewards: 2.398, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.760', 'AMMO4': '-0.066', 'AMMO2': '-0.013', 'HITCOUNT': '0.080', 'AMMO3': '0.094', 'DAMAGECOUNT': '0.255', 'WEAPON3': '0.500', 'ARMOR': '0.500', 'FRAGCOUNT': '1.000', 'weapon2': '2.608', 'weapon3': '3.700'} [2024-08-01 16:33:32,534][00137] DAMAGECOUNT value on done: 609.0 [2024-08-01 16:33:32,535][00137] Sum rewards: 0.601, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO4': '-0.006', 'AMMO2': '-0.001', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.024', 'weapon4': '0.034', 'AMMO3': '0.170', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'weapon5': '0.294', 'WEAPON5': '0.300', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.942', 'weapon3': '2.922', 'FRAGCOUNT': '3.000', 'weapon2': '4.122'} [2024-08-01 16:33:32,870][00140] DAMAGECOUNT value on done: 589.0 [2024-08-01 16:33:32,873][00140] Sum rewards: -4.333, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.880', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.072', 'AMMO2': '-0.014', 'AMMO5': '0.016', 'ARMOR': '0.032', 'WEAPON1': '0.040', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.142', 'AMMO3': '0.159', 'HITCOUNT': '0.160', 'WEAPON7': '0.200', 'WEAPON5': '0.300', 'weapon5': '0.386', 'DAMAGECOUNT': '0.504', 'WEAPON3': '0.900', 'weapon2': '2.944', 'weapon3': '3.860'} [2024-08-01 16:33:33,710][00132] DAMAGECOUNT value on done: 465.0 [2024-08-01 16:33:33,715][00132] Sum rewards: -5.475, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.720', 'AMMO5': '0.009', 'ARMOR': '0.012', 'AMMO2': '0.019', 'WEAPON1': '0.040', 'AMMO4': '0.096', 'weapon5': '0.104', 'HITCOUNT': '0.140', 'WEAPON5': '0.200', 'AMMO3': '0.245', 'WEAPON4': '0.300', 'weapon4': '0.438', 'DAMAGECOUNT': '0.585', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '3.218', 'weapon3': '3.538'} [2024-08-01 16:33:33,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2901.9). Total num frames: 9601024. Throughput: 0: 1503.5. Samples: 4805580. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:33:33,841][00034] Avg episode reward: [(0, '-1.777')] [2024-08-01 16:33:34,146][00145] DAMAGECOUNT value on done: 869.0 [2024-08-01 16:33:35,238][00146] DAMAGECOUNT value on done: 404.0 [2024-08-01 16:33:35,251][00146] Sum rewards: 0.538, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO2': '0.004', 'AMMO5': '0.014', 'AMMO4': '0.021', 'ARMOR': '0.088', 'AMMO3': '0.127', 'weapon5': '0.158', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'WEAPON4': '0.300', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.810', 'weapon4': '0.926', 'FRAGCOUNT': '2.000', 'weapon2': '2.046', 'weapon3': '3.254'} [2024-08-01 16:33:35,297][00138] DAMAGECOUNT value on done: 549.0 [2024-08-01 16:33:35,298][00138] Sum rewards: -3.087, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.565', 'AMMO4': '-0.078', 'AMMO2': '-0.015', 'AMMO5': '0.004', 'ARMOR': '0.012', 'WEAPON1': '0.020', 'WEAPON5': '0.100', 'weapon5': '0.106', 'AMMO3': '0.222', 'HITCOUNT': '0.270', 'DAMAGECOUNT': '1.050', 'WEAPON3': '1.300', 'FRAGCOUNT': '2.000', 'weapon2': '3.240', 'weapon3': '4.498'} [2024-08-01 16:33:37,329][00139] DAMAGECOUNT value on done: 492.0 [2024-08-01 16:33:37,335][00139] Sum rewards: -5.066, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.165', 'FRAGCOUNT': '-0.500', 'AMMO2': '0.003', 'AMMO4': '0.013', 'AMMO5': '0.018', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'weapon4': '0.048', 'WEAPON4': '0.200', 'weapon5': '0.206', 'HITCOUNT': '0.220', 'AMMO3': '0.225', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.795', 'WEAPON3': '1.200', 'weapon3': '3.226', 'weapon2': '3.486'} [2024-08-01 16:33:37,504][00142] DAMAGECOUNT value on done: 649.0 [2024-08-01 16:33:37,508][00142] Sum rewards: 1.887, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.018', 'AMMO2': '0.007', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'AMMO4': '0.033', 'ARMOR': '0.061', 'weapon4': '0.076', 'WEAPON4': '0.100', 'weapon5': '0.166', 'AMMO3': '0.170', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.960', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '2.554', 'weapon3': '4.614'} [2024-08-01 16:33:37,659][00143] DAMAGECOUNT value on done: 507.0 [2024-08-01 16:33:37,665][00143] Sum rewards: -0.069, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.305', 'AMMO4': '-0.005', 'AMMO2': '-0.001', 'WEAPON1': '0.020', 'ARMOR': '0.034', 'AMMO3': '0.143', 'HITCOUNT': '0.150', 'WEAPON4': '0.300', 'DAMAGECOUNT': '0.594', 'weapon4': '0.752', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon3': '3.198', 'weapon2': '3.400'} [2024-08-01 16:33:38,839][00034] Fps is (10 sec: 2867.1, 60 sec: 3003.7, 300 sec: 2901.9). Total num frames: 9613312. Throughput: 0: 1482.1. Samples: 4813872. Policy #0 lag: (min: 0.0, avg: 2.5, max: 7.0) [2024-08-01 16:33:38,841][00034] Avg episode reward: [(0, '-1.920')] [2024-08-01 16:33:39,699][00133] DAMAGECOUNT value on done: 460.0 [2024-08-01 16:33:39,699][00133] Sum rewards: 1.950, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.490', 'AMMO4': '-0.075', 'AMMO2': '-0.015', 'AMMO5': '0.011', 'WEAPON1': '0.020', 'HITCOUNT': '0.100', 'WEAPON4': '0.100', 'AMMO3': '0.139', 'weapon5': '0.182', 'DAMAGECOUNT': '0.282', 'WEAPON5': '0.300', 'ARMOR': '0.484', 'weapon4': '0.494', 'WEAPON3': '0.700', 'FRAGCOUNT': '1.000', 'weapon2': '3.286', 'weapon3': '3.432'} [2024-08-01 16:33:42,003][00132] DAMAGECOUNT value on done: 423.0 [2024-08-01 16:33:42,010][00132] Sum rewards: -4.334, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.642', 'AMMO2': '0.018', 'WEAPON1': '0.020', 'AMMO5': '0.027', 'AMMO4': '0.092', 'HITCOUNT': '0.170', 'AMMO3': '0.185', 'weapon5': '0.246', 'WEAPON4': '0.300', 'weapon4': '0.408', 'ARMOR': '0.495', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.519', 'WEAPON5': '0.600', 'WEAPON3': '1.300', 'weapon2': '1.888', 'weapon3': '4.790'} [2024-08-01 16:33:42,404][00145] DAMAGECOUNT value on done: 629.0 [2024-08-01 16:33:42,407][00145] Sum rewards: -4.557, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.480', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'weapon4': '0.032', 'ARMOR': '0.072', 'WEAPON4': '0.100', 'AMMO3': '0.178', 'HITCOUNT': '0.220', 'DAMAGECOUNT': '0.840', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon2': '3.088', 'weapon3': '3.574'} [2024-08-01 16:33:42,701][00137] DAMAGECOUNT value on done: 346.0 [2024-08-01 16:33:42,704][00137] Sum rewards: -6.697, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.565', 'AMMO4': '-0.052', 'AMMO2': '-0.010', 'weapon5': '0.002', 'AMMO5': '0.010', 'ARMOR': '0.088', 'WEAPON5': '0.100', 'HITCOUNT': '0.160', 'WEAPON4': '0.200', 'AMMO3': '0.223', 'DAMAGECOUNT': '0.627', 'weapon4': '0.798', 'WEAPON3': '1.200', 'FRAGCOUNT': '2.000', 'weapon3': '3.350', 'weapon2': '3.672'} [2024-08-01 16:33:43,156][00138] DAMAGECOUNT value on done: 536.0 [2024-08-01 16:33:43,157][00138] Sum rewards: 0.086, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.510', 'AMMO4': '-0.023', 'AMMO2': '-0.005', 'ARMOR': '0.004', 'weapon7': '0.006', 'AMMO5': '0.007', 'WEAPON1': '0.040', 'AMMO3': '0.177', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.260', 'weapon5': '0.300', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.005', 'FRAGCOUNT': '2.000', 'weapon2': '2.984', 'weapon3': '4.040'} [2024-08-01 16:33:43,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 9625600. Throughput: 0: 1482.1. Samples: 4818360. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:33:43,841][00034] Avg episode reward: [(0, '-1.992')] [2024-08-01 16:33:44,269][00134] Updated weights for policy 0, policy_version 2351 (0.0021) [2024-08-01 16:33:44,860][00146] DAMAGECOUNT value on done: 100.0 [2024-08-01 16:33:45,069][00139] DAMAGECOUNT value on done: 672.0 [2024-08-01 16:33:45,072][00139] Sum rewards: -2.414, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.185', 'AMMO4': '-0.019', 'AMMO2': '-0.004', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'WEAPON4': '0.100', 'AMMO3': '0.175', 'HITCOUNT': '0.180', 'weapon4': '0.188', 'weapon5': '0.208', 'WEAPON5': '0.300', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.464', 'FRAGCOUNT': '2.000', 'weapon3': '2.586', 'weapon2': '4.162'} [2024-08-01 16:33:45,802][00143] DAMAGECOUNT value on done: 543.0 [2024-08-01 16:33:45,806][00143] Sum rewards: -0.372, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.010', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.014', 'WEAPON4': '0.100', 'ARMOR': '0.108', 'HITCOUNT': '0.130', 'AMMO3': '0.154', 'weapon5': '0.158', 'WEAPON5': '0.200', 'DAMAGECOUNT': '0.336', 'FRAGCOUNT': '0.500', 'weapon4': '0.670', 'WEAPON3': '1.100', 'weapon2': '2.932', 'weapon3': '3.750'} [2024-08-01 16:33:46,525][00142] DAMAGECOUNT value on done: 836.0 [2024-08-01 16:33:46,529][00142] Sum rewards: -1.753, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.960', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.019', 'WEAPON1': '0.040', 'HITCOUNT': '0.100', 'AMMO3': '0.171', 'weapon5': '0.184', 'WEAPON5': '0.400', 'DAMAGECOUNT': '0.480', 'FRAGCOUNT': '0.500', 'ARMOR': '0.500', 'WEAPON3': '0.700', 'weapon2': '2.672', 'weapon3': '2.966'} [2024-08-01 16:33:48,305][00133] DAMAGECOUNT value on done: 384.0 [2024-08-01 16:33:48,309][00133] Sum rewards: -7.683, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.078', 'AMMO2': '-0.016', 'AMMO5': '0.019', 'ARMOR': '0.024', 'WEAPON1': '0.040', 'HITCOUNT': '0.100', 'AMMO3': '0.135', 'weapon5': '0.216', 'DAMAGECOUNT': '0.357', 'WEAPON5': '0.400', 'WEAPON3': '0.800', 'weapon3': '3.036', 'weapon2': '3.474'} [2024-08-01 16:33:48,839][00034] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2901.9). Total num frames: 9646080. Throughput: 0: 1485.0. Samples: 4827348. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:33:48,841][00034] Avg episode reward: [(0, '-2.024')] [2024-08-01 16:33:49,795][00132] DAMAGECOUNT value on done: 415.0 [2024-08-01 16:33:49,796][00132] Sum rewards: 0.147, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.955', 'AMMO4': '-0.053', 'AMMO2': '-0.010', 'AMMO5': '0.009', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO3': '0.093', 'WEAPON4': '0.100', 'weapon5': '0.192', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.855', 'FRAGCOUNT': '1.000', 'weapon3': '3.306', 'weapon2': '3.940'} [2024-08-01 16:33:50,181][00145] DAMAGECOUNT value on done: 520.0 [2024-08-01 16:33:50,182][00145] Sum rewards: -2.305, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.289', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.077', 'AMMO2': '-0.015', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'weapon5': '0.082', 'WEAPON4': '0.100', 'HITCOUNT': '0.110', 'AMMO3': '0.142', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.405', 'ARMOR': '0.484', 'weapon4': '0.590', 'WEAPON3': '0.800', 'weapon2': '3.108', 'weapon3': '3.666'} [2024-08-01 16:33:50,816][00136] Large shaping reward -2.534 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.28500000000000003, -95.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:33:50,862][00138] DAMAGECOUNT value on done: 803.0 [2024-08-01 16:33:50,865][00138] Sum rewards: -3.399, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.082', 'AMMO2': '-0.016', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'AMMO3': '0.092', 'WEAPON4': '0.100', 'weapon5': '0.156', 'HITCOUNT': '0.160', 'WEAPON5': '0.200', 'weapon4': '0.506', 'DAMAGECOUNT': '0.519', 'WEAPON3': '0.700', 'weapon3': '2.882', 'weapon2': '3.306'} [2024-08-01 16:33:51,107][00137] DAMAGECOUNT value on done: 939.0 [2024-08-01 16:33:51,115][00137] Sum rewards: -1.590, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.842', 'AMMO4': '-0.036', 'AMMO2': '-0.007', 'ARMOR': '0.040', 'WEAPON1': '0.040', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.134', 'AMMO3': '0.191', 'WEAPON7': '0.200', 'HITCOUNT': '0.250', 'FRAGCOUNT': '1.000', 'DAMAGECOUNT': '1.140', 'WEAPON3': '1.300', 'weapon2': '3.536', 'weapon3': '3.974'} [2024-08-01 16:33:52,654][00139] DAMAGECOUNT value on done: 579.0 [2024-08-01 16:33:52,660][00139] Sum rewards: 1.950, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.369', 'AMMO4': '-0.053', 'AMMO2': '-0.010', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'ARMOR': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.121', 'weapon5': '0.134', 'WEAPON5': '0.200', 'HITCOUNT': '0.200', 'weapon4': '0.256', 'DAMAGECOUNT': '0.756', 'WEAPON3': '0.900', 'weapon2': '3.414', 'weapon3': '3.484', 'FRAGCOUNT': '4.000'} [2024-08-01 16:33:53,436][00146] DAMAGECOUNT value on done: 733.0 [2024-08-01 16:33:53,440][00146] Sum rewards: -6.296, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.045', 'AMMO2': '-0.009', 'ARMOR': '0.008', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'weapon5': '0.066', 'WEAPON4': '0.100', 'AMMO3': '0.195', 'HITCOUNT': '0.220', 'WEAPON5': '0.300', 'weapon4': '0.482', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '0.669', 'WEAPON3': '1.200', 'weapon3': '2.500', 'weapon2': '4.224'} [2024-08-01 16:33:53,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3004.1, 300 sec: 2915.8). Total num frames: 9658368. Throughput: 0: 1483.2. Samples: 4836228. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:33:53,841][00034] Avg episode reward: [(0, '-2.053')] [2024-08-01 16:33:55,219][00142] DAMAGECOUNT value on done: 687.0 [2024-08-01 16:33:55,225][00142] Sum rewards: -1.474, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.844', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.003', 'ARMOR': '0.040', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.114', 'AMMO3': '0.171', 'weapon4': '0.206', 'HITCOUNT': '0.210', 'DAMAGECOUNT': '0.804', 'WEAPON3': '0.900', 'weapon3': '2.850', 'FRAGCOUNT': '3.000', 'weapon2': '3.690'} [2024-08-01 16:33:56,336][00134] Updated weights for policy 0, policy_version 2361 (0.0021) [2024-08-01 16:33:57,136][00133] DAMAGECOUNT value on done: 436.0 [2024-08-01 16:33:57,862][00132] DAMAGECOUNT value on done: 402.0 [2024-08-01 16:33:57,874][00132] Sum rewards: -3.950, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.399', 'AMMO5': '0.007', 'AMMO2': '0.019', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'AMMO4': '0.096', 'HITCOUNT': '0.130', 'WEAPON5': '0.200', 'weapon5': '0.202', 'AMMO3': '0.212', 'DAMAGECOUNT': '0.351', 'WEAPON4': '0.400', 'weapon4': '0.790', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.300', 'weapon2': '2.082', 'weapon3': '4.108'} [2024-08-01 16:33:58,434][00145] DAMAGECOUNT value on done: 1171.0 [2024-08-01 16:33:58,437][00145] Sum rewards: -1.461, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.160', 'AMMO2': '0.000', 'AMMO4': '0.002', 'AMMO5': '0.008', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.157', 'WEAPON5': '0.200', 'weapon5': '0.222', 'HITCOUNT': '0.250', 'ARMOR': '0.488', 'WEAPON3': '1.200', 'FRAGCOUNT': '1.500', 'DAMAGECOUNT': '1.806', 'weapon2': '2.148', 'weapon3': '5.078'} [2024-08-01 16:33:58,838][00034] Fps is (10 sec: 2457.8, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9670656. Throughput: 0: 1481.1. Samples: 4840764. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:33:58,840][00034] Avg episode reward: [(0, '-2.120')] [2024-08-01 16:33:59,259][00137] DAMAGECOUNT value on done: 459.0 [2024-08-01 16:33:59,260][00137] Sum rewards: 1.263, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.240', 'AMMO5': '0.008', 'AMMO2': '0.022', 'ARMOR': '0.040', 'weapon5': '0.068', 'AMMO4': '0.112', 'AMMO3': '0.153', 'WEAPON5': '0.200', 'HITCOUNT': '0.210', 'WEAPON4': '0.400', 'weapon4': '0.424', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.053', 'weapon2': '2.922', 'FRAGCOUNT': '3.000', 'weapon3': '3.240'} [2024-08-01 16:33:59,356][00138] DAMAGECOUNT value on done: 288.0 [2024-08-01 16:34:01,099][00146] DAMAGECOUNT value on done: 506.0 [2024-08-01 16:34:01,103][00146] Sum rewards: -9.208, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.875', 'FRAGCOUNT': '-3.000', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.030', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'weapon4': '0.126', 'AMMO3': '0.214', 'HITCOUNT': '0.250', 'weapon5': '0.260', 'WEAPON5': '0.600', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.194', 'weapon3': '2.574', 'weapon2': '4.276'} [2024-08-01 16:34:01,383][00139] DAMAGECOUNT value on done: 428.0 [2024-08-01 16:34:01,391][00139] Sum rewards: 0.965, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.380', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.002', 'AMMO2': '-0.000', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'ARMOR': '0.067', 'WEAPON4': '0.100', 'AMMO3': '0.141', 'weapon4': '0.168', 'HITCOUNT': '0.200', 'WEAPON5': '0.200', 'weapon5': '0.292', 'DAMAGECOUNT': '0.774', 'WEAPON3': '0.900', 'weapon2': '1.922', 'weapon3': '5.050'} [2024-08-01 16:34:02,826][00142] DAMAGECOUNT value on done: 908.0 [2024-08-01 16:34:02,829][00142] Sum rewards: 2.088, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.090', 'AMMO2': '-0.018', 'AMMO5': '0.003', 'WEAPON5': '0.100', 'AMMO3': '0.136', 'weapon5': '0.216', 'HITCOUNT': '0.410', 'ARMOR': '0.467', 'WEAPON3': '0.900', 'DAMAGECOUNT': '2.088', 'weapon2': '3.564', 'weapon3': '3.952', 'FRAGCOUNT': '5.000'} [2024-08-01 16:34:03,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2929.7). Total num frames: 9691136. Throughput: 0: 1488.3. Samples: 4849908. Policy #0 lag: (min: 0.0, avg: 3.3, max: 7.0) [2024-08-01 16:34:03,841][00034] Avg episode reward: [(0, '-2.085')] [2024-08-01 16:34:04,933][00133] DAMAGECOUNT value on done: 982.0 [2024-08-01 16:34:04,935][00133] Sum rewards: 1.740, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.900', 'AMMO4': '-0.051', 'AMMO2': '-0.010', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'ARMOR': '0.085', 'AMMO3': '0.136', 'weapon5': '0.142', 'WEAPON4': '0.200', 'WEAPON5': '0.200', 'HITCOUNT': '0.390', 'weapon4': '0.814', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.422', 'FRAGCOUNT': '2.000', 'weapon3': '2.602', 'weapon2': '3.280'} [2024-08-01 16:34:07,183][00137] DAMAGECOUNT value on done: 768.0 [2024-08-01 16:34:07,187][00137] Sum rewards: -2.092, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.506', 'AMMO2': '0.001', 'AMMO4': '0.007', 'AMMO5': '0.015', 'WEAPON1': '0.060', 'ARMOR': '0.080', 'WEAPON4': '0.100', 'AMMO6': '0.120', 'AMMO7': '0.120', 'weapon7': '0.140', 'AMMO3': '0.155', 'HITCOUNT': '0.180', 'WEAPON7': '0.200', 'weapon4': '0.242', 'weapon5': '0.262', 'WEAPON5': '0.400', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.975', 'FRAGCOUNT': '1.000', 'weapon2': '2.624', 'weapon3': '2.832'} [2024-08-01 16:34:07,292][00132] DAMAGECOUNT value on done: 790.0 [2024-08-01 16:34:07,296][00132] Sum rewards: 2.868, reward structure: {'DEATHCOUNT': '-6.000', 'HEALTH': '-2.522', 'AMMO4': '-0.064', 'AMMO2': '-0.013', 'AMMO5': '0.003', 'WEAPON1': '0.040', 'ARMOR': '0.056', 'WEAPON4': '0.100', 'WEAPON5': '0.100', 'weapon5': '0.116', 'AMMO3': '0.119', 'HITCOUNT': '0.260', 'weapon4': '0.370', 'WEAPON3': '0.600', 'DAMAGECOUNT': '0.855', 'FRAGCOUNT': '2.000', 'weapon2': '3.234', 'weapon3': '3.614'} [2024-08-01 16:34:07,876][00145] DAMAGECOUNT value on done: 518.0 [2024-08-01 16:34:07,881][00145] Sum rewards: -1.934, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.440', 'AMMO2': '0.003', 'AMMO5': '0.005', 'AMMO4': '0.015', 'WEAPON1': '0.020', 'weapon7': '0.032', 'weapon4': '0.046', 'weapon5': '0.058', 'ARMOR': '0.084', 'WEAPON5': '0.100', 'AMMO3': '0.171', 'HITCOUNT': '0.180', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'WEAPON4': '0.200', 'DAMAGECOUNT': '0.756', 'WEAPON3': '1.000', 'FRAGCOUNT': '3.000', 'weapon2': '3.240', 'weapon3': '4.246'} [2024-08-01 16:34:08,643][00138] DAMAGECOUNT value on done: 218.0 [2024-08-01 16:34:08,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2888.0). Total num frames: 9699328. Throughput: 0: 1478.1. Samples: 4858404. Policy #0 lag: (min: 0.0, avg: 3.2, max: 6.0) [2024-08-01 16:34:08,840][00034] Avg episode reward: [(0, '-1.972')] [2024-08-01 16:34:08,848][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002368_9699328.pth... [2024-08-01 16:34:09,017][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002199_9007104.pth [2024-08-01 16:34:09,349][00146] DAMAGECOUNT value on done: 961.0 [2024-08-01 16:34:09,350][00146] Sum rewards: -3.927, reward structure: {'DEATHCOUNT': '-13.500', 'HEALTH': '-5.300', 'AMMO4': '-0.068', 'AMMO2': '-0.013', 'AMMO5': '0.014', 'WEAPON1': '0.020', 'ARMOR': '0.044', 'weapon5': '0.098', 'WEAPON5': '0.200', 'AMMO3': '0.207', 'HITCOUNT': '0.450', 'WEAPON3': '1.200', 'DAMAGECOUNT': '1.797', 'weapon2': '2.816', 'FRAGCOUNT': '3.500', 'weapon3': '4.608'} [2024-08-01 16:34:10,752][00139] DAMAGECOUNT value on done: 1384.0 [2024-08-01 16:34:10,756][00139] Sum rewards: 0.734, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.180', 'AMMO5': '0.005', 'AMMO2': '0.010', 'WEAPON1': '0.020', 'weapon4': '0.024', 'AMMO4': '0.049', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.138', 'AMMO3': '0.174', 'HITCOUNT': '0.480', 'WEAPON3': '1.300', 'DAMAGECOUNT': '1.770', 'weapon2': '2.210', 'FRAGCOUNT': '4.000', 'weapon3': '5.034'} [2024-08-01 16:34:11,247][00142] DAMAGECOUNT value on done: 734.0 [2024-08-01 16:34:11,252][00142] Sum rewards: 3.123, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.854', 'AMMO4': '-0.073', 'AMMO2': '-0.015', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.048', 'WEAPON4': '0.100', 'AMMO3': '0.114', 'HITCOUNT': '0.190', 'WEAPON5': '0.200', 'weapon5': '0.218', 'weapon4': '0.262', 'WEAPON3': '0.600', 'DAMAGECOUNT': '1.338', 'weapon3': '2.554', 'FRAGCOUNT': '3.000', 'weapon2': '4.166'} [2024-08-01 16:34:11,460][00134] Updated weights for policy 0, policy_version 2371 (0.0023) [2024-08-01 16:34:13,466][00133] DAMAGECOUNT value on done: 330.0 [2024-08-01 16:34:13,474][00133] Sum rewards: -0.049, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.640', 'AMMO2': '0.005', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'AMMO4': '0.027', 'ARMOR': '0.032', 'AMMO3': '0.109', 'HITCOUNT': '0.230', 'weapon4': '0.274', 'WEAPON4': '0.300', 'WEAPON5': '0.400', 'weapon5': '0.428', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.780', 'weapon3': '1.908', 'FRAGCOUNT': '3.000', 'weapon2': '4.364'} [2024-08-01 16:34:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 2915.8). Total num frames: 9719808. Throughput: 0: 1474.1. Samples: 4862820. Policy #0 lag: (min: 0.0, avg: 3.1, max: 7.0) [2024-08-01 16:34:13,840][00034] Avg episode reward: [(0, '-1.951')] [2024-08-01 16:34:15,580][00137] DAMAGECOUNT value on done: 1036.0 [2024-08-01 16:34:15,586][00137] Sum rewards: 3.560, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.060', 'AMMO4': '-0.025', 'AMMO2': '-0.005', 'AMMO5': '0.021', 'WEAPON1': '0.060', 'AMMO3': '0.233', 'weapon5': '0.270', 'HITCOUNT': '0.450', 'WEAPON5': '0.500', 'WEAPON3': '1.200', 'DAMAGECOUNT': '2.121', 'weapon2': '3.108', 'weapon3': '4.188', 'FRAGCOUNT': '6.000'} [2024-08-01 16:34:16,041][00138] Large shaping reward -2.504 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.255, -85.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:34:16,295][00132] DAMAGECOUNT value on done: 621.0 [2024-08-01 16:34:16,296][00132] Sum rewards: -2.054, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.378', 'AMMO4': '-0.021', 'AMMO2': '-0.004', 'AMMO5': '0.023', 'ARMOR': '0.068', 'WEAPON4': '0.100', 'AMMO3': '0.143', 'weapon4': '0.198', 'weapon5': '0.234', 'HITCOUNT': '0.250', 'WEAPON5': '0.300', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.900', 'DAMAGECOUNT': '0.945', 'weapon2': '2.270', 'weapon3': '3.668'} [2024-08-01 16:34:16,885][00145] DAMAGECOUNT value on done: 642.0 [2024-08-01 16:34:16,897][00145] Sum rewards: 1.529, reward structure: {'DEATHCOUNT': '-6.750', 'HEALTH': '-2.620', 'AMMO2': '0.006', 'AMMO5': '0.009', 'weapon5': '0.024', 'AMMO4': '0.028', 'ARMOR': '0.040', 'HITCOUNT': '0.090', 'WEAPON5': '0.100', 'weapon7': '0.112', 'AMMO6': '0.120', 'AMMO7': '0.120', 'AMMO3': '0.128', 'WEAPON4': '0.200', 'WEAPON7': '0.200', 'weapon4': '0.494', 'DAMAGECOUNT': '0.960', 'WEAPON3': '1.000', 'weapon2': '1.166', 'FRAGCOUNT': '2.000', 'weapon3': '4.102'} [2024-08-01 16:34:17,398][00146] DAMAGECOUNT value on done: 552.0 [2024-08-01 16:34:17,735][00138] DAMAGECOUNT value on done: 311.0 [2024-08-01 16:34:18,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2901.9). Total num frames: 9728000. Throughput: 0: 1470.4. Samples: 4871748. Policy #0 lag: (min: 0.0, avg: 3.3, max: 6.0) [2024-08-01 16:34:18,840][00034] Avg episode reward: [(0, '-1.838')] [2024-08-01 16:34:19,282][00142] DAMAGECOUNT value on done: 666.0 [2024-08-01 16:34:19,286][00142] Sum rewards: -2.662, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.525', 'AMMO4': '-0.012', 'AMMO2': '-0.002', 'AMMO5': '0.005', 'WEAPON1': '0.020', 'ARMOR': '0.032', 'WEAPON5': '0.100', 'weapon5': '0.118', 'WEAPON4': '0.200', 'AMMO3': '0.220', 'HITCOUNT': '0.290', 'weapon4': '0.902', 'DAMAGECOUNT': '1.071', 'WEAPON3': '1.500', 'FRAGCOUNT': '2.000', 'weapon2': '2.212', 'weapon3': '4.458'} [2024-08-01 16:34:21,888][00133] DAMAGECOUNT value on done: 876.0 [2024-08-01 16:34:21,890][00133] Sum rewards: -1.748, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO2': '0.007', 'AMMO5': '0.025', 'AMMO4': '0.036', 'weapon5': '0.058', 'HITCOUNT': '0.150', 'AMMO3': '0.184', 'WEAPON5': '0.300', 'ARMOR': '0.518', 'DAMAGECOUNT': '0.600', 'WEAPON3': '0.900', 'FRAGCOUNT': '2.000', 'weapon2': '2.632', 'weapon3': '3.362'} [2024-08-01 16:34:23,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2901.9). Total num frames: 9748480. Throughput: 0: 1486.4. Samples: 4880760. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:34:23,840][00034] Avg episode reward: [(0, '-1.799')] [2024-08-01 16:34:23,888][00137] DAMAGECOUNT value on done: 811.0 [2024-08-01 16:34:23,889][00137] Sum rewards: -2.812, reward structure: {'DEATHCOUNT': '-10.500', 'HEALTH': '-4.140', 'AMMO4': '-0.091', 'AMMO2': '-0.018', 'AMMO5': '0.012', 'WEAPON1': '0.020', 'ARMOR': '0.020', 'AMMO3': '0.160', 'weapon5': '0.198', 'HITCOUNT': '0.260', 'WEAPON5': '0.300', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.161', 'FRAGCOUNT': '1.500', 'weapon2': '3.636', 'weapon3': '3.670'} [2024-08-01 16:34:24,170][00136] Large shaping reward -2.550 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.3, -100.0), ('AMMO5', -0.0005, -1.0)] [2024-08-01 16:34:25,274][00134] Updated weights for policy 0, policy_version 2381 (0.0028) [2024-08-01 16:34:25,332][00145] DAMAGECOUNT value on done: 993.0 [2024-08-01 16:34:25,335][00145] Sum rewards: 0.344, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.800', 'AMMO4': '-0.057', 'AMMO2': '-0.011', 'AMMO5': '0.021', 'ARMOR': '0.028', 'WEAPON1': '0.040', 'WEAPON4': '0.100', 'AMMO3': '0.182', 'weapon5': '0.304', 'HITCOUNT': '0.340', 'weapon4': '0.390', 'WEAPON5': '0.500', 'WEAPON3': '1.100', 'DAMAGECOUNT': '1.839', 'FRAGCOUNT': '2.500', 'weapon2': '3.116', 'weapon3': '3.502'} [2024-08-01 16:34:25,508][00146] DAMAGECOUNT value on done: 521.0 [2024-08-01 16:34:25,511][00146] Sum rewards: -2.456, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.455', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'weapon5': '0.048', 'ARMOR': '0.072', 'AMMO3': '0.174', 'WEAPON5': '0.200', 'HITCOUNT': '0.310', 'DAMAGECOUNT': '1.002', 'WEAPON3': '1.200', 'FRAGCOUNT': '3.000', 'weapon2': '3.296', 'weapon3': '3.952'} [2024-08-01 16:34:26,098][00138] DAMAGECOUNT value on done: 720.0 [2024-08-01 16:34:26,099][00138] Sum rewards: -1.299, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.230', 'AMMO4': '-0.026', 'AMMO2': '-0.005', 'AMMO5': '0.005', 'ARMOR': '0.010', 'WEAPON1': '0.020', 'AMMO3': '0.136', 'WEAPON5': '0.200', 'WEAPON4': '0.200', 'HITCOUNT': '0.220', 'weapon5': '0.254', 'weapon4': '0.312', 'FRAGCOUNT': '0.500', 'WEAPON3': '0.800', 'DAMAGECOUNT': '0.825', 'weapon3': '2.710', 'weapon2': '4.020'} [2024-08-01 16:34:27,337][00142] DAMAGECOUNT value on done: 365.0 [2024-08-01 16:34:27,341][00142] Sum rewards: 0.725, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.920', 'AMMO4': '-0.058', 'AMMO2': '-0.012', 'AMMO5': '0.007', 'ARMOR': '0.036', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'HITCOUNT': '0.120', 'AMMO3': '0.141', 'WEAPON5': '0.200', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'weapon5': '0.238', 'weapon4': '0.316', 'DAMAGECOUNT': '0.690', 'WEAPON3': '0.800', 'FRAGCOUNT': '1.000', 'weapon2': '3.270', 'weapon3': '3.636'} [2024-08-01 16:34:28,838][00034] Fps is (10 sec: 3686.4, 60 sec: 3003.8, 300 sec: 2929.7). Total num frames: 9764864. Throughput: 0: 1488.3. Samples: 4885332. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:34:28,841][00034] Avg episode reward: [(0, '-1.839')] [2024-08-01 16:34:29,731][00133] DAMAGECOUNT value on done: 1185.0 [2024-08-01 16:34:29,732][00133] Sum rewards: 7.393, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.110', 'AMMO4': '-0.064', 'AMMO2': '-0.013', 'AMMO5': '0.010', 'WEAPON1': '0.040', 'ARMOR': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.141', 'WEAPON5': '0.200', 'weapon5': '0.246', 'HITCOUNT': '0.290', 'weapon4': '0.492', 'WEAPON3': '1.000', 'DAMAGECOUNT': '1.719', 'weapon2': '3.112', 'weapon3': '3.670', 'FRAGCOUNT': '7.000'} [2024-08-01 16:34:31,507][00137] DAMAGECOUNT value on done: 988.0 [2024-08-01 16:34:31,509][00137] Sum rewards: -1.871, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO4': '-0.093', 'AMMO2': '-0.019', 'AMMO5': '0.019', 'WEAPON1': '0.020', 'weapon5': '0.152', 'AMMO3': '0.177', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.371', 'FRAGCOUNT': '1.500', 'weapon3': '2.630', 'weapon2': '3.682'} [2024-08-01 16:34:33,103][00146] DAMAGECOUNT value on done: 496.0 [2024-08-01 16:34:33,106][00146] Sum rewards: 1.705, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.010', 'AMMO5': '0.003', 'AMMO2': '0.014', 'WEAPON1': '0.040', 'AMMO4': '0.071', 'WEAPON5': '0.100', 'weapon5': '0.138', 'AMMO3': '0.162', 'HITCOUNT': '0.190', 'WEAPON4': '0.200', 'weapon4': '0.380', 'ARMOR': '0.546', 'DAMAGECOUNT': '0.687', 'WEAPON3': '0.800', 'FRAGCOUNT': '2.000', 'weapon2': '2.960', 'weapon3': '3.924'} [2024-08-01 16:34:33,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2888.0). Total num frames: 9773056. Throughput: 0: 1491.5. Samples: 4894464. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:34:33,842][00034] Avg episode reward: [(0, '-1.725')] [2024-08-01 16:34:34,282][00138] DAMAGECOUNT value on done: 634.0 [2024-08-01 16:34:34,290][00138] Sum rewards: -0.399, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'AMMO4': '-0.080', 'AMMO2': '-0.016', 'ARMOR': '0.067', 'WEAPON4': '0.100', 'AMMO3': '0.151', 'HITCOUNT': '0.210', 'weapon4': '0.448', 'DAMAGECOUNT': '0.657', 'WEAPON3': '1.000', 'weapon3': '2.838', 'FRAGCOUNT': '3.000', 'weapon2': '3.766'} [2024-08-01 16:34:35,360][00142] DAMAGECOUNT value on done: 438.0 [2024-08-01 16:34:35,366][00142] Sum rewards: -6.027, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.820', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.022', 'AMMO2': '-0.004', 'HITCOUNT': '0.010', 'AMMO5': '0.011', 'DAMAGECOUNT': '0.015', 'ARMOR': '0.064', 'WEAPON4': '0.100', 'weapon5': '0.170', 'AMMO3': '0.236', 'WEAPON5': '0.300', 'WEAPON3': '1.300', 'weapon2': '3.000', 'weapon3': '3.862'} [2024-08-01 16:34:38,168][00134] Updated weights for policy 0, policy_version 2391 (0.0020) [2024-08-01 16:34:38,460][00133] DAMAGECOUNT value on done: 425.0 [2024-08-01 16:34:38,838][00034] Fps is (10 sec: 2867.2, 60 sec: 3003.8, 300 sec: 2915.8). Total num frames: 9793536. Throughput: 0: 1489.6. Samples: 4903260. Policy #0 lag: (min: 0.0, avg: 2.9, max: 7.0) [2024-08-01 16:34:38,840][00034] Avg episode reward: [(0, '-1.758')] [2024-08-01 16:34:41,138][00137] DAMAGECOUNT value on done: 471.0 [2024-08-01 16:34:41,139][00137] Sum rewards: 0.644, reward structure: {'DEATHCOUNT': '-8.250', 'HEALTH': '-3.530', 'AMMO4': '-0.014', 'AMMO2': '-0.003', 'AMMO5': '0.010', 'WEAPON1': '0.020', 'weapon5': '0.068', 'AMMO3': '0.163', 'WEAPON5': '0.200', 'HITCOUNT': '0.230', 'ARMOR': '0.463', 'DAMAGECOUNT': '0.933', 'WEAPON3': '1.000', 'FRAGCOUNT': '2.000', 'weapon2': '2.844', 'weapon3': '4.510'} [2024-08-01 16:34:42,910][00146] DAMAGECOUNT value on done: 597.0 [2024-08-01 16:34:43,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2901.9). Total num frames: 9801728. Throughput: 0: 1474.7. Samples: 4907124. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:34:43,841][00034] Avg episode reward: [(0, '-1.685')] [2024-08-01 16:34:45,029][00142] DAMAGECOUNT value on done: 494.0 [2024-08-01 16:34:45,032][00142] Sum rewards: -2.219, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.520', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.014', 'WEAPON1': '0.040', 'AMMO3': '0.190', 'weapon5': '0.286', 'WEAPON5': '0.300', 'HITCOUNT': '0.310', 'FRAGCOUNT': '0.500', 'DAMAGECOUNT': '1.020', 'WEAPON3': '1.200', 'weapon2': '1.930', 'weapon3': '4.564'} [2024-08-01 16:34:48,151][00133] DAMAGECOUNT value on done: 289.0 [2024-08-01 16:34:48,153][00133] Sum rewards: 2.673, reward structure: {'DEATHCOUNT': '-4.500', 'HEALTH': '-1.746', 'AMMO2': '0.000', 'AMMO4': '0.001', 'HITCOUNT': '0.080', 'weapon4': '0.088', 'WEAPON4': '0.100', 'AMMO3': '0.108', 'DAMAGECOUNT': '0.231', 'ARMOR': '0.532', 'WEAPON3': '0.600', 'FRAGCOUNT': '1.000', 'weapon2': '2.004', 'weapon3': '4.174'} [2024-08-01 16:34:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 9822208. Throughput: 0: 1466.7. Samples: 4915908. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:34:48,841][00034] Avg episode reward: [(0, '-1.608')] [2024-08-01 16:34:49,822][00137] DAMAGECOUNT value on done: 585.0 [2024-08-01 16:34:49,829][00137] Sum rewards: -1.729, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.560', 'AMMO5': '0.013', 'WEAPON1': '0.020', 'AMMO2': '0.024', 'weapon7': '0.026', 'AMMO3': '0.092', 'ARMOR': '0.092', 'weapon5': '0.118', 'AMMO4': '0.121', 'AMMO6': '0.200', 'WEAPON7': '0.200', 'AMMO7': '0.200', 'HITCOUNT': '0.230', 'WEAPON5': '0.300', 'WEAPON3': '0.500', 'WEAPON4': '0.500', 'DAMAGECOUNT': '0.717', 'FRAGCOUNT': '1.000', 'weapon4': '1.122', 'weapon3': '1.944', 'weapon2': '3.412'} [2024-08-01 16:34:51,332][00146] DAMAGECOUNT value on done: 492.0 [2024-08-01 16:34:51,339][00146] Sum rewards: -4.898, reward structure: {'DEATHCOUNT': '-12.000', 'HEALTH': '-4.740', 'AMMO4': '-0.035', 'AMMO2': '-0.007', 'AMMO5': '0.007', 'WEAPON1': '0.020', 'weapon5': '0.160', 'AMMO3': '0.163', 'WEAPON5': '0.200', 'HITCOUNT': '0.250', 'DAMAGECOUNT': '1.026', 'WEAPON3': '1.100', 'FRAGCOUNT': '2.000', 'weapon3': '3.448', 'weapon2': '3.510'} [2024-08-01 16:34:52,849][00134] Updated weights for policy 0, policy_version 2401 (0.0021) [2024-08-01 16:34:53,455][00142] DAMAGECOUNT value on done: 426.0 [2024-08-01 16:34:53,469][00142] Sum rewards: -5.642, reward structure: {'DEATHCOUNT': '-11.250', 'HEALTH': '-4.481', 'AMMO4': '-0.044', 'AMMO2': '-0.009', 'AMMO5': '0.003', 'WEAPON1': '0.020', 'ARMOR': '0.036', 'weapon4': '0.046', 'HITCOUNT': '0.070', 'WEAPON5': '0.100', 'WEAPON4': '0.100', 'weapon5': '0.114', 'AMMO3': '0.183', 'DAMAGECOUNT': '0.228', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon3': '3.422', 'weapon2': '3.720'} [2024-08-01 16:34:53,839][00034] Fps is (10 sec: 3276.6, 60 sec: 2935.4, 300 sec: 2915.8). Total num frames: 9834496. Throughput: 0: 1474.4. Samples: 4924752. Policy #0 lag: (min: 0.0, avg: 2.4, max: 7.0) [2024-08-01 16:34:53,844][00034] Avg episode reward: [(0, '-1.683')] [2024-08-01 16:34:56,402][00133] DAMAGECOUNT value on done: 760.0 [2024-08-01 16:34:57,890][00137] DAMAGECOUNT value on done: 449.0 [2024-08-01 16:34:57,896][00137] Sum rewards: -5.119, reward structure: {'DEATHCOUNT': '-9.000', 'HEALTH': '-3.540', 'FRAGCOUNT': '-1.500', 'AMMO4': '-0.033', 'AMMO2': '-0.007', 'AMMO5': '0.008', 'WEAPON1': '0.020', 'ARMOR': '0.056', 'HITCOUNT': '0.080', 'WEAPON4': '0.100', 'AMMO3': '0.132', 'DAMAGECOUNT': '0.210', 'weapon5': '0.294', 'WEAPON5': '0.300', 'weapon4': '0.316', 'WEAPON3': '0.700', 'weapon3': '2.710', 'weapon2': '4.034'} [2024-08-01 16:34:58,839][00034] Fps is (10 sec: 2867.0, 60 sec: 3003.7, 300 sec: 2901.9). Total num frames: 9850880. Throughput: 0: 1475.7. Samples: 4929228. Policy #0 lag: (min: 0.0, avg: 3.5, max: 6.0) [2024-08-01 16:34:58,842][00034] Avg episode reward: [(0, '-1.660')] [2024-08-01 16:35:03,838][00034] Fps is (10 sec: 3277.0, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 9867264. Throughput: 0: 1486.4. Samples: 4938636. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 16:35:03,840][00034] Avg episode reward: [(0, '-1.660')] [2024-08-01 16:35:04,172][00133] DAMAGECOUNT value on done: 633.0 [2024-08-01 16:35:04,173][00133] Sum rewards: -3.224, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.979', 'AMMO4': '-0.027', 'AMMO2': '-0.005', 'WEAPON1': '0.020', 'AMMO5': '0.024', 'ARMOR': '0.024', 'HITCOUNT': '0.100', 'weapon5': '0.150', 'AMMO3': '0.159', 'WEAPON5': '0.300', 'DAMAGECOUNT': '0.690', 'FRAGCOUNT': '1.000', 'WEAPON3': '1.100', 'weapon2': '3.116', 'weapon3': '3.854'} [2024-08-01 16:35:07,611][00134] Updated weights for policy 0, policy_version 2411 (0.0022) [2024-08-01 16:35:08,838][00034] Fps is (10 sec: 2867.4, 60 sec: 3003.7, 300 sec: 2915.8). Total num frames: 9879552. Throughput: 0: 1486.1. Samples: 4947636. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:35:08,841][00034] Avg episode reward: [(0, '-1.695')] [2024-08-01 16:35:13,116][00133] DAMAGECOUNT value on done: 600.0 [2024-08-01 16:35:13,122][00133] Sum rewards: 0.376, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-2.950', 'AMMO4': '-0.078', 'AMMO2': '-0.016', 'AMMO5': '0.009', 'ARMOR': '0.016', 'weapon5': '0.068', 'AMMO3': '0.129', 'WEAPON5': '0.200', 'HITCOUNT': '0.240', 'WEAPON3': '0.700', 'DAMAGECOUNT': '0.930', 'FRAGCOUNT': '1.500', 'weapon2': '3.122', 'weapon3': '4.006'} [2024-08-01 16:35:13,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2929.7). Total num frames: 9895936. Throughput: 0: 1480.0. Samples: 4951932. Policy #0 lag: (min: 0.0, avg: 3.7, max: 7.0) [2024-08-01 16:35:13,842][00034] Avg episode reward: [(0, '-1.702')] [2024-08-01 16:35:18,838][00034] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2929.7). Total num frames: 9912320. Throughput: 0: 1464.5. Samples: 4960368. Policy #0 lag: (min: 0.0, avg: 2.3, max: 7.0) [2024-08-01 16:35:18,840][00034] Avg episode reward: [(0, '-1.702')] [2024-08-01 16:35:19,736][00134] Updated weights for policy 0, policy_version 2421 (0.0024) [2024-08-01 16:35:21,264][00133] DAMAGECOUNT value on done: 712.0 [2024-08-01 16:35:21,268][00133] Sum rewards: 4.128, reward structure: {'DEATHCOUNT': '-7.500', 'HEALTH': '-3.010', 'AMMO4': '-0.003', 'AMMO2': '-0.000', 'AMMO5': '0.003', 'WEAPON1': '0.040', 'AMMO3': '0.071', 'ARMOR': '0.072', 'WEAPON5': '0.100', 'weapon5': '0.140', 'WEAPON4': '0.200', 'weapon4': '0.416', 'HITCOUNT': '0.450', 'WEAPON3': '0.700', 'DAMAGECOUNT': '1.662', 'weapon2': '2.728', 'FRAGCOUNT': '4.000', 'weapon3': '4.060'} [2024-08-01 16:35:23,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2901.9). Total num frames: 9920512. Throughput: 0: 1464.8. Samples: 4969176. Policy #0 lag: (min: 0.0, avg: 3.8, max: 8.0) [2024-08-01 16:35:23,840][00034] Avg episode reward: [(0, '-1.592')] [2024-08-01 16:35:27,833][00140] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:35:28,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2935.5, 300 sec: 2915.8). Total num frames: 9940992. Throughput: 0: 1477.3. Samples: 4973604. Policy #0 lag: (min: 0.0, avg: 3.5, max: 7.0) [2024-08-01 16:35:28,840][00034] Avg episode reward: [(0, '-1.592')] [2024-08-01 16:35:29,153][00133] DAMAGECOUNT value on done: 391.0 [2024-08-01 16:35:29,154][00133] Sum rewards: -4.405, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.760', 'FRAGCOUNT': '-0.500', 'AMMO4': '-0.034', 'AMMO2': '-0.007', 'AMMO5': '0.015', 'WEAPON1': '0.060', 'WEAPON4': '0.100', 'AMMO3': '0.124', 'HITCOUNT': '0.180', 'weapon4': '0.220', 'WEAPON5': '0.400', 'weapon5': '0.502', 'DAMAGECOUNT': '0.570', 'WEAPON3': '0.800', 'weapon2': '2.852', 'weapon3': '3.822'} [2024-08-01 16:35:33,839][00034] Fps is (10 sec: 3276.5, 60 sec: 3003.7, 300 sec: 2915.8). Total num frames: 9953280. Throughput: 0: 1482.9. Samples: 4982640. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:35:33,841][00034] Avg episode reward: [(0, '-1.584')] [2024-08-01 16:35:34,151][00134] Updated weights for policy 0, policy_version 2431 (0.0021) [2024-08-01 16:35:38,838][00034] Fps is (10 sec: 2457.6, 60 sec: 2867.2, 300 sec: 2915.8). Total num frames: 9965568. Throughput: 0: 1482.7. Samples: 4991472. Policy #0 lag: (min: 0.0, avg: 3.2, max: 7.0) [2024-08-01 16:35:38,841][00034] Avg episode reward: [(0, '-1.584')] [2024-08-01 16:35:43,838][00034] Fps is (10 sec: 3277.1, 60 sec: 3072.0, 300 sec: 2943.6). Total num frames: 9986048. Throughput: 0: 1483.0. Samples: 4995960. Policy #0 lag: (min: 0.0, avg: 2.6, max: 7.0) [2024-08-01 16:35:43,841][00034] Avg episode reward: [(0, '-1.584')] [2024-08-01 16:35:48,838][00034] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2929.7). Total num frames: 9994240. Throughput: 0: 1458.1. Samples: 5004252. Policy #0 lag: (min: 0.0, avg: 3.8, max: 8.0) [2024-08-01 16:35:48,842][00034] Avg episode reward: [(0, '-1.584')] [2024-08-01 16:35:49,235][00134] Updated weights for policy 0, policy_version 2441 (0.0037) [2024-08-01 16:35:50,811][00112] Stopping Batcher_0... [2024-08-01 16:35:50,811][00112] Loop batcher_evt_loop terminating... [2024-08-01 16:35:50,811][00034] Component Batcher_0 stopped! [2024-08-01 16:35:50,820][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth... [2024-08-01 16:35:50,908][00134] Weights refcount: 2 0 [2024-08-01 16:35:50,920][00034] Component InferenceWorker_p0-w0 stopped! [2024-08-01 16:35:50,922][00134] Stopping InferenceWorker_p0-w0... [2024-08-01 16:35:50,923][00134] Loop inference_proc0-0_evt_loop terminating... [2024-08-01 16:35:51,006][00112] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002282_9347072.pth [2024-08-01 16:35:51,022][00112] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth... [2024-08-01 16:35:51,153][00034] Component RolloutWorker_w11 stopped! [2024-08-01 16:35:51,153][00144] Stopping RolloutWorker_w11... [2024-08-01 16:35:51,171][00034] Component RolloutWorker_w10 stopped! [2024-08-01 16:35:51,170][00143] Stopping RolloutWorker_w10... [2024-08-01 16:35:51,173][00144] Loop rollout_proc11_evt_loop terminating... [2024-08-01 16:35:51,174][00143] Loop rollout_proc10_evt_loop terminating... [2024-08-01 16:35:51,206][00132] Stopping RolloutWorker_w0... [2024-08-01 16:35:51,206][00132] Loop rollout_proc0_evt_loop terminating... [2024-08-01 16:35:51,206][00034] Component RolloutWorker_w0 stopped! [2024-08-01 16:35:51,212][00034] Component RolloutWorker_w3 stopped! [2024-08-01 16:35:51,212][00136] Stopping RolloutWorker_w3... [2024-08-01 16:35:51,219][00136] Loop rollout_proc3_evt_loop terminating... [2024-08-01 16:35:51,244][00034] Component RolloutWorker_w6 stopped! [2024-08-01 16:35:51,252][00141] Stopping RolloutWorker_w6... [2024-08-01 16:35:51,253][00141] Loop rollout_proc6_evt_loop terminating... [2024-08-01 16:35:51,261][00034] Component RolloutWorker_w2 stopped! [2024-08-01 16:35:51,264][00135] Stopping RolloutWorker_w2... [2024-08-01 16:35:51,265][00135] Loop rollout_proc2_evt_loop terminating... [2024-08-01 16:35:51,282][00140] Stopping RolloutWorker_w7... [2024-08-01 16:35:51,281][00034] Component RolloutWorker_w7 stopped! [2024-08-01 16:35:51,282][00140] Loop rollout_proc7_evt_loop terminating... [2024-08-01 16:35:51,296][00147] Stopping RolloutWorker_w14... [2024-08-01 16:35:51,297][00034] Component RolloutWorker_w14 stopped! [2024-08-01 16:35:51,296][00147] Loop rollout_proc14_evt_loop terminating... [2024-08-01 16:35:51,361][00148] Stopping RolloutWorker_w15... [2024-08-01 16:35:51,362][00148] Loop rollout_proc15_evt_loop terminating... [2024-08-01 16:35:51,369][00034] Component RolloutWorker_w15 stopped! [2024-08-01 16:35:51,413][00034] Component RolloutWorker_w12 stopped! [2024-08-01 16:35:51,418][00112] Stopping LearnerWorker_p0... [2024-08-01 16:35:51,419][00112] Loop learner_proc0_evt_loop terminating... [2024-08-01 16:35:51,418][00034] Component LearnerWorker_p0 stopped! [2024-08-01 16:35:51,412][00145] Stopping RolloutWorker_w12... [2024-08-01 16:35:51,437][00034] Component RolloutWorker_w1 stopped! [2024-08-01 16:35:51,439][00133] Stopping RolloutWorker_w1... [2024-08-01 16:35:51,441][00034] Component RolloutWorker_w9 stopped! [2024-08-01 16:35:51,441][00142] Stopping RolloutWorker_w9... [2024-08-01 16:35:51,440][00133] Loop rollout_proc1_evt_loop terminating... [2024-08-01 16:35:51,443][00142] Loop rollout_proc9_evt_loop terminating... [2024-08-01 16:35:51,431][00145] Loop rollout_proc12_evt_loop terminating... [2024-08-01 16:35:51,467][00034] Component RolloutWorker_w5 stopped! [2024-08-01 16:35:51,467][00137] Stopping RolloutWorker_w5... [2024-08-01 16:35:51,469][00137] Loop rollout_proc5_evt_loop terminating... [2024-08-01 16:35:51,479][00139] Stopping RolloutWorker_w8... [2024-08-01 16:35:51,480][00034] Component RolloutWorker_w8 stopped! [2024-08-01 16:35:51,479][00139] Loop rollout_proc8_evt_loop terminating... [2024-08-01 16:35:51,482][00034] Component RolloutWorker_w13 stopped! [2024-08-01 16:35:51,483][00146] Stopping RolloutWorker_w13... [2024-08-01 16:35:51,484][00146] Loop rollout_proc13_evt_loop terminating... [2024-08-01 16:35:51,500][00138] Stopping RolloutWorker_w4... [2024-08-01 16:35:51,500][00034] Component RolloutWorker_w4 stopped! [2024-08-01 16:35:51,502][00034] Waiting for process learner_proc0 to stop... [2024-08-01 16:35:51,501][00138] Loop rollout_proc4_evt_loop terminating... [2024-08-01 16:35:52,917][00034] Waiting for process inference_proc0-0 to join... [2024-08-01 16:35:52,919][00034] Waiting for process rollout_proc0 to join... [2024-08-01 16:35:55,059][00034] Waiting for process rollout_proc1 to join... [2024-08-01 16:35:55,120][00034] Waiting for process rollout_proc2 to join... [2024-08-01 16:35:55,122][00034] Waiting for process rollout_proc3 to join... [2024-08-01 16:35:55,132][00034] Waiting for process rollout_proc4 to join... [2024-08-01 16:35:55,133][00034] Waiting for process rollout_proc5 to join... [2024-08-01 16:35:55,134][00034] Waiting for process rollout_proc6 to join... [2024-08-01 16:35:55,135][00034] Waiting for process rollout_proc7 to join... [2024-08-01 16:35:55,145][00034] Waiting for process rollout_proc8 to join... [2024-08-01 16:35:55,146][00034] Waiting for process rollout_proc9 to join... [2024-08-01 16:35:55,147][00034] Waiting for process rollout_proc10 to join... [2024-08-01 16:35:55,148][00034] Waiting for process rollout_proc11 to join... [2024-08-01 16:35:55,149][00034] Waiting for process rollout_proc12 to join... [2024-08-01 16:35:55,150][00034] Waiting for process rollout_proc13 to join... [2024-08-01 16:35:55,151][00034] Waiting for process rollout_proc14 to join... [2024-08-01 16:35:55,153][00034] Waiting for process rollout_proc15 to join... [2024-08-01 16:35:55,154][00034] Batcher 0 profile tree view: batching: 115.0959, releasing_batches: 0.1816 [2024-08-01 16:35:55,154][00034] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0051 wait_policy_total: 2499.5722 update_model: 12.8552 weight_update: 0.0036 one_step: 0.0072 handle_policy_step: 869.0282 deserialize: 51.5175, stack: 4.0875, obs_to_device_normalize: 167.5697, forward: 523.4587, send_messages: 24.2994 prepare_outputs: 74.2895 to_cpu: 29.7800 [2024-08-01 16:35:55,155][00034] Learner 0 profile tree view: misc: 0.0159, prepare_batch: 24.3744 train: 166.1362 epoch_init: 0.0194, minibatch_init: 0.0170, losses_postprocess: 1.0342, kl_divergence: 4.5768, after_optimizer: 68.1203 calculate_losses: 54.6025 losses_init: 0.0122, forward_head: 3.8602, bptt_initial: 26.7536, tail: 6.1786, advantages_returns: 0.7299, losses: 10.9377 bptt: 5.2574 bptt_forward_core: 5.0258 update: 36.1019 clip: 2.6315 [2024-08-01 16:35:55,156][00034] RolloutWorker_w0 profile tree view: wait_for_trajectories: 1.3566, enqueue_policy_requests: 135.7016, env_step: 2938.8411, overhead: 34.6193, complete_rollouts: 8.4061 save_policy_outputs: 156.2332 split_output_tensors: 53.9475 [2024-08-01 16:35:55,157][00034] RolloutWorker_w15 profile tree view: wait_for_trajectories: 1.2823, enqueue_policy_requests: 122.4323, env_step: 2949.4268, overhead: 33.0949, complete_rollouts: 9.1447 save_policy_outputs: 162.8393 split_output_tensors: 56.5126 [2024-08-01 16:35:55,158][00034] Loop Runner_EvtLoop terminating... [2024-08-01 16:35:55,160][00034] Runner profile tree view: main_loop: 3460.2025 [2024-08-01 16:35:55,160][00034] Collected {0: 10006528}, FPS: 2891.9 [2024-08-01 16:46:24,133][00034] Environment doom_basic already registered, overwriting... [2024-08-01 16:46:24,134][00034] Environment doom_two_colors_easy already registered, overwriting... [2024-08-01 16:46:24,135][00034] Environment doom_two_colors_hard already registered, overwriting... [2024-08-01 16:46:24,136][00034] Environment doom_dm already registered, overwriting... [2024-08-01 16:46:24,137][00034] Environment doom_dwango5 already registered, overwriting... [2024-08-01 16:46:24,138][00034] Environment doom_my_way_home_flat_actions already registered, overwriting... [2024-08-01 16:46:24,139][00034] Environment doom_defend_the_center_flat_actions already registered, overwriting... [2024-08-01 16:46:24,140][00034] Environment doom_my_way_home already registered, overwriting... [2024-08-01 16:46:24,141][00034] Environment doom_deadly_corridor already registered, overwriting... [2024-08-01 16:46:24,141][00034] Environment doom_defend_the_center already registered, overwriting... [2024-08-01 16:46:24,142][00034] Environment doom_defend_the_line already registered, overwriting... [2024-08-01 16:46:24,143][00034] Environment doom_health_gathering already registered, overwriting... [2024-08-01 16:46:24,143][00034] Environment doom_health_gathering_supreme already registered, overwriting... [2024-08-01 16:46:24,144][00034] Environment doom_battle already registered, overwriting... [2024-08-01 16:46:24,146][00034] Environment doom_battle2 already registered, overwriting... [2024-08-01 16:46:24,146][00034] Environment doom_duel_bots already registered, overwriting... [2024-08-01 16:46:24,147][00034] Environment doom_deathmatch_bots already registered, overwriting... [2024-08-01 16:46:24,148][00034] Environment doom_duel already registered, overwriting... [2024-08-01 16:46:24,148][00034] Environment doom_deathmatch_full already registered, overwriting... [2024-08-01 16:46:24,150][00034] Environment doom_benchmark already registered, overwriting... [2024-08-01 16:46:24,151][00034] register_encoder_factory: [2024-08-01 16:46:24,168][00034] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json [2024-08-01 16:46:24,169][00034] Overriding arg 'num_workers' with value 1 passed from command line [2024-08-01 16:46:24,170][00034] Adding new argument 'no_render'=True that is not in the saved config file! [2024-08-01 16:46:24,171][00034] Adding new argument 'save_video'=True that is not in the saved config file! [2024-08-01 16:46:24,172][00034] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2024-08-01 16:46:24,173][00034] Adding new argument 'video_name'=None that is not in the saved config file! [2024-08-01 16:46:24,173][00034] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2024-08-01 16:46:24,175][00034] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2024-08-01 16:46:24,176][00034] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2024-08-01 16:46:24,176][00034] Adding new argument 'hf_repository'=None that is not in the saved config file! [2024-08-01 16:46:24,177][00034] Adding new argument 'policy_index'=0 that is not in the saved config file! [2024-08-01 16:46:24,179][00034] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2024-08-01 16:46:24,180][00034] Adding new argument 'train_script'=None that is not in the saved config file! [2024-08-01 16:46:24,180][00034] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2024-08-01 16:46:24,181][00034] Using frameskip 1 and render_action_repeat=2 for evaluation [2024-08-01 16:46:24,211][00034] Doom resolution: 160x120, resize resolution: (128, 72) [2024-08-01 16:46:24,215][00034] Port 40300 is available [2024-08-01 16:46:24,215][00034] Using port 40300 [2024-08-01 16:46:24,218][00034] RunningMeanStd input shape: (23,) [2024-08-01 16:46:24,219][00034] RunningMeanStd input shape: (3, 72, 128) [2024-08-01 16:46:24,221][00034] RunningMeanStd input shape: (1,) [2024-08-01 16:46:24,240][00034] ConvEncoder: input_channels=3 [2024-08-01 16:46:24,365][00034] Conv encoder output size: 512 [2024-08-01 16:46:24,368][00034] Policy head output size: 640 [2024-08-01 16:46:24,572][00034] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000002443_10006528.pth... [2024-08-01 16:46:24,619][00034] Using port 40300 on host... [2024-08-01 16:46:24,953][00034] Initialized w:0 v:0 player:0 [2024-08-01 16:46:25,547][00034] Num frames 100... [2024-08-01 16:46:25,841][00034] Num frames 200... [2024-08-01 16:46:26,147][00034] Num frames 300... [2024-08-01 16:46:26,436][00034] Num frames 400... [2024-08-01 16:46:26,741][00034] Num frames 500... [2024-08-01 16:46:27,062][00034] Num frames 600... [2024-08-01 16:46:27,381][00034] Num frames 700... [2024-08-01 16:46:27,707][00034] Num frames 800... [2024-08-01 16:46:28,020][00034] Num frames 900... [2024-08-01 16:46:28,333][00034] Num frames 1000... [2024-08-01 16:46:28,638][00034] Num frames 1100... [2024-08-01 16:46:28,933][00034] Num frames 1200... [2024-08-01 16:46:29,232][00034] Num frames 1300... [2024-08-01 16:46:29,529][00034] Num frames 1400... [2024-08-01 16:46:29,828][00034] Num frames 1500... [2024-08-01 16:46:30,142][00034] Num frames 1600... [2024-08-01 16:46:30,454][00034] Num frames 1700... [2024-08-01 16:46:30,751][00034] Num frames 1800... [2024-08-01 16:46:31,049][00034] Num frames 1900... [2024-08-01 16:46:31,354][00034] Num frames 2000... [2024-08-01 16:46:31,661][00034] Num frames 2100... [2024-08-01 16:46:31,964][00034] Num frames 2200... [2024-08-01 16:46:32,271][00034] Num frames 2300... [2024-08-01 16:46:32,578][00034] Num frames 2400... [2024-08-01 16:46:32,883][00034] Num frames 2500... [2024-08-01 16:46:33,197][00034] Num frames 2600... [2024-08-01 16:46:33,535][00034] Num frames 2700... [2024-08-01 16:46:33,851][00034] Num frames 2800... [2024-08-01 16:46:34,173][00034] Num frames 2900... [2024-08-01 16:46:34,475][00034] Num frames 3000... [2024-08-01 16:46:34,774][00034] Num frames 3100... [2024-08-01 16:46:35,082][00034] Num frames 3200... [2024-08-01 16:46:35,392][00034] Num frames 3300... [2024-08-01 16:46:35,706][00034] Num frames 3400... [2024-08-01 16:46:36,031][00034] Num frames 3500... [2024-08-01 16:46:36,347][00034] Num frames 3600... [2024-08-01 16:46:36,651][00034] Num frames 3700... [2024-08-01 16:46:36,965][00034] Num frames 3800... [2024-08-01 16:46:37,262][00034] Num frames 3900... [2024-08-01 16:46:37,557][00034] Num frames 4000... [2024-08-01 16:46:37,863][00034] Num frames 4100... [2024-08-01 16:46:38,171][00034] Num frames 4200... [2024-08-01 16:46:38,478][00034] Num frames 4300... [2024-08-01 16:46:38,786][00034] Num frames 4400... [2024-08-01 16:46:39,093][00034] Num frames 4500... [2024-08-01 16:46:39,395][00034] Num frames 4600... [2024-08-01 16:46:39,694][00034] Num frames 4700... [2024-08-01 16:46:39,992][00034] Num frames 4800... [2024-08-01 16:46:40,294][00034] Num frames 4900... [2024-08-01 16:46:40,602][00034] Num frames 5000... [2024-08-01 16:46:40,910][00034] Num frames 5100... [2024-08-01 16:46:41,217][00034] Num frames 5200... [2024-08-01 16:46:41,523][00034] Num frames 5300... [2024-08-01 16:46:41,820][00034] Num frames 5400... [2024-08-01 16:46:42,137][00034] Num frames 5500... [2024-08-01 16:46:42,489][00034] Num frames 5600... [2024-08-01 16:46:42,847][00034] Num frames 5700... [2024-08-01 16:46:43,163][00034] Num frames 5800... [2024-08-01 16:46:43,514][00034] Num frames 5900... [2024-08-01 16:46:43,824][00034] Num frames 6000... [2024-08-01 16:46:44,135][00034] Num frames 6100... [2024-08-01 16:46:44,208][00034] Large shaping reward -2.519 for [('FRAGCOUNT', -1.5, -1.0), ('DEATHCOUNT', -0.75, 1.0), ('HEALTH', -0.27, -90.0), ('AMMO5', -0.0005, -1.0), ('weapon5', 0.002)] [2024-08-01 16:46:44,447][00034] Num frames 6200... [2024-08-01 16:46:44,746][00034] Num frames 6300... [2024-08-01 16:46:45,036][00034] Num frames 6400... [2024-08-01 16:46:45,331][00034] Num frames 6500... [2024-08-01 16:46:45,642][00034] Num frames 6600... [2024-08-01 16:46:45,937][00034] Num frames 6700... [2024-08-01 16:46:46,244][00034] Num frames 6800... [2024-08-01 16:46:46,545][00034] Num frames 6900... [2024-08-01 16:46:46,850][00034] Num frames 7000... [2024-08-01 16:46:47,153][00034] Num frames 7100... [2024-08-01 16:46:47,451][00034] Num frames 7200... [2024-08-01 16:46:47,746][00034] Num frames 7300... [2024-08-01 16:46:48,053][00034] Num frames 7400... [2024-08-01 16:46:48,365][00034] Num frames 7500... [2024-08-01 16:46:48,661][00034] Num frames 7600... [2024-08-01 16:46:48,960][00034] Num frames 7700... [2024-08-01 16:46:49,260][00034] Num frames 7800... [2024-08-01 16:46:49,580][00034] Num frames 7900... [2024-08-01 16:46:49,886][00034] Num frames 8000... [2024-08-01 16:46:50,195][00034] Num frames 8100... [2024-08-01 16:46:50,494][00034] Num frames 8200... [2024-08-01 16:46:50,793][00034] Num frames 8300... [2024-08-01 16:46:51,092][00034] DAMAGECOUNT value on done: 369.0 [2024-08-01 16:46:51,094][00034] Sum rewards: 3.767, reward structure: {'DEATHCOUNT': '-9.750', 'HEALTH': '-3.870', 'FRAGCOUNT': '0.000', 'AMMO2': '0.004', 'AMMO5': '0.015', 'WEAPON1': '0.020', 'AMMO4': '0.022', 'ARMOR': '0.036', 'weapon4': '0.080', 'WEAPON4': '0.100', 'HITCOUNT': '0.160', 'AMMO3': '0.170', 'WEAPON5': '0.400', 'weapon5': '0.722', 'WEAPON3': '0.900', 'DAMAGECOUNT': '1.107', 'weapon2': '6.442', 'weapon3': '7.208'} [2024-08-01 16:46:51,156][00034] Avg episode rewards: #0: 3.767, true rewards: #0: 1.000 [2024-08-01 16:46:51,157][00034] Avg episode reward: 3.767, avg true_objective: 1.000 [2024-08-01 16:46:51,163][00034] Num frames 8400... [2024-08-01 16:46:51,456][00034] Num frames 8500... [2024-08-01 16:46:51,748][00034] Num frames 8600... [2024-08-01 16:46:52,040][00034] Num frames 8700... [2024-08-01 16:46:52,330][00034] Num frames 8800... [2024-08-01 16:46:52,624][00034] Num frames 8900... [2024-08-01 16:46:52,919][00034] Num frames 9000... [2024-08-01 16:46:53,225][00034] Num frames 9100... [2024-08-01 16:46:53,543][00034] Num frames 9200... [2024-08-01 16:46:53,837][00034] Num frames 9300... [2024-08-01 16:46:54,159][00034] Num frames 9400... [2024-08-01 16:46:54,484][00034] Num frames 9500... [2024-08-01 16:46:54,803][00034] Num frames 9600... [2024-08-01 16:46:55,118][00034] Num frames 9700... [2024-08-01 16:46:55,432][00034] Num frames 9800... [2024-08-01 16:46:55,739][00034] Num frames 9900... [2024-08-01 16:46:56,042][00034] Num frames 10000... [2024-08-01 16:46:56,345][00034] Num frames 10100... [2024-08-01 16:46:56,645][00034] Num frames 10200... [2024-08-01 16:46:56,954][00034] Num frames 10300... [2024-08-01 16:46:57,259][00034] Num frames 10400... [2024-08-01 16:46:57,566][00034] Num frames 10500... [2024-08-01 16:46:57,876][00034] Num frames 10600... [2024-08-01 16:46:58,184][00034] Num frames 10700... [2024-08-01 16:46:58,489][00034] Num frames 10800... [2024-08-01 16:46:58,796][00034] Num frames 10900... [2024-08-01 16:46:59,106][00034] Num frames 11000... [2024-08-01 16:46:59,415][00034] Num frames 11100... [2024-08-01 16:46:59,726][00034] Num frames 11200... [2024-08-01 16:47:00,027][00034] Num frames 11300... [2024-08-01 16:47:00,332][00034] Num frames 11400... [2024-08-01 16:47:00,628][00034] Num frames 11500... [2024-08-01 16:47:00,924][00034] Num frames 11600... [2024-08-01 16:47:01,230][00034] Num frames 11700... [2024-08-01 16:47:01,537][00034] Num frames 11800... [2024-08-01 16:47:01,844][00034] Num frames 11900... [2024-08-01 16:47:02,150][00034] Num frames 12000... [2024-08-01 16:47:02,462][00034] Num frames 12100... [2024-08-01 16:47:02,758][00034] Num frames 12200... [2024-08-01 16:47:03,057][00034] Num frames 12300... [2024-08-01 16:47:03,370][00034] Num frames 12400... [2024-08-01 16:47:03,692][00034] Num frames 12500... [2024-08-01 16:47:03,999][00034] Num frames 12600... [2024-08-01 16:47:04,305][00034] Num frames 12700... [2024-08-01 16:47:04,613][00034] Num frames 12800... [2024-08-01 16:47:04,927][00034] Num frames 12900... [2024-08-01 16:47:05,238][00034] Num frames 13000... [2024-08-01 16:47:05,538][00034] Num frames 13100... [2024-08-01 16:47:05,842][00034] Num frames 13200... [2024-08-01 16:47:06,144][00034] Num frames 13300... [2024-08-01 16:47:06,445][00034] Num frames 13400... [2024-08-01 16:47:06,750][00034] Num frames 13500... [2024-08-01 16:47:07,052][00034] Num frames 13600... [2024-08-01 16:47:07,370][00034] Num frames 13700... [2024-08-01 16:47:07,665][00034] Num frames 13800... [2024-08-01 16:47:07,981][00034] Num frames 13900... [2024-08-01 16:47:08,290][00034] Num frames 14000... [2024-08-01 16:47:08,592][00034] Num frames 14100... [2024-08-01 16:47:08,897][00034] Num frames 14200... [2024-08-01 16:47:09,221][00034] Num frames 14300... [2024-08-01 16:47:09,541][00034] Num frames 14400... [2024-08-01 16:47:09,860][00034] Num frames 14500... [2024-08-01 16:47:10,175][00034] Num frames 14600... [2024-08-01 16:47:10,479][00034] Num frames 14700... [2024-08-01 16:47:10,785][00034] Num frames 14800... [2024-08-01 16:47:11,098][00034] Num frames 14900... [2024-08-01 16:47:11,403][00034] Num frames 15000... [2024-08-01 16:47:11,712][00034] Num frames 15100... [2024-08-01 16:47:12,021][00034] Num frames 15200... [2024-08-01 16:47:12,335][00034] Num frames 15300... [2024-08-01 16:47:12,649][00034] Num frames 15400... [2024-08-01 16:47:12,957][00034] Num frames 15500... [2024-08-01 16:47:13,274][00034] Num frames 15600... [2024-08-01 16:47:13,665][00034] Num frames 15700... [2024-08-01 16:47:14,018][00034] Num frames 15800... [2024-08-01 16:47:14,345][00034] Num frames 15900... [2024-08-01 16:47:14,684][00034] Num frames 16000... [2024-08-01 16:47:15,010][00034] Num frames 16100... [2024-08-01 16:47:15,321][00034] Num frames 16200... [2024-08-01 16:47:15,633][00034] Num frames 16300... [2024-08-01 16:47:15,940][00034] Num frames 16400... [2024-08-01 16:47:16,258][00034] Num frames 16500...