| [2025-01-08 18:07:19,496][01481] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2025-01-08 18:07:19,498][01481] Rollout worker 0 uses device cpu | |
| [2025-01-08 18:07:19,499][01481] Rollout worker 1 uses device cpu | |
| [2025-01-08 18:07:19,501][01481] Rollout worker 2 uses device cpu | |
| [2025-01-08 18:07:19,502][01481] Rollout worker 3 uses device cpu | |
| [2025-01-08 18:07:19,503][01481] Rollout worker 4 uses device cpu | |
| [2025-01-08 18:07:19,504][01481] Rollout worker 5 uses device cpu | |
| [2025-01-08 18:07:19,505][01481] Rollout worker 6 uses device cpu | |
| [2025-01-08 18:07:19,506][01481] Rollout worker 7 uses device cpu | |
| [2025-01-08 18:07:19,660][01481] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-08 18:07:19,662][01481] InferenceWorker_p0-w0: min num requests: 2 | |
| [2025-01-08 18:07:19,697][01481] Starting all processes... | |
| [2025-01-08 18:07:19,699][01481] Starting process learner_proc0 | |
| [2025-01-08 18:07:19,744][01481] Starting all processes... | |
| [2025-01-08 18:07:19,753][01481] Starting process inference_proc0-0 | |
| [2025-01-08 18:07:19,753][01481] Starting process rollout_proc0 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc1 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc2 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc3 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc4 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc5 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc6 | |
| [2025-01-08 18:07:19,755][01481] Starting process rollout_proc7 | |
| [2025-01-08 18:07:39,083][03278] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-08 18:07:39,093][03285] Worker 5 uses CPU cores [1] | |
| [2025-01-08 18:07:39,089][03278] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2025-01-08 18:07:39,101][03282] Worker 1 uses CPU cores [1] | |
| [2025-01-08 18:07:39,193][03278] Num visible devices: 1 | |
| [2025-01-08 18:07:39,287][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-08 18:07:39,296][03265] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2025-01-08 18:07:39,299][03279] Worker 2 uses CPU cores [0] | |
| [2025-01-08 18:07:39,305][03281] Worker 3 uses CPU cores [1] | |
| [2025-01-08 18:07:39,333][03265] Num visible devices: 1 | |
| [2025-01-08 18:07:39,357][03265] Starting seed is not provided | |
| [2025-01-08 18:07:39,358][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-08 18:07:39,359][03265] Initializing actor-critic model on device cuda:0 | |
| [2025-01-08 18:07:39,360][03265] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-08 18:07:39,363][03265] RunningMeanStd input shape: (1,) | |
| [2025-01-08 18:07:39,404][03265] ConvEncoder: input_channels=3 | |
| [2025-01-08 18:07:39,418][03283] Worker 4 uses CPU cores [0] | |
| [2025-01-08 18:07:39,446][03284] Worker 6 uses CPU cores [0] | |
| [2025-01-08 18:07:39,499][03280] Worker 0 uses CPU cores [0] | |
| [2025-01-08 18:07:39,619][03286] Worker 7 uses CPU cores [1] | |
| [2025-01-08 18:07:39,658][01481] Heartbeat connected on Batcher_0 | |
| [2025-01-08 18:07:39,664][01481] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2025-01-08 18:07:39,670][01481] Heartbeat connected on RolloutWorker_w0 | |
| [2025-01-08 18:07:39,673][01481] Heartbeat connected on RolloutWorker_w1 | |
| [2025-01-08 18:07:39,676][01481] Heartbeat connected on RolloutWorker_w2 | |
| [2025-01-08 18:07:39,679][01481] Heartbeat connected on RolloutWorker_w3 | |
| [2025-01-08 18:07:39,684][01481] Heartbeat connected on RolloutWorker_w4 | |
| [2025-01-08 18:07:39,688][01481] Heartbeat connected on RolloutWorker_w5 | |
| [2025-01-08 18:07:39,693][01481] Heartbeat connected on RolloutWorker_w6 | |
| [2025-01-08 18:07:39,713][01481] Heartbeat connected on RolloutWorker_w7 | |
| [2025-01-08 18:07:39,938][03265] Conv encoder output size: 512 | |
| [2025-01-08 18:07:39,939][03265] Policy head output size: 512 | |
| [2025-01-08 18:07:40,004][03265] Created Actor Critic model with architecture: | |
| [2025-01-08 18:07:40,005][03265] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (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=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 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=5, bias=True) | |
| ) | |
| ) | |
| [2025-01-08 18:07:40,493][03265] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2025-01-08 18:07:46,990][03265] No checkpoints found | |
| [2025-01-08 18:07:46,990][03265] Did not load from checkpoint, starting from scratch! | |
| [2025-01-08 18:07:46,990][03265] Initialized policy 0 weights for model version 0 | |
| [2025-01-08 18:07:46,995][03265] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-08 18:07:47,002][03265] LearnerWorker_p0 finished initialization! | |
| [2025-01-08 18:07:47,004][01481] Heartbeat connected on LearnerWorker_p0 | |
| [2025-01-08 18:07:47,091][03278] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-08 18:07:47,092][03278] RunningMeanStd input shape: (1,) | |
| [2025-01-08 18:07:47,104][03278] ConvEncoder: input_channels=3 | |
| [2025-01-08 18:07:47,221][03278] Conv encoder output size: 512 | |
| [2025-01-08 18:07:47,221][03278] Policy head output size: 512 | |
| [2025-01-08 18:07:47,277][01481] Inference worker 0-0 is ready! | |
| [2025-01-08 18:07:47,279][01481] All inference workers are ready! Signal rollout workers to start! | |
| [2025-01-08 18:07:47,482][03286] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,483][03285] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,485][03281] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,489][03282] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,498][03284] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,495][03283] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,499][03279] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:47,505][03280] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:07:48,462][03284] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:48,463][03283] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:48,820][01481] 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) | |
| [2025-01-08 18:07:48,839][03283] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:49,114][03286] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:49,112][03285] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:49,120][03281] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:49,123][03282] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:49,940][03279] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:49,953][03280] Decorrelating experience for 0 frames... | |
| [2025-01-08 18:07:50,246][03286] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:50,249][03285] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:50,255][03282] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:50,606][03280] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:51,417][03284] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:51,525][03279] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:51,821][03281] Decorrelating experience for 32 frames... | |
| [2025-01-08 18:07:52,248][03282] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:52,250][03286] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:52,257][03285] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:52,267][03280] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:52,764][03283] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:53,022][03284] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:53,477][03281] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:53,514][03280] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:53,589][03282] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:53,601][03285] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:53,820][01481] 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) | |
| [2025-01-08 18:07:54,218][03283] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:54,237][03286] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:54,324][03284] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:54,727][03279] Decorrelating experience for 64 frames... | |
| [2025-01-08 18:07:55,294][03281] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:55,521][03279] Decorrelating experience for 96 frames... | |
| [2025-01-08 18:07:58,823][01481] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 43.6. Samples: 436. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-08 18:07:58,827][01481] Avg episode reward: [(0, '1.692')] | |
| [2025-01-08 18:07:59,458][03265] Signal inference workers to stop experience collection... | |
| [2025-01-08 18:07:59,484][03278] InferenceWorker_p0-w0: stopping experience collection | |
| [2025-01-08 18:08:03,820][01481] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 147.2. Samples: 2208. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-08 18:08:03,823][01481] Avg episode reward: [(0, '2.162')] | |
| [2025-01-08 18:08:04,613][03265] Signal inference workers to resume experience collection... | |
| [2025-01-08 18:08:04,614][03278] InferenceWorker_p0-w0: resuming experience collection | |
| [2025-01-08 18:08:08,820][01481] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 309.8. Samples: 6196. Policy #0 lag: (min: 0.0, avg: 0.2, max: 2.0) | |
| [2025-01-08 18:08:08,826][01481] Avg episode reward: [(0, '3.603')] | |
| [2025-01-08 18:08:12,239][03278] Updated weights for policy 0, policy_version 10 (0.0020) | |
| [2025-01-08 18:08:13,822][01481] Fps is (10 sec: 4505.0, 60 sec: 1802.1, 300 sec: 1802.1). Total num frames: 45056. Throughput: 0: 389.2. Samples: 9730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-08 18:08:13,824][01481] Avg episode reward: [(0, '4.159')] | |
| [2025-01-08 18:08:18,820][01481] Fps is (10 sec: 3276.8, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 467.7. Samples: 14030. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-08 18:08:18,825][01481] Avg episode reward: [(0, '4.450')] | |
| [2025-01-08 18:08:23,820][01481] Fps is (10 sec: 3277.2, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 562.3. Samples: 19680. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2025-01-08 18:08:23,822][01481] Avg episode reward: [(0, '4.448')] | |
| [2025-01-08 18:08:24,316][03278] Updated weights for policy 0, policy_version 20 (0.0027) | |
| [2025-01-08 18:08:28,820][01481] Fps is (10 sec: 4505.6, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 580.9. Samples: 23234. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-08 18:08:28,828][01481] Avg episode reward: [(0, '4.265')] | |
| [2025-01-08 18:08:28,831][03265] Saving new best policy, reward=4.265! | |
| [2025-01-08 18:08:33,820][01481] Fps is (10 sec: 3686.4, 60 sec: 2548.6, 300 sec: 2548.6). Total num frames: 114688. Throughput: 0: 631.8. Samples: 28432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-08 18:08:33,823][01481] Avg episode reward: [(0, '4.200')] | |
| [2025-01-08 18:08:37,452][03278] Updated weights for policy 0, policy_version 30 (0.0030) | |
| [2025-01-08 18:08:38,820][01481] Fps is (10 sec: 2457.6, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 716.4. Samples: 32236. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2025-01-08 18:08:38,827][01481] Avg episode reward: [(0, '4.319')] | |
| [2025-01-08 18:08:38,831][03265] Saving new best policy, reward=4.319! | |
| [2025-01-08 18:08:43,820][01481] Fps is (10 sec: 3686.4, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 783.2. Samples: 35678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:08:43,823][01481] Avg episode reward: [(0, '4.355')] | |
| [2025-01-08 18:08:43,830][03265] Saving new best policy, reward=4.355! | |
| [2025-01-08 18:08:46,337][03278] Updated weights for policy 0, policy_version 40 (0.0019) | |
| [2025-01-08 18:08:48,820][01481] Fps is (10 sec: 4096.0, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 892.7. Samples: 42378. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-08 18:08:48,827][01481] Avg episode reward: [(0, '4.407')] | |
| [2025-01-08 18:08:48,832][03265] Saving new best policy, reward=4.407! | |
| [2025-01-08 18:08:53,820][01481] Fps is (10 sec: 3276.8, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 897.6. Samples: 46588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-08 18:08:53,826][01481] Avg episode reward: [(0, '4.432')] | |
| [2025-01-08 18:08:53,834][03265] Saving new best policy, reward=4.432! | |
| [2025-01-08 18:08:57,825][03278] Updated weights for policy 0, policy_version 50 (0.0040) | |
| [2025-01-08 18:08:58,821][01481] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 2984.2). Total num frames: 208896. Throughput: 0: 891.3. Samples: 49838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-08 18:08:58,822][01481] Avg episode reward: [(0, '4.377')] | |
| [2025-01-08 18:09:03,820][01481] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3058.3). Total num frames: 229376. Throughput: 0: 952.1. Samples: 56876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-08 18:09:03,825][01481] Avg episode reward: [(0, '4.433')] | |
| [2025-01-08 18:09:03,835][03265] Saving new best policy, reward=4.433! | |
| [2025-01-08 18:09:08,828][01481] Fps is (10 sec: 3274.4, 60 sec: 3617.7, 300 sec: 3020.5). Total num frames: 241664. Throughput: 0: 931.4. Samples: 61600. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-08 18:09:08,830][01481] Avg episode reward: [(0, '4.509')] | |
| [2025-01-08 18:09:08,880][03278] Updated weights for policy 0, policy_version 60 (0.0022) | |
| [2025-01-08 18:09:08,886][03265] Saving new best policy, reward=4.509! | |
| [2025-01-08 18:09:13,820][01481] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 903.9. Samples: 63908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:09:13,823][01481] Avg episode reward: [(0, '4.460')] | |
| [2025-01-08 18:09:13,830][03265] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth... | |
| [2025-01-08 18:09:18,816][03278] Updated weights for policy 0, policy_version 70 (0.0023) | |
| [2025-01-08 18:09:18,820][01481] Fps is (10 sec: 4509.0, 60 sec: 3822.9, 300 sec: 3185.8). Total num frames: 286720. Throughput: 0: 934.0. Samples: 70464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-08 18:09:18,823][01481] Avg episode reward: [(0, '4.261')] | |
| [2025-01-08 18:09:23,821][01481] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3147.4). Total num frames: 299008. Throughput: 0: 970.3. Samples: 75900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:09:23,823][01481] Avg episode reward: [(0, '4.314')] | |
| [2025-01-08 18:09:28,820][01481] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3153.9). Total num frames: 315392. Throughput: 0: 939.6. Samples: 77958. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-08 18:09:28,827][01481] Avg episode reward: [(0, '4.418')] | |
| [2025-01-08 18:09:30,916][03278] Updated weights for policy 0, policy_version 80 (0.0017) | |
| [2025-01-08 18:09:33,820][01481] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3237.8). Total num frames: 339968. Throughput: 0: 926.2. Samples: 84058. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-08 18:09:33,828][01481] Avg episode reward: [(0, '4.295')] | |
| [2025-01-08 18:09:38,820][01481] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3276.8). Total num frames: 360448. Throughput: 0: 973.0. Samples: 90374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:09:38,828][01481] Avg episode reward: [(0, '4.214')] | |
| [2025-01-08 18:09:42,629][03278] Updated weights for policy 0, policy_version 90 (0.0018) | |
| [2025-01-08 18:09:43,826][01481] Fps is (10 sec: 2865.6, 60 sec: 3617.8, 300 sec: 3205.4). Total num frames: 368640. Throughput: 0: 936.8. Samples: 92000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:09:43,830][01481] Avg episode reward: [(0, '4.260')] | |
| [2025-01-08 18:09:48,820][01481] Fps is (10 sec: 2048.0, 60 sec: 3549.9, 300 sec: 3174.4). Total num frames: 380928. Throughput: 0: 852.0. Samples: 95218. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-08 18:09:48,823][01481] Avg episode reward: [(0, '4.373')] | |
| [2025-01-08 18:09:53,820][01481] Fps is (10 sec: 3278.6, 60 sec: 3618.1, 300 sec: 3211.3). Total num frames: 401408. Throughput: 0: 874.3. Samples: 100938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-08 18:09:53,824][01481] Avg episode reward: [(0, '4.383')] | |
| [2025-01-08 18:09:55,221][03278] Updated weights for policy 0, policy_version 100 (0.0033) | |
| [2025-01-08 18:09:58,823][01481] Fps is (10 sec: 4504.4, 60 sec: 3618.0, 300 sec: 3276.7). Total num frames: 425984. Throughput: 0: 899.1. Samples: 104370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-08 18:09:58,826][01481] Avg episode reward: [(0, '4.462')] | |
| [2025-01-08 18:09:59,546][01481] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 1481], exiting... | |
| [2025-01-08 18:09:59,556][03265] Stopping Batcher_0... | |
| [2025-01-08 18:09:59,558][03265] Loop batcher_evt_loop terminating... | |
| [2025-01-08 18:09:59,556][01481] Runner profile tree view: | |
| main_loop: 159.8596 | |
| [2025-01-08 18:09:59,562][01481] Collected {0: 425984}, FPS: 2664.7 | |
| [2025-01-08 18:09:59,563][03265] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth... | |
| [2025-01-08 18:09:59,740][03278] Weights refcount: 2 0 | |
| [2025-01-08 18:09:59,749][03278] Stopping InferenceWorker_p0-w0... | |
| [2025-01-08 18:09:59,750][03278] Loop inference_proc0-0_evt_loop terminating... | |
| [2025-01-08 18:09:59,886][03280] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance0'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:09:59,941][03280] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop | |
| [2025-01-08 18:09:59,930][03265] Stopping LearnerWorker_p0... | |
| [2025-01-08 18:09:59,942][03265] Loop learner_proc0_evt_loop terminating... | |
| [2025-01-08 18:09:59,955][03283] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance4'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:09:59,961][03283] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop | |
| [2025-01-08 18:10:00,088][03279] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance2'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,090][03279] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc2_evt_loop | |
| [2025-01-08 18:10:00,056][03284] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance6'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,093][03284] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop | |
| [2025-01-08 18:10:00,055][03285] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance5'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,152][03285] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop | |
| [2025-01-08 18:10:00,139][03286] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance7'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,194][03286] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc7_evt_loop | |
| [2025-01-08 18:10:00,212][03282] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance1'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,250][03282] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc1_evt_loop | |
| [2025-01-08 18:10:00,344][03281] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance3'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 522, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 461, in step | |
| return self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2025-01-08 18:10:00,359][03281] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc3_evt_loop | |
| [2025-01-08 18:10:01,515][01481] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-08 18:10:01,522][01481] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-08 18:10:01,528][01481] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-08 18:10:01,530][01481] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-08 18:10:01,533][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-08 18:10:01,535][01481] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-08 18:10:01,552][01481] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-08 18:10:01,557][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-08 18:10:01,562][01481] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2025-01-08 18:10:01,581][01481] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2025-01-08 18:10:01,583][01481] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-08 18:10:01,586][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-08 18:10:01,601][01481] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-08 18:10:01,604][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-08 18:10:01,657][01481] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-08 18:10:01,747][01481] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-08 18:10:01,752][01481] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-08 18:10:01,761][01481] RunningMeanStd input shape: (1,) | |
| [2025-01-08 18:10:01,796][01481] ConvEncoder: input_channels=3 | |
| [2025-01-08 18:10:02,139][01481] Conv encoder output size: 512 | |
| [2025-01-08 18:10:02,143][01481] Policy head output size: 512 | |
| [2025-01-08 18:10:02,663][01481] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth... | |
| [2025-01-08 18:10:05,006][01481] Num frames 100... | |
| [2025-01-08 18:10:05,235][01481] Num frames 200... | |
| [2025-01-08 18:10:05,435][01481] Num frames 300... | |
| [2025-01-08 18:10:05,662][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 | |
| [2025-01-08 18:10:05,664][01481] Avg episode reward: 3.840, avg true_objective: 3.840 | |
| [2025-01-08 18:10:05,701][01481] Num frames 400... | |
| [2025-01-08 18:10:05,914][01481] Num frames 500... | |
| [2025-01-08 18:10:06,147][01481] Num frames 600... | |
| [2025-01-08 18:10:06,346][01481] Num frames 700... | |
| [2025-01-08 18:10:06,545][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 | |
| [2025-01-08 18:10:06,551][01481] Avg episode reward: 3.840, avg true_objective: 3.840 | |
| [2025-01-08 18:10:06,619][01481] Num frames 800... | |
| [2025-01-08 18:10:06,819][01481] Num frames 900... | |
| [2025-01-08 18:10:07,029][01481] Num frames 1000... | |
| [2025-01-08 18:10:07,225][01481] Num frames 1100... | |
| [2025-01-08 18:10:07,371][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 | |
| [2025-01-08 18:10:07,373][01481] Avg episode reward: 3.840, avg true_objective: 3.840 | |
| [2025-01-08 18:11:05,889][01481] Loading legacy config file train_dir/doom_health_gathering_supreme_2222/cfg.json instead of train_dir/doom_health_gathering_supreme_2222/config.json | |
| [2025-01-08 18:11:05,891][01481] Loading existing experiment configuration from train_dir/doom_health_gathering_supreme_2222/config.json | |
| [2025-01-08 18:11:05,893][01481] Overriding arg 'experiment' with value 'doom_health_gathering_supreme_2222' passed from command line | |
| [2025-01-08 18:11:05,895][01481] Overriding arg 'train_dir' with value 'train_dir' passed from command line | |
| [2025-01-08 18:11:05,896][01481] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-08 18:11:05,898][01481] Adding new argument 'lr_adaptive_min'=1e-06 that is not in the saved config file! | |
| [2025-01-08 18:11:05,900][01481] Adding new argument 'lr_adaptive_max'=0.01 that is not in the saved config file! | |
| [2025-01-08 18:11:05,900][01481] Adding new argument 'env_gpu_observations'=True that is not in the saved config file! | |
| [2025-01-08 18:11:05,901][01481] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-08 18:11:05,902][01481] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-08 18:11:05,903][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-08 18:11:05,904][01481] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-08 18:11:05,905][01481] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-08 18:11:05,906][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-08 18:11:05,907][01481] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2025-01-08 18:11:05,908][01481] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2025-01-08 18:11:05,909][01481] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-08 18:11:05,910][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-08 18:11:05,911][01481] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-08 18:11:05,912][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-08 18:11:05,913][01481] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-08 18:11:05,953][01481] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-08 18:11:05,954][01481] RunningMeanStd input shape: (1,) | |
| [2025-01-08 18:11:05,970][01481] ConvEncoder: input_channels=3 | |
| [2025-01-08 18:11:06,018][01481] Conv encoder output size: 512 | |
| [2025-01-08 18:11:06,020][01481] Policy head output size: 512 | |
| [2025-01-08 18:11:06,043][01481] Loading state from checkpoint train_dir/doom_health_gathering_supreme_2222/checkpoint_p0/checkpoint_000539850_4422451200.pth... | |
| [2025-01-08 18:11:06,482][01481] Num frames 100... | |
| [2025-01-08 18:11:06,616][01481] Num frames 200... | |
| [2025-01-08 18:11:06,738][01481] Num frames 300... | |
| [2025-01-08 18:11:06,865][01481] Num frames 400... | |
| [2025-01-08 18:11:06,990][01481] Num frames 500... | |
| [2025-01-08 18:11:07,114][01481] Num frames 600... | |
| [2025-01-08 18:11:07,243][01481] Num frames 700... | |
| [2025-01-08 18:11:07,372][01481] Num frames 800... | |
| [2025-01-08 18:11:07,498][01481] Num frames 900... | |
| [2025-01-08 18:11:07,629][01481] Num frames 1000... | |
| [2025-01-08 18:11:07,755][01481] Num frames 1100... | |
| [2025-01-08 18:11:07,883][01481] Num frames 1200... | |
| [2025-01-08 18:11:08,010][01481] Num frames 1300... | |
| [2025-01-08 18:11:08,142][01481] Num frames 1400... | |
| [2025-01-08 18:11:08,272][01481] Num frames 1500... | |
| [2025-01-08 18:11:08,405][01481] Num frames 1600... | |
| [2025-01-08 18:11:08,530][01481] Num frames 1700... | |
| [2025-01-08 18:11:08,661][01481] Num frames 1800... | |
| [2025-01-08 18:11:08,786][01481] Num frames 1900... | |
| [2025-01-08 18:11:08,920][01481] Num frames 2000... | |
| [2025-01-08 18:11:09,046][01481] Num frames 2100... | |
| [2025-01-08 18:11:09,098][01481] Avg episode rewards: #0: 55.999, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:09,100][01481] Avg episode reward: 55.999, avg true_objective: 21.000 | |
| [2025-01-08 18:11:09,229][01481] Num frames 2200... | |
| [2025-01-08 18:11:09,359][01481] Num frames 2300... | |
| [2025-01-08 18:11:09,481][01481] Num frames 2400... | |
| [2025-01-08 18:11:09,604][01481] Num frames 2500... | |
| [2025-01-08 18:11:09,735][01481] Num frames 2600... | |
| [2025-01-08 18:11:09,859][01481] Num frames 2700... | |
| [2025-01-08 18:11:09,984][01481] Num frames 2800... | |
| [2025-01-08 18:11:10,105][01481] Num frames 2900... | |
| [2025-01-08 18:11:10,233][01481] Num frames 3000... | |
| [2025-01-08 18:11:10,361][01481] Num frames 3100... | |
| [2025-01-08 18:11:10,484][01481] Num frames 3200... | |
| [2025-01-08 18:11:10,607][01481] Num frames 3300... | |
| [2025-01-08 18:11:10,737][01481] Num frames 3400... | |
| [2025-01-08 18:11:10,869][01481] Num frames 3500... | |
| [2025-01-08 18:11:10,999][01481] Num frames 3600... | |
| [2025-01-08 18:11:11,123][01481] Num frames 3700... | |
| [2025-01-08 18:11:11,251][01481] Num frames 3800... | |
| [2025-01-08 18:11:11,388][01481] Num frames 3900... | |
| [2025-01-08 18:11:11,517][01481] Num frames 4000... | |
| [2025-01-08 18:11:11,639][01481] Num frames 4100... | |
| [2025-01-08 18:11:11,774][01481] Num frames 4200... | |
| [2025-01-08 18:11:11,826][01481] Avg episode rewards: #0: 61.999, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:11,828][01481] Avg episode reward: 61.999, avg true_objective: 21.000 | |
| [2025-01-08 18:11:11,954][01481] Num frames 4300... | |
| [2025-01-08 18:11:12,081][01481] Num frames 4400... | |
| [2025-01-08 18:11:12,204][01481] Num frames 4500... | |
| [2025-01-08 18:11:12,332][01481] Num frames 4600... | |
| [2025-01-08 18:11:12,460][01481] Num frames 4700... | |
| [2025-01-08 18:11:12,590][01481] Num frames 4800... | |
| [2025-01-08 18:11:12,725][01481] Num frames 4900... | |
| [2025-01-08 18:11:12,862][01481] Num frames 5000... | |
| [2025-01-08 18:11:12,986][01481] Num frames 5100... | |
| [2025-01-08 18:11:13,110][01481] Num frames 5200... | |
| [2025-01-08 18:11:13,236][01481] Num frames 5300... | |
| [2025-01-08 18:11:13,364][01481] Num frames 5400... | |
| [2025-01-08 18:11:13,494][01481] Num frames 5500... | |
| [2025-01-08 18:11:13,615][01481] Num frames 5600... | |
| [2025-01-08 18:11:13,743][01481] Num frames 5700... | |
| [2025-01-08 18:11:13,876][01481] Num frames 5800... | |
| [2025-01-08 18:11:14,002][01481] Num frames 5900... | |
| [2025-01-08 18:11:14,126][01481] Num frames 6000... | |
| [2025-01-08 18:11:14,250][01481] Num frames 6100... | |
| [2025-01-08 18:11:14,380][01481] Num frames 6200... | |
| [2025-01-08 18:11:14,507][01481] Num frames 6300... | |
| [2025-01-08 18:11:14,560][01481] Avg episode rewards: #0: 64.666, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:14,562][01481] Avg episode reward: 64.666, avg true_objective: 21.000 | |
| [2025-01-08 18:11:14,739][01481] Num frames 6400... | |
| [2025-01-08 18:11:14,924][01481] Num frames 6500... | |
| [2025-01-08 18:11:15,091][01481] Num frames 6600... | |
| [2025-01-08 18:11:15,262][01481] Num frames 6700... | |
| [2025-01-08 18:11:15,438][01481] Num frames 6800... | |
| [2025-01-08 18:11:15,607][01481] Num frames 6900... | |
| [2025-01-08 18:11:15,771][01481] Num frames 7000... | |
| [2025-01-08 18:11:15,961][01481] Num frames 7100... | |
| [2025-01-08 18:11:16,147][01481] Num frames 7200... | |
| [2025-01-08 18:11:16,322][01481] Num frames 7300... | |
| [2025-01-08 18:11:16,517][01481] Num frames 7400... | |
| [2025-01-08 18:11:16,694][01481] Num frames 7500... | |
| [2025-01-08 18:11:16,871][01481] Num frames 7600... | |
| [2025-01-08 18:11:17,065][01481] Num frames 7700... | |
| [2025-01-08 18:11:17,228][01481] Num frames 7800... | |
| [2025-01-08 18:11:17,361][01481] Num frames 7900... | |
| [2025-01-08 18:11:17,487][01481] Num frames 8000... | |
| [2025-01-08 18:11:17,609][01481] Num frames 8100... | |
| [2025-01-08 18:11:17,733][01481] Num frames 8200... | |
| [2025-01-08 18:11:17,862][01481] Num frames 8300... | |
| [2025-01-08 18:11:18,007][01481] Num frames 8400... | |
| [2025-01-08 18:11:18,060][01481] Avg episode rewards: #0: 64.499, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:18,062][01481] Avg episode reward: 64.499, avg true_objective: 21.000 | |
| [2025-01-08 18:11:18,192][01481] Num frames 8500... | |
| [2025-01-08 18:11:18,323][01481] Num frames 8600... | |
| [2025-01-08 18:11:18,461][01481] Num frames 8700... | |
| [2025-01-08 18:11:18,589][01481] Num frames 8800... | |
| [2025-01-08 18:11:18,718][01481] Num frames 8900... | |
| [2025-01-08 18:11:18,846][01481] Num frames 9000... | |
| [2025-01-08 18:11:18,971][01481] Num frames 9100... | |
| [2025-01-08 18:11:19,108][01481] Num frames 9200... | |
| [2025-01-08 18:11:19,236][01481] Num frames 9300... | |
| [2025-01-08 18:11:19,368][01481] Num frames 9400... | |
| [2025-01-08 18:11:19,491][01481] Num frames 9500... | |
| [2025-01-08 18:11:19,614][01481] Num frames 9600... | |
| [2025-01-08 18:11:19,737][01481] Num frames 9700... | |
| [2025-01-08 18:11:19,861][01481] Num frames 9800... | |
| [2025-01-08 18:11:19,989][01481] Num frames 9900... | |
| [2025-01-08 18:11:20,123][01481] Num frames 10000... | |
| [2025-01-08 18:11:20,250][01481] Num frames 10100... | |
| [2025-01-08 18:11:20,387][01481] Num frames 10200... | |
| [2025-01-08 18:11:20,517][01481] Num frames 10300... | |
| [2025-01-08 18:11:20,643][01481] Num frames 10400... | |
| [2025-01-08 18:11:20,789][01481] Num frames 10500... | |
| [2025-01-08 18:11:20,843][01481] Avg episode rewards: #0: 63.999, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:20,845][01481] Avg episode reward: 63.999, avg true_objective: 21.000 | |
| [2025-01-08 18:11:20,976][01481] Num frames 10600... | |
| [2025-01-08 18:11:21,109][01481] Num frames 10700... | |
| [2025-01-08 18:11:21,236][01481] Num frames 10800... | |
| [2025-01-08 18:11:21,365][01481] Num frames 10900... | |
| [2025-01-08 18:11:21,490][01481] Num frames 11000... | |
| [2025-01-08 18:11:21,611][01481] Num frames 11100... | |
| [2025-01-08 18:11:21,733][01481] Num frames 11200... | |
| [2025-01-08 18:11:21,858][01481] Num frames 11300... | |
| [2025-01-08 18:11:21,984][01481] Num frames 11400... | |
| [2025-01-08 18:11:22,121][01481] Num frames 11500... | |
| [2025-01-08 18:11:22,248][01481] Num frames 11600... | |
| [2025-01-08 18:11:22,384][01481] Num frames 11700... | |
| [2025-01-08 18:11:22,509][01481] Num frames 11800... | |
| [2025-01-08 18:11:22,634][01481] Num frames 11900... | |
| [2025-01-08 18:11:22,759][01481] Num frames 12000... | |
| [2025-01-08 18:11:22,884][01481] Num frames 12100... | |
| [2025-01-08 18:11:23,012][01481] Num frames 12200... | |
| [2025-01-08 18:11:23,144][01481] Num frames 12300... | |
| [2025-01-08 18:11:23,279][01481] Num frames 12400... | |
| [2025-01-08 18:11:23,402][01481] Num frames 12500... | |
| [2025-01-08 18:11:23,528][01481] Num frames 12600... | |
| [2025-01-08 18:11:23,581][01481] Avg episode rewards: #0: 63.499, true rewards: #0: 21.000 | |
| [2025-01-08 18:11:23,582][01481] Avg episode reward: 63.499, avg true_objective: 21.000 | |
| [2025-01-08 18:11:23,706][01481] Num frames 12700... | |
| [2025-01-08 18:11:23,831][01481] Num frames 12800... | |
| [2025-01-08 18:11:23,960][01481] Num frames 12900... | |
| [2025-01-08 18:11:24,089][01481] Num frames 13000... | |
| [2025-01-08 18:11:24,224][01481] Num frames 13100... | |
| [2025-01-08 18:11:24,356][01481] Num frames 13200... | |
| [2025-01-08 18:11:24,481][01481] Num frames 13300... | |
| [2025-01-08 18:11:24,605][01481] Num frames 13400... | |
| [2025-01-08 18:11:24,728][01481] Num frames 13500... | |
| [2025-01-08 18:11:24,860][01481] Num frames 13600... | |
| [2025-01-08 18:11:24,985][01481] Num frames 13700... | |
| [2025-01-08 18:11:25,110][01481] Num frames 13800... | |
| [2025-01-08 18:11:25,244][01481] Num frames 13900... | |
| [2025-01-08 18:11:25,318][01481] Avg episode rewards: #0: 59.445, true rewards: #0: 19.874 | |
| [2025-01-08 18:11:25,320][01481] Avg episode reward: 59.445, avg true_objective: 19.874 | |
| [2025-01-08 18:11:25,428][01481] Num frames 14000... | |
| [2025-01-08 18:11:25,551][01481] Num frames 14100... | |
| [2025-01-08 18:11:25,677][01481] Num frames 14200... | |
| [2025-01-08 18:11:25,802][01481] Num frames 14300... | |
| [2025-01-08 18:11:25,929][01481] Num frames 14400... | |
| [2025-01-08 18:11:26,058][01481] Num frames 14500... | |
| [2025-01-08 18:11:26,191][01481] Num frames 14600... | |
| [2025-01-08 18:11:26,324][01481] Num frames 14700... | |
| [2025-01-08 18:11:26,448][01481] Num frames 14800... | |
| [2025-01-08 18:11:26,573][01481] Num frames 14900... | |
| [2025-01-08 18:11:26,695][01481] Num frames 15000... | |
| [2025-01-08 18:11:26,830][01481] Num frames 15100... | |
| [2025-01-08 18:11:26,959][01481] Num frames 15200... | |
| [2025-01-08 18:11:27,087][01481] Num frames 15300... | |
| [2025-01-08 18:11:27,261][01481] Num frames 15400... | |
| [2025-01-08 18:11:27,449][01481] Num frames 15500... | |
| [2025-01-08 18:11:27,621][01481] Num frames 15600... | |
| [2025-01-08 18:11:27,791][01481] Num frames 15700... | |
| [2025-01-08 18:11:27,969][01481] Num frames 15800... | |
| [2025-01-08 18:11:28,139][01481] Num frames 15900... | |
| [2025-01-08 18:11:28,323][01481] Num frames 16000... | |
| [2025-01-08 18:11:28,401][01481] Avg episode rewards: #0: 59.889, true rewards: #0: 20.015 | |
| [2025-01-08 18:11:28,403][01481] Avg episode reward: 59.889, avg true_objective: 20.015 | |
| [2025-01-08 18:11:28,552][01481] Num frames 16100... | |
| [2025-01-08 18:11:28,737][01481] Num frames 16200... | |
| [2025-01-08 18:11:28,912][01481] Num frames 16300... | |
| [2025-01-08 18:11:29,095][01481] Num frames 16400... | |
| [2025-01-08 18:11:29,277][01481] Num frames 16500... | |
| [2025-01-08 18:11:29,460][01481] Num frames 16600... | |
| [2025-01-08 18:11:29,636][01481] Num frames 16700... | |
| [2025-01-08 18:11:29,809][01481] Num frames 16800... | |
| [2025-01-08 18:11:29,933][01481] Num frames 16900... | |
| [2025-01-08 18:11:30,056][01481] Num frames 17000... | |
| [2025-01-08 18:11:30,187][01481] Num frames 17100... | |
| [2025-01-08 18:11:30,317][01481] Num frames 17200... | |
| [2025-01-08 18:11:30,454][01481] Num frames 17300... | |
| [2025-01-08 18:11:30,579][01481] Num frames 17400... | |
| [2025-01-08 18:11:30,704][01481] Num frames 17500... | |
| [2025-01-08 18:11:30,833][01481] Num frames 17600... | |
| [2025-01-08 18:11:30,949][01481] Avg episode rewards: #0: 58.497, true rewards: #0: 19.609 | |
| [2025-01-08 18:11:30,951][01481] Avg episode reward: 58.497, avg true_objective: 19.609 | |
| [2025-01-08 18:11:31,021][01481] Num frames 17700... | |
| [2025-01-08 18:11:31,143][01481] Num frames 17800... | |
| [2025-01-08 18:11:31,276][01481] Num frames 17900... | |
| [2025-01-08 18:11:31,414][01481] Num frames 18000... | |
| [2025-01-08 18:11:31,539][01481] Num frames 18100... | |
| [2025-01-08 18:11:31,665][01481] Num frames 18200... | |
| [2025-01-08 18:11:31,791][01481] Num frames 18300... | |
| [2025-01-08 18:11:31,917][01481] Num frames 18400... | |
| [2025-01-08 18:11:32,045][01481] Num frames 18500... | |
| [2025-01-08 18:11:32,172][01481] Num frames 18600... | |
| [2025-01-08 18:11:32,309][01481] Num frames 18700... | |
| [2025-01-08 18:11:32,445][01481] Num frames 18800... | |
| [2025-01-08 18:11:32,573][01481] Num frames 18900... | |
| [2025-01-08 18:11:32,700][01481] Num frames 19000... | |
| [2025-01-08 18:11:32,826][01481] Num frames 19100... | |
| [2025-01-08 18:11:32,958][01481] Num frames 19200... | |
| [2025-01-08 18:11:33,084][01481] Num frames 19300... | |
| [2025-01-08 18:11:33,214][01481] Num frames 19400... | |
| [2025-01-08 18:11:33,350][01481] Num frames 19500... | |
| [2025-01-08 18:11:33,486][01481] Num frames 19600... | |
| [2025-01-08 18:11:33,658][01481] Num frames 19700... | |
| [2025-01-08 18:11:33,815][01481] Avg episode rewards: #0: 59.047, true rewards: #0: 19.748 | |
| [2025-01-08 18:11:33,817][01481] Avg episode reward: 59.047, avg true_objective: 19.748 | |
| [2025-01-08 18:13:39,180][01481] Replay video saved to train_dir/doom_health_gathering_supreme_2222/replay.mp4! | |
| [2025-01-08 18:15:38,880][01481] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-08 18:15:38,882][01481] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-08 18:15:38,883][01481] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-08 18:15:38,885][01481] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-08 18:15:38,887][01481] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-08 18:15:38,889][01481] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-08 18:15:38,890][01481] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-01-08 18:15:38,892][01481] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-08 18:15:38,893][01481] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-01-08 18:15:38,894][01481] Adding new argument 'hf_repository'='jdollman/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-01-08 18:15:38,895][01481] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-08 18:15:38,896][01481] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-08 18:15:38,897][01481] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-08 18:15:38,898][01481] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-08 18:15:38,899][01481] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-08 18:15:38,928][01481] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-08 18:15:38,930][01481] RunningMeanStd input shape: (1,) | |
| [2025-01-08 18:15:38,943][01481] ConvEncoder: input_channels=3 | |
| [2025-01-08 18:15:38,979][01481] Conv encoder output size: 512 | |
| [2025-01-08 18:15:38,981][01481] Policy head output size: 512 | |
| [2025-01-08 18:15:38,999][01481] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000104_425984.pth... | |
| [2025-01-08 18:15:39,448][01481] Num frames 100... | |
| [2025-01-08 18:15:39,569][01481] Num frames 200... | |
| [2025-01-08 18:15:39,687][01481] Num frames 300... | |
| [2025-01-08 18:15:39,851][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 | |
| [2025-01-08 18:15:39,853][01481] Avg episode reward: 3.840, avg true_objective: 3.840 | |
| [2025-01-08 18:15:39,876][01481] Num frames 400... | |
| [2025-01-08 18:15:39,992][01481] Num frames 500... | |
| [2025-01-08 18:15:40,111][01481] Num frames 600... | |
| [2025-01-08 18:15:40,234][01481] Num frames 700... | |
| [2025-01-08 18:15:40,377][01481] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 | |
| [2025-01-08 18:15:40,379][01481] Avg episode reward: 3.840, avg true_objective: 3.840 | |
| [2025-01-08 18:15:40,419][01481] Num frames 800... | |
| [2025-01-08 18:15:40,540][01481] Num frames 900... | |
| [2025-01-08 18:15:40,662][01481] Num frames 1000... | |
| [2025-01-08 18:15:40,808][01481] Avg episode rewards: #0: 3.557, true rewards: #0: 3.557 | |
| [2025-01-08 18:15:40,810][01481] Avg episode reward: 3.557, avg true_objective: 3.557 | |
| [2025-01-08 18:15:40,850][01481] Num frames 1100... | |
| [2025-01-08 18:15:40,966][01481] Num frames 1200... | |
| [2025-01-08 18:15:41,085][01481] Num frames 1300... | |
| [2025-01-08 18:15:41,203][01481] Num frames 1400... | |
| [2025-01-08 18:15:41,324][01481] Avg episode rewards: #0: 3.627, true rewards: #0: 3.627 | |
| [2025-01-08 18:15:41,326][01481] Avg episode reward: 3.627, avg true_objective: 3.627 | |
| [2025-01-08 18:15:41,390][01481] Num frames 1500... | |
| [2025-01-08 18:15:41,509][01481] Num frames 1600... | |
| [2025-01-08 18:15:41,634][01481] Num frames 1700... | |
| [2025-01-08 18:15:41,754][01481] Num frames 1800... | |
| [2025-01-08 18:15:41,936][01481] Avg episode rewards: #0: 3.998, true rewards: #0: 3.798 | |
| [2025-01-08 18:15:41,938][01481] Avg episode reward: 3.998, avg true_objective: 3.798 | |
| [2025-01-08 18:15:41,942][01481] Num frames 1900... | |
| [2025-01-08 18:15:42,062][01481] Num frames 2000... | |
| [2025-01-08 18:15:42,184][01481] Num frames 2100... | |
| [2025-01-08 18:15:42,315][01481] Num frames 2200... | |
| [2025-01-08 18:15:42,470][01481] Avg episode rewards: #0: 3.972, true rewards: #0: 3.805 | |
| [2025-01-08 18:15:42,472][01481] Avg episode reward: 3.972, avg true_objective: 3.805 | |
| [2025-01-08 18:15:42,497][01481] Num frames 2300... | |
| [2025-01-08 18:15:42,621][01481] Num frames 2400... | |
| [2025-01-08 18:15:42,739][01481] Num frames 2500... | |
| [2025-01-08 18:15:42,844][01481] Avg episode rewards: #0: 3.770, true rewards: #0: 3.627 | |
| [2025-01-08 18:15:42,846][01481] Avg episode reward: 3.770, avg true_objective: 3.627 | |
| [2025-01-08 18:15:42,923][01481] Num frames 2600... | |
| [2025-01-08 18:15:43,043][01481] Num frames 2700... | |
| [2025-01-08 18:15:43,164][01481] Num frames 2800... | |
| [2025-01-08 18:15:43,253][01481] Avg episode rewards: #0: 3.659, true rewards: #0: 3.534 | |
| [2025-01-08 18:15:43,254][01481] Avg episode reward: 3.659, avg true_objective: 3.534 | |
| [2025-01-08 18:15:43,354][01481] Num frames 2900... | |
| [2025-01-08 18:15:43,475][01481] Num frames 3000... | |
| [2025-01-08 18:15:43,599][01481] Num frames 3100... | |
| [2025-01-08 18:15:43,721][01481] Num frames 3200... | |
| [2025-01-08 18:15:43,864][01481] Avg episode rewards: #0: 3.861, true rewards: #0: 3.639 | |
| [2025-01-08 18:15:43,868][01481] Avg episode reward: 3.861, avg true_objective: 3.639 | |
| [2025-01-08 18:15:43,899][01481] Num frames 3300... | |
| [2025-01-08 18:15:44,016][01481] Num frames 3400... | |
| [2025-01-08 18:15:44,134][01481] Num frames 3500... | |
| [2025-01-08 18:15:44,260][01481] Num frames 3600... | |
| [2025-01-08 18:15:44,392][01481] Avg episode rewards: #0: 3.859, true rewards: #0: 3.659 | |
| [2025-01-08 18:15:44,394][01481] Avg episode reward: 3.859, avg true_objective: 3.659 | |
| [2025-01-08 18:16:05,322][01481] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |