diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1217 @@ +[2024-11-08 16:35:18,085][00398] Saving configuration to /content/train_dir/default_experiment/config.json... +[2024-11-08 16:35:18,089][00398] Rollout worker 0 uses device cpu +[2024-11-08 16:35:18,091][00398] Rollout worker 1 uses device cpu +[2024-11-08 16:35:18,092][00398] Rollout worker 2 uses device cpu +[2024-11-08 16:35:18,093][00398] Rollout worker 3 uses device cpu +[2024-11-08 16:35:18,097][00398] Rollout worker 4 uses device cpu +[2024-11-08 16:35:18,098][00398] Rollout worker 5 uses device cpu +[2024-11-08 16:35:18,099][00398] Rollout worker 6 uses device cpu +[2024-11-08 16:35:18,100][00398] Rollout worker 7 uses device cpu +[2024-11-08 16:35:18,284][00398] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-11-08 16:35:18,288][00398] InferenceWorker_p0-w0: min num requests: 2 +[2024-11-08 16:35:18,332][00398] Starting all processes... +[2024-11-08 16:35:18,337][00398] Starting process learner_proc0 +[2024-11-08 16:35:18,410][00398] Starting all processes... +[2024-11-08 16:35:18,418][00398] Starting process inference_proc0-0 +[2024-11-08 16:35:18,418][00398] Starting process rollout_proc0 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc1 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc2 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc3 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc4 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc5 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc6 +[2024-11-08 16:35:18,419][00398] Starting process rollout_proc7 +[2024-11-08 16:35:35,461][07782] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-11-08 16:35:35,464][07782] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2024-11-08 16:35:35,538][07782] Num visible devices: 1 +[2024-11-08 16:35:35,584][07782] Starting seed is not provided +[2024-11-08 16:35:35,585][07782] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-11-08 16:35:35,586][07782] Initializing actor-critic model on device cuda:0 +[2024-11-08 16:35:35,587][07782] RunningMeanStd input shape: (3, 72, 128) +[2024-11-08 16:35:35,590][07782] RunningMeanStd input shape: (1,) +[2024-11-08 16:35:35,669][07782] ConvEncoder: input_channels=3 +[2024-11-08 16:35:36,111][07795] Worker 0 uses CPU cores [0] +[2024-11-08 16:35:36,140][07800] Worker 4 uses CPU cores [0] +[2024-11-08 16:35:36,396][07803] Worker 6 uses CPU cores [0] +[2024-11-08 16:35:36,482][07801] Worker 5 uses CPU cores [1] +[2024-11-08 16:35:36,494][07799] Worker 3 uses CPU cores [1] +[2024-11-08 16:35:36,505][07796] Worker 2 uses CPU cores [0] +[2024-11-08 16:35:36,529][07797] Worker 1 uses CPU cores [1] +[2024-11-08 16:35:36,530][07802] Worker 7 uses CPU cores [1] +[2024-11-08 16:35:36,540][07782] Conv encoder output size: 512 +[2024-11-08 16:35:36,540][07782] Policy head output size: 512 +[2024-11-08 16:35:36,594][07798] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-11-08 16:35:36,594][07798] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2024-11-08 16:35:36,611][07798] Num visible devices: 1 +[2024-11-08 16:35:36,622][07782] Created Actor Critic model with architecture: +[2024-11-08 16:35:36,622][07782] 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) + ) +) +[2024-11-08 16:35:36,915][07782] Using optimizer +[2024-11-08 16:35:38,275][00398] Heartbeat connected on Batcher_0 +[2024-11-08 16:35:38,284][00398] Heartbeat connected on InferenceWorker_p0-w0 +[2024-11-08 16:35:38,297][00398] Heartbeat connected on RolloutWorker_w0 +[2024-11-08 16:35:38,302][00398] Heartbeat connected on RolloutWorker_w1 +[2024-11-08 16:35:38,307][00398] Heartbeat connected on RolloutWorker_w2 +[2024-11-08 16:35:38,312][00398] Heartbeat connected on RolloutWorker_w3 +[2024-11-08 16:35:38,319][00398] Heartbeat connected on RolloutWorker_w4 +[2024-11-08 16:35:38,323][00398] Heartbeat connected on RolloutWorker_w5 +[2024-11-08 16:35:38,327][00398] Heartbeat connected on RolloutWorker_w6 +[2024-11-08 16:35:38,331][00398] Heartbeat connected on RolloutWorker_w7 +[2024-11-08 16:35:40,248][07782] No checkpoints found +[2024-11-08 16:35:40,248][07782] Did not load from checkpoint, starting from scratch! +[2024-11-08 16:35:40,248][07782] Initialized policy 0 weights for model version 0 +[2024-11-08 16:35:40,251][07782] LearnerWorker_p0 finished initialization! +[2024-11-08 16:35:40,258][07782] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2024-11-08 16:35:40,252][00398] Heartbeat connected on LearnerWorker_p0 +[2024-11-08 16:35:40,359][07798] RunningMeanStd input shape: (3, 72, 128) +[2024-11-08 16:35:40,360][07798] RunningMeanStd input shape: (1,) +[2024-11-08 16:35:40,372][07798] ConvEncoder: input_channels=3 +[2024-11-08 16:35:40,473][07798] Conv encoder output size: 512 +[2024-11-08 16:35:40,474][07798] Policy head output size: 512 +[2024-11-08 16:35:40,527][00398] Inference worker 0-0 is ready! +[2024-11-08 16:35:40,528][00398] All inference workers are ready! Signal rollout workers to start! +[2024-11-08 16:35:40,718][07795] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,720][07803] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,723][07796] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,724][07800] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,744][07801] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,742][07802] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,740][07797] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:40,745][07799] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:35:42,210][07797] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,208][07802] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,208][07799] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,506][07795] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,509][07803] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,517][07800] Decorrelating experience for 0 frames... +[2024-11-08 16:35:42,514][07796] Decorrelating experience for 0 frames... +[2024-11-08 16:35:43,071][07797] Decorrelating experience for 32 frames... +[2024-11-08 16:35:43,345][00398] 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) +[2024-11-08 16:35:43,834][07795] Decorrelating experience for 32 frames... +[2024-11-08 16:35:43,839][07796] Decorrelating experience for 32 frames... +[2024-11-08 16:35:43,854][07800] Decorrelating experience for 32 frames... +[2024-11-08 16:35:44,533][07802] Decorrelating experience for 32 frames... +[2024-11-08 16:35:45,248][07797] Decorrelating experience for 64 frames... +[2024-11-08 16:35:45,268][07801] Decorrelating experience for 0 frames... +[2024-11-08 16:35:45,620][07800] Decorrelating experience for 64 frames... +[2024-11-08 16:35:45,816][07795] Decorrelating experience for 64 frames... +[2024-11-08 16:35:46,640][07802] Decorrelating experience for 64 frames... +[2024-11-08 16:35:46,669][07796] Decorrelating experience for 64 frames... +[2024-11-08 16:35:46,971][07801] Decorrelating experience for 32 frames... +[2024-11-08 16:35:47,743][07800] Decorrelating experience for 96 frames... +[2024-11-08 16:35:47,878][07795] Decorrelating experience for 96 frames... +[2024-11-08 16:35:48,345][00398] 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) +[2024-11-08 16:35:48,392][07799] Decorrelating experience for 32 frames... +[2024-11-08 16:35:48,489][07803] Decorrelating experience for 32 frames... +[2024-11-08 16:35:48,488][07802] Decorrelating experience for 96 frames... +[2024-11-08 16:35:48,597][07796] Decorrelating experience for 96 frames... +[2024-11-08 16:35:49,203][07801] Decorrelating experience for 64 frames... +[2024-11-08 16:35:49,402][07797] Decorrelating experience for 96 frames... +[2024-11-08 16:35:49,793][07801] Decorrelating experience for 96 frames... +[2024-11-08 16:35:49,987][07803] Decorrelating experience for 64 frames... +[2024-11-08 16:35:50,797][07803] Decorrelating experience for 96 frames... +[2024-11-08 16:35:52,764][07799] Decorrelating experience for 64 frames... +[2024-11-08 16:35:53,345][00398] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 191.2. Samples: 1912. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2024-11-08 16:35:53,348][00398] Avg episode reward: [(0, '2.264')] +[2024-11-08 16:35:53,496][07782] Signal inference workers to stop experience collection... +[2024-11-08 16:35:53,511][07798] InferenceWorker_p0-w0: stopping experience collection +[2024-11-08 16:35:54,313][07799] Decorrelating experience for 96 frames... +[2024-11-08 16:35:56,939][07782] Signal inference workers to resume experience collection... +[2024-11-08 16:35:56,940][07798] InferenceWorker_p0-w0: resuming experience collection +[2024-11-08 16:35:58,346][00398] Fps is (10 sec: 819.2, 60 sec: 546.1, 300 sec: 546.1). Total num frames: 8192. Throughput: 0: 168.3. Samples: 2524. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2024-11-08 16:35:58,354][00398] Avg episode reward: [(0, '3.146')] +[2024-11-08 16:36:03,345][00398] Fps is (10 sec: 2457.5, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 283.5. Samples: 5670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:36:03,348][00398] Avg episode reward: [(0, '3.550')] +[2024-11-08 16:36:07,787][07798] Updated weights for policy 0, policy_version 10 (0.0154) +[2024-11-08 16:36:08,345][00398] Fps is (10 sec: 3277.0, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 40960. Throughput: 0: 423.7. Samples: 10592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:36:08,349][00398] Avg episode reward: [(0, '4.067')] +[2024-11-08 16:36:13,345][00398] Fps is (10 sec: 4096.1, 60 sec: 2184.5, 300 sec: 2184.5). Total num frames: 65536. Throughput: 0: 462.3. Samples: 13870. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:36:13,347][00398] Avg episode reward: [(0, '4.570')] +[2024-11-08 16:36:17,775][07798] Updated weights for policy 0, policy_version 20 (0.0026) +[2024-11-08 16:36:18,346][00398] Fps is (10 sec: 4095.6, 60 sec: 2340.5, 300 sec: 2340.5). Total num frames: 81920. Throughput: 0: 571.5. Samples: 20004. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-11-08 16:36:18,349][00398] Avg episode reward: [(0, '4.566')] +[2024-11-08 16:36:23,345][00398] Fps is (10 sec: 3276.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 603.1. Samples: 24126. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:36:23,347][00398] Avg episode reward: [(0, '4.638')] +[2024-11-08 16:36:28,345][00398] Fps is (10 sec: 3686.7, 60 sec: 2639.6, 300 sec: 2639.6). Total num frames: 118784. Throughput: 0: 606.3. Samples: 27282. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:36:28,348][00398] Avg episode reward: [(0, '4.618')] +[2024-11-08 16:36:28,357][07782] Saving new best policy, reward=4.618! +[2024-11-08 16:36:29,075][07798] Updated weights for policy 0, policy_version 30 (0.0023) +[2024-11-08 16:36:33,345][00398] Fps is (10 sec: 3686.4, 60 sec: 2703.4, 300 sec: 2703.4). Total num frames: 135168. Throughput: 0: 742.3. Samples: 33404. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:36:33,348][00398] Avg episode reward: [(0, '4.406')] +[2024-11-08 16:36:38,358][00398] Fps is (10 sec: 2863.4, 60 sec: 2680.4, 300 sec: 2680.4). Total num frames: 147456. Throughput: 0: 794.6. Samples: 37680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:36:38,363][00398] Avg episode reward: [(0, '4.428')] +[2024-11-08 16:36:41,673][07798] Updated weights for policy 0, policy_version 40 (0.0031) +[2024-11-08 16:36:43,345][00398] Fps is (10 sec: 3276.8, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 836.8. Samples: 40178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:36:43,351][00398] Avg episode reward: [(0, '4.423')] +[2024-11-08 16:36:48,345][00398] Fps is (10 sec: 4511.5, 60 sec: 3208.5, 300 sec: 2961.7). Total num frames: 192512. Throughput: 0: 911.9. Samples: 46704. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:36:48,348][00398] Avg episode reward: [(0, '4.425')] +[2024-11-08 16:36:52,422][07798] Updated weights for policy 0, policy_version 50 (0.0031) +[2024-11-08 16:36:53,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 914.4. Samples: 51738. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:36:53,351][00398] Avg episode reward: [(0, '4.422')] +[2024-11-08 16:36:58,345][00398] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 2894.5). Total num frames: 217088. Throughput: 0: 880.0. Samples: 53468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:36:58,351][00398] Avg episode reward: [(0, '4.402')] +[2024-11-08 16:37:03,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 2969.6). Total num frames: 237568. Throughput: 0: 856.8. Samples: 58560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:37:03,348][00398] Avg episode reward: [(0, '4.323')] +[2024-11-08 16:37:04,989][07798] Updated weights for policy 0, policy_version 60 (0.0033) +[2024-11-08 16:37:08,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3035.9). Total num frames: 258048. Throughput: 0: 898.8. Samples: 64572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:37:08,347][00398] Avg episode reward: [(0, '4.298')] +[2024-11-08 16:37:08,367][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000063_258048.pth... +[2024-11-08 16:37:13,345][00398] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3003.7). Total num frames: 270336. Throughput: 0: 873.0. Samples: 66568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:37:13,348][00398] Avg episode reward: [(0, '4.450')] +[2024-11-08 16:37:17,954][07798] Updated weights for policy 0, policy_version 70 (0.0035) +[2024-11-08 16:37:18,348][00398] Fps is (10 sec: 2866.4, 60 sec: 3413.2, 300 sec: 3018.0). Total num frames: 286720. Throughput: 0: 829.5. Samples: 70734. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:37:18,350][00398] Avg episode reward: [(0, '4.490')] +[2024-11-08 16:37:23,345][00398] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3072.0). Total num frames: 307200. Throughput: 0: 876.9. Samples: 77130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:37:23,351][00398] Avg episode reward: [(0, '4.312')] +[2024-11-08 16:37:28,345][00398] Fps is (10 sec: 3687.4, 60 sec: 3413.3, 300 sec: 3081.7). Total num frames: 323584. Throughput: 0: 892.7. Samples: 80350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:37:28,351][00398] Avg episode reward: [(0, '4.439')] +[2024-11-08 16:37:28,724][07798] Updated weights for policy 0, policy_version 80 (0.0028) +[2024-11-08 16:37:33,345][00398] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3090.6). Total num frames: 339968. Throughput: 0: 836.0. Samples: 84322. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-11-08 16:37:33,348][00398] Avg episode reward: [(0, '4.396')] +[2024-11-08 16:37:38,352][00398] Fps is (10 sec: 3683.8, 60 sec: 3550.2, 300 sec: 3134.1). Total num frames: 360448. Throughput: 0: 865.1. Samples: 90672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:37:38,355][00398] Avg episode reward: [(0, '4.256')] +[2024-11-08 16:37:39,480][07798] Updated weights for policy 0, policy_version 90 (0.0018) +[2024-11-08 16:37:43,345][00398] Fps is (10 sec: 4505.8, 60 sec: 3618.1, 300 sec: 3208.5). Total num frames: 385024. Throughput: 0: 900.8. Samples: 94002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:37:43,349][00398] Avg episode reward: [(0, '4.622')] +[2024-11-08 16:37:43,362][07782] Saving new best policy, reward=4.622! +[2024-11-08 16:37:48,345][00398] Fps is (10 sec: 3689.1, 60 sec: 3413.3, 300 sec: 3178.5). Total num frames: 397312. Throughput: 0: 895.3. Samples: 98848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:37:48,348][00398] Avg episode reward: [(0, '4.712')] +[2024-11-08 16:37:48,352][07782] Saving new best policy, reward=4.712! +[2024-11-08 16:37:51,452][07798] Updated weights for policy 0, policy_version 100 (0.0024) +[2024-11-08 16:37:53,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3213.8). Total num frames: 417792. Throughput: 0: 881.0. Samples: 104216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:37:53,349][00398] Avg episode reward: [(0, '4.581')] +[2024-11-08 16:37:58,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3246.5). Total num frames: 438272. Throughput: 0: 912.7. Samples: 107638. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:37:58,350][00398] Avg episode reward: [(0, '4.663')] +[2024-11-08 16:38:01,652][07798] Updated weights for policy 0, policy_version 110 (0.0015) +[2024-11-08 16:38:03,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 942.9. Samples: 113164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:38:03,354][00398] Avg episode reward: [(0, '4.708')] +[2024-11-08 16:38:08,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3248.6). Total num frames: 471040. Throughput: 0: 898.4. Samples: 117556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:38:08,351][00398] Avg episode reward: [(0, '4.562')] +[2024-11-08 16:38:12,890][07798] Updated weights for policy 0, policy_version 120 (0.0046) +[2024-11-08 16:38:13,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 491520. Throughput: 0: 900.3. Samples: 120864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:38:13,347][00398] Avg episode reward: [(0, '4.578')] +[2024-11-08 16:38:18,346][00398] Fps is (10 sec: 4095.6, 60 sec: 3754.8, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 959.4. Samples: 127496. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:38:18,354][00398] Avg episode reward: [(0, '4.628')] +[2024-11-08 16:38:23,346][00398] Fps is (10 sec: 3276.5, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 524288. Throughput: 0: 908.8. Samples: 131564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:38:23,357][00398] Avg episode reward: [(0, '4.818')] +[2024-11-08 16:38:23,359][07782] Saving new best policy, reward=4.818! +[2024-11-08 16:38:24,745][07798] Updated weights for policy 0, policy_version 130 (0.0016) +[2024-11-08 16:38:28,345][00398] Fps is (10 sec: 3277.1, 60 sec: 3686.4, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 900.0. Samples: 134504. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:38:28,352][00398] Avg episode reward: [(0, '4.746')] +[2024-11-08 16:38:33,345][00398] Fps is (10 sec: 4096.4, 60 sec: 3754.7, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 938.0. Samples: 141058. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:38:33,347][00398] Avg episode reward: [(0, '4.577')] +[2024-11-08 16:38:34,723][07798] Updated weights for policy 0, policy_version 140 (0.0019) +[2024-11-08 16:38:38,345][00398] Fps is (10 sec: 3686.3, 60 sec: 3686.8, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 928.2. Samples: 145986. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:38:38,348][00398] Avg episode reward: [(0, '4.446')] +[2024-11-08 16:38:43,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3322.3). Total num frames: 598016. Throughput: 0: 898.4. Samples: 148068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:38:43,349][00398] Avg episode reward: [(0, '4.283')] +[2024-11-08 16:38:45,850][07798] Updated weights for policy 0, policy_version 150 (0.0021) +[2024-11-08 16:38:48,345][00398] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3365.4). Total num frames: 622592. Throughput: 0: 925.7. Samples: 154822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:38:48,349][00398] Avg episode reward: [(0, '4.423')] +[2024-11-08 16:38:53,346][00398] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3363.0). Total num frames: 638976. Throughput: 0: 957.2. Samples: 160630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:38:53,353][00398] Avg episode reward: [(0, '4.586')] +[2024-11-08 16:38:57,984][07798] Updated weights for policy 0, policy_version 160 (0.0017) +[2024-11-08 16:38:58,345][00398] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3360.8). Total num frames: 655360. Throughput: 0: 928.4. Samples: 162642. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:38:58,348][00398] Avg episode reward: [(0, '4.618')] +[2024-11-08 16:39:03,345][00398] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 3379.2). Total num frames: 675840. Throughput: 0: 907.2. Samples: 168320. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:39:03,348][00398] Avg episode reward: [(0, '4.486')] +[2024-11-08 16:39:07,239][07798] Updated weights for policy 0, policy_version 170 (0.0026) +[2024-11-08 16:39:08,345][00398] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 966.6. Samples: 175062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:39:08,349][00398] Avg episode reward: [(0, '4.310')] +[2024-11-08 16:39:08,359][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000171_700416.pth... +[2024-11-08 16:39:13,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 948.5. Samples: 177186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:39:13,350][00398] Avg episode reward: [(0, '4.366')] +[2024-11-08 16:39:18,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3410.2). Total num frames: 733184. Throughput: 0: 908.8. Samples: 181952. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:39:18,347][00398] Avg episode reward: [(0, '4.379')] +[2024-11-08 16:39:19,249][07798] Updated weights for policy 0, policy_version 180 (0.0017) +[2024-11-08 16:39:23,345][00398] Fps is (10 sec: 4095.9, 60 sec: 3823.0, 300 sec: 3425.7). Total num frames: 753664. Throughput: 0: 949.1. Samples: 188696. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:39:23,348][00398] Avg episode reward: [(0, '4.595')] +[2024-11-08 16:39:28,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3422.4). Total num frames: 770048. Throughput: 0: 971.7. Samples: 191796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:39:28,347][00398] Avg episode reward: [(0, '4.542')] +[2024-11-08 16:39:30,562][07798] Updated weights for policy 0, policy_version 190 (0.0021) +[2024-11-08 16:39:33,345][00398] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3419.3). Total num frames: 786432. Throughput: 0: 912.2. Samples: 195872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:39:33,348][00398] Avg episode reward: [(0, '4.753')] +[2024-11-08 16:39:38,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3433.7). Total num frames: 806912. Throughput: 0: 926.4. Samples: 202316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:39:38,353][00398] Avg episode reward: [(0, '4.848')] +[2024-11-08 16:39:38,366][07782] Saving new best policy, reward=4.848! +[2024-11-08 16:39:40,343][07798] Updated weights for policy 0, policy_version 200 (0.0022) +[2024-11-08 16:39:43,350][00398] Fps is (10 sec: 4094.1, 60 sec: 3822.6, 300 sec: 3447.4). Total num frames: 827392. Throughput: 0: 955.3. Samples: 205636. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:39:43,361][00398] Avg episode reward: [(0, '4.536')] +[2024-11-08 16:39:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 938.2. Samples: 210538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:39:48,347][00398] Avg episode reward: [(0, '4.424')] +[2024-11-08 16:39:51,883][07798] Updated weights for policy 0, policy_version 210 (0.0018) +[2024-11-08 16:39:53,346][00398] Fps is (10 sec: 3687.9, 60 sec: 3754.7, 300 sec: 3457.0). Total num frames: 864256. Throughput: 0: 915.6. Samples: 216266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:39:53,351][00398] Avg episode reward: [(0, '4.438')] +[2024-11-08 16:39:58,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3485.6). Total num frames: 888832. Throughput: 0: 943.9. Samples: 219662. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-11-08 16:39:58,350][00398] Avg episode reward: [(0, '4.582')] +[2024-11-08 16:40:01,963][07798] Updated weights for policy 0, policy_version 220 (0.0020) +[2024-11-08 16:40:03,349][00398] Fps is (10 sec: 3685.3, 60 sec: 3754.5, 300 sec: 3465.8). Total num frames: 901120. Throughput: 0: 965.1. Samples: 225386. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-11-08 16:40:03,353][00398] Avg episode reward: [(0, '4.668')] +[2024-11-08 16:40:08,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3477.7). Total num frames: 921600. Throughput: 0: 921.9. Samples: 230182. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-11-08 16:40:08,348][00398] Avg episode reward: [(0, '4.601')] +[2024-11-08 16:40:12,730][07798] Updated weights for policy 0, policy_version 230 (0.0018) +[2024-11-08 16:40:13,346][00398] Fps is (10 sec: 4097.3, 60 sec: 3822.9, 300 sec: 3489.2). Total num frames: 942080. Throughput: 0: 930.7. Samples: 233680. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:40:13,349][00398] Avg episode reward: [(0, '4.649')] +[2024-11-08 16:40:18,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3500.2). Total num frames: 962560. Throughput: 0: 988.1. Samples: 240336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:40:18,349][00398] Avg episode reward: [(0, '4.895')] +[2024-11-08 16:40:18,362][07782] Saving new best policy, reward=4.895! +[2024-11-08 16:40:23,345][00398] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3496.2). Total num frames: 978944. Throughput: 0: 938.0. Samples: 244526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:40:23,348][00398] Avg episode reward: [(0, '4.776')] +[2024-11-08 16:40:24,150][07798] Updated weights for policy 0, policy_version 240 (0.0027) +[2024-11-08 16:40:28,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3506.8). Total num frames: 999424. Throughput: 0: 938.2. Samples: 247850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:40:28,349][00398] Avg episode reward: [(0, '4.747')] +[2024-11-08 16:40:33,016][07798] Updated weights for policy 0, policy_version 250 (0.0024) +[2024-11-08 16:40:33,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3531.0). Total num frames: 1024000. Throughput: 0: 982.2. Samples: 254736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:40:33,348][00398] Avg episode reward: [(0, '4.769')] +[2024-11-08 16:40:38,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3512.8). Total num frames: 1036288. Throughput: 0: 968.0. Samples: 259826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:40:38,352][00398] Avg episode reward: [(0, '4.742')] +[2024-11-08 16:40:43,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3823.2, 300 sec: 3582.3). Total num frames: 1056768. Throughput: 0: 947.0. Samples: 262278. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:40:43,347][00398] Avg episode reward: [(0, '4.922')] +[2024-11-08 16:40:43,351][07782] Saving new best policy, reward=4.922! +[2024-11-08 16:40:44,424][07798] Updated weights for policy 0, policy_version 260 (0.0027) +[2024-11-08 16:40:48,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 977.1. Samples: 269352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:40:48,355][00398] Avg episode reward: [(0, '5.223')] +[2024-11-08 16:40:48,366][07782] Saving new best policy, reward=5.223! +[2024-11-08 16:40:53,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3693.4). Total num frames: 1097728. Throughput: 0: 1002.0. Samples: 275270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:40:53,347][00398] Avg episode reward: [(0, '5.115')] +[2024-11-08 16:40:55,425][07798] Updated weights for policy 0, policy_version 270 (0.0023) +[2024-11-08 16:40:58,347][00398] Fps is (10 sec: 3276.1, 60 sec: 3754.5, 300 sec: 3693.3). Total num frames: 1114112. Throughput: 0: 970.3. Samples: 277346. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-11-08 16:40:58,350][00398] Avg episode reward: [(0, '5.038')] +[2024-11-08 16:41:03,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.7, 300 sec: 3721.1). Total num frames: 1138688. Throughput: 0: 966.6. Samples: 283834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:41:03,347][00398] Avg episode reward: [(0, '5.062')] +[2024-11-08 16:41:04,566][07798] Updated weights for policy 0, policy_version 280 (0.0028) +[2024-11-08 16:41:08,345][00398] Fps is (10 sec: 4506.5, 60 sec: 3959.5, 300 sec: 3707.2). Total num frames: 1159168. Throughput: 0: 1025.5. Samples: 290674. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:41:08,350][00398] Avg episode reward: [(0, '5.010')] +[2024-11-08 16:41:08,368][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000283_1159168.pth... +[2024-11-08 16:41:08,525][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000063_258048.pth +[2024-11-08 16:41:13,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3707.2). Total num frames: 1175552. Throughput: 0: 998.1. Samples: 292764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:41:13,352][00398] Avg episode reward: [(0, '5.294')] +[2024-11-08 16:41:13,357][07782] Saving new best policy, reward=5.294! +[2024-11-08 16:41:16,002][07798] Updated weights for policy 0, policy_version 290 (0.0029) +[2024-11-08 16:41:18,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 1196032. Throughput: 0: 969.6. Samples: 298370. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) +[2024-11-08 16:41:18,353][00398] Avg episode reward: [(0, '5.436')] +[2024-11-08 16:41:18,363][07782] Saving new best policy, reward=5.436! +[2024-11-08 16:41:23,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3735.0). Total num frames: 1220608. Throughput: 0: 1008.3. Samples: 305200. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:41:23,347][00398] Avg episode reward: [(0, '5.510')] +[2024-11-08 16:41:23,354][07782] Saving new best policy, reward=5.510! +[2024-11-08 16:41:25,337][07798] Updated weights for policy 0, policy_version 300 (0.0015) +[2024-11-08 16:41:28,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 1232896. Throughput: 0: 1011.7. Samples: 307804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:41:28,349][00398] Avg episode reward: [(0, '5.508')] +[2024-11-08 16:41:33,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3749.0). Total num frames: 1253376. Throughput: 0: 952.5. Samples: 312214. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-11-08 16:41:33,348][00398] Avg episode reward: [(0, '5.877')] +[2024-11-08 16:41:33,351][07782] Saving new best policy, reward=5.877! +[2024-11-08 16:41:36,650][07798] Updated weights for policy 0, policy_version 310 (0.0022) +[2024-11-08 16:41:38,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3748.9). Total num frames: 1273856. Throughput: 0: 976.3. Samples: 319204. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:41:38,347][00398] Avg episode reward: [(0, '6.002')] +[2024-11-08 16:41:38,441][07782] Saving new best policy, reward=6.002! +[2024-11-08 16:41:43,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3735.0). Total num frames: 1294336. Throughput: 0: 1005.8. Samples: 322604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:41:43,347][00398] Avg episode reward: [(0, '6.109')] +[2024-11-08 16:41:43,354][07782] Saving new best policy, reward=6.109! +[2024-11-08 16:41:48,035][07798] Updated weights for policy 0, policy_version 320 (0.0039) +[2024-11-08 16:41:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1310720. Throughput: 0: 962.3. Samples: 327138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:41:48,352][00398] Avg episode reward: [(0, '6.354')] +[2024-11-08 16:41:48,362][07782] Saving new best policy, reward=6.354! +[2024-11-08 16:41:53,345][00398] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3776.6). Total num frames: 1331200. Throughput: 0: 949.8. Samples: 333414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:41:53,350][00398] Avg episode reward: [(0, '6.108')] +[2024-11-08 16:41:56,848][07798] Updated weights for policy 0, policy_version 330 (0.0024) +[2024-11-08 16:41:58,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.9, 300 sec: 3790.5). Total num frames: 1355776. Throughput: 0: 982.0. Samples: 336954. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:41:58,349][00398] Avg episode reward: [(0, '6.091')] +[2024-11-08 16:42:03,350][00398] Fps is (10 sec: 3684.6, 60 sec: 3822.6, 300 sec: 3762.7). Total num frames: 1368064. Throughput: 0: 978.2. Samples: 342394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:42:03,352][00398] Avg episode reward: [(0, '6.226')] +[2024-11-08 16:42:08,345][00398] Fps is (10 sec: 2457.6, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 1380352. Throughput: 0: 890.4. Samples: 345266. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:08,351][00398] Avg episode reward: [(0, '6.207')] +[2024-11-08 16:42:10,606][07798] Updated weights for policy 0, policy_version 340 (0.0018) +[2024-11-08 16:42:13,345][00398] Fps is (10 sec: 3278.6, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 1400832. Throughput: 0: 907.6. Samples: 348646. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:13,347][00398] Avg episode reward: [(0, '6.507')] +[2024-11-08 16:42:13,386][07782] Saving new best policy, reward=6.507! +[2024-11-08 16:42:18,346][00398] Fps is (10 sec: 4095.6, 60 sec: 3754.6, 300 sec: 3776.6). Total num frames: 1421312. Throughput: 0: 947.0. Samples: 354830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:18,350][00398] Avg episode reward: [(0, '7.064')] +[2024-11-08 16:42:18,360][07782] Saving new best policy, reward=7.064! +[2024-11-08 16:42:22,527][07798] Updated weights for policy 0, policy_version 350 (0.0022) +[2024-11-08 16:42:23,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 1433600. Throughput: 0: 881.5. Samples: 358872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:23,351][00398] Avg episode reward: [(0, '7.601')] +[2024-11-08 16:42:23,419][07782] Saving new best policy, reward=7.601! +[2024-11-08 16:42:28,345][00398] Fps is (10 sec: 3686.8, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 1458176. Throughput: 0: 883.6. Samples: 362366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:42:28,351][00398] Avg episode reward: [(0, '7.268')] +[2024-11-08 16:42:31,554][07798] Updated weights for policy 0, policy_version 360 (0.0015) +[2024-11-08 16:42:33,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3790.6). Total num frames: 1478656. Throughput: 0: 937.4. Samples: 369322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:33,351][00398] Avg episode reward: [(0, '6.425')] +[2024-11-08 16:42:38,354][00398] Fps is (10 sec: 3683.0, 60 sec: 3685.8, 300 sec: 3762.6). Total num frames: 1495040. Throughput: 0: 901.6. Samples: 373996. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:38,357][00398] Avg episode reward: [(0, '6.733')] +[2024-11-08 16:42:42,990][07798] Updated weights for policy 0, policy_version 370 (0.0033) +[2024-11-08 16:42:43,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 1515520. Throughput: 0: 882.5. Samples: 376668. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:42:43,348][00398] Avg episode reward: [(0, '7.082')] +[2024-11-08 16:42:48,345][00398] Fps is (10 sec: 4509.8, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 1540096. Throughput: 0: 917.5. Samples: 383678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:42:48,348][00398] Avg episode reward: [(0, '8.131')] +[2024-11-08 16:42:48,358][07782] Saving new best policy, reward=8.131! +[2024-11-08 16:42:53,345][00398] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3776.6). Total num frames: 1552384. Throughput: 0: 972.2. Samples: 389016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:42:53,351][00398] Avg episode reward: [(0, '7.947')] +[2024-11-08 16:42:53,425][07798] Updated weights for policy 0, policy_version 380 (0.0030) +[2024-11-08 16:42:58,345][00398] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3790.5). Total num frames: 1572864. Throughput: 0: 944.8. Samples: 391162. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:42:58,350][00398] Avg episode reward: [(0, '7.739')] +[2024-11-08 16:43:03,345][00398] Fps is (10 sec: 4096.2, 60 sec: 3755.0, 300 sec: 3804.4). Total num frames: 1593344. Throughput: 0: 954.0. Samples: 397758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:43:03,347][00398] Avg episode reward: [(0, '7.499')] +[2024-11-08 16:43:03,361][07798] Updated weights for policy 0, policy_version 390 (0.0014) +[2024-11-08 16:43:08,345][00398] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 1617920. Throughput: 0: 1013.0. Samples: 404458. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:43:08,351][00398] Avg episode reward: [(0, '7.843')] +[2024-11-08 16:43:08,369][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000395_1617920.pth... +[2024-11-08 16:43:08,529][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000171_700416.pth +[2024-11-08 16:43:13,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 1630208. Throughput: 0: 979.6. Samples: 406446. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:43:13,347][00398] Avg episode reward: [(0, '8.761')] +[2024-11-08 16:43:13,351][07782] Saving new best policy, reward=8.761! +[2024-11-08 16:43:14,720][07798] Updated weights for policy 0, policy_version 400 (0.0020) +[2024-11-08 16:43:18,349][00398] Fps is (10 sec: 3685.1, 60 sec: 3891.0, 300 sec: 3832.2). Total num frames: 1654784. Throughput: 0: 952.9. Samples: 412206. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:43:18,351][00398] Avg episode reward: [(0, '9.176')] +[2024-11-08 16:43:18,359][07782] Saving new best policy, reward=9.176! +[2024-11-08 16:43:23,345][00398] Fps is (10 sec: 4505.5, 60 sec: 4027.7, 300 sec: 3832.2). Total num frames: 1675264. Throughput: 0: 1008.1. Samples: 419352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:43:23,347][00398] Avg episode reward: [(0, '9.124')] +[2024-11-08 16:43:23,542][07798] Updated weights for policy 0, policy_version 410 (0.0020) +[2024-11-08 16:43:28,345][00398] Fps is (10 sec: 3687.8, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1691648. Throughput: 0: 1006.4. Samples: 421958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:43:28,350][00398] Avg episode reward: [(0, '8.979')] +[2024-11-08 16:43:33,347][00398] Fps is (10 sec: 3276.2, 60 sec: 3822.8, 300 sec: 3818.3). Total num frames: 1708032. Throughput: 0: 946.2. Samples: 426260. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:43:33,350][00398] Avg episode reward: [(0, '9.677')] +[2024-11-08 16:43:33,352][07782] Saving new best policy, reward=9.677! +[2024-11-08 16:43:35,372][07798] Updated weights for policy 0, policy_version 420 (0.0016) +[2024-11-08 16:43:38,350][00398] Fps is (10 sec: 4094.2, 60 sec: 3959.8, 300 sec: 3846.0). Total num frames: 1732608. Throughput: 0: 986.2. Samples: 433398. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:43:38,352][00398] Avg episode reward: [(0, '10.265')] +[2024-11-08 16:43:38,365][07782] Saving new best policy, reward=10.265! +[2024-11-08 16:43:43,345][00398] Fps is (10 sec: 4506.5, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 1753088. Throughput: 0: 1016.1. Samples: 436888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:43:43,348][00398] Avg episode reward: [(0, '9.775')] +[2024-11-08 16:43:46,130][07798] Updated weights for policy 0, policy_version 430 (0.0021) +[2024-11-08 16:43:48,345][00398] Fps is (10 sec: 3278.2, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 1765376. Throughput: 0: 965.4. Samples: 441202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:43:48,348][00398] Avg episode reward: [(0, '9.429')] +[2024-11-08 16:43:53,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3846.1). Total num frames: 1789952. Throughput: 0: 962.5. Samples: 447772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:43:53,348][00398] Avg episode reward: [(0, '10.243')] +[2024-11-08 16:43:55,367][07798] Updated weights for policy 0, policy_version 440 (0.0038) +[2024-11-08 16:43:58,345][00398] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3860.0). Total num frames: 1814528. Throughput: 0: 997.4. Samples: 451330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:43:58,349][00398] Avg episode reward: [(0, '10.725')] +[2024-11-08 16:43:58,366][07782] Saving new best policy, reward=10.725! +[2024-11-08 16:44:03,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 1826816. Throughput: 0: 986.4. Samples: 456590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:44:03,352][00398] Avg episode reward: [(0, '11.317')] +[2024-11-08 16:44:03,355][07782] Saving new best policy, reward=11.317! +[2024-11-08 16:44:06,772][07798] Updated weights for policy 0, policy_version 450 (0.0027) +[2024-11-08 16:44:08,348][00398] Fps is (10 sec: 3276.0, 60 sec: 3822.8, 300 sec: 3846.0). Total num frames: 1847296. Throughput: 0: 953.1. Samples: 462244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:44:08,353][00398] Avg episode reward: [(0, '11.963')] +[2024-11-08 16:44:08,362][07782] Saving new best policy, reward=11.963! +[2024-11-08 16:44:13,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3860.0). Total num frames: 1871872. Throughput: 0: 971.0. Samples: 465654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:44:13,348][00398] Avg episode reward: [(0, '12.533')] +[2024-11-08 16:44:13,355][07782] Saving new best policy, reward=12.533! +[2024-11-08 16:44:16,848][07798] Updated weights for policy 0, policy_version 460 (0.0029) +[2024-11-08 16:44:18,345][00398] Fps is (10 sec: 3687.3, 60 sec: 3823.2, 300 sec: 3832.2). Total num frames: 1884160. Throughput: 0: 1005.9. Samples: 471524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:44:18,359][00398] Avg episode reward: [(0, '13.212')] +[2024-11-08 16:44:18,373][07782] Saving new best policy, reward=13.212! +[2024-11-08 16:44:23,345][00398] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 1900544. Throughput: 0: 942.4. Samples: 475804. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:44:23,351][00398] Avg episode reward: [(0, '13.446')] +[2024-11-08 16:44:23,355][07782] Saving new best policy, reward=13.446! +[2024-11-08 16:44:27,894][07798] Updated weights for policy 0, policy_version 470 (0.0020) +[2024-11-08 16:44:28,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 1925120. Throughput: 0: 937.6. Samples: 479078. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:44:28,348][00398] Avg episode reward: [(0, '13.287')] +[2024-11-08 16:44:33,349][00398] Fps is (10 sec: 4504.0, 60 sec: 3959.4, 300 sec: 3859.9). Total num frames: 1945600. Throughput: 0: 993.5. Samples: 485914. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:44:33,351][00398] Avg episode reward: [(0, '12.779')] +[2024-11-08 16:44:38,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3823.2, 300 sec: 3846.1). Total num frames: 1961984. Throughput: 0: 945.3. Samples: 490310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:44:38,351][00398] Avg episode reward: [(0, '13.667')] +[2024-11-08 16:44:38,367][07782] Saving new best policy, reward=13.667! +[2024-11-08 16:44:39,517][07798] Updated weights for policy 0, policy_version 480 (0.0026) +[2024-11-08 16:44:43,345][00398] Fps is (10 sec: 3687.6, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 1982464. Throughput: 0: 931.8. Samples: 493260. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:44:43,348][00398] Avg episode reward: [(0, '14.642')] +[2024-11-08 16:44:43,354][07782] Saving new best policy, reward=14.642! +[2024-11-08 16:44:48,278][07798] Updated weights for policy 0, policy_version 490 (0.0016) +[2024-11-08 16:44:48,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3873.9). Total num frames: 2007040. Throughput: 0: 972.8. Samples: 500364. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:44:48,350][00398] Avg episode reward: [(0, '14.741')] +[2024-11-08 16:44:48,360][07782] Saving new best policy, reward=14.741! +[2024-11-08 16:44:53,345][00398] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 2019328. Throughput: 0: 963.4. Samples: 505594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:44:53,348][00398] Avg episode reward: [(0, '16.117')] +[2024-11-08 16:44:53,350][07782] Saving new best policy, reward=16.117! +[2024-11-08 16:44:58,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 2039808. Throughput: 0: 937.2. Samples: 507826. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:44:58,349][00398] Avg episode reward: [(0, '15.230')] +[2024-11-08 16:44:59,509][07798] Updated weights for policy 0, policy_version 500 (0.0017) +[2024-11-08 16:45:03,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2064384. Throughput: 0: 959.6. Samples: 514704. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:45:03,348][00398] Avg episode reward: [(0, '14.788')] +[2024-11-08 16:45:08,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.4, 300 sec: 3860.0). Total num frames: 2080768. Throughput: 0: 1007.7. Samples: 521152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:45:08,349][00398] Avg episode reward: [(0, '16.691')] +[2024-11-08 16:45:08,422][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth... +[2024-11-08 16:45:08,615][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000283_1159168.pth +[2024-11-08 16:45:08,640][07782] Saving new best policy, reward=16.691! +[2024-11-08 16:45:10,273][07798] Updated weights for policy 0, policy_version 510 (0.0030) +[2024-11-08 16:45:13,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2097152. Throughput: 0: 978.9. Samples: 523130. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:45:13,352][00398] Avg episode reward: [(0, '16.397')] +[2024-11-08 16:45:18,347][00398] Fps is (10 sec: 4095.1, 60 sec: 3959.3, 300 sec: 3873.8). Total num frames: 2121728. Throughput: 0: 961.4. Samples: 529174. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:45:18,353][00398] Avg episode reward: [(0, '16.611')] +[2024-11-08 16:45:19,693][07798] Updated weights for policy 0, policy_version 520 (0.0014) +[2024-11-08 16:45:23,345][00398] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3887.7). Total num frames: 2146304. Throughput: 0: 1025.4. Samples: 536452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:45:23,352][00398] Avg episode reward: [(0, '19.002')] +[2024-11-08 16:45:23,354][07782] Saving new best policy, reward=19.002! +[2024-11-08 16:45:28,345][00398] Fps is (10 sec: 3687.3, 60 sec: 3891.2, 300 sec: 3846.1). Total num frames: 2158592. Throughput: 0: 1010.7. Samples: 538742. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-11-08 16:45:28,351][00398] Avg episode reward: [(0, '18.417')] +[2024-11-08 16:45:31,231][07798] Updated weights for policy 0, policy_version 530 (0.0024) +[2024-11-08 16:45:33,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3891.4, 300 sec: 3873.8). Total num frames: 2179072. Throughput: 0: 965.2. Samples: 543798. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:45:33,347][00398] Avg episode reward: [(0, '17.655')] +[2024-11-08 16:45:38,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2203648. Throughput: 0: 1005.8. Samples: 550856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:45:38,347][00398] Avg episode reward: [(0, '17.443')] +[2024-11-08 16:45:39,943][07798] Updated weights for policy 0, policy_version 540 (0.0037) +[2024-11-08 16:45:43,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3860.0). Total num frames: 2220032. Throughput: 0: 1026.4. Samples: 554016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:45:43,351][00398] Avg episode reward: [(0, '16.267')] +[2024-11-08 16:45:48,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3860.0). Total num frames: 2236416. Throughput: 0: 965.4. Samples: 558148. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-11-08 16:45:48,350][00398] Avg episode reward: [(0, '15.885')] +[2024-11-08 16:45:51,485][07798] Updated weights for policy 0, policy_version 550 (0.0018) +[2024-11-08 16:45:53,345][00398] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 3887.8). Total num frames: 2260992. Throughput: 0: 979.6. Samples: 565232. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:45:53,353][00398] Avg episode reward: [(0, '15.990')] +[2024-11-08 16:45:58,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3873.8). Total num frames: 2281472. Throughput: 0: 1014.9. Samples: 568800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:45:58,350][00398] Avg episode reward: [(0, '16.006')] +[2024-11-08 16:46:02,490][07798] Updated weights for policy 0, policy_version 560 (0.0018) +[2024-11-08 16:46:03,345][00398] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3846.1). Total num frames: 2293760. Throughput: 0: 987.2. Samples: 573594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:46:03,347][00398] Avg episode reward: [(0, '16.343')] +[2024-11-08 16:46:08,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3873.8). Total num frames: 2318336. Throughput: 0: 962.4. Samples: 579762. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) +[2024-11-08 16:46:08,352][00398] Avg episode reward: [(0, '16.109')] +[2024-11-08 16:46:11,498][07798] Updated weights for policy 0, policy_version 570 (0.0016) +[2024-11-08 16:46:13,345][00398] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3887.7). Total num frames: 2342912. Throughput: 0: 992.8. Samples: 583420. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2024-11-08 16:46:13,356][00398] Avg episode reward: [(0, '16.205')] +[2024-11-08 16:46:18,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 3860.0). Total num frames: 2359296. Throughput: 0: 1010.8. Samples: 589284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:18,348][00398] Avg episode reward: [(0, '16.904')] +[2024-11-08 16:46:22,656][07798] Updated weights for policy 0, policy_version 580 (0.0029) +[2024-11-08 16:46:23,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 2375680. Throughput: 0: 967.5. Samples: 594394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:23,352][00398] Avg episode reward: [(0, '17.085')] +[2024-11-08 16:46:28,345][00398] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2400256. Throughput: 0: 972.2. Samples: 597766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:28,347][00398] Avg episode reward: [(0, '18.434')] +[2024-11-08 16:46:32,179][07798] Updated weights for policy 0, policy_version 590 (0.0022) +[2024-11-08 16:46:33,345][00398] Fps is (10 sec: 4095.9, 60 sec: 3959.4, 300 sec: 3873.8). Total num frames: 2416640. Throughput: 0: 1026.3. Samples: 604332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:33,350][00398] Avg episode reward: [(0, '19.151')] +[2024-11-08 16:46:33,352][07782] Saving new best policy, reward=19.151! +[2024-11-08 16:46:38,352][00398] Fps is (10 sec: 3274.6, 60 sec: 3822.5, 300 sec: 3859.9). Total num frames: 2433024. Throughput: 0: 963.1. Samples: 608578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:38,358][00398] Avg episode reward: [(0, '19.118')] +[2024-11-08 16:46:43,129][07798] Updated weights for policy 0, policy_version 600 (0.0031) +[2024-11-08 16:46:43,345][00398] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3887.7). Total num frames: 2457600. Throughput: 0: 958.7. Samples: 611940. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:43,349][00398] Avg episode reward: [(0, '18.880')] +[2024-11-08 16:46:48,345][00398] Fps is (10 sec: 4508.6, 60 sec: 4027.7, 300 sec: 3887.7). Total num frames: 2478080. Throughput: 0: 1011.4. Samples: 619106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:46:48,350][00398] Avg episode reward: [(0, '17.790')] +[2024-11-08 16:46:53,347][00398] Fps is (10 sec: 3685.5, 60 sec: 3891.1, 300 sec: 3859.9). Total num frames: 2494464. Throughput: 0: 984.0. Samples: 624046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:46:53,350][00398] Avg episode reward: [(0, '17.345')] +[2024-11-08 16:46:54,118][07798] Updated weights for policy 0, policy_version 610 (0.0023) +[2024-11-08 16:46:58,347][00398] Fps is (10 sec: 3685.6, 60 sec: 3891.1, 300 sec: 3887.8). Total num frames: 2514944. Throughput: 0: 957.0. Samples: 626488. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:46:58,350][00398] Avg episode reward: [(0, '17.442')] +[2024-11-08 16:47:03,148][07798] Updated weights for policy 0, policy_version 620 (0.0024) +[2024-11-08 16:47:03,345][00398] Fps is (10 sec: 4506.7, 60 sec: 4096.0, 300 sec: 3929.4). Total num frames: 2539520. Throughput: 0: 984.9. Samples: 633606. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:47:03,351][00398] Avg episode reward: [(0, '17.475')] +[2024-11-08 16:47:08,345][00398] Fps is (10 sec: 4096.9, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 2555904. Throughput: 0: 998.4. Samples: 639320. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2024-11-08 16:47:08,348][00398] Avg episode reward: [(0, '18.167')] +[2024-11-08 16:47:08,358][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth... +[2024-11-08 16:47:08,519][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000395_1617920.pth +[2024-11-08 16:47:13,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 2572288. Throughput: 0: 967.4. Samples: 641300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:47:13,347][00398] Avg episode reward: [(0, '18.070')] +[2024-11-08 16:47:14,981][07798] Updated weights for policy 0, policy_version 630 (0.0033) +[2024-11-08 16:47:18,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2592768. Throughput: 0: 963.4. Samples: 647686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:47:18,352][00398] Avg episode reward: [(0, '18.227')] +[2024-11-08 16:47:23,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 2617344. Throughput: 0: 1024.5. Samples: 654672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:47:23,353][00398] Avg episode reward: [(0, '18.433')] +[2024-11-08 16:47:24,325][07798] Updated weights for policy 0, policy_version 640 (0.0019) +[2024-11-08 16:47:28,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 2629632. Throughput: 0: 997.1. Samples: 656810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:47:28,350][00398] Avg episode reward: [(0, '18.709')] +[2024-11-08 16:47:33,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3929.5). Total num frames: 2654208. Throughput: 0: 958.5. Samples: 662240. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:47:33,348][00398] Avg episode reward: [(0, '19.791')] +[2024-11-08 16:47:33,353][07782] Saving new best policy, reward=19.791! +[2024-11-08 16:47:35,038][07798] Updated weights for policy 0, policy_version 650 (0.0030) +[2024-11-08 16:47:38,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4028.2, 300 sec: 3929.4). Total num frames: 2674688. Throughput: 0: 1004.9. Samples: 669266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:47:38,350][00398] Avg episode reward: [(0, '20.690')] +[2024-11-08 16:47:38,376][07782] Saving new best policy, reward=20.690! +[2024-11-08 16:47:43,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 2691072. Throughput: 0: 1013.0. Samples: 672070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:47:43,349][00398] Avg episode reward: [(0, '20.479')] +[2024-11-08 16:47:46,408][07798] Updated weights for policy 0, policy_version 660 (0.0017) +[2024-11-08 16:47:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2711552. Throughput: 0: 956.3. Samples: 676638. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:47:48,351][00398] Avg episode reward: [(0, '20.607')] +[2024-11-08 16:47:53,345][00398] Fps is (10 sec: 4505.6, 60 sec: 4027.9, 300 sec: 3943.3). Total num frames: 2736128. Throughput: 0: 987.6. Samples: 683762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:47:53,352][00398] Avg episode reward: [(0, '20.481')] +[2024-11-08 16:47:55,095][07798] Updated weights for policy 0, policy_version 670 (0.0021) +[2024-11-08 16:47:58,346][00398] Fps is (10 sec: 4095.7, 60 sec: 3959.6, 300 sec: 3929.4). Total num frames: 2752512. Throughput: 0: 1022.0. Samples: 687290. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:47:58,353][00398] Avg episode reward: [(0, '18.352')] +[2024-11-08 16:48:03,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 2768896. Throughput: 0: 981.8. Samples: 691866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:48:03,352][00398] Avg episode reward: [(0, '19.381')] +[2024-11-08 16:48:06,430][07798] Updated weights for policy 0, policy_version 680 (0.0029) +[2024-11-08 16:48:08,345][00398] Fps is (10 sec: 4096.3, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2793472. Throughput: 0: 967.9. Samples: 698226. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:48:08,347][00398] Avg episode reward: [(0, '20.949')] +[2024-11-08 16:48:08,361][07782] Saving new best policy, reward=20.949! +[2024-11-08 16:48:13,345][00398] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3943.3). Total num frames: 2818048. Throughput: 0: 1000.4. Samples: 701826. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:48:13,347][00398] Avg episode reward: [(0, '18.901')] +[2024-11-08 16:48:15,950][07798] Updated weights for policy 0, policy_version 690 (0.0015) +[2024-11-08 16:48:18,347][00398] Fps is (10 sec: 3685.9, 60 sec: 3959.4, 300 sec: 3915.5). Total num frames: 2830336. Throughput: 0: 1003.3. Samples: 707390. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:48:18,350][00398] Avg episode reward: [(0, '19.482')] +[2024-11-08 16:48:23,345][00398] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2850816. Throughput: 0: 972.7. Samples: 713038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:48:23,348][00398] Avg episode reward: [(0, '19.123')] +[2024-11-08 16:48:26,236][07798] Updated weights for policy 0, policy_version 700 (0.0023) +[2024-11-08 16:48:28,345][00398] Fps is (10 sec: 4506.2, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 2875392. Throughput: 0: 989.1. Samples: 716578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:48:28,347][00398] Avg episode reward: [(0, '18.187')] +[2024-11-08 16:48:33,346][00398] Fps is (10 sec: 4095.8, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 2891776. Throughput: 0: 1020.7. Samples: 722568. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:48:33,351][00398] Avg episode reward: [(0, '18.208')] +[2024-11-08 16:48:38,313][07798] Updated weights for policy 0, policy_version 710 (0.0024) +[2024-11-08 16:48:38,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 2908160. Throughput: 0: 951.5. Samples: 726578. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:48:38,349][00398] Avg episode reward: [(0, '18.570')] +[2024-11-08 16:48:43,345][00398] Fps is (10 sec: 3686.6, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2928640. Throughput: 0: 947.1. Samples: 729910. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:48:43,347][00398] Avg episode reward: [(0, '20.672')] +[2024-11-08 16:48:47,134][07798] Updated weights for policy 0, policy_version 720 (0.0017) +[2024-11-08 16:48:48,346][00398] Fps is (10 sec: 4095.8, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 2949120. Throughput: 0: 1005.7. Samples: 737124. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2024-11-08 16:48:48,357][00398] Avg episode reward: [(0, '22.206')] +[2024-11-08 16:48:48,372][07782] Saving new best policy, reward=22.206! +[2024-11-08 16:48:53,350][00398] Fps is (10 sec: 3684.8, 60 sec: 3822.7, 300 sec: 3901.6). Total num frames: 2965504. Throughput: 0: 965.6. Samples: 741680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:48:53,355][00398] Avg episode reward: [(0, '22.947')] +[2024-11-08 16:48:53,364][07782] Saving new best policy, reward=22.947! +[2024-11-08 16:48:58,345][00398] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 2985984. Throughput: 0: 948.8. Samples: 744520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:48:58,352][00398] Avg episode reward: [(0, '22.912')] +[2024-11-08 16:48:58,531][07798] Updated weights for policy 0, policy_version 730 (0.0018) +[2024-11-08 16:49:03,347][00398] Fps is (10 sec: 4506.6, 60 sec: 4027.6, 300 sec: 3943.3). Total num frames: 3010560. Throughput: 0: 986.3. Samples: 751776. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:49:03,350][00398] Avg episode reward: [(0, '21.757')] +[2024-11-08 16:49:08,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 3026944. Throughput: 0: 980.4. Samples: 757158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:08,349][00398] Avg episode reward: [(0, '21.314')] +[2024-11-08 16:49:08,359][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000739_3026944.pth... +[2024-11-08 16:49:08,529][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000509_2084864.pth +[2024-11-08 16:49:09,367][07798] Updated weights for policy 0, policy_version 740 (0.0017) +[2024-11-08 16:49:13,345][00398] Fps is (10 sec: 3277.5, 60 sec: 3754.7, 300 sec: 3929.4). Total num frames: 3043328. Throughput: 0: 948.1. Samples: 759242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:13,350][00398] Avg episode reward: [(0, '20.990')] +[2024-11-08 16:49:18,353][00398] Fps is (10 sec: 4092.7, 60 sec: 3959.0, 300 sec: 3957.0). Total num frames: 3067904. Throughput: 0: 970.0. Samples: 766224. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:18,357][00398] Avg episode reward: [(0, '20.870')] +[2024-11-08 16:49:18,498][07798] Updated weights for policy 0, policy_version 750 (0.0020) +[2024-11-08 16:49:23,345][00398] Fps is (10 sec: 4505.5, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3088384. Throughput: 0: 1023.2. Samples: 772622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:49:23,348][00398] Avg episode reward: [(0, '20.991')] +[2024-11-08 16:49:28,345][00398] Fps is (10 sec: 3689.4, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 3104768. Throughput: 0: 997.1. Samples: 774778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:49:28,348][00398] Avg episode reward: [(0, '20.565')] +[2024-11-08 16:49:29,806][07798] Updated weights for policy 0, policy_version 760 (0.0019) +[2024-11-08 16:49:33,345][00398] Fps is (10 sec: 4096.1, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3129344. Throughput: 0: 970.9. Samples: 780816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:49:33,347][00398] Avg episode reward: [(0, '20.411')] +[2024-11-08 16:49:38,346][00398] Fps is (10 sec: 4505.4, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 3149824. Throughput: 0: 1028.0. Samples: 787936. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:49:38,348][00398] Avg episode reward: [(0, '20.282')] +[2024-11-08 16:49:38,800][07798] Updated weights for policy 0, policy_version 770 (0.0019) +[2024-11-08 16:49:43,351][00398] Fps is (10 sec: 3684.2, 60 sec: 3959.1, 300 sec: 3929.3). Total num frames: 3166208. Throughput: 0: 1015.3. Samples: 790216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:49:43,356][00398] Avg episode reward: [(0, '19.343')] +[2024-11-08 16:49:48,345][00398] Fps is (10 sec: 3686.5, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3186688. Throughput: 0: 967.3. Samples: 795304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:48,353][00398] Avg episode reward: [(0, '19.287')] +[2024-11-08 16:49:49,929][07798] Updated weights for policy 0, policy_version 780 (0.0023) +[2024-11-08 16:49:53,345][00398] Fps is (10 sec: 4098.5, 60 sec: 4028.0, 300 sec: 3957.2). Total num frames: 3207168. Throughput: 0: 1007.6. Samples: 802502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:53,350][00398] Avg episode reward: [(0, '19.292')] +[2024-11-08 16:49:58,345][00398] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 3227648. Throughput: 0: 1032.8. Samples: 805716. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:49:58,351][00398] Avg episode reward: [(0, '19.196')] +[2024-11-08 16:50:01,065][07798] Updated weights for policy 0, policy_version 790 (0.0016) +[2024-11-08 16:50:03,345][00398] Fps is (10 sec: 3686.3, 60 sec: 3891.3, 300 sec: 3943.3). Total num frames: 3244032. Throughput: 0: 970.1. Samples: 809872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:50:03,352][00398] Avg episode reward: [(0, '18.868')] +[2024-11-08 16:50:08,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 3264512. Throughput: 0: 976.7. Samples: 816574. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:50:08,353][00398] Avg episode reward: [(0, '22.329')] +[2024-11-08 16:50:10,382][07798] Updated weights for policy 0, policy_version 800 (0.0017) +[2024-11-08 16:50:13,347][00398] Fps is (10 sec: 4095.1, 60 sec: 4027.6, 300 sec: 3943.3). Total num frames: 3284992. Throughput: 0: 1005.0. Samples: 820006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:50:13,355][00398] Avg episode reward: [(0, '23.299')] +[2024-11-08 16:50:13,359][07782] Saving new best policy, reward=23.299! +[2024-11-08 16:50:18,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3823.5, 300 sec: 3901.6). Total num frames: 3297280. Throughput: 0: 972.4. Samples: 824576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:50:18,354][00398] Avg episode reward: [(0, '23.962')] +[2024-11-08 16:50:18,368][07782] Saving new best policy, reward=23.962! +[2024-11-08 16:50:22,388][07798] Updated weights for policy 0, policy_version 810 (0.0029) +[2024-11-08 16:50:23,345][00398] Fps is (10 sec: 3687.3, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 3321856. Throughput: 0: 940.0. Samples: 830234. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:50:23,348][00398] Avg episode reward: [(0, '23.098')] +[2024-11-08 16:50:28,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 3342336. Throughput: 0: 965.5. Samples: 833660. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:50:28,347][00398] Avg episode reward: [(0, '23.874')] +[2024-11-08 16:50:32,903][07798] Updated weights for policy 0, policy_version 820 (0.0017) +[2024-11-08 16:50:33,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3358720. Throughput: 0: 976.8. Samples: 839258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:50:33,350][00398] Avg episode reward: [(0, '24.269')] +[2024-11-08 16:50:33,354][07782] Saving new best policy, reward=24.269! +[2024-11-08 16:50:38,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3915.5). Total num frames: 3375104. Throughput: 0: 914.7. Samples: 843664. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:50:38,348][00398] Avg episode reward: [(0, '22.623')] +[2024-11-08 16:50:43,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3823.3, 300 sec: 3929.4). Total num frames: 3395584. Throughput: 0: 915.7. Samples: 846924. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:50:43,350][00398] Avg episode reward: [(0, '21.883')] +[2024-11-08 16:50:43,925][07798] Updated weights for policy 0, policy_version 830 (0.0020) +[2024-11-08 16:50:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 3411968. Throughput: 0: 965.8. Samples: 853334. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2024-11-08 16:50:48,351][00398] Avg episode reward: [(0, '22.066')] +[2024-11-08 16:50:53,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3887.7). Total num frames: 3428352. Throughput: 0: 906.2. Samples: 857352. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:50:53,347][00398] Avg episode reward: [(0, '23.168')] +[2024-11-08 16:50:55,935][07798] Updated weights for policy 0, policy_version 840 (0.0020) +[2024-11-08 16:50:58,348][00398] Fps is (10 sec: 3685.6, 60 sec: 3686.2, 300 sec: 3915.5). Total num frames: 3448832. Throughput: 0: 896.4. Samples: 860344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:50:58,350][00398] Avg episode reward: [(0, '23.532')] +[2024-11-08 16:51:03,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 3473408. Throughput: 0: 945.6. Samples: 867130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:51:03,348][00398] Avg episode reward: [(0, '23.531')] +[2024-11-08 16:51:06,106][07798] Updated weights for policy 0, policy_version 850 (0.0013) +[2024-11-08 16:51:08,345][00398] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3873.8). Total num frames: 3485696. Throughput: 0: 926.4. Samples: 871924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:51:08,358][00398] Avg episode reward: [(0, '23.458')] +[2024-11-08 16:51:08,371][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000851_3485696.pth... +[2024-11-08 16:51:08,519][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000624_2555904.pth +[2024-11-08 16:51:13,346][00398] Fps is (10 sec: 2867.0, 60 sec: 3618.2, 300 sec: 3873.8). Total num frames: 3502080. Throughput: 0: 894.0. Samples: 873892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:51:13,350][00398] Avg episode reward: [(0, '23.363')] +[2024-11-08 16:51:16,969][07798] Updated weights for policy 0, policy_version 860 (0.0013) +[2024-11-08 16:51:18,345][00398] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3901.6). Total num frames: 3526656. Throughput: 0: 922.6. Samples: 880774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:51:18,348][00398] Avg episode reward: [(0, '23.615')] +[2024-11-08 16:51:23,347][00398] Fps is (10 sec: 4095.3, 60 sec: 3686.3, 300 sec: 3873.8). Total num frames: 3543040. Throughput: 0: 952.4. Samples: 886522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:51:23,350][00398] Avg episode reward: [(0, '22.872')] +[2024-11-08 16:51:28,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3873.8). Total num frames: 3559424. Throughput: 0: 924.4. Samples: 888522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:51:28,348][00398] Avg episode reward: [(0, '22.995')] +[2024-11-08 16:51:28,789][07798] Updated weights for policy 0, policy_version 870 (0.0031) +[2024-11-08 16:51:33,345][00398] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3887.8). Total num frames: 3579904. Throughput: 0: 914.4. Samples: 894482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:51:33,353][00398] Avg episode reward: [(0, '21.762')] +[2024-11-08 16:51:38,345][00398] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3873.8). Total num frames: 3600384. Throughput: 0: 973.3. Samples: 901152. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:51:38,350][00398] Avg episode reward: [(0, '21.459')] +[2024-11-08 16:51:38,416][07798] Updated weights for policy 0, policy_version 880 (0.0021) +[2024-11-08 16:51:43,348][00398] Fps is (10 sec: 3685.4, 60 sec: 3686.2, 300 sec: 3859.9). Total num frames: 3616768. Throughput: 0: 951.6. Samples: 903166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:51:43,358][00398] Avg episode reward: [(0, '21.626')] +[2024-11-08 16:51:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3873.9). Total num frames: 3637248. Throughput: 0: 913.3. Samples: 908228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:51:48,348][00398] Avg episode reward: [(0, '21.083')] +[2024-11-08 16:51:49,793][07798] Updated weights for policy 0, policy_version 890 (0.0038) +[2024-11-08 16:51:53,345][00398] Fps is (10 sec: 4097.2, 60 sec: 3822.9, 300 sec: 3873.9). Total num frames: 3657728. Throughput: 0: 958.6. Samples: 915062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:51:53,352][00398] Avg episode reward: [(0, '20.439')] +[2024-11-08 16:51:58,347][00398] Fps is (10 sec: 3685.9, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 3674112. Throughput: 0: 978.6. Samples: 917928. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2024-11-08 16:51:58,351][00398] Avg episode reward: [(0, '21.819')] +[2024-11-08 16:52:01,742][07798] Updated weights for policy 0, policy_version 900 (0.0015) +[2024-11-08 16:52:03,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3846.1). Total num frames: 3690496. Throughput: 0: 916.4. Samples: 922010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:52:03,348][00398] Avg episode reward: [(0, '22.028')] +[2024-11-08 16:52:08,345][00398] Fps is (10 sec: 4096.6, 60 sec: 3822.9, 300 sec: 3873.8). Total num frames: 3715072. Throughput: 0: 935.2. Samples: 928604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:52:08,348][00398] Avg episode reward: [(0, '22.873')] +[2024-11-08 16:52:10,816][07798] Updated weights for policy 0, policy_version 910 (0.0013) +[2024-11-08 16:52:13,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3873.8). Total num frames: 3735552. Throughput: 0: 967.4. Samples: 932056. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2024-11-08 16:52:13,349][00398] Avg episode reward: [(0, '23.257')] +[2024-11-08 16:52:18,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 3747840. Throughput: 0: 935.2. Samples: 936566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:52:18,349][00398] Avg episode reward: [(0, '24.075')] +[2024-11-08 16:52:22,703][07798] Updated weights for policy 0, policy_version 920 (0.0018) +[2024-11-08 16:52:23,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3860.0). Total num frames: 3768320. Throughput: 0: 920.5. Samples: 942574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:52:23,352][00398] Avg episode reward: [(0, '25.222')] +[2024-11-08 16:52:23,355][07782] Saving new best policy, reward=25.222! +[2024-11-08 16:52:28,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3860.0). Total num frames: 3792896. Throughput: 0: 948.6. Samples: 945852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:52:28,353][00398] Avg episode reward: [(0, '24.175')] +[2024-11-08 16:52:33,346][00398] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3805184. Throughput: 0: 956.4. Samples: 951266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2024-11-08 16:52:33,350][00398] Avg episode reward: [(0, '24.388')] +[2024-11-08 16:52:33,924][07798] Updated weights for policy 0, policy_version 930 (0.0019) +[2024-11-08 16:52:38,346][00398] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 3825664. Throughput: 0: 912.8. Samples: 956136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:52:38,349][00398] Avg episode reward: [(0, '23.688')] +[2024-11-08 16:52:43,345][00398] Fps is (10 sec: 4096.2, 60 sec: 3823.1, 300 sec: 3846.1). Total num frames: 3846144. Throughput: 0: 920.7. Samples: 959360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:52:43,351][00398] Avg episode reward: [(0, '24.070')] +[2024-11-08 16:52:44,049][07798] Updated weights for policy 0, policy_version 940 (0.0017) +[2024-11-08 16:52:48,345][00398] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3818.3). Total num frames: 3862528. Throughput: 0: 965.7. Samples: 965468. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:52:48,349][00398] Avg episode reward: [(0, '24.675')] +[2024-11-08 16:52:53,345][00398] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3804.4). Total num frames: 3874816. Throughput: 0: 907.8. Samples: 969454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:52:53,348][00398] Avg episode reward: [(0, '23.609')] +[2024-11-08 16:52:56,015][07798] Updated weights for policy 0, policy_version 950 (0.0023) +[2024-11-08 16:52:58,347][00398] Fps is (10 sec: 3685.9, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3899392. Throughput: 0: 904.9. Samples: 972778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:52:58,350][00398] Avg episode reward: [(0, '24.374')] +[2024-11-08 16:53:03,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3919872. Throughput: 0: 957.0. Samples: 979630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2024-11-08 16:53:03,350][00398] Avg episode reward: [(0, '23.497')] +[2024-11-08 16:53:06,898][07798] Updated weights for policy 0, policy_version 960 (0.0028) +[2024-11-08 16:53:08,345][00398] Fps is (10 sec: 3277.3, 60 sec: 3618.1, 300 sec: 3776.7). Total num frames: 3932160. Throughput: 0: 921.8. Samples: 984054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2024-11-08 16:53:08,352][00398] Avg episode reward: [(0, '23.751')] +[2024-11-08 16:53:08,365][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000960_3932160.pth... +[2024-11-08 16:53:08,577][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000739_3026944.pth +[2024-11-08 16:53:13,345][00398] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3804.4). Total num frames: 3952640. Throughput: 0: 900.4. Samples: 986372. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:53:13,352][00398] Avg episode reward: [(0, '23.549')] +[2024-11-08 16:53:17,241][07798] Updated weights for policy 0, policy_version 970 (0.0027) +[2024-11-08 16:53:18,345][00398] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3977216. Throughput: 0: 930.1. Samples: 993120. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2024-11-08 16:53:18,351][00398] Avg episode reward: [(0, '21.946')] +[2024-11-08 16:53:23,345][00398] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3993600. Throughput: 0: 946.6. Samples: 998732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2024-11-08 16:53:23,350][00398] Avg episode reward: [(0, '21.303')] +[2024-11-08 16:53:27,246][07782] Stopping Batcher_0... +[2024-11-08 16:53:27,248][07782] Loop batcher_evt_loop terminating... +[2024-11-08 16:53:27,249][00398] Component Batcher_0 stopped! +[2024-11-08 16:53:27,250][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-11-08 16:53:27,311][07798] Weights refcount: 2 0 +[2024-11-08 16:53:27,316][00398] Component InferenceWorker_p0-w0 stopped! +[2024-11-08 16:53:27,316][07798] Stopping InferenceWorker_p0-w0... +[2024-11-08 16:53:27,323][07798] Loop inference_proc0-0_evt_loop terminating... +[2024-11-08 16:53:27,385][07782] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000851_3485696.pth +[2024-11-08 16:53:27,403][07782] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-11-08 16:53:27,600][00398] Component LearnerWorker_p0 stopped! +[2024-11-08 16:53:27,599][07782] Stopping LearnerWorker_p0... +[2024-11-08 16:53:27,606][07782] Loop learner_proc0_evt_loop terminating... +[2024-11-08 16:53:27,629][00398] Component RolloutWorker_w2 stopped! +[2024-11-08 16:53:27,629][07796] Stopping RolloutWorker_w2... +[2024-11-08 16:53:27,635][07796] Loop rollout_proc2_evt_loop terminating... +[2024-11-08 16:53:27,652][00398] Component RolloutWorker_w7 stopped! +[2024-11-08 16:53:27,654][07802] Stopping RolloutWorker_w7... +[2024-11-08 16:53:27,655][07802] Loop rollout_proc7_evt_loop terminating... +[2024-11-08 16:53:27,671][00398] Component RolloutWorker_w3 stopped! +[2024-11-08 16:53:27,673][07799] Stopping RolloutWorker_w3... +[2024-11-08 16:53:27,676][00398] Component RolloutWorker_w5 stopped! +[2024-11-08 16:53:27,678][07801] Stopping RolloutWorker_w5... +[2024-11-08 16:53:27,682][07801] Loop rollout_proc5_evt_loop terminating... +[2024-11-08 16:53:27,681][07799] Loop rollout_proc3_evt_loop terminating... +[2024-11-08 16:53:27,689][00398] Component RolloutWorker_w1 stopped! +[2024-11-08 16:53:27,692][07797] Stopping RolloutWorker_w1... +[2024-11-08 16:53:27,694][07797] Loop rollout_proc1_evt_loop terminating... +[2024-11-08 16:53:27,705][07803] Stopping RolloutWorker_w6... +[2024-11-08 16:53:27,709][07803] Loop rollout_proc6_evt_loop terminating... +[2024-11-08 16:53:27,705][00398] Component RolloutWorker_w6 stopped! +[2024-11-08 16:53:27,736][00398] Component RolloutWorker_w0 stopped! +[2024-11-08 16:53:27,740][07795] Stopping RolloutWorker_w0... +[2024-11-08 16:53:27,741][07795] Loop rollout_proc0_evt_loop terminating... +[2024-11-08 16:53:27,778][00398] Component RolloutWorker_w4 stopped! +[2024-11-08 16:53:27,781][00398] Waiting for process learner_proc0 to stop... +[2024-11-08 16:53:27,784][07800] Stopping RolloutWorker_w4... +[2024-11-08 16:53:27,784][07800] Loop rollout_proc4_evt_loop terminating... +[2024-11-08 16:53:29,342][00398] Waiting for process inference_proc0-0 to join... +[2024-11-08 16:53:29,347][00398] Waiting for process rollout_proc0 to join... +[2024-11-08 16:53:31,217][00398] Waiting for process rollout_proc1 to join... +[2024-11-08 16:53:31,336][00398] Waiting for process rollout_proc2 to join... +[2024-11-08 16:53:31,341][00398] Waiting for process rollout_proc3 to join... +[2024-11-08 16:53:31,346][00398] Waiting for process rollout_proc4 to join... +[2024-11-08 16:53:31,350][00398] Waiting for process rollout_proc5 to join... +[2024-11-08 16:53:31,354][00398] Waiting for process rollout_proc6 to join... +[2024-11-08 16:53:31,357][00398] Waiting for process rollout_proc7 to join... +[2024-11-08 16:53:31,360][00398] Batcher 0 profile tree view: +batching: 27.8422, releasing_batches: 0.0321 +[2024-11-08 16:53:31,362][00398] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0013 + wait_policy_total: 425.8324 +update_model: 8.6693 + weight_update: 0.0014 +one_step: 0.0034 + handle_policy_step: 586.2255 + deserialize: 15.2390, stack: 3.1794, obs_to_device_normalize: 123.0523, forward: 294.2278, send_messages: 29.6808 + prepare_outputs: 90.1222 + to_cpu: 54.2384 +[2024-11-08 16:53:31,365][00398] Learner 0 profile tree view: +misc: 0.0056, prepare_batch: 13.5514 +train: 73.6198 + epoch_init: 0.0055, minibatch_init: 0.0108, losses_postprocess: 0.6547, kl_divergence: 0.6504, after_optimizer: 33.4535 + calculate_losses: 26.5108 + losses_init: 0.0106, forward_head: 1.3310, bptt_initial: 17.7335, tail: 1.0907, advantages_returns: 0.2302, losses: 3.8139 + bptt: 1.9259 + bptt_forward_core: 1.8115 + update: 11.6869 + clip: 0.9193 +[2024-11-08 16:53:31,368][00398] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3345, enqueue_policy_requests: 104.7826, env_step: 829.4559, overhead: 13.5980, complete_rollouts: 6.9065 +save_policy_outputs: 21.0243 + split_output_tensors: 8.2657 +[2024-11-08 16:53:31,370][00398] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3754, enqueue_policy_requests: 105.5336, env_step: 827.7353, overhead: 13.9946, complete_rollouts: 7.3621 +save_policy_outputs: 21.3577 + split_output_tensors: 8.2700 +[2024-11-08 16:53:31,374][00398] Loop Runner_EvtLoop terminating... +[2024-11-08 16:53:31,375][00398] Runner profile tree view: +main_loop: 1093.0430 +[2024-11-08 16:53:31,376][00398] Collected {0: 4005888}, FPS: 3664.9 +[2024-11-08 16:53:31,787][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2024-11-08 16:53:31,789][00398] Overriding arg 'num_workers' with value 1 passed from command line +[2024-11-08 16:53:31,791][00398] Adding new argument 'no_render'=True that is not in the saved config file! +[2024-11-08 16:53:31,793][00398] Adding new argument 'save_video'=True that is not in the saved config file! +[2024-11-08 16:53:31,795][00398] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2024-11-08 16:53:31,797][00398] Adding new argument 'video_name'=None that is not in the saved config file! +[2024-11-08 16:53:31,800][00398] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2024-11-08 16:53:31,801][00398] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2024-11-08 16:53:31,804][00398] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2024-11-08 16:53:31,805][00398] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2024-11-08 16:53:31,806][00398] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2024-11-08 16:53:31,807][00398] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2024-11-08 16:53:31,809][00398] Adding new argument 'train_script'=None that is not in the saved config file! +[2024-11-08 16:53:31,810][00398] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2024-11-08 16:53:31,811][00398] Using frameskip 1 and render_action_repeat=4 for evaluation +[2024-11-08 16:53:31,843][00398] Doom resolution: 160x120, resize resolution: (128, 72) +[2024-11-08 16:53:31,847][00398] RunningMeanStd input shape: (3, 72, 128) +[2024-11-08 16:53:31,851][00398] RunningMeanStd input shape: (1,) +[2024-11-08 16:53:31,867][00398] ConvEncoder: input_channels=3 +[2024-11-08 16:53:31,969][00398] Conv encoder output size: 512 +[2024-11-08 16:53:31,970][00398] Policy head output size: 512 +[2024-11-08 16:53:32,144][00398] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-11-08 16:53:32,954][00398] Num frames 100... +[2024-11-08 16:53:33,074][00398] Num frames 200... +[2024-11-08 16:53:33,203][00398] Num frames 300... +[2024-11-08 16:53:33,326][00398] Num frames 400... +[2024-11-08 16:53:33,445][00398] Num frames 500... +[2024-11-08 16:53:33,571][00398] Num frames 600... +[2024-11-08 16:53:33,712][00398] Avg episode rewards: #0: 14.720, true rewards: #0: 6.720 +[2024-11-08 16:53:33,714][00398] Avg episode reward: 14.720, avg true_objective: 6.720 +[2024-11-08 16:53:33,752][00398] Num frames 700... +[2024-11-08 16:53:33,870][00398] Num frames 800... +[2024-11-08 16:53:33,993][00398] Num frames 900... +[2024-11-08 16:53:34,120][00398] Num frames 1000... +[2024-11-08 16:53:34,251][00398] Num frames 1100... +[2024-11-08 16:53:34,407][00398] Avg episode rewards: #0: 13.920, true rewards: #0: 5.920 +[2024-11-08 16:53:34,408][00398] Avg episode reward: 13.920, avg true_objective: 5.920 +[2024-11-08 16:53:34,432][00398] Num frames 1200... +[2024-11-08 16:53:34,555][00398] Num frames 1300... +[2024-11-08 16:53:34,685][00398] Num frames 1400... +[2024-11-08 16:53:34,804][00398] Num frames 1500... +[2024-11-08 16:53:34,933][00398] Num frames 1600... +[2024-11-08 16:53:35,063][00398] Num frames 1700... +[2024-11-08 16:53:35,185][00398] Num frames 1800... +[2024-11-08 16:53:35,316][00398] Num frames 1900... +[2024-11-08 16:53:35,439][00398] Num frames 2000... +[2024-11-08 16:53:35,569][00398] Num frames 2100... +[2024-11-08 16:53:35,696][00398] Avg episode rewards: #0: 17.183, true rewards: #0: 7.183 +[2024-11-08 16:53:35,697][00398] Avg episode reward: 17.183, avg true_objective: 7.183 +[2024-11-08 16:53:35,755][00398] Num frames 2200... +[2024-11-08 16:53:35,878][00398] Num frames 2300... +[2024-11-08 16:53:35,999][00398] Num frames 2400... +[2024-11-08 16:53:36,119][00398] Num frames 2500... +[2024-11-08 16:53:36,263][00398] Num frames 2600... +[2024-11-08 16:53:36,412][00398] Num frames 2700... +[2024-11-08 16:53:36,535][00398] Num frames 2800... +[2024-11-08 16:53:36,664][00398] Num frames 2900... +[2024-11-08 16:53:36,786][00398] Num frames 3000... +[2024-11-08 16:53:36,939][00398] Num frames 3100... +[2024-11-08 16:53:37,120][00398] Num frames 3200... +[2024-11-08 16:53:37,253][00398] Avg episode rewards: #0: 18.608, true rewards: #0: 8.107 +[2024-11-08 16:53:37,255][00398] Avg episode reward: 18.608, avg true_objective: 8.107 +[2024-11-08 16:53:37,372][00398] Num frames 3300... +[2024-11-08 16:53:37,549][00398] Num frames 3400... +[2024-11-08 16:53:37,716][00398] Num frames 3500... +[2024-11-08 16:53:37,883][00398] Num frames 3600... +[2024-11-08 16:53:38,056][00398] Num frames 3700... +[2024-11-08 16:53:38,230][00398] Num frames 3800... +[2024-11-08 16:53:38,408][00398] Num frames 3900... +[2024-11-08 16:53:38,582][00398] Num frames 4000... +[2024-11-08 16:53:38,754][00398] Num frames 4100... +[2024-11-08 16:53:38,931][00398] Num frames 4200... +[2024-11-08 16:53:39,100][00398] Num frames 4300... +[2024-11-08 16:53:39,279][00398] Num frames 4400... +[2024-11-08 16:53:39,449][00398] Num frames 4500... +[2024-11-08 16:53:39,576][00398] Num frames 4600... +[2024-11-08 16:53:39,694][00398] Num frames 4700... +[2024-11-08 16:53:39,817][00398] Num frames 4800... +[2024-11-08 16:53:39,936][00398] Num frames 4900... +[2024-11-08 16:53:40,057][00398] Num frames 5000... +[2024-11-08 16:53:40,225][00398] Avg episode rewards: #0: 24.588, true rewards: #0: 10.188 +[2024-11-08 16:53:40,227][00398] Avg episode reward: 24.588, avg true_objective: 10.188 +[2024-11-08 16:53:40,237][00398] Num frames 5100... +[2024-11-08 16:53:40,359][00398] Num frames 5200... +[2024-11-08 16:53:40,490][00398] Num frames 5300... +[2024-11-08 16:53:40,623][00398] Num frames 5400... +[2024-11-08 16:53:40,745][00398] Num frames 5500... +[2024-11-08 16:53:40,862][00398] Num frames 5600... +[2024-11-08 16:53:40,986][00398] Num frames 5700... +[2024-11-08 16:53:41,103][00398] Num frames 5800... +[2024-11-08 16:53:41,225][00398] Num frames 5900... +[2024-11-08 16:53:41,349][00398] Num frames 6000... +[2024-11-08 16:53:41,432][00398] Avg episode rewards: #0: 24.538, true rewards: #0: 10.038 +[2024-11-08 16:53:41,435][00398] Avg episode reward: 24.538, avg true_objective: 10.038 +[2024-11-08 16:53:41,527][00398] Num frames 6100... +[2024-11-08 16:53:41,655][00398] Num frames 6200... +[2024-11-08 16:53:41,773][00398] Num frames 6300... +[2024-11-08 16:53:41,893][00398] Num frames 6400... +[2024-11-08 16:53:42,012][00398] Num frames 6500... +[2024-11-08 16:53:42,133][00398] Num frames 6600... +[2024-11-08 16:53:42,254][00398] Num frames 6700... +[2024-11-08 16:53:42,322][00398] Avg episode rewards: #0: 23.299, true rewards: #0: 9.584 +[2024-11-08 16:53:42,324][00398] Avg episode reward: 23.299, avg true_objective: 9.584 +[2024-11-08 16:53:42,432][00398] Num frames 6800... +[2024-11-08 16:53:42,563][00398] Num frames 6900... +[2024-11-08 16:53:42,689][00398] Num frames 7000... +[2024-11-08 16:53:42,813][00398] Num frames 7100... +[2024-11-08 16:53:42,932][00398] Num frames 7200... +[2024-11-08 16:53:43,053][00398] Num frames 7300... +[2024-11-08 16:53:43,181][00398] Num frames 7400... +[2024-11-08 16:53:43,302][00398] Num frames 7500... +[2024-11-08 16:53:43,428][00398] Num frames 7600... +[2024-11-08 16:53:43,492][00398] Avg episode rewards: #0: 22.506, true rewards: #0: 9.506 +[2024-11-08 16:53:43,494][00398] Avg episode reward: 22.506, avg true_objective: 9.506 +[2024-11-08 16:53:43,614][00398] Num frames 7700... +[2024-11-08 16:53:43,731][00398] Num frames 7800... +[2024-11-08 16:53:43,851][00398] Num frames 7900... +[2024-11-08 16:53:43,971][00398] Num frames 8000... +[2024-11-08 16:53:44,095][00398] Num frames 8100... +[2024-11-08 16:53:44,218][00398] Num frames 8200... +[2024-11-08 16:53:44,338][00398] Num frames 8300... +[2024-11-08 16:53:44,455][00398] Num frames 8400... +[2024-11-08 16:53:44,592][00398] Num frames 8500... +[2024-11-08 16:53:44,712][00398] Num frames 8600... +[2024-11-08 16:53:44,841][00398] Avg episode rewards: #0: 22.290, true rewards: #0: 9.623 +[2024-11-08 16:53:44,842][00398] Avg episode reward: 22.290, avg true_objective: 9.623 +[2024-11-08 16:53:44,894][00398] Num frames 8700... +[2024-11-08 16:53:45,014][00398] Num frames 8800... +[2024-11-08 16:53:45,139][00398] Num frames 8900... +[2024-11-08 16:53:45,267][00398] Num frames 9000... +[2024-11-08 16:53:45,388][00398] Num frames 9100... +[2024-11-08 16:53:45,510][00398] Num frames 9200... +[2024-11-08 16:53:45,643][00398] Num frames 9300... +[2024-11-08 16:53:45,702][00398] Avg episode rewards: #0: 21.401, true rewards: #0: 9.301 +[2024-11-08 16:53:45,704][00398] Avg episode reward: 21.401, avg true_objective: 9.301 +[2024-11-08 16:54:40,879][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2024-11-08 16:54:41,450][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2024-11-08 16:54:41,451][00398] Overriding arg 'num_workers' with value 1 passed from command line +[2024-11-08 16:54:41,453][00398] Adding new argument 'no_render'=True that is not in the saved config file! +[2024-11-08 16:54:41,459][00398] Adding new argument 'save_video'=True that is not in the saved config file! +[2024-11-08 16:54:41,461][00398] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2024-11-08 16:54:41,462][00398] Adding new argument 'video_name'=None that is not in the saved config file! +[2024-11-08 16:54:41,464][00398] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2024-11-08 16:54:41,466][00398] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2024-11-08 16:54:41,468][00398] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2024-11-08 16:54:41,469][00398] Adding new argument 'hf_repository'='Brumocas/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2024-11-08 16:54:41,471][00398] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2024-11-08 16:54:41,474][00398] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2024-11-08 16:54:41,475][00398] Adding new argument 'train_script'=None that is not in the saved config file! +[2024-11-08 16:54:41,477][00398] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2024-11-08 16:54:41,478][00398] Using frameskip 1 and render_action_repeat=4 for evaluation +[2024-11-08 16:54:41,522][00398] RunningMeanStd input shape: (3, 72, 128) +[2024-11-08 16:54:41,530][00398] RunningMeanStd input shape: (1,) +[2024-11-08 16:54:41,555][00398] ConvEncoder: input_channels=3 +[2024-11-08 16:54:41,632][00398] Conv encoder output size: 512 +[2024-11-08 16:54:41,634][00398] Policy head output size: 512 +[2024-11-08 16:54:41,669][00398] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-11-08 16:54:42,348][00398] Num frames 100... +[2024-11-08 16:54:42,525][00398] Num frames 200... +[2024-11-08 16:54:42,746][00398] Num frames 300... +[2024-11-08 16:54:42,910][00398] Num frames 400... +[2024-11-08 16:54:43,066][00398] Num frames 500... +[2024-11-08 16:54:43,268][00398] Avg episode rewards: #0: 9.760, true rewards: #0: 5.760 +[2024-11-08 16:54:43,270][00398] Avg episode reward: 9.760, avg true_objective: 5.760 +[2024-11-08 16:54:43,320][00398] Num frames 600... +[2024-11-08 16:54:43,481][00398] Num frames 700... +[2024-11-08 16:54:43,689][00398] Num frames 800... +[2024-11-08 16:54:43,891][00398] Num frames 900... +[2024-11-08 16:54:44,089][00398] Num frames 1000... +[2024-11-08 16:54:44,283][00398] Num frames 1100... +[2024-11-08 16:54:44,479][00398] Num frames 1200... +[2024-11-08 16:54:44,666][00398] Num frames 1300... +[2024-11-08 16:54:44,866][00398] Num frames 1400... +[2024-11-08 16:54:45,072][00398] Num frames 1500... +[2024-11-08 16:54:45,284][00398] Num frames 1600... +[2024-11-08 16:54:45,468][00398] Num frames 1700... +[2024-11-08 16:54:45,633][00398] Num frames 1800... +[2024-11-08 16:54:45,808][00398] Num frames 1900... +[2024-11-08 16:54:45,992][00398] Num frames 2000... +[2024-11-08 16:54:46,180][00398] Num frames 2100... +[2024-11-08 16:54:46,256][00398] Avg episode rewards: #0: 23.555, true rewards: #0: 10.555 +[2024-11-08 16:54:46,259][00398] Avg episode reward: 23.555, avg true_objective: 10.555 +[2024-11-08 16:54:46,407][00398] Num frames 2200... +[2024-11-08 16:54:46,600][00398] Num frames 2300... +[2024-11-08 16:54:46,822][00398] Num frames 2400... +[2024-11-08 16:54:47,032][00398] Num frames 2500... +[2024-11-08 16:54:47,224][00398] Num frames 2600... +[2024-11-08 16:54:47,391][00398] Num frames 2700... +[2024-11-08 16:54:47,556][00398] Num frames 2800... +[2024-11-08 16:54:47,640][00398] Avg episode rewards: #0: 20.050, true rewards: #0: 9.383 +[2024-11-08 16:54:47,642][00398] Avg episode reward: 20.050, avg true_objective: 9.383 +[2024-11-08 16:54:47,801][00398] Num frames 2900... +[2024-11-08 16:54:47,986][00398] Num frames 3000... +[2024-11-08 16:54:48,176][00398] Num frames 3100... +[2024-11-08 16:54:48,357][00398] Num frames 3200... +[2024-11-08 16:54:48,537][00398] Num frames 3300... +[2024-11-08 16:54:48,731][00398] Num frames 3400... +[2024-11-08 16:54:48,913][00398] Num frames 3500... +[2024-11-08 16:54:49,077][00398] Num frames 3600... +[2024-11-08 16:54:49,198][00398] Num frames 3700... +[2024-11-08 16:54:49,267][00398] Avg episode rewards: #0: 18.778, true rewards: #0: 9.277 +[2024-11-08 16:54:49,269][00398] Avg episode reward: 18.778, avg true_objective: 9.277 +[2024-11-08 16:54:49,378][00398] Num frames 3800... +[2024-11-08 16:54:49,497][00398] Num frames 3900... +[2024-11-08 16:54:49,622][00398] Num frames 4000... +[2024-11-08 16:54:49,743][00398] Num frames 4100... +[2024-11-08 16:54:49,862][00398] Num frames 4200... +[2024-11-08 16:54:49,991][00398] Avg episode rewards: #0: 16.726, true rewards: #0: 8.526 +[2024-11-08 16:54:49,992][00398] Avg episode reward: 16.726, avg true_objective: 8.526 +[2024-11-08 16:54:50,041][00398] Num frames 4300... +[2024-11-08 16:54:50,167][00398] Num frames 4400... +[2024-11-08 16:54:50,285][00398] Num frames 4500... +[2024-11-08 16:54:50,405][00398] Num frames 4600... +[2024-11-08 16:54:50,524][00398] Num frames 4700... +[2024-11-08 16:54:50,652][00398] Num frames 4800... +[2024-11-08 16:54:50,753][00398] Avg episode rewards: #0: 15.398, true rewards: #0: 8.065 +[2024-11-08 16:54:50,756][00398] Avg episode reward: 15.398, avg true_objective: 8.065 +[2024-11-08 16:54:50,830][00398] Num frames 4900... +[2024-11-08 16:54:50,954][00398] Num frames 5000... +[2024-11-08 16:54:51,072][00398] Num frames 5100... +[2024-11-08 16:54:51,201][00398] Num frames 5200... +[2024-11-08 16:54:51,322][00398] Num frames 5300... +[2024-11-08 16:54:51,443][00398] Num frames 5400... +[2024-11-08 16:54:51,569][00398] Num frames 5500... +[2024-11-08 16:54:51,691][00398] Num frames 5600... +[2024-11-08 16:54:51,796][00398] Avg episode rewards: #0: 15.484, true rewards: #0: 8.056 +[2024-11-08 16:54:51,797][00398] Avg episode reward: 15.484, avg true_objective: 8.056 +[2024-11-08 16:54:51,872][00398] Num frames 5700... +[2024-11-08 16:54:52,002][00398] Num frames 5800... +[2024-11-08 16:54:52,133][00398] Num frames 5900... +[2024-11-08 16:54:52,253][00398] Num frames 6000... +[2024-11-08 16:54:52,377][00398] Num frames 6100... +[2024-11-08 16:54:52,499][00398] Num frames 6200... +[2024-11-08 16:54:52,623][00398] Num frames 6300... +[2024-11-08 16:54:52,743][00398] Num frames 6400... +[2024-11-08 16:54:52,863][00398] Num frames 6500... +[2024-11-08 16:54:52,981][00398] Num frames 6600... +[2024-11-08 16:54:53,103][00398] Num frames 6700... +[2024-11-08 16:54:53,230][00398] Num frames 6800... +[2024-11-08 16:54:53,353][00398] Num frames 6900... +[2024-11-08 16:54:53,475][00398] Num frames 7000... +[2024-11-08 16:54:53,603][00398] Num frames 7100... +[2024-11-08 16:54:53,726][00398] Num frames 7200... +[2024-11-08 16:54:53,846][00398] Num frames 7300... +[2024-11-08 16:54:53,971][00398] Num frames 7400... +[2024-11-08 16:54:54,092][00398] Num frames 7500... +[2024-11-08 16:54:54,228][00398] Num frames 7600... +[2024-11-08 16:54:54,352][00398] Num frames 7700... +[2024-11-08 16:54:54,455][00398] Avg episode rewards: #0: 20.424, true rewards: #0: 9.674 +[2024-11-08 16:54:54,456][00398] Avg episode reward: 20.424, avg true_objective: 9.674 +[2024-11-08 16:54:54,531][00398] Num frames 7800... +[2024-11-08 16:54:54,668][00398] Num frames 7900... +[2024-11-08 16:54:54,803][00398] Num frames 8000... +[2024-11-08 16:54:54,924][00398] Num frames 8100... +[2024-11-08 16:54:55,044][00398] Num frames 8200... +[2024-11-08 16:54:55,165][00398] Num frames 8300... +[2024-11-08 16:54:55,293][00398] Num frames 8400... +[2024-11-08 16:54:55,445][00398] Num frames 8500... +[2024-11-08 16:54:55,623][00398] Avg episode rewards: #0: 19.968, true rewards: #0: 9.523 +[2024-11-08 16:54:55,626][00398] Avg episode reward: 19.968, avg true_objective: 9.523 +[2024-11-08 16:54:55,676][00398] Num frames 8600... +[2024-11-08 16:54:55,848][00398] Num frames 8700... +[2024-11-08 16:54:56,011][00398] Num frames 8800... +[2024-11-08 16:54:56,178][00398] Num frames 8900... +[2024-11-08 16:54:56,381][00398] Avg episode rewards: #0: 18.787, true rewards: #0: 8.987 +[2024-11-08 16:54:56,383][00398] Avg episode reward: 18.787, avg true_objective: 8.987 +[2024-11-08 16:55:26,338][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2024-11-08 16:55:39,763][00398] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2024-11-08 16:55:39,765][00398] Overriding arg 'num_workers' with value 1 passed from command line +[2024-11-08 16:55:39,767][00398] Adding new argument 'no_render'=True that is not in the saved config file! +[2024-11-08 16:55:39,768][00398] Adding new argument 'save_video'=True that is not in the saved config file! +[2024-11-08 16:55:39,770][00398] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2024-11-08 16:55:39,772][00398] Adding new argument 'video_name'=None that is not in the saved config file! +[2024-11-08 16:55:39,773][00398] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2024-11-08 16:55:39,774][00398] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2024-11-08 16:55:39,775][00398] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2024-11-08 16:55:39,777][00398] Adding new argument 'hf_repository'='Brumocas/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2024-11-08 16:55:39,778][00398] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2024-11-08 16:55:39,779][00398] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2024-11-08 16:55:39,780][00398] Adding new argument 'train_script'=None that is not in the saved config file! +[2024-11-08 16:55:39,781][00398] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2024-11-08 16:55:39,782][00398] Using frameskip 1 and render_action_repeat=4 for evaluation +[2024-11-08 16:55:39,817][00398] RunningMeanStd input shape: (3, 72, 128) +[2024-11-08 16:55:39,819][00398] RunningMeanStd input shape: (1,) +[2024-11-08 16:55:39,833][00398] ConvEncoder: input_channels=3 +[2024-11-08 16:55:39,871][00398] Conv encoder output size: 512 +[2024-11-08 16:55:39,873][00398] Policy head output size: 512 +[2024-11-08 16:55:39,891][00398] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2024-11-08 16:55:40,304][00398] Num frames 100... +[2024-11-08 16:55:40,424][00398] Num frames 200... +[2024-11-08 16:55:40,542][00398] Num frames 300... +[2024-11-08 16:55:40,692][00398] Num frames 400... +[2024-11-08 16:55:40,810][00398] Num frames 500... +[2024-11-08 16:55:40,935][00398] Num frames 600... +[2024-11-08 16:55:41,000][00398] Avg episode rewards: #0: 13.080, true rewards: #0: 6.080 +[2024-11-08 16:55:41,003][00398] Avg episode reward: 13.080, avg true_objective: 6.080 +[2024-11-08 16:55:41,113][00398] Num frames 700... +[2024-11-08 16:55:41,235][00398] Num frames 800... +[2024-11-08 16:55:41,356][00398] Num frames 900... +[2024-11-08 16:55:41,478][00398] Num frames 1000... +[2024-11-08 16:55:41,608][00398] Num frames 1100... +[2024-11-08 16:55:41,740][00398] Num frames 1200... +[2024-11-08 16:55:41,858][00398] Num frames 1300... +[2024-11-08 16:55:41,982][00398] Num frames 1400... +[2024-11-08 16:55:42,103][00398] Num frames 1500... +[2024-11-08 16:55:42,222][00398] Num frames 1600... +[2024-11-08 16:55:42,345][00398] Num frames 1700... +[2024-11-08 16:55:42,467][00398] Num frames 1800... +[2024-11-08 16:55:42,596][00398] Num frames 1900... +[2024-11-08 16:55:42,728][00398] Num frames 2000... +[2024-11-08 16:55:42,859][00398] Num frames 2100... +[2024-11-08 16:55:42,924][00398] Avg episode rewards: #0: 27.035, true rewards: #0: 10.535 +[2024-11-08 16:55:42,926][00398] Avg episode reward: 27.035, avg true_objective: 10.535 +[2024-11-08 16:55:43,048][00398] Num frames 2200... +[2024-11-08 16:55:43,171][00398] Num frames 2300... +[2024-11-08 16:55:43,296][00398] Num frames 2400... +[2024-11-08 16:55:43,425][00398] Num frames 2500... +[2024-11-08 16:55:43,557][00398] Num frames 2600... +[2024-11-08 16:55:43,692][00398] Num frames 2700... +[2024-11-08 16:55:43,815][00398] Num frames 2800... +[2024-11-08 16:55:43,940][00398] Num frames 2900... +[2024-11-08 16:55:44,045][00398] Avg episode rewards: #0: 24.463, true rewards: #0: 9.797 +[2024-11-08 16:55:44,046][00398] Avg episode reward: 24.463, avg true_objective: 9.797 +[2024-11-08 16:55:44,122][00398] Num frames 3000... +[2024-11-08 16:55:44,241][00398] Num frames 3100... +[2024-11-08 16:55:44,369][00398] Num frames 3200... +[2024-11-08 16:55:44,489][00398] Num frames 3300... +[2024-11-08 16:55:44,618][00398] Num frames 3400... +[2024-11-08 16:55:44,747][00398] Num frames 3500... +[2024-11-08 16:55:44,871][00398] Num frames 3600... +[2024-11-08 16:55:44,995][00398] Num frames 3700... +[2024-11-08 16:55:45,122][00398] Num frames 3800... +[2024-11-08 16:55:45,242][00398] Num frames 3900... +[2024-11-08 16:55:45,384][00398] Num frames 4000... +[2024-11-08 16:55:45,555][00398] Num frames 4100... +[2024-11-08 16:55:45,738][00398] Num frames 4200... +[2024-11-08 16:55:45,911][00398] Num frames 4300... +[2024-11-08 16:55:46,082][00398] Num frames 4400... +[2024-11-08 16:55:46,249][00398] Num frames 4500... +[2024-11-08 16:55:46,389][00398] Avg episode rewards: #0: 28.622, true rewards: #0: 11.372 +[2024-11-08 16:55:46,391][00398] Avg episode reward: 28.622, avg true_objective: 11.372 +[2024-11-08 16:55:46,479][00398] Num frames 4600... +[2024-11-08 16:55:46,657][00398] Num frames 4700... +[2024-11-08 16:55:46,835][00398] Num frames 4800... +[2024-11-08 16:55:47,000][00398] Num frames 4900... +[2024-11-08 16:55:47,169][00398] Num frames 5000... +[2024-11-08 16:55:47,343][00398] Num frames 5100... +[2024-11-08 16:55:47,511][00398] Num frames 5200... +[2024-11-08 16:55:47,682][00398] Num frames 5300... +[2024-11-08 16:55:47,852][00398] Num frames 5400... +[2024-11-08 16:55:47,973][00398] Num frames 5500... +[2024-11-08 16:55:48,099][00398] Num frames 5600... +[2024-11-08 16:55:48,220][00398] Num frames 5700... +[2024-11-08 16:55:48,361][00398] Num frames 5800... +[2024-11-08 16:55:48,482][00398] Num frames 5900... +[2024-11-08 16:55:48,569][00398] Avg episode rewards: #0: 30.050, true rewards: #0: 11.850 +[2024-11-08 16:55:48,571][00398] Avg episode reward: 30.050, avg true_objective: 11.850 +[2024-11-08 16:55:48,666][00398] Num frames 6000... +[2024-11-08 16:55:48,786][00398] Num frames 6100... +[2024-11-08 16:55:48,916][00398] Num frames 6200... +[2024-11-08 16:55:49,043][00398] Num frames 6300... +[2024-11-08 16:55:49,185][00398] Avg episode rewards: #0: 25.955, true rewards: #0: 10.622 +[2024-11-08 16:55:49,187][00398] Avg episode reward: 25.955, avg true_objective: 10.622 +[2024-11-08 16:55:49,224][00398] Num frames 6400... +[2024-11-08 16:55:49,345][00398] Num frames 6500... +[2024-11-08 16:55:49,468][00398] Num frames 6600... +[2024-11-08 16:55:49,591][00398] Num frames 6700... +[2024-11-08 16:55:49,713][00398] Num frames 6800... +[2024-11-08 16:55:49,831][00398] Num frames 6900... +[2024-11-08 16:55:49,962][00398] Num frames 7000... +[2024-11-08 16:55:50,081][00398] Num frames 7100... +[2024-11-08 16:55:50,148][00398] Avg episode rewards: #0: 24.441, true rewards: #0: 10.156 +[2024-11-08 16:55:50,149][00398] Avg episode reward: 24.441, avg true_objective: 10.156 +[2024-11-08 16:55:50,256][00398] Num frames 7200... +[2024-11-08 16:55:50,379][00398] Num frames 7300... +[2024-11-08 16:55:50,499][00398] Num frames 7400... +[2024-11-08 16:55:50,631][00398] Num frames 7500... +[2024-11-08 16:55:50,753][00398] Num frames 7600... +[2024-11-08 16:55:50,836][00398] Avg episode rewards: #0: 22.526, true rewards: #0: 9.526 +[2024-11-08 16:55:50,838][00398] Avg episode reward: 22.526, avg true_objective: 9.526 +[2024-11-08 16:55:50,941][00398] Num frames 7700... +[2024-11-08 16:55:51,063][00398] Num frames 7800... +[2024-11-08 16:55:51,190][00398] Num frames 7900... +[2024-11-08 16:55:51,311][00398] Num frames 8000... +[2024-11-08 16:55:51,432][00398] Num frames 8100... +[2024-11-08 16:55:51,554][00398] Num frames 8200... +[2024-11-08 16:55:51,678][00398] Num frames 8300... +[2024-11-08 16:55:51,798][00398] Num frames 8400... +[2024-11-08 16:55:51,930][00398] Num frames 8500... +[2024-11-08 16:55:52,057][00398] Num frames 8600... +[2024-11-08 16:55:52,175][00398] Num frames 8700... +[2024-11-08 16:55:52,297][00398] Num frames 8800... +[2024-11-08 16:55:52,399][00398] Avg episode rewards: #0: 23.152, true rewards: #0: 9.819 +[2024-11-08 16:55:52,402][00398] Avg episode reward: 23.152, avg true_objective: 9.819 +[2024-11-08 16:55:52,482][00398] Num frames 8900... +[2024-11-08 16:55:52,612][00398] Num frames 9000... +[2024-11-08 16:55:52,702][00398] Avg episode rewards: #0: 21.129, true rewards: #0: 9.029 +[2024-11-08 16:55:52,704][00398] Avg episode reward: 21.129, avg true_objective: 9.029 +[2024-11-08 16:56:46,049][00398] Replay video saved to /content/train_dir/default_experiment/replay.mp4!