diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1116 @@ +[2025-01-04 20:28:51,693][01523] Saving configuration to /content/train_dir/default_experiment/config.json... +[2025-01-04 20:28:51,697][01523] Rollout worker 0 uses device cpu +[2025-01-04 20:28:51,698][01523] Rollout worker 1 uses device cpu +[2025-01-04 20:28:51,700][01523] Rollout worker 2 uses device cpu +[2025-01-04 20:28:51,701][01523] Rollout worker 3 uses device cpu +[2025-01-04 20:28:51,706][01523] Rollout worker 4 uses device cpu +[2025-01-04 20:28:51,707][01523] Rollout worker 5 uses device cpu +[2025-01-04 20:28:51,708][01523] Rollout worker 6 uses device cpu +[2025-01-04 20:28:51,709][01523] Rollout worker 7 uses device cpu +[2025-01-04 20:28:51,904][01523] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2025-01-04 20:28:51,909][01523] InferenceWorker_p0-w0: min num requests: 2 +[2025-01-04 20:28:51,955][01523] Starting all processes... +[2025-01-04 20:28:51,959][01523] Starting process learner_proc0 +[2025-01-04 20:28:52,026][01523] Starting all processes... +[2025-01-04 20:28:52,042][01523] Starting process inference_proc0-0 +[2025-01-04 20:28:52,054][01523] Starting process rollout_proc0 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc1 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc2 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc3 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc4 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc5 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc6 +[2025-01-04 20:28:52,058][01523] Starting process rollout_proc7 +[2025-01-04 20:29:11,548][03812] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2025-01-04 20:29:11,551][03812] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2025-01-04 20:29:11,599][03828] Worker 2 uses CPU cores [0] +[2025-01-04 20:29:11,625][03812] Num visible devices: 1 +[2025-01-04 20:29:11,674][03812] Starting seed is not provided +[2025-01-04 20:29:11,675][03812] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2025-01-04 20:29:11,675][03812] Initializing actor-critic model on device cuda:0 +[2025-01-04 20:29:11,676][03812] RunningMeanStd input shape: (3, 72, 128) +[2025-01-04 20:29:11,680][03812] RunningMeanStd input shape: (1,) +[2025-01-04 20:29:11,769][03812] ConvEncoder: input_channels=3 +[2025-01-04 20:29:11,894][01523] Heartbeat connected on Batcher_0 +[2025-01-04 20:29:11,929][01523] Heartbeat connected on RolloutWorker_w2 +[2025-01-04 20:29:11,945][03827] Worker 1 uses CPU cores [1] +[2025-01-04 20:29:12,000][03829] Worker 3 uses CPU cores [1] +[2025-01-04 20:29:12,043][01523] Heartbeat connected on RolloutWorker_w1 +[2025-01-04 20:29:12,066][03826] Worker 0 uses CPU cores [0] +[2025-01-04 20:29:12,097][03831] Worker 6 uses CPU cores [0] +[2025-01-04 20:29:12,096][01523] Heartbeat connected on RolloutWorker_w3 +[2025-01-04 20:29:12,103][03833] Worker 7 uses CPU cores [1] +[2025-01-04 20:29:12,154][03825] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2025-01-04 20:29:12,155][03825] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2025-01-04 20:29:12,178][01523] Heartbeat connected on RolloutWorker_w7 +[2025-01-04 20:29:12,188][01523] Heartbeat connected on RolloutWorker_w0 +[2025-01-04 20:29:12,191][03825] Num visible devices: 1 +[2025-01-04 20:29:12,202][01523] Heartbeat connected on RolloutWorker_w6 +[2025-01-04 20:29:12,222][01523] Heartbeat connected on InferenceWorker_p0-w0 +[2025-01-04 20:29:12,256][03832] Worker 5 uses CPU cores [1] +[2025-01-04 20:29:12,266][01523] Heartbeat connected on RolloutWorker_w5 +[2025-01-04 20:29:12,309][03830] Worker 4 uses CPU cores [0] +[2025-01-04 20:29:12,323][03812] Conv encoder output size: 512 +[2025-01-04 20:29:12,324][03812] Policy head output size: 512 +[2025-01-04 20:29:12,332][01523] Heartbeat connected on RolloutWorker_w4 +[2025-01-04 20:29:12,381][03812] Created Actor Critic model with architecture: +[2025-01-04 20:29:12,381][03812] ActorCriticSharedWeights( + (obs_normalizer): ObservationNormalizer( + (running_mean_std): RunningMeanStdDictInPlace( + (running_mean_std): ModuleDict( + (obs): RunningMeanStdInPlace() + ) + ) + ) + (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) + (encoder): VizdoomEncoder( + (basic_encoder): ConvEncoder( + (enc): RecursiveScriptModule( + original_name=ConvEncoderImpl + (conv_head): RecursiveScriptModule( + original_name=Sequential + (0): RecursiveScriptModule(original_name=Conv2d) + (1): RecursiveScriptModule(original_name=ELU) + (2): RecursiveScriptModule(original_name=Conv2d) + (3): RecursiveScriptModule(original_name=ELU) + (4): RecursiveScriptModule(original_name=Conv2d) + (5): RecursiveScriptModule(original_name=ELU) + ) + (mlp_layers): RecursiveScriptModule( + original_name=Sequential + (0): RecursiveScriptModule(original_name=Linear) + (1): RecursiveScriptModule(original_name=ELU) + ) + ) + ) + ) + (core): ModelCoreRNN( + (core): GRU(512, 512) + ) + (decoder): MlpDecoder( + (mlp): Identity() + ) + (critic_linear): Linear(in_features=512, out_features=1, bias=True) + (action_parameterization): ActionParameterizationDefault( + (distribution_linear): Linear(in_features=512, out_features=5, bias=True) + ) +) +[2025-01-04 20:29:12,804][03812] Using optimizer +[2025-01-04 20:29:16,184][03812] No checkpoints found +[2025-01-04 20:29:16,184][03812] Did not load from checkpoint, starting from scratch! +[2025-01-04 20:29:16,184][03812] Initialized policy 0 weights for model version 0 +[2025-01-04 20:29:16,188][03812] LearnerWorker_p0 finished initialization! +[2025-01-04 20:29:16,189][03812] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2025-01-04 20:29:16,196][01523] Heartbeat connected on LearnerWorker_p0 +[2025-01-04 20:29:16,325][01523] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2025-01-04 20:29:16,396][03825] RunningMeanStd input shape: (3, 72, 128) +[2025-01-04 20:29:16,397][03825] RunningMeanStd input shape: (1,) +[2025-01-04 20:29:16,409][03825] ConvEncoder: input_channels=3 +[2025-01-04 20:29:16,519][03825] Conv encoder output size: 512 +[2025-01-04 20:29:16,520][03825] Policy head output size: 512 +[2025-01-04 20:29:16,575][01523] Inference worker 0-0 is ready! +[2025-01-04 20:29:16,577][01523] All inference workers are ready! Signal rollout workers to start! +[2025-01-04 20:29:16,783][03828] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,785][03830] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,780][03831] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,793][03826] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,810][03832] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,802][03827] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,813][03833] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:16,807][03829] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:29:17,410][03833] Decorrelating experience for 0 frames... +[2025-01-04 20:29:18,055][03828] Decorrelating experience for 0 frames... +[2025-01-04 20:29:18,061][03830] Decorrelating experience for 0 frames... +[2025-01-04 20:29:18,063][03831] Decorrelating experience for 0 frames... +[2025-01-04 20:29:18,065][03826] Decorrelating experience for 0 frames... +[2025-01-04 20:29:19,555][03829] Decorrelating experience for 0 frames... +[2025-01-04 20:29:19,603][03833] Decorrelating experience for 32 frames... +[2025-01-04 20:29:19,613][03827] Decorrelating experience for 0 frames... +[2025-01-04 20:29:19,980][03828] Decorrelating experience for 32 frames... +[2025-01-04 20:29:19,983][03831] Decorrelating experience for 32 frames... +[2025-01-04 20:29:20,000][03826] Decorrelating experience for 32 frames... +[2025-01-04 20:29:21,229][03832] Decorrelating experience for 0 frames... +[2025-01-04 20:29:21,325][01523] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2025-01-04 20:29:21,454][03829] Decorrelating experience for 32 frames... +[2025-01-04 20:29:21,625][03833] Decorrelating experience for 64 frames... +[2025-01-04 20:29:21,785][03830] Decorrelating experience for 32 frames... +[2025-01-04 20:29:22,229][03828] Decorrelating experience for 64 frames... +[2025-01-04 20:29:23,166][03827] Decorrelating experience for 32 frames... +[2025-01-04 20:29:23,561][03826] Decorrelating experience for 64 frames... +[2025-01-04 20:29:23,868][03832] Decorrelating experience for 32 frames... +[2025-01-04 20:29:24,256][03833] Decorrelating experience for 96 frames... +[2025-01-04 20:29:24,649][03830] Decorrelating experience for 64 frames... +[2025-01-04 20:29:24,709][03829] Decorrelating experience for 64 frames... +[2025-01-04 20:29:25,989][03828] Decorrelating experience for 96 frames... +[2025-01-04 20:29:26,147][03832] Decorrelating experience for 64 frames... +[2025-01-04 20:29:26,293][03831] Decorrelating experience for 64 frames... +[2025-01-04 20:29:26,300][03829] Decorrelating experience for 96 frames... +[2025-01-04 20:29:26,325][01523] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2025-01-04 20:29:26,644][03830] Decorrelating experience for 96 frames... +[2025-01-04 20:29:26,953][03827] Decorrelating experience for 64 frames... +[2025-01-04 20:29:27,787][03826] Decorrelating experience for 96 frames... +[2025-01-04 20:29:27,901][03831] Decorrelating experience for 96 frames... +[2025-01-04 20:29:29,555][03832] Decorrelating experience for 96 frames... +[2025-01-04 20:29:29,641][03827] Decorrelating experience for 96 frames... +[2025-01-04 20:29:31,007][03812] Signal inference workers to stop experience collection... +[2025-01-04 20:29:31,022][03825] InferenceWorker_p0-w0: stopping experience collection +[2025-01-04 20:29:31,325][01523] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 72.7. Samples: 1090. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2025-01-04 20:29:31,326][01523] Avg episode reward: [(0, '2.455')] +[2025-01-04 20:29:33,550][03812] Signal inference workers to resume experience collection... +[2025-01-04 20:29:33,550][03825] InferenceWorker_p0-w0: resuming experience collection +[2025-01-04 20:29:36,324][01523] Fps is (10 sec: 1638.4, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 174.2. Samples: 3484. Policy #0 lag: (min: 0.0, avg: 1.0, max: 2.0) +[2025-01-04 20:29:36,328][01523] Avg episode reward: [(0, '3.158')] +[2025-01-04 20:29:41,325][01523] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 317.4. Samples: 7934. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:29:41,332][01523] Avg episode reward: [(0, '3.694')] +[2025-01-04 20:29:43,809][03825] Updated weights for policy 0, policy_version 10 (0.0021) +[2025-01-04 20:29:46,325][01523] Fps is (10 sec: 3276.8, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 49152. Throughput: 0: 353.0. Samples: 10590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:29:46,331][01523] Avg episode reward: [(0, '4.401')] +[2025-01-04 20:29:51,325][01523] Fps is (10 sec: 4096.0, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 494.9. Samples: 17322. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:29:51,331][01523] Avg episode reward: [(0, '4.431')] +[2025-01-04 20:29:54,083][03825] Updated weights for policy 0, policy_version 20 (0.0023) +[2025-01-04 20:29:56,325][01523] Fps is (10 sec: 3686.4, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 86016. Throughput: 0: 550.0. Samples: 22000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:29:56,329][01523] Avg episode reward: [(0, '4.288')] +[2025-01-04 20:30:01,325][01523] Fps is (10 sec: 3276.7, 60 sec: 2275.5, 300 sec: 2275.5). Total num frames: 102400. Throughput: 0: 534.1. Samples: 24036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:30:01,327][01523] Avg episode reward: [(0, '4.399')] +[2025-01-04 20:30:01,332][03812] Saving new best policy, reward=4.399! +[2025-01-04 20:30:05,113][03825] Updated weights for policy 0, policy_version 30 (0.0018) +[2025-01-04 20:30:06,325][01523] Fps is (10 sec: 4096.0, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 680.0. Samples: 30602. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:30:06,327][01523] Avg episode reward: [(0, '4.505')] +[2025-01-04 20:30:06,333][03812] Saving new best policy, reward=4.505! +[2025-01-04 20:30:11,325][01523] Fps is (10 sec: 4096.1, 60 sec: 2606.5, 300 sec: 2606.5). Total num frames: 143360. Throughput: 0: 813.6. Samples: 36610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:30:11,327][01523] Avg episode reward: [(0, '4.457')] +[2025-01-04 20:30:16,325][01523] Fps is (10 sec: 3276.8, 60 sec: 2662.4, 300 sec: 2662.4). Total num frames: 159744. Throughput: 0: 833.4. Samples: 38592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:30:16,329][01523] Avg episode reward: [(0, '4.480')] +[2025-01-04 20:30:16,934][03825] Updated weights for policy 0, policy_version 40 (0.0015) +[2025-01-04 20:30:21,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3003.7, 300 sec: 2772.7). Total num frames: 180224. Throughput: 0: 911.8. Samples: 44514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:30:21,326][01523] Avg episode reward: [(0, '4.450')] +[2025-01-04 20:30:26,326][01523] Fps is (10 sec: 4095.4, 60 sec: 3345.0, 300 sec: 2867.1). Total num frames: 200704. Throughput: 0: 959.2. Samples: 51100. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:30:26,328][01523] Avg episode reward: [(0, '4.377')] +[2025-01-04 20:30:26,387][03825] Updated weights for policy 0, policy_version 50 (0.0028) +[2025-01-04 20:30:31,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 2894.5). Total num frames: 217088. Throughput: 0: 945.6. Samples: 53144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:30:31,327][01523] Avg episode reward: [(0, '4.410')] +[2025-01-04 20:30:36,325][01523] Fps is (10 sec: 3686.9, 60 sec: 3686.4, 300 sec: 2969.6). Total num frames: 237568. Throughput: 0: 906.6. Samples: 58118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:30:36,327][01523] Avg episode reward: [(0, '4.334')] +[2025-01-04 20:30:38,122][03825] Updated weights for policy 0, policy_version 60 (0.0017) +[2025-01-04 20:30:41,325][01523] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3035.8). Total num frames: 258048. Throughput: 0: 953.5. Samples: 64910. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:30:41,332][01523] Avg episode reward: [(0, '4.302')] +[2025-01-04 20:30:46,325][01523] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3049.2). Total num frames: 274432. Throughput: 0: 972.3. Samples: 67790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:30:46,327][01523] Avg episode reward: [(0, '4.455')] +[2025-01-04 20:30:46,332][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth... +[2025-01-04 20:30:50,044][03825] Updated weights for policy 0, policy_version 70 (0.0025) +[2025-01-04 20:30:51,325][01523] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3061.2). Total num frames: 290816. Throughput: 0: 916.7. Samples: 71852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:30:51,326][01523] Avg episode reward: [(0, '4.449')] +[2025-01-04 20:30:56,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3113.0). Total num frames: 311296. Throughput: 0: 922.7. Samples: 78130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:30:56,328][01523] Avg episode reward: [(0, '4.432')] +[2025-01-04 20:30:59,531][03825] Updated weights for policy 0, policy_version 80 (0.0045) +[2025-01-04 20:31:01,327][01523] Fps is (10 sec: 4095.1, 60 sec: 3822.8, 300 sec: 3159.7). Total num frames: 331776. Throughput: 0: 953.3. Samples: 81492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:31:01,329][01523] Avg episode reward: [(0, '4.456')] +[2025-01-04 20:31:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3127.9). Total num frames: 344064. Throughput: 0: 918.4. Samples: 85842. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:31:06,327][01523] Avg episode reward: [(0, '4.512')] +[2025-01-04 20:31:06,336][03812] Saving new best policy, reward=4.512! +[2025-01-04 20:31:11,312][03825] Updated weights for policy 0, policy_version 90 (0.0027) +[2025-01-04 20:31:11,324][01523] Fps is (10 sec: 3687.2, 60 sec: 3754.7, 300 sec: 3205.6). Total num frames: 368640. Throughput: 0: 904.9. Samples: 91820. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:31:11,332][01523] Avg episode reward: [(0, '4.639')] +[2025-01-04 20:31:11,335][03812] Saving new best policy, reward=4.639! +[2025-01-04 20:31:16,325][01523] Fps is (10 sec: 4505.2, 60 sec: 3822.9, 300 sec: 3242.6). Total num frames: 389120. Throughput: 0: 934.0. Samples: 95176. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:31:16,332][01523] Avg episode reward: [(0, '4.706')] +[2025-01-04 20:31:16,346][03812] Saving new best policy, reward=4.706! +[2025-01-04 20:31:21,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3211.3). Total num frames: 401408. Throughput: 0: 937.3. Samples: 100298. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:31:21,327][01523] Avg episode reward: [(0, '4.650')] +[2025-01-04 20:31:23,664][03825] Updated weights for policy 0, policy_version 100 (0.0015) +[2025-01-04 20:31:26,325][01523] Fps is (10 sec: 2867.5, 60 sec: 3618.2, 300 sec: 3213.8). Total num frames: 417792. Throughput: 0: 897.5. Samples: 105296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:31:26,327][01523] Avg episode reward: [(0, '4.583')] +[2025-01-04 20:31:31,325][01523] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 442368. Throughput: 0: 908.6. Samples: 108678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:31:31,331][01523] Avg episode reward: [(0, '4.708')] +[2025-01-04 20:31:31,334][03812] Saving new best policy, reward=4.708! +[2025-01-04 20:31:32,870][03825] Updated weights for policy 0, policy_version 110 (0.0029) +[2025-01-04 20:31:36,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 458752. Throughput: 0: 952.8. Samples: 114730. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:31:36,326][01523] Avg episode reward: [(0, '4.568')] +[2025-01-04 20:31:41,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 908.2. Samples: 118998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:31:41,327][01523] Avg episode reward: [(0, '4.498')] +[2025-01-04 20:31:44,528][03825] Updated weights for policy 0, policy_version 120 (0.0021) +[2025-01-04 20:31:46,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3304.1). Total num frames: 495616. Throughput: 0: 909.7. Samples: 122426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:31:46,330][01523] Avg episode reward: [(0, '4.632')] +[2025-01-04 20:31:51,325][01523] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3329.6). Total num frames: 516096. Throughput: 0: 962.7. Samples: 129162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:31:51,332][01523] Avg episode reward: [(0, '4.894')] +[2025-01-04 20:31:51,339][03812] Saving new best policy, reward=4.894! +[2025-01-04 20:31:56,124][03825] Updated weights for policy 0, policy_version 130 (0.0024) +[2025-01-04 20:31:56,327][01523] Fps is (10 sec: 3685.4, 60 sec: 3686.2, 300 sec: 3327.9). Total num frames: 532480. Throughput: 0: 922.7. Samples: 133346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:31:56,330][01523] Avg episode reward: [(0, '4.943')] +[2025-01-04 20:31:56,338][03812] Saving new best policy, reward=4.943! +[2025-01-04 20:32:01,324][01523] Fps is (10 sec: 3686.5, 60 sec: 3686.5, 300 sec: 3351.3). Total num frames: 552960. Throughput: 0: 906.0. Samples: 135946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:32:01,332][01523] Avg episode reward: [(0, '4.593')] +[2025-01-04 20:32:05,931][03825] Updated weights for policy 0, policy_version 140 (0.0024) +[2025-01-04 20:32:06,325][01523] Fps is (10 sec: 4097.1, 60 sec: 3822.9, 300 sec: 3373.2). Total num frames: 573440. Throughput: 0: 943.6. Samples: 142758. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2025-01-04 20:32:06,330][01523] Avg episode reward: [(0, '4.537')] +[2025-01-04 20:32:11,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3370.4). Total num frames: 589824. Throughput: 0: 947.9. Samples: 147950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:32:11,328][01523] Avg episode reward: [(0, '4.636')] +[2025-01-04 20:32:16,326][01523] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3367.8). Total num frames: 606208. Throughput: 0: 920.6. Samples: 150104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:32:16,331][01523] Avg episode reward: [(0, '4.408')] +[2025-01-04 20:32:17,570][03825] Updated weights for policy 0, policy_version 150 (0.0023) +[2025-01-04 20:32:21,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3409.6). Total num frames: 630784. Throughput: 0: 931.3. Samples: 156638. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:32:21,326][01523] Avg episode reward: [(0, '4.425')] +[2025-01-04 20:32:26,326][01523] Fps is (10 sec: 4095.7, 60 sec: 3822.8, 300 sec: 3406.1). Total num frames: 647168. Throughput: 0: 970.4. Samples: 162668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:32:26,329][01523] Avg episode reward: [(0, '4.619')] +[2025-01-04 20:32:28,191][03825] Updated weights for policy 0, policy_version 160 (0.0018) +[2025-01-04 20:32:31,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3402.8). Total num frames: 663552. Throughput: 0: 937.2. Samples: 164602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:32:31,327][01523] Avg episode reward: [(0, '4.598')] +[2025-01-04 20:32:36,325][01523] Fps is (10 sec: 3687.1, 60 sec: 3754.7, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 915.8. Samples: 170374. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:32:36,329][01523] Avg episode reward: [(0, '4.606')] +[2025-01-04 20:32:38,322][03825] Updated weights for policy 0, policy_version 170 (0.0039) +[2025-01-04 20:32:41,328][01523] Fps is (10 sec: 4504.2, 60 sec: 3891.0, 300 sec: 3456.6). Total num frames: 708608. Throughput: 0: 972.7. Samples: 177118. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:32:41,330][01523] Avg episode reward: [(0, '4.439')] +[2025-01-04 20:32:46,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3432.8). Total num frames: 720896. Throughput: 0: 964.6. Samples: 179352. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:32:46,328][01523] Avg episode reward: [(0, '4.372')] +[2025-01-04 20:32:46,338][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth... +[2025-01-04 20:32:50,220][03825] Updated weights for policy 0, policy_version 180 (0.0031) +[2025-01-04 20:32:51,325][01523] Fps is (10 sec: 3277.9, 60 sec: 3754.7, 300 sec: 3448.3). Total num frames: 741376. Throughput: 0: 918.9. Samples: 184110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:32:51,326][01523] Avg episode reward: [(0, '4.656')] +[2025-01-04 20:32:56,325][01523] Fps is (10 sec: 4096.1, 60 sec: 3823.1, 300 sec: 3463.0). Total num frames: 761856. Throughput: 0: 950.5. Samples: 190724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:32:56,329][01523] Avg episode reward: [(0, '4.918')] +[2025-01-04 20:33:00,711][03825] Updated weights for policy 0, policy_version 190 (0.0020) +[2025-01-04 20:33:01,325][01523] Fps is (10 sec: 3686.2, 60 sec: 3754.6, 300 sec: 3458.8). Total num frames: 778240. Throughput: 0: 968.6. Samples: 193692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:33:01,327][01523] Avg episode reward: [(0, '4.827')] +[2025-01-04 20:33:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3454.9). Total num frames: 794624. Throughput: 0: 912.3. Samples: 197692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:33:06,327][01523] Avg episode reward: [(0, '4.826')] +[2025-01-04 20:33:11,329][01523] Fps is (10 sec: 3685.0, 60 sec: 3754.4, 300 sec: 3468.5). Total num frames: 815104. Throughput: 0: 923.6. Samples: 204234. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:33:11,333][01523] Avg episode reward: [(0, '4.812')] +[2025-01-04 20:33:11,622][03825] Updated weights for policy 0, policy_version 200 (0.0016) +[2025-01-04 20:33:16,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3481.6). Total num frames: 835584. Throughput: 0: 953.4. Samples: 207506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:33:16,327][01523] Avg episode reward: [(0, '4.548')] +[2025-01-04 20:33:21,325][01523] Fps is (10 sec: 3278.1, 60 sec: 3618.1, 300 sec: 3460.7). Total num frames: 847872. Throughput: 0: 927.1. Samples: 212094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:33:21,326][01523] Avg episode reward: [(0, '4.325')] +[2025-01-04 20:33:23,514][03825] Updated weights for policy 0, policy_version 210 (0.0018) +[2025-01-04 20:33:26,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3473.4). Total num frames: 868352. Throughput: 0: 903.8. Samples: 217786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:33:26,329][01523] Avg episode reward: [(0, '4.537')] +[2025-01-04 20:33:31,325][01523] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3501.7). Total num frames: 892928. Throughput: 0: 929.3. Samples: 221172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:33:31,330][01523] Avg episode reward: [(0, '4.581')] +[2025-01-04 20:33:33,545][03825] Updated weights for policy 0, policy_version 220 (0.0022) +[2025-01-04 20:33:36,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 944.1. Samples: 226596. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:33:36,331][01523] Avg episode reward: [(0, '4.459')] +[2025-01-04 20:33:41,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3493.2). Total num frames: 925696. Throughput: 0: 907.7. Samples: 231572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:33:41,326][01523] Avg episode reward: [(0, '4.750')] +[2025-01-04 20:33:44,552][03825] Updated weights for policy 0, policy_version 230 (0.0013) +[2025-01-04 20:33:46,327][01523] Fps is (10 sec: 4095.2, 60 sec: 3754.5, 300 sec: 3504.3). Total num frames: 946176. Throughput: 0: 918.0. Samples: 235002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:33:46,331][01523] Avg episode reward: [(0, '4.987')] +[2025-01-04 20:33:46,355][03812] Saving new best policy, reward=4.987! +[2025-01-04 20:33:51,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3515.1). Total num frames: 966656. Throughput: 0: 967.6. Samples: 241236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:33:51,329][01523] Avg episode reward: [(0, '4.940')] +[2025-01-04 20:33:56,325][01523] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3496.2). Total num frames: 978944. Throughput: 0: 912.1. Samples: 245276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:33:56,327][01523] Avg episode reward: [(0, '4.817')] +[2025-01-04 20:33:56,613][03825] Updated weights for policy 0, policy_version 240 (0.0033) +[2025-01-04 20:34:01,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3521.1). Total num frames: 1003520. Throughput: 0: 913.0. Samples: 248592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:01,329][01523] Avg episode reward: [(0, '4.792')] +[2025-01-04 20:34:05,786][03825] Updated weights for policy 0, policy_version 250 (0.0015) +[2025-01-04 20:34:06,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3531.0). Total num frames: 1024000. Throughput: 0: 961.2. Samples: 255350. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:34:06,328][01523] Avg episode reward: [(0, '4.844')] +[2025-01-04 20:34:11,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.7, 300 sec: 3512.8). Total num frames: 1036288. Throughput: 0: 934.5. Samples: 259840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:34:11,329][01523] Avg episode reward: [(0, '4.905')] +[2025-01-04 20:34:16,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1056768. Throughput: 0: 916.8. Samples: 262428. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:16,330][01523] Avg episode reward: [(0, '4.954')] +[2025-01-04 20:34:17,438][03825] Updated weights for policy 0, policy_version 260 (0.0023) +[2025-01-04 20:34:21,324][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3665.6). Total num frames: 1081344. Throughput: 0: 947.8. Samples: 269248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:34:21,331][01523] Avg episode reward: [(0, '4.850')] +[2025-01-04 20:34:26,326][01523] Fps is (10 sec: 4095.3, 60 sec: 3822.8, 300 sec: 3721.1). Total num frames: 1097728. Throughput: 0: 958.1. Samples: 274686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:26,330][01523] Avg episode reward: [(0, '4.912')] +[2025-01-04 20:34:29,052][03825] Updated weights for policy 0, policy_version 270 (0.0022) +[2025-01-04 20:34:31,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 1114112. Throughput: 0: 926.7. Samples: 276702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:34:31,330][01523] Avg episode reward: [(0, '4.930')] +[2025-01-04 20:34:36,324][01523] Fps is (10 sec: 4096.7, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1138688. Throughput: 0: 932.4. Samples: 283192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:36,331][01523] Avg episode reward: [(0, '5.038')] +[2025-01-04 20:34:36,341][03812] Saving new best policy, reward=5.038! +[2025-01-04 20:34:38,327][03825] Updated weights for policy 0, policy_version 280 (0.0016) +[2025-01-04 20:34:41,326][01523] Fps is (10 sec: 4095.2, 60 sec: 3822.8, 300 sec: 3748.9). Total num frames: 1155072. Throughput: 0: 980.8. Samples: 289414. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:41,328][01523] Avg episode reward: [(0, '5.126')] +[2025-01-04 20:34:41,336][03812] Saving new best policy, reward=5.126! +[2025-01-04 20:34:46,325][01523] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3721.1). Total num frames: 1167360. Throughput: 0: 951.3. Samples: 291402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:46,331][01523] Avg episode reward: [(0, '5.194')] +[2025-01-04 20:34:46,340][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000285_1167360.pth... +[2025-01-04 20:34:46,510][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth +[2025-01-04 20:34:46,531][03812] Saving new best policy, reward=5.194! +[2025-01-04 20:34:50,384][03825] Updated weights for policy 0, policy_version 290 (0.0044) +[2025-01-04 20:34:51,325][01523] Fps is (10 sec: 3687.1, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1191936. Throughput: 0: 919.1. Samples: 296708. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:34:51,327][01523] Avg episode reward: [(0, '5.347')] +[2025-01-04 20:34:51,329][03812] Saving new best policy, reward=5.347! +[2025-01-04 20:34:56,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1212416. Throughput: 0: 967.5. Samples: 303378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:34:56,328][01523] Avg episode reward: [(0, '5.159')] +[2025-01-04 20:35:01,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 1224704. Throughput: 0: 963.6. Samples: 305788. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2025-01-04 20:35:01,327][01523] Avg episode reward: [(0, '5.107')] +[2025-01-04 20:35:01,413][03825] Updated weights for policy 0, policy_version 300 (0.0016) +[2025-01-04 20:35:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1245184. Throughput: 0: 915.7. Samples: 310454. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:35:06,332][01523] Avg episode reward: [(0, '5.234')] +[2025-01-04 20:35:11,273][03825] Updated weights for policy 0, policy_version 310 (0.0019) +[2025-01-04 20:35:11,324][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1269760. Throughput: 0: 946.1. Samples: 317260. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:35:11,327][01523] Avg episode reward: [(0, '5.701')] +[2025-01-04 20:35:11,332][03812] Saving new best policy, reward=5.701! +[2025-01-04 20:35:16,325][01523] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1286144. Throughput: 0: 973.9. Samples: 320528. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:35:16,329][01523] Avg episode reward: [(0, '6.229')] +[2025-01-04 20:35:16,339][03812] Saving new best policy, reward=6.229! +[2025-01-04 20:35:21,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1302528. Throughput: 0: 918.8. Samples: 324538. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:35:21,329][01523] Avg episode reward: [(0, '6.444')] +[2025-01-04 20:35:21,335][03812] Saving new best policy, reward=6.444! +[2025-01-04 20:35:23,219][03825] Updated weights for policy 0, policy_version 320 (0.0030) +[2025-01-04 20:35:26,325][01523] Fps is (10 sec: 3686.5, 60 sec: 3754.8, 300 sec: 3748.9). Total num frames: 1323008. Throughput: 0: 920.1. Samples: 330818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:35:26,326][01523] Avg episode reward: [(0, '6.132')] +[2025-01-04 20:35:31,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1343488. Throughput: 0: 949.2. Samples: 334114. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:35:31,327][01523] Avg episode reward: [(0, '6.383')] +[2025-01-04 20:35:33,948][03825] Updated weights for policy 0, policy_version 330 (0.0018) +[2025-01-04 20:35:36,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 1355776. Throughput: 0: 938.0. Samples: 338918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:35:36,331][01523] Avg episode reward: [(0, '6.351')] +[2025-01-04 20:35:41,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3735.0). Total num frames: 1376256. Throughput: 0: 914.8. Samples: 344542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:35:41,329][01523] Avg episode reward: [(0, '6.477')] +[2025-01-04 20:35:41,331][03812] Saving new best policy, reward=6.477! +[2025-01-04 20:35:44,402][03825] Updated weights for policy 0, policy_version 340 (0.0017) +[2025-01-04 20:35:46,325][01523] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1400832. Throughput: 0: 934.6. Samples: 347846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:35:46,327][01523] Avg episode reward: [(0, '6.383')] +[2025-01-04 20:35:51,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1413120. Throughput: 0: 958.0. Samples: 353562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:35:51,327][01523] Avg episode reward: [(0, '6.169')] +[2025-01-04 20:35:56,325][01523] Fps is (10 sec: 2867.3, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 1429504. Throughput: 0: 906.2. Samples: 358038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:35:56,327][01523] Avg episode reward: [(0, '6.758')] +[2025-01-04 20:35:56,337][03812] Saving new best policy, reward=6.758! +[2025-01-04 20:35:56,585][03825] Updated weights for policy 0, policy_version 350 (0.0029) +[2025-01-04 20:36:01,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1454080. Throughput: 0: 906.7. Samples: 361330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:36:01,327][01523] Avg episode reward: [(0, '7.049')] +[2025-01-04 20:36:01,329][03812] Saving new best policy, reward=7.049! +[2025-01-04 20:36:06,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1470464. Throughput: 0: 961.6. Samples: 367808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:36:06,328][01523] Avg episode reward: [(0, '7.205')] +[2025-01-04 20:36:06,337][03812] Saving new best policy, reward=7.205! +[2025-01-04 20:36:06,895][03825] Updated weights for policy 0, policy_version 360 (0.0036) +[2025-01-04 20:36:11,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 1486848. Throughput: 0: 909.7. Samples: 371754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:36:11,330][01523] Avg episode reward: [(0, '6.961')] +[2025-01-04 20:36:16,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1507328. Throughput: 0: 909.7. Samples: 375050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:36:16,327][01523] Avg episode reward: [(0, '6.474')] +[2025-01-04 20:36:17,457][03825] Updated weights for policy 0, policy_version 370 (0.0016) +[2025-01-04 20:36:21,328][01523] Fps is (10 sec: 4504.0, 60 sec: 3822.7, 300 sec: 3776.6). Total num frames: 1531904. Throughput: 0: 952.9. Samples: 381802. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:36:21,336][01523] Avg episode reward: [(0, '7.076')] +[2025-01-04 20:36:26,330][01523] Fps is (10 sec: 3684.4, 60 sec: 3686.1, 300 sec: 3734.9). Total num frames: 1544192. Throughput: 0: 929.1. Samples: 386356. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:36:26,332][01523] Avg episode reward: [(0, '7.207')] +[2025-01-04 20:36:26,345][03812] Saving new best policy, reward=7.207! +[2025-01-04 20:36:29,410][03825] Updated weights for policy 0, policy_version 380 (0.0029) +[2025-01-04 20:36:31,325][01523] Fps is (10 sec: 3278.0, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 1564672. Throughput: 0: 907.1. Samples: 388666. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:36:31,331][01523] Avg episode reward: [(0, '7.802')] +[2025-01-04 20:36:31,336][03812] Saving new best policy, reward=7.802! +[2025-01-04 20:36:36,325][01523] Fps is (10 sec: 4098.2, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1585152. Throughput: 0: 929.0. Samples: 395366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:36:36,327][01523] Avg episode reward: [(0, '7.761')] +[2025-01-04 20:36:39,225][03825] Updated weights for policy 0, policy_version 390 (0.0024) +[2025-01-04 20:36:41,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 1601536. Throughput: 0: 951.4. Samples: 400852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:36:41,327][01523] Avg episode reward: [(0, '8.141')] +[2025-01-04 20:36:41,335][03812] Saving new best policy, reward=8.141! +[2025-01-04 20:36:46,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 1617920. Throughput: 0: 923.2. Samples: 402874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:36:46,329][01523] Avg episode reward: [(0, '8.251')] +[2025-01-04 20:36:46,340][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000395_1617920.pth... +[2025-01-04 20:36:46,492][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000176_720896.pth +[2025-01-04 20:36:46,505][03812] Saving new best policy, reward=8.251! +[2025-01-04 20:36:50,665][03825] Updated weights for policy 0, policy_version 400 (0.0016) +[2025-01-04 20:36:51,325][01523] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1638400. Throughput: 0: 913.7. Samples: 408924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:36:51,332][01523] Avg episode reward: [(0, '8.147')] +[2025-01-04 20:36:56,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1658880. Throughput: 0: 968.7. Samples: 415346. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:36:56,331][01523] Avg episode reward: [(0, '8.068')] +[2025-01-04 20:37:01,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 1671168. Throughput: 0: 940.4. Samples: 417366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2025-01-04 20:37:01,329][01523] Avg episode reward: [(0, '8.100')] +[2025-01-04 20:37:02,664][03825] Updated weights for policy 0, policy_version 410 (0.0026) +[2025-01-04 20:37:06,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1695744. Throughput: 0: 909.8. Samples: 422740. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:37:06,332][01523] Avg episode reward: [(0, '8.159')] +[2025-01-04 20:37:11,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 1716224. Throughput: 0: 960.4. Samples: 429568. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2025-01-04 20:37:11,331][01523] Avg episode reward: [(0, '8.529')] +[2025-01-04 20:37:11,334][03812] Saving new best policy, reward=8.529! +[2025-01-04 20:37:11,657][03825] Updated weights for policy 0, policy_version 420 (0.0024) +[2025-01-04 20:37:16,327][01523] Fps is (10 sec: 3276.0, 60 sec: 3686.3, 300 sec: 3721.1). Total num frames: 1728512. Throughput: 0: 963.3. Samples: 432018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:37:16,333][01523] Avg episode reward: [(0, '8.452')] +[2025-01-04 20:37:21,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.4, 300 sec: 3735.0). Total num frames: 1748992. Throughput: 0: 916.7. Samples: 436616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:37:21,329][01523] Avg episode reward: [(0, '8.839')] +[2025-01-04 20:37:21,332][03812] Saving new best policy, reward=8.839! +[2025-01-04 20:37:23,416][03825] Updated weights for policy 0, policy_version 430 (0.0023) +[2025-01-04 20:37:26,324][01523] Fps is (10 sec: 4506.7, 60 sec: 3823.3, 300 sec: 3762.8). Total num frames: 1773568. Throughput: 0: 945.6. Samples: 443402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:37:26,330][01523] Avg episode reward: [(0, '9.256')] +[2025-01-04 20:37:26,337][03812] Saving new best policy, reward=9.256! +[2025-01-04 20:37:31,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1789952. Throughput: 0: 971.1. Samples: 446574. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:37:31,327][01523] Avg episode reward: [(0, '9.669')] +[2025-01-04 20:37:31,329][03812] Saving new best policy, reward=9.669! +[2025-01-04 20:37:35,370][03825] Updated weights for policy 0, policy_version 440 (0.0016) +[2025-01-04 20:37:36,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.2). Total num frames: 1806336. Throughput: 0: 925.8. Samples: 450584. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:37:36,326][01523] Avg episode reward: [(0, '9.500')] +[2025-01-04 20:37:41,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1826816. Throughput: 0: 929.0. Samples: 457152. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:37:41,330][01523] Avg episode reward: [(0, '10.241')] +[2025-01-04 20:37:41,334][03812] Saving new best policy, reward=10.241! +[2025-01-04 20:37:44,365][03825] Updated weights for policy 0, policy_version 450 (0.0027) +[2025-01-04 20:37:46,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 1847296. Throughput: 0: 957.8. Samples: 460468. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:37:46,331][01523] Avg episode reward: [(0, '10.294')] +[2025-01-04 20:37:46,340][03812] Saving new best policy, reward=10.294! +[2025-01-04 20:37:51,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1863680. Throughput: 0: 945.2. Samples: 465274. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:37:51,327][01523] Avg episode reward: [(0, '10.636')] +[2025-01-04 20:37:51,334][03812] Saving new best policy, reward=10.636! +[2025-01-04 20:37:56,127][03825] Updated weights for policy 0, policy_version 460 (0.0036) +[2025-01-04 20:37:56,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1884160. Throughput: 0: 919.0. Samples: 470922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:37:56,327][01523] Avg episode reward: [(0, '11.184')] +[2025-01-04 20:37:56,336][03812] Saving new best policy, reward=11.184! +[2025-01-04 20:38:01,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 1904640. Throughput: 0: 935.5. Samples: 474114. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:38:01,333][01523] Avg episode reward: [(0, '11.397')] +[2025-01-04 20:38:01,335][03812] Saving new best policy, reward=11.397! +[2025-01-04 20:38:06,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 1921024. Throughput: 0: 960.9. Samples: 479858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:06,327][01523] Avg episode reward: [(0, '12.068')] +[2025-01-04 20:38:06,335][03812] Saving new best policy, reward=12.068! +[2025-01-04 20:38:07,820][03825] Updated weights for policy 0, policy_version 470 (0.0019) +[2025-01-04 20:38:11,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1937408. Throughput: 0: 914.7. Samples: 484566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:38:11,332][01523] Avg episode reward: [(0, '11.702')] +[2025-01-04 20:38:16,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3891.3, 300 sec: 3776.7). Total num frames: 1961984. Throughput: 0: 920.9. Samples: 488014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:16,329][01523] Avg episode reward: [(0, '10.874')] +[2025-01-04 20:38:17,086][03825] Updated weights for policy 0, policy_version 480 (0.0015) +[2025-01-04 20:38:21,325][01523] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 1978368. Throughput: 0: 976.8. Samples: 494540. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:38:21,328][01523] Avg episode reward: [(0, '11.418')] +[2025-01-04 20:38:26,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 1994752. Throughput: 0: 921.4. Samples: 498614. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:38:26,332][01523] Avg episode reward: [(0, '11.228')] +[2025-01-04 20:38:29,070][03825] Updated weights for policy 0, policy_version 490 (0.0023) +[2025-01-04 20:38:31,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3762.8). Total num frames: 2015232. Throughput: 0: 916.3. Samples: 501700. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:31,332][01523] Avg episode reward: [(0, '12.109')] +[2025-01-04 20:38:31,335][03812] Saving new best policy, reward=12.109! +[2025-01-04 20:38:36,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2035712. Throughput: 0: 959.3. Samples: 508442. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:36,332][01523] Avg episode reward: [(0, '13.102')] +[2025-01-04 20:38:36,341][03812] Saving new best policy, reward=13.102! +[2025-01-04 20:38:40,020][03825] Updated weights for policy 0, policy_version 500 (0.0016) +[2025-01-04 20:38:41,325][01523] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2048000. Throughput: 0: 935.1. Samples: 513002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:38:41,327][01523] Avg episode reward: [(0, '13.170')] +[2025-01-04 20:38:41,332][03812] Saving new best policy, reward=13.170! +[2025-01-04 20:38:46,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2068480. Throughput: 0: 917.6. Samples: 515406. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:38:46,327][01523] Avg episode reward: [(0, '12.861')] +[2025-01-04 20:38:46,338][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth... +[2025-01-04 20:38:46,471][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000285_1167360.pth +[2025-01-04 20:38:50,064][03825] Updated weights for policy 0, policy_version 510 (0.0027) +[2025-01-04 20:38:51,324][01523] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 2093056. Throughput: 0: 940.8. Samples: 522194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:51,327][01523] Avg episode reward: [(0, '12.639')] +[2025-01-04 20:38:56,326][01523] Fps is (10 sec: 4095.6, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 2109440. Throughput: 0: 957.9. Samples: 527672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:38:56,333][01523] Avg episode reward: [(0, '12.599')] +[2025-01-04 20:39:01,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2125824. Throughput: 0: 925.7. Samples: 529670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:39:01,327][01523] Avg episode reward: [(0, '13.569')] +[2025-01-04 20:39:01,332][03812] Saving new best policy, reward=13.569! +[2025-01-04 20:39:02,099][03825] Updated weights for policy 0, policy_version 520 (0.0021) +[2025-01-04 20:39:06,325][01523] Fps is (10 sec: 3686.8, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2146304. Throughput: 0: 915.3. Samples: 535730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:39:06,326][01523] Avg episode reward: [(0, '14.347')] +[2025-01-04 20:39:06,340][03812] Saving new best policy, reward=14.347! +[2025-01-04 20:39:11,324][01523] Fps is (10 sec: 4096.1, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 2166784. Throughput: 0: 966.6. Samples: 542110. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:11,329][01523] Avg episode reward: [(0, '14.296')] +[2025-01-04 20:39:12,249][03825] Updated weights for policy 0, policy_version 530 (0.0027) +[2025-01-04 20:39:16,326][01523] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 2179072. Throughput: 0: 941.4. Samples: 544062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:16,333][01523] Avg episode reward: [(0, '14.244')] +[2025-01-04 20:39:21,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2199552. Throughput: 0: 909.8. Samples: 549384. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:21,331][01523] Avg episode reward: [(0, '14.036')] +[2025-01-04 20:39:23,225][03825] Updated weights for policy 0, policy_version 540 (0.0026) +[2025-01-04 20:39:26,325][01523] Fps is (10 sec: 4506.2, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2224128. Throughput: 0: 959.6. Samples: 556182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:26,332][01523] Avg episode reward: [(0, '14.758')] +[2025-01-04 20:39:26,340][03812] Saving new best policy, reward=14.758! +[2025-01-04 20:39:31,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2236416. Throughput: 0: 961.6. Samples: 558676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:39:31,329][01523] Avg episode reward: [(0, '15.348')] +[2025-01-04 20:39:31,332][03812] Saving new best policy, reward=15.348! +[2025-01-04 20:39:35,471][03825] Updated weights for policy 0, policy_version 550 (0.0023) +[2025-01-04 20:39:36,325][01523] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 2252800. Throughput: 0: 903.0. Samples: 562830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:39:36,337][01523] Avg episode reward: [(0, '16.737')] +[2025-01-04 20:39:36,350][03812] Saving new best policy, reward=16.737! +[2025-01-04 20:39:41,326][01523] Fps is (10 sec: 4095.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2277376. Throughput: 0: 929.2. Samples: 569486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:41,332][01523] Avg episode reward: [(0, '16.556')] +[2025-01-04 20:39:44,860][03825] Updated weights for policy 0, policy_version 560 (0.0014) +[2025-01-04 20:39:46,328][01523] Fps is (10 sec: 4094.7, 60 sec: 3754.5, 300 sec: 3735.0). Total num frames: 2293760. Throughput: 0: 960.0. Samples: 572874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:46,330][01523] Avg episode reward: [(0, '15.810')] +[2025-01-04 20:39:51,324][01523] Fps is (10 sec: 3277.2, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 2310144. Throughput: 0: 920.2. Samples: 577140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:39:51,327][01523] Avg episode reward: [(0, '15.541')] +[2025-01-04 20:39:56,324][01523] Fps is (10 sec: 4097.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 2334720. Throughput: 0: 917.8. Samples: 583410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:39:56,327][01523] Avg episode reward: [(0, '14.640')] +[2025-01-04 20:39:56,332][03825] Updated weights for policy 0, policy_version 570 (0.0019) +[2025-01-04 20:40:01,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 2355200. Throughput: 0: 946.2. Samples: 586640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:40:01,332][01523] Avg episode reward: [(0, '15.241')] +[2025-01-04 20:40:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2367488. Throughput: 0: 941.2. Samples: 591738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:40:06,336][01523] Avg episode reward: [(0, '15.664')] +[2025-01-04 20:40:08,301][03825] Updated weights for policy 0, policy_version 580 (0.0029) +[2025-01-04 20:40:11,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2387968. Throughput: 0: 910.0. Samples: 597132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:40:11,327][01523] Avg episode reward: [(0, '15.094')] +[2025-01-04 20:40:16,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 2408448. Throughput: 0: 930.0. Samples: 600526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:40:16,327][01523] Avg episode reward: [(0, '14.200')] +[2025-01-04 20:40:17,384][03825] Updated weights for policy 0, policy_version 590 (0.0019) +[2025-01-04 20:40:21,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2424832. Throughput: 0: 970.2. Samples: 606490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:40:21,327][01523] Avg episode reward: [(0, '14.496')] +[2025-01-04 20:40:26,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 2441216. Throughput: 0: 925.2. Samples: 611118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:40:26,330][01523] Avg episode reward: [(0, '15.216')] +[2025-01-04 20:40:29,313][03825] Updated weights for policy 0, policy_version 600 (0.0036) +[2025-01-04 20:40:31,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2465792. Throughput: 0: 922.4. Samples: 614380. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2025-01-04 20:40:31,330][01523] Avg episode reward: [(0, '16.163')] +[2025-01-04 20:40:36,324][01523] Fps is (10 sec: 4505.8, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 2486272. Throughput: 0: 980.6. Samples: 621268. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2025-01-04 20:40:36,333][01523] Avg episode reward: [(0, '16.207')] +[2025-01-04 20:40:40,775][03825] Updated weights for policy 0, policy_version 610 (0.0032) +[2025-01-04 20:40:41,325][01523] Fps is (10 sec: 3276.7, 60 sec: 3686.5, 300 sec: 3721.1). Total num frames: 2498560. Throughput: 0: 931.3. Samples: 625318. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2025-01-04 20:40:41,332][01523] Avg episode reward: [(0, '16.278')] +[2025-01-04 20:40:46,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3754.9, 300 sec: 3748.9). Total num frames: 2519040. Throughput: 0: 928.1. Samples: 628404. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2025-01-04 20:40:46,330][01523] Avg episode reward: [(0, '15.362')] +[2025-01-04 20:40:46,387][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000616_2523136.pth... +[2025-01-04 20:40:46,507][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000395_1617920.pth +[2025-01-04 20:40:49,813][03825] Updated weights for policy 0, policy_version 620 (0.0017) +[2025-01-04 20:40:51,324][01523] Fps is (10 sec: 4505.8, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 2543616. Throughput: 0: 964.0. Samples: 635118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:40:51,331][01523] Avg episode reward: [(0, '14.256')] +[2025-01-04 20:40:56,326][01523] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3735.0). Total num frames: 2555904. Throughput: 0: 951.0. Samples: 639930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:40:56,328][01523] Avg episode reward: [(0, '14.985')] +[2025-01-04 20:41:01,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 2576384. Throughput: 0: 920.7. Samples: 641958. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:41:01,332][01523] Avg episode reward: [(0, '16.785')] +[2025-01-04 20:41:01,337][03812] Saving new best policy, reward=16.785! +[2025-01-04 20:41:01,986][03825] Updated weights for policy 0, policy_version 630 (0.0031) +[2025-01-04 20:41:06,325][01523] Fps is (10 sec: 4096.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2596864. Throughput: 0: 937.3. Samples: 648670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:41:06,332][01523] Avg episode reward: [(0, '16.690')] +[2025-01-04 20:41:11,326][01523] Fps is (10 sec: 4095.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2617344. Throughput: 0: 962.3. Samples: 654422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:41:11,328][01523] Avg episode reward: [(0, '17.237')] +[2025-01-04 20:41:11,330][03812] Saving new best policy, reward=17.237! +[2025-01-04 20:41:12,910][03825] Updated weights for policy 0, policy_version 640 (0.0037) +[2025-01-04 20:41:16,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.2). Total num frames: 2629632. Throughput: 0: 932.9. Samples: 656360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:41:16,329][01523] Avg episode reward: [(0, '18.217')] +[2025-01-04 20:41:16,338][03812] Saving new best policy, reward=18.217! +[2025-01-04 20:41:21,324][01523] Fps is (10 sec: 3686.9, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 2654208. Throughput: 0: 912.7. Samples: 662340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:21,330][01523] Avg episode reward: [(0, '18.109')] +[2025-01-04 20:41:22,989][03825] Updated weights for policy 0, policy_version 650 (0.0023) +[2025-01-04 20:41:26,325][01523] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 2674688. Throughput: 0: 969.0. Samples: 668924. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:26,327][01523] Avg episode reward: [(0, '17.867')] +[2025-01-04 20:41:31,328][01523] Fps is (10 sec: 3275.7, 60 sec: 3686.2, 300 sec: 3735.0). Total num frames: 2686976. Throughput: 0: 944.7. Samples: 670918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:41:31,333][01523] Avg episode reward: [(0, '17.726')] +[2025-01-04 20:41:34,913][03825] Updated weights for policy 0, policy_version 660 (0.0018) +[2025-01-04 20:41:36,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 2707456. Throughput: 0: 909.1. Samples: 676028. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:36,326][01523] Avg episode reward: [(0, '18.112')] +[2025-01-04 20:41:41,325][01523] Fps is (10 sec: 4097.4, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 2727936. Throughput: 0: 951.3. Samples: 682738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:41:41,326][01523] Avg episode reward: [(0, '17.743')] +[2025-01-04 20:41:45,294][03825] Updated weights for policy 0, policy_version 670 (0.0026) +[2025-01-04 20:41:46,325][01523] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2744320. Throughput: 0: 968.9. Samples: 685560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:46,328][01523] Avg episode reward: [(0, '18.203')] +[2025-01-04 20:41:51,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 2760704. Throughput: 0: 911.5. Samples: 689686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:51,327][01523] Avg episode reward: [(0, '16.897')] +[2025-01-04 20:41:56,003][03825] Updated weights for policy 0, policy_version 680 (0.0032) +[2025-01-04 20:41:56,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3776.7). Total num frames: 2785280. Throughput: 0: 934.0. Samples: 696452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:41:56,327][01523] Avg episode reward: [(0, '18.193')] +[2025-01-04 20:42:01,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2801664. Throughput: 0: 962.4. Samples: 699670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:42:01,330][01523] Avg episode reward: [(0, '18.759')] +[2025-01-04 20:42:01,332][03812] Saving new best policy, reward=18.759! +[2025-01-04 20:42:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2818048. Throughput: 0: 923.2. Samples: 703882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:42:06,327][01523] Avg episode reward: [(0, '17.910')] +[2025-01-04 20:42:08,071][03825] Updated weights for policy 0, policy_version 690 (0.0015) +[2025-01-04 20:42:11,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3762.8). Total num frames: 2838528. Throughput: 0: 914.4. Samples: 710072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:42:11,327][01523] Avg episode reward: [(0, '18.210')] +[2025-01-04 20:42:16,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 2863104. Throughput: 0: 943.4. Samples: 713368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:42:16,327][01523] Avg episode reward: [(0, '19.097')] +[2025-01-04 20:42:16,332][03812] Saving new best policy, reward=19.097! +[2025-01-04 20:42:17,807][03825] Updated weights for policy 0, policy_version 700 (0.0024) +[2025-01-04 20:42:21,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 2875392. Throughput: 0: 941.6. Samples: 718398. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:42:21,332][01523] Avg episode reward: [(0, '19.162')] +[2025-01-04 20:42:21,334][03812] Saving new best policy, reward=19.162! +[2025-01-04 20:42:26,325][01523] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 2891776. Throughput: 0: 909.2. Samples: 723650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:42:26,326][01523] Avg episode reward: [(0, '18.802')] +[2025-01-04 20:42:29,261][03825] Updated weights for policy 0, policy_version 710 (0.0029) +[2025-01-04 20:42:31,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.2, 300 sec: 3762.8). Total num frames: 2916352. Throughput: 0: 920.4. Samples: 726980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:42:31,327][01523] Avg episode reward: [(0, '19.855')] +[2025-01-04 20:42:31,331][03812] Saving new best policy, reward=19.855! +[2025-01-04 20:42:36,327][01523] Fps is (10 sec: 4095.1, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 2932736. Throughput: 0: 956.1. Samples: 732712. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2025-01-04 20:42:36,329][01523] Avg episode reward: [(0, '19.940')] +[2025-01-04 20:42:36,346][03812] Saving new best policy, reward=19.940! +[2025-01-04 20:42:41,325][01523] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 2945024. Throughput: 0: 901.4. Samples: 737016. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:42:41,327][01523] Avg episode reward: [(0, '19.764')] +[2025-01-04 20:42:41,341][03825] Updated weights for policy 0, policy_version 720 (0.0017) +[2025-01-04 20:42:46,325][01523] Fps is (10 sec: 3687.2, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2969600. Throughput: 0: 905.0. Samples: 740396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:42:46,327][01523] Avg episode reward: [(0, '19.419')] +[2025-01-04 20:42:46,336][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000725_2969600.pth... +[2025-01-04 20:42:46,462][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth +[2025-01-04 20:42:50,648][03825] Updated weights for policy 0, policy_version 730 (0.0017) +[2025-01-04 20:42:51,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2990080. Throughput: 0: 959.9. Samples: 747076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:42:51,327][01523] Avg episode reward: [(0, '19.098')] +[2025-01-04 20:42:56,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3002368. Throughput: 0: 914.9. Samples: 751242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:42:56,327][01523] Avg episode reward: [(0, '19.357')] +[2025-01-04 20:43:01,325][01523] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3022848. Throughput: 0: 905.8. Samples: 754128. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:43:01,329][01523] Avg episode reward: [(0, '18.996')] +[2025-01-04 20:43:02,528][03825] Updated weights for policy 0, policy_version 740 (0.0019) +[2025-01-04 20:43:06,325][01523] Fps is (10 sec: 4505.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3047424. Throughput: 0: 941.5. Samples: 760766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:43:06,331][01523] Avg episode reward: [(0, '18.748')] +[2025-01-04 20:43:11,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3059712. Throughput: 0: 933.0. Samples: 765636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:43:11,331][01523] Avg episode reward: [(0, '18.702')] +[2025-01-04 20:43:14,134][03825] Updated weights for policy 0, policy_version 750 (0.0023) +[2025-01-04 20:43:16,325][01523] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3080192. Throughput: 0: 908.1. Samples: 767846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2025-01-04 20:43:16,332][01523] Avg episode reward: [(0, '18.229')] +[2025-01-04 20:43:21,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3100672. Throughput: 0: 931.9. Samples: 774644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:43:21,332][01523] Avg episode reward: [(0, '19.050')] +[2025-01-04 20:43:23,256][03825] Updated weights for policy 0, policy_version 760 (0.0015) +[2025-01-04 20:43:26,326][01523] Fps is (10 sec: 4095.2, 60 sec: 3822.8, 300 sec: 3748.9). Total num frames: 3121152. Throughput: 0: 964.0. Samples: 780396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:43:26,329][01523] Avg episode reward: [(0, '20.250')] +[2025-01-04 20:43:26,336][03812] Saving new best policy, reward=20.250! +[2025-01-04 20:43:31,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3133440. Throughput: 0: 932.8. Samples: 782370. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:43:31,332][01523] Avg episode reward: [(0, '20.404')] +[2025-01-04 20:43:31,335][03812] Saving new best policy, reward=20.404! +[2025-01-04 20:43:35,329][03825] Updated weights for policy 0, policy_version 770 (0.0030) +[2025-01-04 20:43:36,325][01523] Fps is (10 sec: 3687.1, 60 sec: 3754.8, 300 sec: 3762.8). Total num frames: 3158016. Throughput: 0: 912.4. Samples: 788134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:43:36,332][01523] Avg episode reward: [(0, '21.600')] +[2025-01-04 20:43:36,341][03812] Saving new best policy, reward=21.600! +[2025-01-04 20:43:41,324][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 3178496. Throughput: 0: 968.5. Samples: 794824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:43:41,329][01523] Avg episode reward: [(0, '22.521')] +[2025-01-04 20:43:41,334][03812] Saving new best policy, reward=22.521! +[2025-01-04 20:43:46,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3190784. Throughput: 0: 948.4. Samples: 796804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:43:46,329][01523] Avg episode reward: [(0, '22.601')] +[2025-01-04 20:43:46,345][03812] Saving new best policy, reward=22.601! +[2025-01-04 20:43:47,378][03825] Updated weights for policy 0, policy_version 780 (0.0037) +[2025-01-04 20:43:51,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3211264. Throughput: 0: 910.8. Samples: 801752. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:43:51,327][01523] Avg episode reward: [(0, '21.942')] +[2025-01-04 20:43:56,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3231744. Throughput: 0: 954.0. Samples: 808564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:43:56,327][01523] Avg episode reward: [(0, '20.954')] +[2025-01-04 20:43:56,532][03825] Updated weights for policy 0, policy_version 790 (0.0018) +[2025-01-04 20:44:01,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3248128. Throughput: 0: 968.2. Samples: 811414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:44:01,327][01523] Avg episode reward: [(0, '20.302')] +[2025-01-04 20:44:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3264512. Throughput: 0: 908.5. Samples: 815528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:44:06,327][01523] Avg episode reward: [(0, '19.839')] +[2025-01-04 20:44:08,383][03825] Updated weights for policy 0, policy_version 800 (0.0021) +[2025-01-04 20:44:11,325][01523] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3289088. Throughput: 0: 931.8. Samples: 822326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:44:11,327][01523] Avg episode reward: [(0, '19.111')] +[2025-01-04 20:44:16,327][01523] Fps is (10 sec: 4504.6, 60 sec: 3822.8, 300 sec: 3762.7). Total num frames: 3309568. Throughput: 0: 964.8. Samples: 825790. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:44:16,329][01523] Avg episode reward: [(0, '19.422')] +[2025-01-04 20:44:19,025][03825] Updated weights for policy 0, policy_version 810 (0.0015) +[2025-01-04 20:44:21,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3321856. Throughput: 0: 936.1. Samples: 830260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:44:21,331][01523] Avg episode reward: [(0, '19.316')] +[2025-01-04 20:44:26,324][01523] Fps is (10 sec: 3277.5, 60 sec: 3686.5, 300 sec: 3748.9). Total num frames: 3342336. Throughput: 0: 919.8. Samples: 836214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:44:26,327][01523] Avg episode reward: [(0, '18.744')] +[2025-01-04 20:44:29,154][03825] Updated weights for policy 0, policy_version 820 (0.0018) +[2025-01-04 20:44:31,324][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 3366912. Throughput: 0: 953.2. Samples: 839698. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:44:31,330][01523] Avg episode reward: [(0, '19.867')] +[2025-01-04 20:44:36,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3379200. Throughput: 0: 958.0. Samples: 844862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:44:36,329][01523] Avg episode reward: [(0, '19.777')] +[2025-01-04 20:44:41,091][03825] Updated weights for policy 0, policy_version 830 (0.0016) +[2025-01-04 20:44:41,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 3399680. Throughput: 0: 921.4. Samples: 850026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:44:41,330][01523] Avg episode reward: [(0, '20.614')] +[2025-01-04 20:44:46,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3420160. Throughput: 0: 932.8. Samples: 853392. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:44:46,329][01523] Avg episode reward: [(0, '21.290')] +[2025-01-04 20:44:46,341][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth... +[2025-01-04 20:44:46,465][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000616_2523136.pth +[2025-01-04 20:44:51,282][03825] Updated weights for policy 0, policy_version 840 (0.0019) +[2025-01-04 20:44:51,325][01523] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3440640. Throughput: 0: 978.3. Samples: 859550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:44:51,330][01523] Avg episode reward: [(0, '19.980')] +[2025-01-04 20:44:56,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3452928. Throughput: 0: 922.8. Samples: 863854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:44:56,327][01523] Avg episode reward: [(0, '21.088')] +[2025-01-04 20:45:01,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3477504. Throughput: 0: 921.2. Samples: 867244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:45:01,332][01523] Avg episode reward: [(0, '21.502')] +[2025-01-04 20:45:01,990][03825] Updated weights for policy 0, policy_version 850 (0.0021) +[2025-01-04 20:45:06,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 3497984. Throughput: 0: 971.4. Samples: 873972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:45:06,331][01523] Avg episode reward: [(0, '20.476')] +[2025-01-04 20:45:11,324][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3510272. Throughput: 0: 932.4. Samples: 878172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:45:11,329][01523] Avg episode reward: [(0, '20.705')] +[2025-01-04 20:45:13,859][03825] Updated weights for policy 0, policy_version 860 (0.0014) +[2025-01-04 20:45:16,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3748.9). Total num frames: 3530752. Throughput: 0: 918.6. Samples: 881034. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:45:16,327][01523] Avg episode reward: [(0, '21.677')] +[2025-01-04 20:45:21,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 3555328. Throughput: 0: 953.2. Samples: 887758. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:45:21,327][01523] Avg episode reward: [(0, '22.269')] +[2025-01-04 20:45:23,468][03825] Updated weights for policy 0, policy_version 870 (0.0015) +[2025-01-04 20:45:26,325][01523] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3735.0). Total num frames: 3567616. Throughput: 0: 950.8. Samples: 892812. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:45:26,327][01523] Avg episode reward: [(0, '20.239')] +[2025-01-04 20:45:31,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3588096. Throughput: 0: 920.2. Samples: 894800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:45:31,330][01523] Avg episode reward: [(0, '20.169')] +[2025-01-04 20:45:34,910][03825] Updated weights for policy 0, policy_version 880 (0.0037) +[2025-01-04 20:45:36,325][01523] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3608576. Throughput: 0: 928.7. Samples: 901342. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:45:36,331][01523] Avg episode reward: [(0, '20.179')] +[2025-01-04 20:45:41,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3624960. Throughput: 0: 964.7. Samples: 907264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:45:41,326][01523] Avg episode reward: [(0, '20.428')] +[2025-01-04 20:45:46,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3641344. Throughput: 0: 934.4. Samples: 909294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:45:46,328][01523] Avg episode reward: [(0, '19.161')] +[2025-01-04 20:45:46,715][03825] Updated weights for policy 0, policy_version 890 (0.0031) +[2025-01-04 20:45:51,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3665920. Throughput: 0: 917.2. Samples: 915244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:45:51,329][01523] Avg episode reward: [(0, '18.993')] +[2025-01-04 20:45:55,908][03825] Updated weights for policy 0, policy_version 900 (0.0032) +[2025-01-04 20:45:56,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 3686400. Throughput: 0: 975.4. Samples: 922066. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2025-01-04 20:45:56,328][01523] Avg episode reward: [(0, '18.647')] +[2025-01-04 20:46:01,326][01523] Fps is (10 sec: 3276.4, 60 sec: 3686.3, 300 sec: 3735.0). Total num frames: 3698688. Throughput: 0: 957.3. Samples: 924114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:01,329][01523] Avg episode reward: [(0, '18.784')] +[2025-01-04 20:46:06,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3719168. Throughput: 0: 915.8. Samples: 928968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:06,331][01523] Avg episode reward: [(0, '18.480')] +[2025-01-04 20:46:07,678][03825] Updated weights for policy 0, policy_version 910 (0.0022) +[2025-01-04 20:46:11,325][01523] Fps is (10 sec: 4096.5, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3739648. Throughput: 0: 952.1. Samples: 935656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:11,331][01523] Avg episode reward: [(0, '19.133')] +[2025-01-04 20:46:16,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3756032. Throughput: 0: 973.1. Samples: 938588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:16,327][01523] Avg episode reward: [(0, '19.930')] +[2025-01-04 20:46:19,570][03825] Updated weights for policy 0, policy_version 920 (0.0026) +[2025-01-04 20:46:21,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 3772416. Throughput: 0: 918.5. Samples: 942676. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:46:21,332][01523] Avg episode reward: [(0, '21.248')] +[2025-01-04 20:46:26,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 3796992. Throughput: 0: 937.1. Samples: 949434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:26,326][01523] Avg episode reward: [(0, '21.774')] +[2025-01-04 20:46:28,748][03825] Updated weights for policy 0, policy_version 930 (0.0017) +[2025-01-04 20:46:31,325][01523] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3813376. Throughput: 0: 967.4. Samples: 952828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:31,329][01523] Avg episode reward: [(0, '22.259')] +[2025-01-04 20:46:36,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3829760. Throughput: 0: 930.5. Samples: 957118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:46:36,329][01523] Avg episode reward: [(0, '22.545')] +[2025-01-04 20:46:40,651][03825] Updated weights for policy 0, policy_version 940 (0.0019) +[2025-01-04 20:46:41,324][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3850240. Throughput: 0: 910.0. Samples: 963016. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2025-01-04 20:46:41,332][01523] Avg episode reward: [(0, '23.133')] +[2025-01-04 20:46:41,334][03812] Saving new best policy, reward=23.133! +[2025-01-04 20:46:46,325][01523] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 3874816. Throughput: 0: 937.5. Samples: 966300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:46:46,330][01523] Avg episode reward: [(0, '22.369')] +[2025-01-04 20:46:46,339][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000946_3874816.pth... +[2025-01-04 20:46:46,472][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000725_2969600.pth +[2025-01-04 20:46:51,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3887104. Throughput: 0: 947.4. Samples: 971602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:46:51,329][01523] Avg episode reward: [(0, '22.088')] +[2025-01-04 20:46:52,236][03825] Updated weights for policy 0, policy_version 950 (0.0015) +[2025-01-04 20:46:56,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 3907584. Throughput: 0: 911.8. Samples: 976688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2025-01-04 20:46:56,327][01523] Avg episode reward: [(0, '22.256')] +[2025-01-04 20:47:01,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 3928064. Throughput: 0: 921.4. Samples: 980050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:47:01,327][01523] Avg episode reward: [(0, '21.996')] +[2025-01-04 20:47:01,936][03825] Updated weights for policy 0, policy_version 960 (0.0020) +[2025-01-04 20:47:06,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3944448. Throughput: 0: 965.6. Samples: 986130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:47:06,327][01523] Avg episode reward: [(0, '21.449')] +[2025-01-04 20:47:11,325][01523] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3960832. Throughput: 0: 909.6. Samples: 990368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2025-01-04 20:47:11,327][01523] Avg episode reward: [(0, '21.248')] +[2025-01-04 20:47:13,808][03825] Updated weights for policy 0, policy_version 970 (0.0020) +[2025-01-04 20:47:16,325][01523] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3981312. Throughput: 0: 908.1. Samples: 993692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2025-01-04 20:47:16,328][01523] Avg episode reward: [(0, '22.059')] +[2025-01-04 20:47:21,324][01523] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 4001792. Throughput: 0: 963.7. Samples: 1000484. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2025-01-04 20:47:21,332][01523] Avg episode reward: [(0, '21.533')] +[2025-01-04 20:47:21,406][03812] Stopping Batcher_0... +[2025-01-04 20:47:21,407][03812] Loop batcher_evt_loop terminating... +[2025-01-04 20:47:21,409][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2025-01-04 20:47:21,408][01523] Component Batcher_0 stopped! +[2025-01-04 20:47:21,522][03825] Weights refcount: 2 0 +[2025-01-04 20:47:21,536][01523] Component InferenceWorker_p0-w0 stopped! +[2025-01-04 20:47:21,542][03825] Stopping InferenceWorker_p0-w0... +[2025-01-04 20:47:21,542][03825] Loop inference_proc0-0_evt_loop terminating... +[2025-01-04 20:47:21,600][03812] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth +[2025-01-04 20:47:21,619][03812] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2025-01-04 20:47:21,877][01523] Component LearnerWorker_p0 stopped! +[2025-01-04 20:47:21,880][03812] Stopping LearnerWorker_p0... +[2025-01-04 20:47:21,881][03812] Loop learner_proc0_evt_loop terminating... +[2025-01-04 20:47:22,088][01523] Component RolloutWorker_w7 stopped! +[2025-01-04 20:47:22,095][03833] Stopping RolloutWorker_w7... +[2025-01-04 20:47:22,095][03833] Loop rollout_proc7_evt_loop terminating... +[2025-01-04 20:47:22,107][01523] Component RolloutWorker_w1 stopped! +[2025-01-04 20:47:22,113][03827] Stopping RolloutWorker_w1... +[2025-01-04 20:47:22,113][03827] Loop rollout_proc1_evt_loop terminating... +[2025-01-04 20:47:22,143][01523] Component RolloutWorker_w3 stopped! +[2025-01-04 20:47:22,149][03829] Stopping RolloutWorker_w3... +[2025-01-04 20:47:22,152][03829] Loop rollout_proc3_evt_loop terminating... +[2025-01-04 20:47:22,156][01523] Component RolloutWorker_w5 stopped! +[2025-01-04 20:47:22,160][03832] Stopping RolloutWorker_w5... +[2025-01-04 20:47:22,161][03832] Loop rollout_proc5_evt_loop terminating... +[2025-01-04 20:47:22,317][01523] Component RolloutWorker_w4 stopped! +[2025-01-04 20:47:22,324][03830] Stopping RolloutWorker_w4... +[2025-01-04 20:47:22,336][03830] Loop rollout_proc4_evt_loop terminating... +[2025-01-04 20:47:22,347][01523] Component RolloutWorker_w6 stopped! +[2025-01-04 20:47:22,353][03831] Stopping RolloutWorker_w6... +[2025-01-04 20:47:22,355][03831] Loop rollout_proc6_evt_loop terminating... +[2025-01-04 20:47:22,367][01523] Component RolloutWorker_w0 stopped! +[2025-01-04 20:47:22,373][03826] Stopping RolloutWorker_w0... +[2025-01-04 20:47:22,374][03826] Loop rollout_proc0_evt_loop terminating... +[2025-01-04 20:47:22,418][01523] Component RolloutWorker_w2 stopped! +[2025-01-04 20:47:22,424][01523] Waiting for process learner_proc0 to stop... +[2025-01-04 20:47:22,430][03828] Stopping RolloutWorker_w2... +[2025-01-04 20:47:22,431][03828] Loop rollout_proc2_evt_loop terminating... +[2025-01-04 20:47:24,204][01523] Waiting for process inference_proc0-0 to join... +[2025-01-04 20:47:24,415][01523] Waiting for process rollout_proc0 to join... +[2025-01-04 20:47:26,678][01523] Waiting for process rollout_proc1 to join... +[2025-01-04 20:47:26,684][01523] Waiting for process rollout_proc2 to join... +[2025-01-04 20:47:26,692][01523] Waiting for process rollout_proc3 to join... +[2025-01-04 20:47:26,695][01523] Waiting for process rollout_proc4 to join... +[2025-01-04 20:47:26,701][01523] Waiting for process rollout_proc5 to join... +[2025-01-04 20:47:26,705][01523] Waiting for process rollout_proc6 to join... +[2025-01-04 20:47:26,708][01523] Waiting for process rollout_proc7 to join... +[2025-01-04 20:47:26,712][01523] Batcher 0 profile tree view: +batching: 26.5564, releasing_batches: 0.0326 +[2025-01-04 20:47:26,713][01523] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0245 + wait_policy_total: 447.8795 +update_model: 8.8279 + weight_update: 0.0023 +one_step: 0.0033 + handle_policy_step: 582.0091 + deserialize: 15.0943, stack: 3.2264, obs_to_device_normalize: 123.8602, forward: 293.2148, send_messages: 29.0786 + prepare_outputs: 88.5470 + to_cpu: 53.0443 +[2025-01-04 20:47:26,715][01523] Learner 0 profile tree view: +misc: 0.0046, prepare_batch: 13.4460 +train: 73.5411 + epoch_init: 0.0077, minibatch_init: 0.0120, losses_postprocess: 0.6086, kl_divergence: 0.6007, after_optimizer: 33.6175 + calculate_losses: 26.0910 + losses_init: 0.0034, forward_head: 1.3486, bptt_initial: 17.3386, tail: 1.0920, advantages_returns: 0.2714, losses: 3.8370 + bptt: 1.9299 + bptt_forward_core: 1.8335 + update: 11.9088 + clip: 0.9267 +[2025-01-04 20:47:26,717][01523] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3557, enqueue_policy_requests: 113.5694, env_step: 839.5745, overhead: 15.0578, complete_rollouts: 7.1031 +save_policy_outputs: 21.4281 + split_output_tensors: 8.3076 +[2025-01-04 20:47:26,719][01523] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3068, enqueue_policy_requests: 112.9861, env_step: 839.7892, overhead: 14.8994, complete_rollouts: 7.1939 +save_policy_outputs: 21.4032 + split_output_tensors: 8.5942 +[2025-01-04 20:47:26,723][01523] Loop Runner_EvtLoop terminating... +[2025-01-04 20:47:26,724][01523] Runner profile tree view: +main_loop: 1114.7703 +[2025-01-04 20:47:26,727][01523] Collected {0: 4005888}, FPS: 3593.5 +[2025-01-04 20:47:55,143][01523] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2025-01-04 20:47:55,146][01523] Overriding arg 'num_workers' with value 1 passed from command line +[2025-01-04 20:47:55,149][01523] Adding new argument 'no_render'=True that is not in the saved config file! +[2025-01-04 20:47:55,151][01523] Adding new argument 'save_video'=True that is not in the saved config file! +[2025-01-04 20:47:55,152][01523] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2025-01-04 20:47:55,154][01523] Adding new argument 'video_name'=None that is not in the saved config file! +[2025-01-04 20:47:55,156][01523] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2025-01-04 20:47:55,158][01523] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2025-01-04 20:47:55,160][01523] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2025-01-04 20:47:55,162][01523] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2025-01-04 20:47:55,164][01523] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2025-01-04 20:47:55,165][01523] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2025-01-04 20:47:55,168][01523] Adding new argument 'train_script'=None that is not in the saved config file! +[2025-01-04 20:47:55,169][01523] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2025-01-04 20:47:55,170][01523] Using frameskip 1 and render_action_repeat=4 for evaluation +[2025-01-04 20:47:55,202][01523] Doom resolution: 160x120, resize resolution: (128, 72) +[2025-01-04 20:47:55,206][01523] RunningMeanStd input shape: (3, 72, 128) +[2025-01-04 20:47:55,209][01523] RunningMeanStd input shape: (1,) +[2025-01-04 20:47:55,226][01523] ConvEncoder: input_channels=3 +[2025-01-04 20:47:55,328][01523] Conv encoder output size: 512 +[2025-01-04 20:47:55,331][01523] Policy head output size: 512 +[2025-01-04 20:47:55,611][01523] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2025-01-04 20:47:56,401][01523] Num frames 100... +[2025-01-04 20:47:56,521][01523] Num frames 200... +[2025-01-04 20:47:56,646][01523] Num frames 300... +[2025-01-04 20:47:56,811][01523] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840 +[2025-01-04 20:47:56,813][01523] Avg episode reward: 3.840, avg true_objective: 3.840 +[2025-01-04 20:47:56,839][01523] Num frames 400... +[2025-01-04 20:47:56,956][01523] Num frames 500... +[2025-01-04 20:47:57,083][01523] Num frames 600... +[2025-01-04 20:47:57,202][01523] Num frames 700... +[2025-01-04 20:47:57,325][01523] Num frames 800... +[2025-01-04 20:47:57,443][01523] Num frames 900... +[2025-01-04 20:47:57,564][01523] Num frames 1000... +[2025-01-04 20:47:57,726][01523] Num frames 1100... +[2025-01-04 20:47:57,911][01523] Num frames 1200... +[2025-01-04 20:47:58,091][01523] Num frames 1300... +[2025-01-04 20:47:58,273][01523] Num frames 1400... +[2025-01-04 20:47:58,439][01523] Num frames 1500... +[2025-01-04 20:47:58,613][01523] Num frames 1600... +[2025-01-04 20:47:58,784][01523] Num frames 1700... +[2025-01-04 20:47:58,952][01523] Num frames 1800... +[2025-01-04 20:47:59,129][01523] Num frames 1900... +[2025-01-04 20:47:59,276][01523] Avg episode rewards: #0: 18.760, true rewards: #0: 9.760 +[2025-01-04 20:47:59,279][01523] Avg episode reward: 18.760, avg true_objective: 9.760 +[2025-01-04 20:47:59,368][01523] Num frames 2000... +[2025-01-04 20:47:59,539][01523] Num frames 2100... +[2025-01-04 20:47:59,717][01523] Num frames 2200... +[2025-01-04 20:47:59,915][01523] Num frames 2300... +[2025-01-04 20:48:00,093][01523] Num frames 2400... +[2025-01-04 20:48:00,295][01523] Avg episode rewards: #0: 15.987, true rewards: #0: 8.320 +[2025-01-04 20:48:00,297][01523] Avg episode reward: 15.987, avg true_objective: 8.320 +[2025-01-04 20:48:00,308][01523] Num frames 2500... +[2025-01-04 20:48:00,426][01523] Num frames 2600... +[2025-01-04 20:48:00,549][01523] Num frames 2700... +[2025-01-04 20:48:00,670][01523] Num frames 2800... +[2025-01-04 20:48:00,802][01523] Num frames 2900... +[2025-01-04 20:48:00,929][01523] Num frames 3000... +[2025-01-04 20:48:01,053][01523] Num frames 3100... +[2025-01-04 20:48:01,174][01523] Num frames 3200... +[2025-01-04 20:48:01,299][01523] Num frames 3300... +[2025-01-04 20:48:01,421][01523] Num frames 3400... +[2025-01-04 20:48:01,545][01523] Num frames 3500... +[2025-01-04 20:48:01,675][01523] Num frames 3600... +[2025-01-04 20:48:01,821][01523] Num frames 3700... +[2025-01-04 20:48:01,973][01523] Num frames 3800... +[2025-01-04 20:48:02,096][01523] Num frames 3900... +[2025-01-04 20:48:02,220][01523] Num frames 4000... +[2025-01-04 20:48:02,343][01523] Num frames 4100... +[2025-01-04 20:48:02,467][01523] Num frames 4200... +[2025-01-04 20:48:02,587][01523] Num frames 4300... +[2025-01-04 20:48:02,713][01523] Num frames 4400... +[2025-01-04 20:48:02,849][01523] Avg episode rewards: #0: 23.892, true rewards: #0: 11.142 +[2025-01-04 20:48:02,852][01523] Avg episode reward: 23.892, avg true_objective: 11.142 +[2025-01-04 20:48:02,906][01523] Num frames 4500... +[2025-01-04 20:48:03,037][01523] Num frames 4600... +[2025-01-04 20:48:03,159][01523] Num frames 4700... +[2025-01-04 20:48:03,281][01523] Num frames 4800... +[2025-01-04 20:48:03,401][01523] Num frames 4900... +[2025-01-04 20:48:03,522][01523] Num frames 5000... +[2025-01-04 20:48:03,641][01523] Num frames 5100... +[2025-01-04 20:48:03,775][01523] Num frames 5200... +[2025-01-04 20:48:03,901][01523] Num frames 5300... +[2025-01-04 20:48:03,983][01523] Avg episode rewards: #0: 22.842, true rewards: #0: 10.642 +[2025-01-04 20:48:03,986][01523] Avg episode reward: 22.842, avg true_objective: 10.642 +[2025-01-04 20:48:04,083][01523] Num frames 5400... +[2025-01-04 20:48:04,202][01523] Num frames 5500... +[2025-01-04 20:48:04,325][01523] Num frames 5600... +[2025-01-04 20:48:04,443][01523] Num frames 5700... +[2025-01-04 20:48:04,565][01523] Num frames 5800... +[2025-01-04 20:48:04,687][01523] Num frames 5900... +[2025-01-04 20:48:04,827][01523] Avg episode rewards: #0: 20.768, true rewards: #0: 9.935 +[2025-01-04 20:48:04,828][01523] Avg episode reward: 20.768, avg true_objective: 9.935 +[2025-01-04 20:48:04,877][01523] Num frames 6000... +[2025-01-04 20:48:05,005][01523] Num frames 6100... +[2025-01-04 20:48:05,130][01523] Num frames 6200... +[2025-01-04 20:48:05,254][01523] Num frames 6300... +[2025-01-04 20:48:05,375][01523] Num frames 6400... +[2025-01-04 20:48:05,495][01523] Num frames 6500... +[2025-01-04 20:48:05,617][01523] Num frames 6600... +[2025-01-04 20:48:05,742][01523] Num frames 6700... +[2025-01-04 20:48:05,868][01523] Num frames 6800... +[2025-01-04 20:48:05,993][01523] Num frames 6900... +[2025-01-04 20:48:06,124][01523] Num frames 7000... +[2025-01-04 20:48:06,246][01523] Num frames 7100... +[2025-01-04 20:48:06,369][01523] Num frames 7200... +[2025-01-04 20:48:06,487][01523] Num frames 7300... +[2025-01-04 20:48:06,626][01523] Avg episode rewards: #0: 23.384, true rewards: #0: 10.527 +[2025-01-04 20:48:06,629][01523] Avg episode reward: 23.384, avg true_objective: 10.527 +[2025-01-04 20:48:06,670][01523] Num frames 7400... +[2025-01-04 20:48:06,809][01523] Num frames 7500... +[2025-01-04 20:48:06,927][01523] Num frames 7600... +[2025-01-04 20:48:07,049][01523] Num frames 7700... +[2025-01-04 20:48:07,178][01523] Num frames 7800... +[2025-01-04 20:48:07,255][01523] Avg episode rewards: #0: 21.521, true rewards: #0: 9.771 +[2025-01-04 20:48:07,257][01523] Avg episode reward: 21.521, avg true_objective: 9.771 +[2025-01-04 20:48:07,357][01523] Num frames 7900... +[2025-01-04 20:48:07,478][01523] Num frames 8000... +[2025-01-04 20:48:07,596][01523] Num frames 8100... +[2025-01-04 20:48:07,723][01523] Num frames 8200... +[2025-01-04 20:48:07,809][01523] Avg episode rewards: #0: 20.021, true rewards: #0: 9.132 +[2025-01-04 20:48:07,811][01523] Avg episode reward: 20.021, avg true_objective: 9.132 +[2025-01-04 20:48:07,913][01523] Num frames 8300... +[2025-01-04 20:48:08,043][01523] Num frames 8400... +[2025-01-04 20:48:08,172][01523] Num frames 8500... +[2025-01-04 20:48:08,296][01523] Num frames 8600... +[2025-01-04 20:48:08,415][01523] Num frames 8700... +[2025-01-04 20:48:08,539][01523] Num frames 8800... +[2025-01-04 20:48:08,660][01523] Num frames 8900... +[2025-01-04 20:48:08,788][01523] Avg episode rewards: #0: 19.355, true rewards: #0: 8.955 +[2025-01-04 20:48:08,790][01523] Avg episode reward: 19.355, avg true_objective: 8.955 +[2025-01-04 20:48:59,972][01523] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2025-01-04 20:50:42,512][01523] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2025-01-04 20:50:42,514][01523] Overriding arg 'num_workers' with value 1 passed from command line +[2025-01-04 20:50:42,516][01523] Adding new argument 'no_render'=True that is not in the saved config file! +[2025-01-04 20:50:42,518][01523] Adding new argument 'save_video'=True that is not in the saved config file! +[2025-01-04 20:50:42,520][01523] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2025-01-04 20:50:42,522][01523] Adding new argument 'video_name'=None that is not in the saved config file! +[2025-01-04 20:50:42,523][01523] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2025-01-04 20:50:42,525][01523] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2025-01-04 20:50:42,526][01523] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2025-01-04 20:50:42,527][01523] Adding new argument 'hf_repository'='RafaelJaime/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2025-01-04 20:50:42,528][01523] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2025-01-04 20:50:42,529][01523] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2025-01-04 20:50:42,530][01523] Adding new argument 'train_script'=None that is not in the saved config file! +[2025-01-04 20:50:42,531][01523] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2025-01-04 20:50:42,533][01523] Using frameskip 1 and render_action_repeat=4 for evaluation +[2025-01-04 20:50:42,561][01523] RunningMeanStd input shape: (3, 72, 128) +[2025-01-04 20:50:42,564][01523] RunningMeanStd input shape: (1,) +[2025-01-04 20:50:42,576][01523] ConvEncoder: input_channels=3 +[2025-01-04 20:50:42,613][01523] Conv encoder output size: 512 +[2025-01-04 20:50:42,614][01523] Policy head output size: 512 +[2025-01-04 20:50:42,634][01523] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2025-01-04 20:50:43,073][01523] Num frames 100... +[2025-01-04 20:50:43,192][01523] Num frames 200... +[2025-01-04 20:50:43,321][01523] Num frames 300... +[2025-01-04 20:50:43,446][01523] Num frames 400... +[2025-01-04 20:50:43,566][01523] Num frames 500... +[2025-01-04 20:50:43,686][01523] Num frames 600... +[2025-01-04 20:50:43,817][01523] Num frames 700... +[2025-01-04 20:50:43,941][01523] Num frames 800... +[2025-01-04 20:50:44,064][01523] Num frames 900... +[2025-01-04 20:50:44,182][01523] Num frames 1000... +[2025-01-04 20:50:44,304][01523] Num frames 1100... +[2025-01-04 20:50:44,432][01523] Num frames 1200... +[2025-01-04 20:50:44,555][01523] Num frames 1300... +[2025-01-04 20:50:44,678][01523] Num frames 1400... +[2025-01-04 20:50:44,809][01523] Num frames 1500... +[2025-01-04 20:50:44,909][01523] Avg episode rewards: #0: 36.360, true rewards: #0: 15.360 +[2025-01-04 20:50:44,911][01523] Avg episode reward: 36.360, avg true_objective: 15.360 +[2025-01-04 20:50:44,997][01523] Num frames 1600... +[2025-01-04 20:50:45,116][01523] Num frames 1700... +[2025-01-04 20:50:45,238][01523] Num frames 1800... +[2025-01-04 20:50:45,356][01523] Num frames 1900... +[2025-01-04 20:50:45,480][01523] Num frames 2000... +[2025-01-04 20:50:45,599][01523] Num frames 2100... +[2025-01-04 20:50:45,722][01523] Num frames 2200... +[2025-01-04 20:50:45,852][01523] Num frames 2300... +[2025-01-04 20:50:45,983][01523] Num frames 2400... +[2025-01-04 20:50:46,109][01523] Num frames 2500... +[2025-01-04 20:50:46,230][01523] Num frames 2600... +[2025-01-04 20:50:46,315][01523] Avg episode rewards: #0: 29.620, true rewards: #0: 13.120 +[2025-01-04 20:50:46,318][01523] Avg episode reward: 29.620, avg true_objective: 13.120 +[2025-01-04 20:50:46,420][01523] Num frames 2700... +[2025-01-04 20:50:46,597][01523] Num frames 2800... +[2025-01-04 20:50:46,773][01523] Num frames 2900... +[2025-01-04 20:50:46,952][01523] Num frames 3000... +[2025-01-04 20:50:47,117][01523] Num frames 3100... +[2025-01-04 20:50:47,283][01523] Num frames 3200... +[2025-01-04 20:50:47,444][01523] Num frames 3300... +[2025-01-04 20:50:47,609][01523] Num frames 3400... +[2025-01-04 20:50:47,759][01523] Avg episode rewards: #0: 24.853, true rewards: #0: 11.520 +[2025-01-04 20:50:47,762][01523] Avg episode reward: 24.853, avg true_objective: 11.520 +[2025-01-04 20:50:47,845][01523] Num frames 3500... +[2025-01-04 20:50:48,023][01523] Num frames 3600... +[2025-01-04 20:50:48,193][01523] Num frames 3700... +[2025-01-04 20:50:48,369][01523] Num frames 3800... +[2025-01-04 20:50:48,543][01523] Num frames 3900... +[2025-01-04 20:50:48,718][01523] Num frames 4000... +[2025-01-04 20:50:48,891][01523] Num frames 4100... +[2025-01-04 20:50:49,021][01523] Num frames 4200... +[2025-01-04 20:50:49,147][01523] Num frames 4300... +[2025-01-04 20:50:49,269][01523] Num frames 4400... +[2025-01-04 20:50:49,399][01523] Num frames 4500... +[2025-01-04 20:50:49,519][01523] Num frames 4600... +[2025-01-04 20:50:49,661][01523] Avg episode rewards: #0: 25.430, true rewards: #0: 11.680 +[2025-01-04 20:50:49,663][01523] Avg episode reward: 25.430, avg true_objective: 11.680 +[2025-01-04 20:50:49,701][01523] Num frames 4700... +[2025-01-04 20:50:49,830][01523] Num frames 4800... +[2025-01-04 20:50:49,953][01523] Num frames 4900... +[2025-01-04 20:50:50,083][01523] Num frames 5000... +[2025-01-04 20:50:50,204][01523] Num frames 5100... +[2025-01-04 20:50:50,327][01523] Num frames 5200... +[2025-01-04 20:50:50,448][01523] Num frames 5300... +[2025-01-04 20:50:50,570][01523] Num frames 5400... +[2025-01-04 20:50:50,696][01523] Num frames 5500... +[2025-01-04 20:50:50,822][01523] Num frames 5600... +[2025-01-04 20:50:50,942][01523] Num frames 5700... +[2025-01-04 20:50:51,073][01523] Num frames 5800... +[2025-01-04 20:50:51,204][01523] Num frames 5900... +[2025-01-04 20:50:51,327][01523] Num frames 6000... +[2025-01-04 20:50:51,448][01523] Num frames 6100... +[2025-01-04 20:50:51,567][01523] Num frames 6200... +[2025-01-04 20:50:51,690][01523] Num frames 6300... +[2025-01-04 20:50:51,821][01523] Num frames 6400... +[2025-01-04 20:50:51,955][01523] Num frames 6500... +[2025-01-04 20:50:52,087][01523] Num frames 6600... +[2025-01-04 20:50:52,215][01523] Avg episode rewards: #0: 31.512, true rewards: #0: 13.312 +[2025-01-04 20:50:52,216][01523] Avg episode reward: 31.512, avg true_objective: 13.312 +[2025-01-04 20:50:52,273][01523] Num frames 6700... +[2025-01-04 20:50:52,397][01523] Num frames 6800... +[2025-01-04 20:50:52,518][01523] Num frames 6900... +[2025-01-04 20:50:52,640][01523] Num frames 7000... +[2025-01-04 20:50:52,774][01523] Num frames 7100... +[2025-01-04 20:50:52,893][01523] Num frames 7200... +[2025-01-04 20:50:53,014][01523] Num frames 7300... +[2025-01-04 20:50:53,140][01523] Num frames 7400... +[2025-01-04 20:50:53,262][01523] Num frames 7500... +[2025-01-04 20:50:53,381][01523] Num frames 7600... +[2025-01-04 20:50:53,456][01523] Avg episode rewards: #0: 29.527, true rewards: #0: 12.693 +[2025-01-04 20:50:53,457][01523] Avg episode reward: 29.527, avg true_objective: 12.693 +[2025-01-04 20:50:53,566][01523] Num frames 7700... +[2025-01-04 20:50:53,685][01523] Num frames 7800... +[2025-01-04 20:50:53,816][01523] Num frames 7900... +[2025-01-04 20:50:53,936][01523] Num frames 8000... +[2025-01-04 20:50:54,061][01523] Num frames 8100... +[2025-01-04 20:50:54,190][01523] Num frames 8200... +[2025-01-04 20:50:54,310][01523] Num frames 8300... +[2025-01-04 20:50:54,435][01523] Num frames 8400... +[2025-01-04 20:50:54,552][01523] Num frames 8500... +[2025-01-04 20:50:54,620][01523] Avg episode rewards: #0: 27.870, true rewards: #0: 12.156 +[2025-01-04 20:50:54,623][01523] Avg episode reward: 27.870, avg true_objective: 12.156 +[2025-01-04 20:50:54,741][01523] Num frames 8600... +[2025-01-04 20:50:54,872][01523] Num frames 8700... +[2025-01-04 20:50:54,996][01523] Num frames 8800... +[2025-01-04 20:50:55,117][01523] Num frames 8900... +[2025-01-04 20:50:55,252][01523] Avg episode rewards: #0: 25.446, true rewards: #0: 11.196 +[2025-01-04 20:50:55,254][01523] Avg episode reward: 25.446, avg true_objective: 11.196 +[2025-01-04 20:50:55,311][01523] Num frames 9000... +[2025-01-04 20:50:55,433][01523] Num frames 9100... +[2025-01-04 20:50:55,557][01523] Num frames 9200... +[2025-01-04 20:50:55,682][01523] Num frames 9300... +[2025-01-04 20:50:55,815][01523] Num frames 9400... +[2025-01-04 20:50:55,939][01523] Num frames 9500... +[2025-01-04 20:50:56,061][01523] Num frames 9600... +[2025-01-04 20:50:56,197][01523] Num frames 9700... +[2025-01-04 20:50:56,322][01523] Num frames 9800... +[2025-01-04 20:50:56,405][01523] Avg episode rewards: #0: 24.357, true rewards: #0: 10.912 +[2025-01-04 20:50:56,407][01523] Avg episode reward: 24.357, avg true_objective: 10.912 +[2025-01-04 20:50:56,503][01523] Num frames 9900... +[2025-01-04 20:50:56,628][01523] Num frames 10000... +[2025-01-04 20:50:56,756][01523] Num frames 10100... +[2025-01-04 20:50:56,883][01523] Num frames 10200... +[2025-01-04 20:50:57,007][01523] Num frames 10300... +[2025-01-04 20:50:57,128][01523] Num frames 10400... +[2025-01-04 20:50:57,202][01523] Avg episode rewards: #0: 23.114, true rewards: #0: 10.414 +[2025-01-04 20:50:57,205][01523] Avg episode reward: 23.114, avg true_objective: 10.414 +[2025-01-04 20:51:56,028][01523] Replay video saved to /content/train_dir/default_experiment/replay.mp4!