| [2024-08-15 13:11:28,399][3168197] Saving configuration to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json... | |
| [2024-08-15 13:11:28,399][3168197] Rollout worker 0 uses device cpu | |
| [2024-08-15 13:11:28,400][3168197] Rollout worker 1 uses device cpu | |
| [2024-08-15 13:11:28,400][3168197] Rollout worker 2 uses device cpu | |
| [2024-08-15 13:11:28,400][3168197] Rollout worker 3 uses device cpu | |
| [2024-08-15 13:11:28,400][3168197] Rollout worker 4 uses device cpu | |
| [2024-08-15 13:11:28,401][3168197] Rollout worker 5 uses device cpu | |
| [2024-08-15 13:11:28,401][3168197] Rollout worker 6 uses device cpu | |
| [2024-08-15 13:11:28,401][3168197] Rollout worker 7 uses device cpu | |
| [2024-08-15 13:11:28,429][3168197] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-08-15 13:11:28,430][3168197] InferenceWorker_p0-w0: min num requests: 2 | |
| [2024-08-15 13:11:28,446][3168197] Starting all processes... | |
| [2024-08-15 13:11:28,446][3168197] Starting process learner_proc0 | |
| [2024-08-15 13:11:28,496][3168197] Starting all processes... | |
| [2024-08-15 13:11:28,501][3168197] Starting process inference_proc0-0 | |
| [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc0 | |
| [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc1 | |
| [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc2 | |
| [2024-08-15 13:11:28,501][3168197] Starting process rollout_proc3 | |
| [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc4 | |
| [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc5 | |
| [2024-08-15 13:11:28,502][3168197] Starting process rollout_proc6 | |
| [2024-08-15 13:11:28,504][3168197] Starting process rollout_proc7 | |
| [2024-08-15 13:11:29,293][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-08-15 13:11:29,293][3172197] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2024-08-15 13:11:29,303][3172197] Num visible devices: 1 | |
| [2024-08-15 13:11:29,331][3172197] Starting seed is not provided | |
| [2024-08-15 13:11:29,331][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-08-15 13:11:29,331][3172197] Initializing actor-critic model on device cuda:0 | |
| [2024-08-15 13:11:29,331][3172197] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-08-15 13:11:29,331][3172197] RunningMeanStd input shape: (1,) | |
| [2024-08-15 13:11:29,338][3172197] ConvEncoder: input_channels=3 | |
| [2024-08-15 13:11:29,345][3172212] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,374][3172218] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,377][3172210] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,391][3172211] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-08-15 13:11:29,392][3172211] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2024-08-15 13:11:29,402][3172211] Num visible devices: 1 | |
| [2024-08-15 13:11:29,403][3172197] Conv encoder output size: 512 | |
| [2024-08-15 13:11:29,403][3172197] Policy head output size: 512 | |
| [2024-08-15 13:11:29,407][3172217] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,408][3172216] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,412][3172197] Created Actor Critic model with architecture: | |
| [2024-08-15 13:11:29,412][3172197] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2024-08-15 13:11:29,413][3172213] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,426][3172214] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:29,540][3172215] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] | |
| [2024-08-15 13:11:30,026][3172197] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2024-08-15 13:11:30,026][3172197] No checkpoints found | |
| [2024-08-15 13:11:30,026][3172197] Did not load from checkpoint, starting from scratch! | |
| [2024-08-15 13:11:30,027][3172197] Initialized policy 0 weights for model version 0 | |
| [2024-08-15 13:11:30,028][3172197] LearnerWorker_p0 finished initialization! | |
| [2024-08-15 13:11:30,028][3172197] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-08-15 13:11:30,065][3172211] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-08-15 13:11:30,066][3172211] RunningMeanStd input shape: (1,) | |
| [2024-08-15 13:11:30,072][3172211] ConvEncoder: input_channels=3 | |
| [2024-08-15 13:11:30,113][3172211] Conv encoder output size: 512 | |
| [2024-08-15 13:11:30,113][3172211] Policy head output size: 512 | |
| [2024-08-15 13:11:30,625][3168197] Inference worker 0-0 is ready! | |
| [2024-08-15 13:11:30,626][3168197] All inference workers are ready! Signal rollout workers to start! | |
| [2024-08-15 13:11:30,640][3172210] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,640][3172216] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,641][3172214] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,641][3172213] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,641][3172217] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,641][3172215] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,641][3172212] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:30,643][3172218] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:11:31,104][3172215] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,107][3172210] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,108][3172217] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,108][3172218] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,109][3172212] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,109][3172216] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,111][3172213] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,306][3172213] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,311][3172215] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,312][3172216] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,314][3172210] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,346][3172214] Decorrelating experience for 0 frames... | |
| [2024-08-15 13:11:31,404][3172217] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,511][3172213] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,513][3172212] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,535][3172214] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,544][3172215] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,588][3172218] Decorrelating experience for 32 frames... | |
| [2024-08-15 13:11:31,636][3172217] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,736][3172216] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,742][3172214] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,761][3172213] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:31,766][3172212] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,771][3172215] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:31,799][3172218] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,859][3172217] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:31,945][3172210] Decorrelating experience for 64 frames... | |
| [2024-08-15 13:11:31,976][3172212] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:31,987][3172218] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:31,990][3172216] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:32,058][3172214] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:32,076][3168197] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-08-15 13:11:32,299][3172210] Decorrelating experience for 96 frames... | |
| [2024-08-15 13:11:32,370][3172197] Signal inference workers to stop experience collection... | |
| [2024-08-15 13:11:32,372][3172211] InferenceWorker_p0-w0: stopping experience collection | |
| [2024-08-15 13:11:33,006][3172197] Signal inference workers to resume experience collection... | |
| [2024-08-15 13:11:33,006][3172211] InferenceWorker_p0-w0: resuming experience collection | |
| [2024-08-15 13:11:34,056][3172211] Updated weights for policy 0, policy_version 10 (0.0154) | |
| [2024-08-15 13:11:34,925][3172211] Updated weights for policy 0, policy_version 20 (0.0004) | |
| [2024-08-15 13:11:35,796][3172211] Updated weights for policy 0, policy_version 30 (0.0004) | |
| [2024-08-15 13:11:36,649][3172211] Updated weights for policy 0, policy_version 40 (0.0004) | |
| [2024-08-15 13:11:37,076][3168197] Fps is (10 sec: 36045.0, 60 sec: 36045.0, 300 sec: 36045.0). Total num frames: 180224. Throughput: 0: 8297.2. Samples: 41486. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:11:37,077][3168197] Avg episode reward: [(0, '4.445')] | |
| [2024-08-15 13:11:37,088][3172197] Saving new best policy, reward=4.445! | |
| [2024-08-15 13:11:37,537][3172211] Updated weights for policy 0, policy_version 50 (0.0004) | |
| [2024-08-15 13:11:38,389][3172211] Updated weights for policy 0, policy_version 60 (0.0004) | |
| [2024-08-15 13:11:39,274][3172211] Updated weights for policy 0, policy_version 70 (0.0004) | |
| [2024-08-15 13:11:40,124][3172211] Updated weights for policy 0, policy_version 80 (0.0004) | |
| [2024-08-15 13:11:40,985][3172211] Updated weights for policy 0, policy_version 90 (0.0004) | |
| [2024-08-15 13:11:41,854][3172211] Updated weights for policy 0, policy_version 100 (0.0004) | |
| [2024-08-15 13:11:42,076][3168197] Fps is (10 sec: 41778.8, 60 sec: 41778.8, 300 sec: 41778.8). Total num frames: 417792. Throughput: 0: 7677.9. Samples: 76780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-08-15 13:11:42,077][3168197] Avg episode reward: [(0, '4.514')] | |
| [2024-08-15 13:11:42,078][3172197] Saving new best policy, reward=4.514! | |
| [2024-08-15 13:11:42,747][3172211] Updated weights for policy 0, policy_version 110 (0.0004) | |
| [2024-08-15 13:11:43,616][3172211] Updated weights for policy 0, policy_version 120 (0.0004) | |
| [2024-08-15 13:11:44,492][3172211] Updated weights for policy 0, policy_version 130 (0.0004) | |
| [2024-08-15 13:11:45,375][3172211] Updated weights for policy 0, policy_version 140 (0.0003) | |
| [2024-08-15 13:11:46,255][3172211] Updated weights for policy 0, policy_version 150 (0.0004) | |
| [2024-08-15 13:11:47,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 43417.6, 300 sec: 43417.6). Total num frames: 651264. Throughput: 0: 9817.6. Samples: 147264. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) | |
| [2024-08-15 13:11:47,077][3168197] Avg episode reward: [(0, '4.628')] | |
| [2024-08-15 13:11:47,079][3172197] Saving new best policy, reward=4.628! | |
| [2024-08-15 13:11:47,140][3172211] Updated weights for policy 0, policy_version 160 (0.0004) | |
| [2024-08-15 13:11:48,013][3172211] Updated weights for policy 0, policy_version 170 (0.0004) | |
| [2024-08-15 13:11:48,423][3168197] Heartbeat connected on Batcher_0 | |
| [2024-08-15 13:11:48,426][3168197] Heartbeat connected on LearnerWorker_p0 | |
| [2024-08-15 13:11:48,431][3168197] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2024-08-15 13:11:48,433][3168197] Heartbeat connected on RolloutWorker_w0 | |
| [2024-08-15 13:11:48,436][3168197] Heartbeat connected on RolloutWorker_w1 | |
| [2024-08-15 13:11:48,437][3168197] Heartbeat connected on RolloutWorker_w2 | |
| [2024-08-15 13:11:48,440][3168197] Heartbeat connected on RolloutWorker_w4 | |
| [2024-08-15 13:11:48,441][3168197] Heartbeat connected on RolloutWorker_w3 | |
| [2024-08-15 13:11:48,442][3168197] Heartbeat connected on RolloutWorker_w5 | |
| [2024-08-15 13:11:48,443][3168197] Heartbeat connected on RolloutWorker_w6 | |
| [2024-08-15 13:11:48,446][3168197] Heartbeat connected on RolloutWorker_w7 | |
| [2024-08-15 13:11:48,895][3172211] Updated weights for policy 0, policy_version 180 (0.0004) | |
| [2024-08-15 13:11:49,765][3172211] Updated weights for policy 0, policy_version 190 (0.0004) | |
| [2024-08-15 13:11:50,636][3172211] Updated weights for policy 0, policy_version 200 (0.0003) | |
| [2024-08-15 13:11:51,502][3172211] Updated weights for policy 0, policy_version 210 (0.0003) | |
| [2024-08-15 13:11:52,076][3168197] Fps is (10 sec: 46695.0, 60 sec: 44236.8, 300 sec: 44236.8). Total num frames: 884736. Throughput: 0: 10870.5. Samples: 217410. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) | |
| [2024-08-15 13:11:52,077][3168197] Avg episode reward: [(0, '4.880')] | |
| [2024-08-15 13:11:52,078][3172197] Saving new best policy, reward=4.880! | |
| [2024-08-15 13:11:52,396][3172211] Updated weights for policy 0, policy_version 220 (0.0004) | |
| [2024-08-15 13:11:53,249][3172211] Updated weights for policy 0, policy_version 230 (0.0003) | |
| [2024-08-15 13:11:54,116][3172211] Updated weights for policy 0, policy_version 240 (0.0003) | |
| [2024-08-15 13:11:54,974][3172211] Updated weights for policy 0, policy_version 250 (0.0004) | |
| [2024-08-15 13:11:55,824][3172211] Updated weights for policy 0, policy_version 260 (0.0003) | |
| [2024-08-15 13:11:56,706][3172211] Updated weights for policy 0, policy_version 270 (0.0004) | |
| [2024-08-15 13:11:57,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 44892.1, 300 sec: 44892.1). Total num frames: 1122304. Throughput: 0: 10109.1. Samples: 252728. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:11:57,077][3168197] Avg episode reward: [(0, '5.626')] | |
| [2024-08-15 13:11:57,079][3172197] Saving new best policy, reward=5.626! | |
| [2024-08-15 13:11:57,573][3172211] Updated weights for policy 0, policy_version 280 (0.0003) | |
| [2024-08-15 13:11:58,444][3172211] Updated weights for policy 0, policy_version 290 (0.0004) | |
| [2024-08-15 13:11:59,315][3172211] Updated weights for policy 0, policy_version 300 (0.0004) | |
| [2024-08-15 13:12:00,181][3172211] Updated weights for policy 0, policy_version 310 (0.0004) | |
| [2024-08-15 13:12:01,066][3172211] Updated weights for policy 0, policy_version 320 (0.0003) | |
| [2024-08-15 13:12:01,926][3172211] Updated weights for policy 0, policy_version 330 (0.0003) | |
| [2024-08-15 13:12:02,076][3168197] Fps is (10 sec: 47103.8, 60 sec: 45192.5, 300 sec: 45192.5). Total num frames: 1355776. Throughput: 0: 10783.3. Samples: 323498. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) | |
| [2024-08-15 13:12:02,077][3168197] Avg episode reward: [(0, '6.828')] | |
| [2024-08-15 13:12:02,078][3172197] Saving new best policy, reward=6.828! | |
| [2024-08-15 13:12:02,830][3172211] Updated weights for policy 0, policy_version 340 (0.0004) | |
| [2024-08-15 13:12:03,696][3172211] Updated weights for policy 0, policy_version 350 (0.0003) | |
| [2024-08-15 13:12:04,564][3172211] Updated weights for policy 0, policy_version 360 (0.0004) | |
| [2024-08-15 13:12:05,482][3172211] Updated weights for policy 0, policy_version 370 (0.0004) | |
| [2024-08-15 13:12:06,361][3172211] Updated weights for policy 0, policy_version 380 (0.0004) | |
| [2024-08-15 13:12:07,076][3168197] Fps is (10 sec: 46694.8, 60 sec: 45407.1, 300 sec: 45407.1). Total num frames: 1589248. Throughput: 0: 11232.9. Samples: 393152. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:12:07,077][3168197] Avg episode reward: [(0, '10.695')] | |
| [2024-08-15 13:12:07,079][3172197] Saving new best policy, reward=10.695! | |
| [2024-08-15 13:12:07,245][3172211] Updated weights for policy 0, policy_version 390 (0.0004) | |
| [2024-08-15 13:12:08,131][3172211] Updated weights for policy 0, policy_version 400 (0.0004) | |
| [2024-08-15 13:12:08,993][3172211] Updated weights for policy 0, policy_version 410 (0.0003) | |
| [2024-08-15 13:12:09,852][3172211] Updated weights for policy 0, policy_version 420 (0.0003) | |
| [2024-08-15 13:12:10,727][3172211] Updated weights for policy 0, policy_version 430 (0.0004) | |
| [2024-08-15 13:12:11,589][3172211] Updated weights for policy 0, policy_version 440 (0.0004) | |
| [2024-08-15 13:12:12,076][3168197] Fps is (10 sec: 46694.6, 60 sec: 45568.0, 300 sec: 45568.0). Total num frames: 1822720. Throughput: 0: 10705.9. Samples: 428234. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:12:12,077][3168197] Avg episode reward: [(0, '12.163')] | |
| [2024-08-15 13:12:12,078][3172197] Saving new best policy, reward=12.163! | |
| [2024-08-15 13:12:12,460][3172211] Updated weights for policy 0, policy_version 450 (0.0003) | |
| [2024-08-15 13:12:13,334][3172211] Updated weights for policy 0, policy_version 460 (0.0003) | |
| [2024-08-15 13:12:14,198][3172211] Updated weights for policy 0, policy_version 470 (0.0003) | |
| [2024-08-15 13:12:15,069][3172211] Updated weights for policy 0, policy_version 480 (0.0004) | |
| [2024-08-15 13:12:15,946][3172211] Updated weights for policy 0, policy_version 490 (0.0004) | |
| [2024-08-15 13:12:16,823][3172211] Updated weights for policy 0, policy_version 500 (0.0004) | |
| [2024-08-15 13:12:17,076][3168197] Fps is (10 sec: 46694.3, 60 sec: 45693.1, 300 sec: 45693.1). Total num frames: 2056192. Throughput: 0: 11089.5. Samples: 499028. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0) | |
| [2024-08-15 13:12:17,077][3168197] Avg episode reward: [(0, '15.741')] | |
| [2024-08-15 13:12:17,084][3172197] Saving new best policy, reward=15.741! | |
| [2024-08-15 13:12:17,704][3172211] Updated weights for policy 0, policy_version 510 (0.0004) | |
| [2024-08-15 13:12:18,575][3172211] Updated weights for policy 0, policy_version 520 (0.0004) | |
| [2024-08-15 13:12:19,455][3172211] Updated weights for policy 0, policy_version 530 (0.0003) | |
| [2024-08-15 13:12:20,333][3172211] Updated weights for policy 0, policy_version 540 (0.0004) | |
| [2024-08-15 13:12:21,193][3172211] Updated weights for policy 0, policy_version 550 (0.0004) | |
| [2024-08-15 13:12:22,059][3172211] Updated weights for policy 0, policy_version 560 (0.0004) | |
| [2024-08-15 13:12:22,076][3168197] Fps is (10 sec: 47103.9, 60 sec: 45875.2, 300 sec: 45875.2). Total num frames: 2293760. Throughput: 0: 11723.2. Samples: 569028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-08-15 13:12:22,077][3168197] Avg episode reward: [(0, '17.828')] | |
| [2024-08-15 13:12:22,078][3172197] Saving new best policy, reward=17.828! | |
| [2024-08-15 13:12:22,951][3172211] Updated weights for policy 0, policy_version 570 (0.0004) | |
| [2024-08-15 13:12:23,809][3172211] Updated weights for policy 0, policy_version 580 (0.0004) | |
| [2024-08-15 13:12:24,688][3172211] Updated weights for policy 0, policy_version 590 (0.0004) | |
| [2024-08-15 13:12:25,572][3172211] Updated weights for policy 0, policy_version 600 (0.0004) | |
| [2024-08-15 13:12:26,449][3172211] Updated weights for policy 0, policy_version 610 (0.0004) | |
| [2024-08-15 13:12:27,076][3168197] Fps is (10 sec: 47103.5, 60 sec: 45949.6, 300 sec: 45949.6). Total num frames: 2527232. Throughput: 0: 11717.0. Samples: 604044. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:12:27,077][3168197] Avg episode reward: [(0, '18.732')] | |
| [2024-08-15 13:12:27,079][3172197] Saving new best policy, reward=18.732! | |
| [2024-08-15 13:12:27,346][3172211] Updated weights for policy 0, policy_version 620 (0.0004) | |
| [2024-08-15 13:12:28,185][3172211] Updated weights for policy 0, policy_version 630 (0.0003) | |
| [2024-08-15 13:12:29,080][3172211] Updated weights for policy 0, policy_version 640 (0.0004) | |
| [2024-08-15 13:12:29,961][3172211] Updated weights for policy 0, policy_version 650 (0.0003) | |
| [2024-08-15 13:12:30,833][3172211] Updated weights for policy 0, policy_version 660 (0.0004) | |
| [2024-08-15 13:12:31,705][3172211] Updated weights for policy 0, policy_version 670 (0.0004) | |
| [2024-08-15 13:12:32,076][3168197] Fps is (10 sec: 46693.9, 60 sec: 46011.7, 300 sec: 46011.7). Total num frames: 2760704. Throughput: 0: 11712.9. Samples: 674344. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2024-08-15 13:12:32,077][3168197] Avg episode reward: [(0, '18.633')] | |
| [2024-08-15 13:12:32,592][3172211] Updated weights for policy 0, policy_version 680 (0.0004) | |
| [2024-08-15 13:12:33,478][3172211] Updated weights for policy 0, policy_version 690 (0.0004) | |
| [2024-08-15 13:12:34,345][3172211] Updated weights for policy 0, policy_version 700 (0.0003) | |
| [2024-08-15 13:12:35,215][3172211] Updated weights for policy 0, policy_version 710 (0.0003) | |
| [2024-08-15 13:12:36,082][3172211] Updated weights for policy 0, policy_version 720 (0.0004) | |
| [2024-08-15 13:12:36,960][3172211] Updated weights for policy 0, policy_version 730 (0.0003) | |
| [2024-08-15 13:12:37,076][3168197] Fps is (10 sec: 46694.7, 60 sec: 46899.1, 300 sec: 46064.2). Total num frames: 2994176. Throughput: 0: 11715.3. Samples: 744598. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) | |
| [2024-08-15 13:12:37,077][3168197] Avg episode reward: [(0, '20.341')] | |
| [2024-08-15 13:12:37,079][3172197] Saving new best policy, reward=20.341! | |
| [2024-08-15 13:12:37,841][3172211] Updated weights for policy 0, policy_version 740 (0.0004) | |
| [2024-08-15 13:12:38,688][3172211] Updated weights for policy 0, policy_version 750 (0.0004) | |
| [2024-08-15 13:12:39,546][3172211] Updated weights for policy 0, policy_version 760 (0.0004) | |
| [2024-08-15 13:12:40,411][3172211] Updated weights for policy 0, policy_version 770 (0.0004) | |
| [2024-08-15 13:12:41,294][3172211] Updated weights for policy 0, policy_version 780 (0.0004) | |
| [2024-08-15 13:12:42,076][3168197] Fps is (10 sec: 46694.6, 60 sec: 46831.0, 300 sec: 46109.2). Total num frames: 3227648. Throughput: 0: 11714.5. Samples: 779880. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-08-15 13:12:42,077][3168197] Avg episode reward: [(0, '22.969')] | |
| [2024-08-15 13:12:42,086][3172197] Saving new best policy, reward=22.969! | |
| [2024-08-15 13:12:42,178][3172211] Updated weights for policy 0, policy_version 790 (0.0004) | |
| [2024-08-15 13:12:43,053][3172211] Updated weights for policy 0, policy_version 800 (0.0004) | |
| [2024-08-15 13:12:43,939][3172211] Updated weights for policy 0, policy_version 810 (0.0004) | |
| [2024-08-15 13:12:44,819][3172211] Updated weights for policy 0, policy_version 820 (0.0003) | |
| [2024-08-15 13:12:45,699][3172211] Updated weights for policy 0, policy_version 830 (0.0004) | |
| [2024-08-15 13:12:46,556][3172211] Updated weights for policy 0, policy_version 840 (0.0004) | |
| [2024-08-15 13:12:47,076][3168197] Fps is (10 sec: 46694.4, 60 sec: 46830.9, 300 sec: 46148.2). Total num frames: 3461120. Throughput: 0: 11700.8. Samples: 850036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-08-15 13:12:47,077][3168197] Avg episode reward: [(0, '22.828')] | |
| [2024-08-15 13:12:47,432][3172211] Updated weights for policy 0, policy_version 850 (0.0003) | |
| [2024-08-15 13:12:48,292][3172211] Updated weights for policy 0, policy_version 860 (0.0004) | |
| [2024-08-15 13:12:49,167][3172211] Updated weights for policy 0, policy_version 870 (0.0003) | |
| [2024-08-15 13:12:50,038][3172211] Updated weights for policy 0, policy_version 880 (0.0003) | |
| [2024-08-15 13:12:50,900][3172211] Updated weights for policy 0, policy_version 890 (0.0004) | |
| [2024-08-15 13:12:51,758][3172211] Updated weights for policy 0, policy_version 900 (0.0004) | |
| [2024-08-15 13:12:52,076][3168197] Fps is (10 sec: 47103.7, 60 sec: 46899.1, 300 sec: 46233.5). Total num frames: 3698688. Throughput: 0: 11723.1. Samples: 920692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-08-15 13:12:52,077][3168197] Avg episode reward: [(0, '25.759')] | |
| [2024-08-15 13:12:52,078][3172197] Saving new best policy, reward=25.759! | |
| [2024-08-15 13:12:52,639][3172211] Updated weights for policy 0, policy_version 910 (0.0004) | |
| [2024-08-15 13:12:53,552][3172211] Updated weights for policy 0, policy_version 920 (0.0004) | |
| [2024-08-15 13:12:54,413][3172211] Updated weights for policy 0, policy_version 930 (0.0003) | |
| [2024-08-15 13:12:55,282][3172211] Updated weights for policy 0, policy_version 940 (0.0003) | |
| [2024-08-15 13:12:56,165][3172211] Updated weights for policy 0, policy_version 950 (0.0004) | |
| [2024-08-15 13:12:57,048][3172211] Updated weights for policy 0, policy_version 960 (0.0004) | |
| [2024-08-15 13:12:57,076][3168197] Fps is (10 sec: 47104.1, 60 sec: 46831.0, 300 sec: 46260.7). Total num frames: 3932160. Throughput: 0: 11717.8. Samples: 955536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-08-15 13:12:57,077][3168197] Avg episode reward: [(0, '25.022')] | |
| [2024-08-15 13:12:57,924][3172211] Updated weights for policy 0, policy_version 970 (0.0004) | |
| [2024-08-15 13:12:58,621][3172197] Stopping Batcher_0... | |
| [2024-08-15 13:12:58,621][3172197] Saving /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-08-15 13:12:58,621][3168197] Component Batcher_0 stopped! | |
| [2024-08-15 13:12:58,622][3172197] Loop batcher_evt_loop terminating... | |
| [2024-08-15 13:12:58,628][3172211] Weights refcount: 2 0 | |
| [2024-08-15 13:12:58,628][3172211] Stopping InferenceWorker_p0-w0... | |
| [2024-08-15 13:12:58,629][3172211] Loop inference_proc0-0_evt_loop terminating... | |
| [2024-08-15 13:12:58,629][3168197] Component InferenceWorker_p0-w0 stopped! | |
| [2024-08-15 13:12:58,650][3172197] Saving /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-08-15 13:12:58,693][3172197] Stopping LearnerWorker_p0... | |
| [2024-08-15 13:12:58,693][3172197] Loop learner_proc0_evt_loop terminating... | |
| [2024-08-15 13:12:58,693][3168197] Component LearnerWorker_p0 stopped! | |
| [2024-08-15 13:12:58,754][3172213] Stopping RolloutWorker_w2... | |
| [2024-08-15 13:12:58,754][3172216] Stopping RolloutWorker_w5... | |
| [2024-08-15 13:12:58,755][3172213] Loop rollout_proc2_evt_loop terminating... | |
| [2024-08-15 13:12:58,755][3172216] Loop rollout_proc5_evt_loop terminating... | |
| [2024-08-15 13:12:58,754][3168197] Component RolloutWorker_w2 stopped! | |
| [2024-08-15 13:12:58,755][3168197] Component RolloutWorker_w5 stopped! | |
| [2024-08-15 13:12:58,758][3172215] Stopping RolloutWorker_w3... | |
| [2024-08-15 13:12:58,758][3172214] Stopping RolloutWorker_w4... | |
| [2024-08-15 13:12:58,759][3172214] Loop rollout_proc4_evt_loop terminating... | |
| [2024-08-15 13:12:58,759][3172215] Loop rollout_proc3_evt_loop terminating... | |
| [2024-08-15 13:12:58,758][3168197] Component RolloutWorker_w3 stopped! | |
| [2024-08-15 13:12:58,759][3168197] Component RolloutWorker_w4 stopped! | |
| [2024-08-15 13:12:58,762][3172217] Stopping RolloutWorker_w6... | |
| [2024-08-15 13:12:58,763][3172217] Loop rollout_proc6_evt_loop terminating... | |
| [2024-08-15 13:12:58,762][3168197] Component RolloutWorker_w6 stopped! | |
| [2024-08-15 13:12:58,766][3172210] Stopping RolloutWorker_w1... | |
| [2024-08-15 13:12:58,767][3172210] Loop rollout_proc1_evt_loop terminating... | |
| [2024-08-15 13:12:58,767][3168197] Component RolloutWorker_w1 stopped! | |
| [2024-08-15 13:12:58,775][3172212] Stopping RolloutWorker_w0... | |
| [2024-08-15 13:12:58,775][3172218] Stopping RolloutWorker_w7... | |
| [2024-08-15 13:12:58,775][3172218] Loop rollout_proc7_evt_loop terminating... | |
| [2024-08-15 13:12:58,775][3172212] Loop rollout_proc0_evt_loop terminating... | |
| [2024-08-15 13:12:58,775][3168197] Component RolloutWorker_w0 stopped! | |
| [2024-08-15 13:12:58,776][3168197] Component RolloutWorker_w7 stopped! | |
| [2024-08-15 13:12:58,777][3168197] Waiting for process learner_proc0 to stop... | |
| [2024-08-15 13:12:59,139][3168197] Waiting for process inference_proc0-0 to join... | |
| [2024-08-15 13:12:59,140][3168197] Waiting for process rollout_proc0 to join... | |
| [2024-08-15 13:12:59,140][3168197] Waiting for process rollout_proc1 to join... | |
| [2024-08-15 13:12:59,141][3168197] Waiting for process rollout_proc2 to join... | |
| [2024-08-15 13:12:59,141][3168197] Waiting for process rollout_proc3 to join... | |
| [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc4 to join... | |
| [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc5 to join... | |
| [2024-08-15 13:12:59,142][3168197] Waiting for process rollout_proc6 to join... | |
| [2024-08-15 13:12:59,143][3168197] Waiting for process rollout_proc7 to join... | |
| [2024-08-15 13:12:59,143][3168197] Batcher 0 profile tree view: | |
| batching: 10.6741, releasing_batches: 0.0124 | |
| [2024-08-15 13:12:59,143][3168197] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 2.1037 | |
| update_model: 1.3475 | |
| weight_update: 0.0004 | |
| one_step: 0.0011 | |
| handle_policy_step: 79.5799 | |
| deserialize: 3.9274, stack: 0.4281, obs_to_device_normalize: 20.3408, forward: 33.8913, send_messages: 4.7144 | |
| prepare_outputs: 13.3851 | |
| to_cpu: 9.1897 | |
| [2024-08-15 13:12:59,144][3168197] Learner 0 profile tree view: | |
| misc: 0.0035, prepare_batch: 4.7486 | |
| train: 11.9903 | |
| epoch_init: 0.0025, minibatch_init: 0.0029, losses_postprocess: 0.1409, kl_divergence: 0.1522, after_optimizer: 2.5395 | |
| calculate_losses: 5.2697 | |
| losses_init: 0.0013, forward_head: 0.5091, bptt_initial: 3.4423, tail: 0.2683, advantages_returns: 0.0777, losses: 0.4859 | |
| bptt: 0.4023 | |
| bptt_forward_core: 0.3841 | |
| update: 3.7039 | |
| clip: 0.4612 | |
| [2024-08-15 13:12:59,144][3168197] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.0762, enqueue_policy_requests: 4.2272, env_step: 45.6476, overhead: 3.0472, complete_rollouts: 0.1297 | |
| save_policy_outputs: 4.6212 | |
| split_output_tensors: 1.6420 | |
| [2024-08-15 13:12:59,144][3168197] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.0735, enqueue_policy_requests: 4.1537, env_step: 45.6444, overhead: 3.0266, complete_rollouts: 0.1277 | |
| save_policy_outputs: 4.6463 | |
| split_output_tensors: 1.6661 | |
| [2024-08-15 13:12:59,144][3168197] Loop Runner_EvtLoop terminating... | |
| [2024-08-15 13:12:59,145][3168197] Runner profile tree view: | |
| main_loop: 90.6988 | |
| [2024-08-15 13:12:59,145][3168197] Collected {0: 4005888}, FPS: 44167.0 | |
| [2024-08-15 13:13:38,128][3168197] Loading existing experiment configuration from /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json | |
| [2024-08-15 13:13:38,129][3168197] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-08-15 13:13:38,130][3168197] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-08-15 13:13:38,130][3168197] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-08-15 13:13:38,130][3168197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-08-15 13:13:38,131][3168197] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-08-15 13:13:38,131][3168197] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-08-15 13:13:38,131][3168197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-08-15 13:13:38,132][3168197] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-08-15 13:13:38,138][3168197] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-08-15 13:13:38,138][3168197] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-08-15 13:13:38,139][3168197] RunningMeanStd input shape: (1,) | |
| [2024-08-15 13:13:38,144][3168197] ConvEncoder: input_channels=3 | |
| [2024-08-15 13:13:38,203][3168197] Conv encoder output size: 512 | |
| [2024-08-15 13:13:38,204][3168197] Policy head output size: 512 | |
| [2024-08-15 13:13:38,771][3168197] Loading state from checkpoint /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-08-15 13:13:39,495][3168197] Num frames 100... | |
| [2024-08-15 13:13:39,536][3168197] Num frames 200... | |
| [2024-08-15 13:13:39,576][3168197] Num frames 300... | |
| [2024-08-15 13:13:39,617][3168197] Num frames 400... | |
| [2024-08-15 13:13:39,657][3168197] Num frames 500... | |
| [2024-08-15 13:13:39,697][3168197] Num frames 600... | |
| [2024-08-15 13:13:39,738][3168197] Num frames 700... | |
| [2024-08-15 13:13:39,780][3168197] Num frames 800... | |
| [2024-08-15 13:13:39,821][3168197] Num frames 900... | |
| [2024-08-15 13:13:39,862][3168197] Num frames 1000... | |
| [2024-08-15 13:13:39,902][3168197] Num frames 1100... | |
| [2024-08-15 13:13:39,944][3168197] Num frames 1200... | |
| [2024-08-15 13:13:39,985][3168197] Num frames 1300... | |
| [2024-08-15 13:13:40,026][3168197] Num frames 1400... | |
| [2024-08-15 13:13:40,067][3168197] Num frames 1500... | |
| [2024-08-15 13:13:40,108][3168197] Num frames 1600... | |
| [2024-08-15 13:13:40,149][3168197] Num frames 1700... | |
| [2024-08-15 13:13:40,190][3168197] Num frames 1800... | |
| [2024-08-15 13:13:40,232][3168197] Num frames 1900... | |
| [2024-08-15 13:13:40,273][3168197] Num frames 2000... | |
| [2024-08-15 13:13:40,325][3168197] Num frames 2100... | |
| [2024-08-15 13:13:40,376][3168197] Avg episode rewards: #0: 55.999, true rewards: #0: 21.000 | |
| [2024-08-15 13:13:40,377][3168197] Avg episode reward: 55.999, avg true_objective: 21.000 | |
| [2024-08-15 13:13:40,419][3168197] Num frames 2200... | |
| [2024-08-15 13:13:40,460][3168197] Num frames 2300... | |
| [2024-08-15 13:13:40,501][3168197] Num frames 2400... | |
| [2024-08-15 13:13:40,542][3168197] Num frames 2500... | |
| [2024-08-15 13:13:40,583][3168197] Num frames 2600... | |
| [2024-08-15 13:13:40,667][3168197] Avg episode rewards: #0: 32.379, true rewards: #0: 13.380 | |
| [2024-08-15 13:13:40,667][3168197] Avg episode reward: 32.379, avg true_objective: 13.380 | |
| [2024-08-15 13:13:40,678][3168197] Num frames 2700... | |
| [2024-08-15 13:13:40,719][3168197] Num frames 2800... | |
| [2024-08-15 13:13:40,760][3168197] Num frames 2900... | |
| [2024-08-15 13:13:40,800][3168197] Num frames 3000... | |
| [2024-08-15 13:13:40,840][3168197] Num frames 3100... | |
| [2024-08-15 13:13:40,880][3168197] Num frames 3200... | |
| [2024-08-15 13:13:40,921][3168197] Num frames 3300... | |
| [2024-08-15 13:13:40,961][3168197] Num frames 3400... | |
| [2024-08-15 13:13:41,001][3168197] Num frames 3500... | |
| [2024-08-15 13:13:41,042][3168197] Num frames 3600... | |
| [2024-08-15 13:13:41,083][3168197] Num frames 3700... | |
| [2024-08-15 13:13:41,123][3168197] Num frames 3800... | |
| [2024-08-15 13:13:41,163][3168197] Num frames 3900... | |
| [2024-08-15 13:13:41,247][3168197] Avg episode rewards: #0: 32.593, true rewards: #0: 13.260 | |
| [2024-08-15 13:13:41,248][3168197] Avg episode reward: 32.593, avg true_objective: 13.260 | |
| [2024-08-15 13:13:41,259][3168197] Num frames 4000... | |
| [2024-08-15 13:13:41,299][3168197] Num frames 4100... | |
| [2024-08-15 13:13:41,339][3168197] Num frames 4200... | |
| [2024-08-15 13:13:41,379][3168197] Num frames 4300... | |
| [2024-08-15 13:13:41,420][3168197] Num frames 4400... | |
| [2024-08-15 13:13:41,460][3168197] Num frames 4500... | |
| [2024-08-15 13:13:41,500][3168197] Num frames 4600... | |
| [2024-08-15 13:13:41,540][3168197] Num frames 4700... | |
| [2024-08-15 13:13:41,579][3168197] Num frames 4800... | |
| [2024-08-15 13:13:41,640][3168197] Avg episode rewards: #0: 29.050, true rewards: #0: 12.050 | |
| [2024-08-15 13:13:41,640][3168197] Avg episode reward: 29.050, avg true_objective: 12.050 | |
| [2024-08-15 13:13:41,674][3168197] Num frames 4900... | |
| [2024-08-15 13:13:41,714][3168197] Num frames 5000... | |
| [2024-08-15 13:13:41,754][3168197] Num frames 5100... | |
| [2024-08-15 13:13:41,794][3168197] Num frames 5200... | |
| [2024-08-15 13:13:41,835][3168197] Num frames 5300... | |
| [2024-08-15 13:13:41,875][3168197] Num frames 5400... | |
| [2024-08-15 13:13:41,915][3168197] Num frames 5500... | |
| [2024-08-15 13:13:41,956][3168197] Num frames 5600... | |
| [2024-08-15 13:13:41,996][3168197] Num frames 5700... | |
| [2024-08-15 13:13:42,039][3168197] Num frames 5800... | |
| [2024-08-15 13:13:42,111][3168197] Avg episode rewards: #0: 27.694, true rewards: #0: 11.694 | |
| [2024-08-15 13:13:42,112][3168197] Avg episode reward: 27.694, avg true_objective: 11.694 | |
| [2024-08-15 13:13:42,135][3168197] Num frames 5900... | |
| [2024-08-15 13:13:42,178][3168197] Num frames 6000... | |
| [2024-08-15 13:13:42,220][3168197] Num frames 6100... | |
| [2024-08-15 13:13:42,296][3168197] Avg episode rewards: #0: 23.923, true rewards: #0: 10.257 | |
| [2024-08-15 13:13:42,297][3168197] Avg episode reward: 23.923, avg true_objective: 10.257 | |
| [2024-08-15 13:13:42,317][3168197] Num frames 6200... | |
| [2024-08-15 13:13:42,359][3168197] Num frames 6300... | |
| [2024-08-15 13:13:42,402][3168197] Num frames 6400... | |
| [2024-08-15 13:13:42,444][3168197] Num frames 6500... | |
| [2024-08-15 13:13:42,487][3168197] Num frames 6600... | |
| [2024-08-15 13:13:42,530][3168197] Num frames 6700... | |
| [2024-08-15 13:13:42,595][3168197] Avg episode rewards: #0: 21.900, true rewards: #0: 9.614 | |
| [2024-08-15 13:13:42,595][3168197] Avg episode reward: 21.900, avg true_objective: 9.614 | |
| [2024-08-15 13:13:42,625][3168197] Num frames 6800... | |
| [2024-08-15 13:13:42,667][3168197] Num frames 6900... | |
| [2024-08-15 13:13:42,710][3168197] Num frames 7000... | |
| [2024-08-15 13:13:42,789][3168197] Avg episode rewards: #0: 19.827, true rewards: #0: 8.827 | |
| [2024-08-15 13:13:42,790][3168197] Avg episode reward: 19.827, avg true_objective: 8.827 | |
| [2024-08-15 13:13:42,807][3168197] Num frames 7100... | |
| [2024-08-15 13:13:42,850][3168197] Num frames 7200... | |
| [2024-08-15 13:13:42,892][3168197] Num frames 7300... | |
| [2024-08-15 13:13:42,935][3168197] Num frames 7400... | |
| [2024-08-15 13:13:42,993][3168197] Avg episode rewards: #0: 18.127, true rewards: #0: 8.238 | |
| [2024-08-15 13:13:42,994][3168197] Avg episode reward: 18.127, avg true_objective: 8.238 | |
| [2024-08-15 13:13:43,031][3168197] Num frames 7500... | |
| [2024-08-15 13:13:43,074][3168197] Num frames 7600... | |
| [2024-08-15 13:13:43,116][3168197] Num frames 7700... | |
| [2024-08-15 13:13:43,159][3168197] Num frames 7800... | |
| [2024-08-15 13:13:43,201][3168197] Num frames 7900... | |
| [2024-08-15 13:13:43,245][3168197] Num frames 8000... | |
| [2024-08-15 13:13:43,288][3168197] Num frames 8100... | |
| [2024-08-15 13:13:43,331][3168197] Num frames 8200... | |
| [2024-08-15 13:13:43,403][3168197] Avg episode rewards: #0: 17.846, true rewards: #0: 8.246 | |
| [2024-08-15 13:13:43,403][3168197] Avg episode reward: 17.846, avg true_objective: 8.246 | |
| [2024-08-15 13:13:51,561][3168197] Replay video saved to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/replay.mp4! | |
| [2024-08-15 13:16:21,918][3168197] Loading existing experiment configuration from /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/config.json | |
| [2024-08-15 13:16:21,919][3168197] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-08-15 13:16:21,919][3168197] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-08-15 13:16:21,919][3168197] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-08-15 13:16:21,919][3168197] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-08-15 13:16:21,919][3168197] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-08-15 13:16:21,920][3168197] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-08-15 13:16:21,920][3168197] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-08-15 13:16:21,920][3168197] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-08-15 13:16:21,920][3168197] Adding new argument 'hf_repository'='ToonAga/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-08-15 13:16:21,921][3168197] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-08-15 13:16:21,921][3168197] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-08-15 13:16:21,921][3168197] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-08-15 13:16:21,921][3168197] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-08-15 13:16:21,921][3168197] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-08-15 13:16:21,927][3168197] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-08-15 13:16:21,927][3168197] RunningMeanStd input shape: (1,) | |
| [2024-08-15 13:16:21,932][3168197] ConvEncoder: input_channels=3 | |
| [2024-08-15 13:16:21,946][3168197] Conv encoder output size: 512 | |
| [2024-08-15 13:16:21,946][3168197] Policy head output size: 512 | |
| [2024-08-15 13:16:21,972][3168197] Loading state from checkpoint /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-08-15 13:16:22,484][3168197] Num frames 100... | |
| [2024-08-15 13:16:22,524][3168197] Num frames 200... | |
| [2024-08-15 13:16:22,563][3168197] Num frames 300... | |
| [2024-08-15 13:16:22,604][3168197] Num frames 400... | |
| [2024-08-15 13:16:22,643][3168197] Num frames 500... | |
| [2024-08-15 13:16:22,699][3168197] Avg episode rewards: #0: 11.100, true rewards: #0: 5.100 | |
| [2024-08-15 13:16:22,700][3168197] Avg episode reward: 11.100, avg true_objective: 5.100 | |
| [2024-08-15 13:16:22,737][3168197] Num frames 600... | |
| [2024-08-15 13:16:22,776][3168197] Num frames 700... | |
| [2024-08-15 13:16:22,815][3168197] Num frames 800... | |
| [2024-08-15 13:16:22,854][3168197] Num frames 900... | |
| [2024-08-15 13:16:22,893][3168197] Num frames 1000... | |
| [2024-08-15 13:16:22,932][3168197] Num frames 1100... | |
| [2024-08-15 13:16:22,972][3168197] Num frames 1200... | |
| [2024-08-15 13:16:23,030][3168197] Avg episode rewards: #0: 13.070, true rewards: #0: 6.070 | |
| [2024-08-15 13:16:23,030][3168197] Avg episode reward: 13.070, avg true_objective: 6.070 | |
| [2024-08-15 13:16:23,066][3168197] Num frames 1300... | |
| [2024-08-15 13:16:23,105][3168197] Num frames 1400... | |
| [2024-08-15 13:16:23,145][3168197] Num frames 1500... | |
| [2024-08-15 13:16:23,186][3168197] Num frames 1600... | |
| [2024-08-15 13:16:23,227][3168197] Num frames 1700... | |
| [2024-08-15 13:16:23,268][3168197] Num frames 1800... | |
| [2024-08-15 13:16:23,307][3168197] Num frames 1900... | |
| [2024-08-15 13:16:23,347][3168197] Num frames 2000... | |
| [2024-08-15 13:16:23,387][3168197] Num frames 2100... | |
| [2024-08-15 13:16:23,426][3168197] Num frames 2200... | |
| [2024-08-15 13:16:23,465][3168197] Num frames 2300... | |
| [2024-08-15 13:16:23,539][3168197] Avg episode rewards: #0: 17.513, true rewards: #0: 7.847 | |
| [2024-08-15 13:16:23,540][3168197] Avg episode reward: 17.513, avg true_objective: 7.847 | |
| [2024-08-15 13:16:23,559][3168197] Num frames 2400... | |
| [2024-08-15 13:16:23,598][3168197] Num frames 2500... | |
| [2024-08-15 13:16:23,638][3168197] Num frames 2600... | |
| [2024-08-15 13:16:23,677][3168197] Num frames 2700... | |
| [2024-08-15 13:16:23,716][3168197] Num frames 2800... | |
| [2024-08-15 13:16:23,756][3168197] Num frames 2900... | |
| [2024-08-15 13:16:23,795][3168197] Num frames 3000... | |
| [2024-08-15 13:16:23,835][3168197] Num frames 3100... | |
| [2024-08-15 13:16:23,911][3168197] Avg episode rewards: #0: 18.403, true rewards: #0: 7.902 | |
| [2024-08-15 13:16:23,912][3168197] Avg episode reward: 18.403, avg true_objective: 7.902 | |
| [2024-08-15 13:16:23,928][3168197] Num frames 3200... | |
| [2024-08-15 13:16:23,967][3168197] Num frames 3300... | |
| [2024-08-15 13:16:24,006][3168197] Num frames 3400... | |
| [2024-08-15 13:16:24,046][3168197] Num frames 3500... | |
| [2024-08-15 13:16:24,085][3168197] Num frames 3600... | |
| [2024-08-15 13:16:24,125][3168197] Num frames 3700... | |
| [2024-08-15 13:16:24,165][3168197] Num frames 3800... | |
| [2024-08-15 13:16:24,206][3168197] Num frames 3900... | |
| [2024-08-15 13:16:24,246][3168197] Num frames 4000... | |
| [2024-08-15 13:16:24,287][3168197] Num frames 4100... | |
| [2024-08-15 13:16:24,329][3168197] Num frames 4200... | |
| [2024-08-15 13:16:24,370][3168197] Num frames 4300... | |
| [2024-08-15 13:16:24,409][3168197] Num frames 4400... | |
| [2024-08-15 13:16:24,449][3168197] Num frames 4500... | |
| [2024-08-15 13:16:24,489][3168197] Num frames 4600... | |
| [2024-08-15 13:16:24,528][3168197] Num frames 4700... | |
| [2024-08-15 13:16:24,569][3168197] Num frames 4800... | |
| [2024-08-15 13:16:24,623][3168197] Num frames 4900... | |
| [2024-08-15 13:16:24,664][3168197] Num frames 5000... | |
| [2024-08-15 13:16:24,704][3168197] Num frames 5100... | |
| [2024-08-15 13:16:24,743][3168197] Num frames 5200... | |
| [2024-08-15 13:16:24,820][3168197] Avg episode rewards: #0: 25.322, true rewards: #0: 10.522 | |
| [2024-08-15 13:16:24,821][3168197] Avg episode reward: 25.322, avg true_objective: 10.522 | |
| [2024-08-15 13:16:24,837][3168197] Num frames 5300... | |
| [2024-08-15 13:16:24,877][3168197] Num frames 5400... | |
| [2024-08-15 13:16:24,916][3168197] Num frames 5500... | |
| [2024-08-15 13:16:24,955][3168197] Num frames 5600... | |
| [2024-08-15 13:16:24,995][3168197] Num frames 5700... | |
| [2024-08-15 13:16:25,037][3168197] Num frames 5800... | |
| [2024-08-15 13:16:25,077][3168197] Num frames 5900... | |
| [2024-08-15 13:16:25,117][3168197] Num frames 6000... | |
| [2024-08-15 13:16:25,157][3168197] Num frames 6100... | |
| [2024-08-15 13:16:25,196][3168197] Num frames 6200... | |
| [2024-08-15 13:16:25,235][3168197] Num frames 6300... | |
| [2024-08-15 13:16:25,311][3168197] Avg episode rewards: #0: 25.598, true rewards: #0: 10.598 | |
| [2024-08-15 13:16:25,311][3168197] Avg episode reward: 25.598, avg true_objective: 10.598 | |
| [2024-08-15 13:16:25,330][3168197] Num frames 6400... | |
| [2024-08-15 13:16:25,372][3168197] Num frames 6500... | |
| [2024-08-15 13:16:25,411][3168197] Num frames 6600... | |
| [2024-08-15 13:16:25,450][3168197] Num frames 6700... | |
| [2024-08-15 13:16:25,490][3168197] Num frames 6800... | |
| [2024-08-15 13:16:25,529][3168197] Num frames 6900... | |
| [2024-08-15 13:16:25,569][3168197] Num frames 7000... | |
| [2024-08-15 13:16:25,633][3168197] Avg episode rewards: #0: 23.759, true rewards: #0: 10.044 | |
| [2024-08-15 13:16:25,634][3168197] Avg episode reward: 23.759, avg true_objective: 10.044 | |
| [2024-08-15 13:16:25,663][3168197] Num frames 7100... | |
| [2024-08-15 13:16:25,703][3168197] Num frames 7200... | |
| [2024-08-15 13:16:25,791][3168197] Avg episode rewards: #0: 21.109, true rewards: #0: 9.109 | |
| [2024-08-15 13:16:25,792][3168197] Avg episode reward: 21.109, avg true_objective: 9.109 | |
| [2024-08-15 13:16:25,799][3168197] Num frames 7300... | |
| [2024-08-15 13:16:25,839][3168197] Num frames 7400... | |
| [2024-08-15 13:16:25,880][3168197] Num frames 7500... | |
| [2024-08-15 13:16:25,920][3168197] Num frames 7600... | |
| [2024-08-15 13:16:25,960][3168197] Num frames 7700... | |
| [2024-08-15 13:16:26,002][3168197] Num frames 7800... | |
| [2024-08-15 13:16:26,043][3168197] Num frames 7900... | |
| [2024-08-15 13:16:26,083][3168197] Num frames 8000... | |
| [2024-08-15 13:16:26,125][3168197] Num frames 8100... | |
| [2024-08-15 13:16:26,166][3168197] Num frames 8200... | |
| [2024-08-15 13:16:26,209][3168197] Num frames 8300... | |
| [2024-08-15 13:16:26,279][3168197] Avg episode rewards: #0: 21.382, true rewards: #0: 9.271 | |
| [2024-08-15 13:16:26,279][3168197] Avg episode reward: 21.382, avg true_objective: 9.271 | |
| [2024-08-15 13:16:26,305][3168197] Num frames 8400... | |
| [2024-08-15 13:16:26,347][3168197] Num frames 8500... | |
| [2024-08-15 13:16:26,391][3168197] Num frames 8600... | |
| [2024-08-15 13:16:26,435][3168197] Num frames 8700... | |
| [2024-08-15 13:16:26,478][3168197] Num frames 8800... | |
| [2024-08-15 13:16:26,522][3168197] Num frames 8900... | |
| [2024-08-15 13:16:26,563][3168197] Num frames 9000... | |
| [2024-08-15 13:16:26,605][3168197] Num frames 9100... | |
| [2024-08-15 13:16:26,646][3168197] Num frames 9200... | |
| [2024-08-15 13:16:26,690][3168197] Num frames 9300... | |
| [2024-08-15 13:16:26,731][3168197] Num frames 9400... | |
| [2024-08-15 13:16:26,796][3168197] Avg episode rewards: #0: 21.732, true rewards: #0: 9.432 | |
| [2024-08-15 13:16:26,797][3168197] Avg episode reward: 21.732, avg true_objective: 9.432 | |
| [2024-08-15 13:16:35,950][3168197] Replay video saved to /home/aa/Documents/GitHub/RL-hugging_face/unit8/train_dir/default_experiment/replay.mp4! | |