| [2025-01-15 14:26:06,217][00319] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2025-01-15 14:26:06,224][00319] Rollout worker 0 uses device cpu | |
| [2025-01-15 14:26:06,227][00319] Rollout worker 1 uses device cpu | |
| [2025-01-15 14:26:06,229][00319] Rollout worker 2 uses device cpu | |
| [2025-01-15 14:26:06,231][00319] Rollout worker 3 uses device cpu | |
| [2025-01-15 14:26:06,233][00319] Rollout worker 4 uses device cpu | |
| [2025-01-15 14:26:06,235][00319] Rollout worker 5 uses device cpu | |
| [2025-01-15 14:26:06,237][00319] Rollout worker 6 uses device cpu | |
| [2025-01-15 14:26:06,240][00319] Rollout worker 7 uses device cpu | |
| [2025-01-15 14:26:06,423][00319] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-15 14:26:06,426][00319] InferenceWorker_p0-w0: min num requests: 2 | |
| [2025-01-15 14:26:06,470][00319] Starting all processes... | |
| [2025-01-15 14:26:06,473][00319] Starting process learner_proc0 | |
| [2025-01-15 14:26:06,535][00319] Starting all processes... | |
| [2025-01-15 14:26:06,592][00319] Starting process inference_proc0-0 | |
| [2025-01-15 14:26:06,593][00319] Starting process rollout_proc0 | |
| [2025-01-15 14:26:06,595][00319] Starting process rollout_proc1 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc2 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc3 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc4 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc5 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc6 | |
| [2025-01-15 14:26:06,598][00319] Starting process rollout_proc7 | |
| [2025-01-15 14:26:24,019][01020] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-15 14:26:24,019][01020] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2025-01-15 14:26:24,073][01020] Num visible devices: 1 | |
| [2025-01-15 14:26:24,134][01020] Starting seed is not provided | |
| [2025-01-15 14:26:24,134][01020] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-15 14:26:24,135][01020] Initializing actor-critic model on device cuda:0 | |
| [2025-01-15 14:26:24,137][01020] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-15 14:26:24,141][01020] RunningMeanStd input shape: (1,) | |
| [2025-01-15 14:26:24,203][01020] ConvEncoder: input_channels=3 | |
| [2025-01-15 14:26:24,479][01040] Worker 4 uses CPU cores [0] | |
| [2025-01-15 14:26:24,740][01037] Worker 0 uses CPU cores [0] | |
| [2025-01-15 14:26:24,747][01042] Worker 6 uses CPU cores [0] | |
| [2025-01-15 14:26:24,789][01038] Worker 3 uses CPU cores [1] | |
| [2025-01-15 14:26:24,792][01036] Worker 1 uses CPU cores [1] | |
| [2025-01-15 14:26:24,818][01043] Worker 7 uses CPU cores [1] | |
| [2025-01-15 14:26:24,827][01041] Worker 5 uses CPU cores [1] | |
| [2025-01-15 14:26:24,853][01039] Worker 2 uses CPU cores [0] | |
| [2025-01-15 14:26:24,864][01035] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-15 14:26:24,864][01035] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2025-01-15 14:26:24,884][01035] Num visible devices: 1 | |
| [2025-01-15 14:26:24,910][01020] Conv encoder output size: 512 | |
| [2025-01-15 14:26:24,911][01020] Policy head output size: 512 | |
| [2025-01-15 14:26:24,978][01020] Created Actor Critic model with architecture: | |
| [2025-01-15 14:26:24,978][01020] 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) | |
| ) | |
| ) | |
| [2025-01-15 14:26:25,304][01020] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2025-01-15 14:26:26,413][00319] Heartbeat connected on Batcher_0 | |
| [2025-01-15 14:26:26,424][00319] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2025-01-15 14:26:26,435][00319] Heartbeat connected on RolloutWorker_w0 | |
| [2025-01-15 14:26:26,440][00319] Heartbeat connected on RolloutWorker_w1 | |
| [2025-01-15 14:26:26,450][00319] Heartbeat connected on RolloutWorker_w3 | |
| [2025-01-15 14:26:26,452][00319] Heartbeat connected on RolloutWorker_w2 | |
| [2025-01-15 14:26:26,458][00319] Heartbeat connected on RolloutWorker_w4 | |
| [2025-01-15 14:26:26,462][00319] Heartbeat connected on RolloutWorker_w5 | |
| [2025-01-15 14:26:26,468][00319] Heartbeat connected on RolloutWorker_w6 | |
| [2025-01-15 14:26:26,472][00319] Heartbeat connected on RolloutWorker_w7 | |
| [2025-01-15 14:26:28,661][01020] No checkpoints found | |
| [2025-01-15 14:26:28,661][01020] Did not load from checkpoint, starting from scratch! | |
| [2025-01-15 14:26:28,662][01020] Initialized policy 0 weights for model version 0 | |
| [2025-01-15 14:26:28,666][01020] LearnerWorker_p0 finished initialization! | |
| [2025-01-15 14:26:28,668][01020] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-01-15 14:26:28,668][00319] Heartbeat connected on LearnerWorker_p0 | |
| [2025-01-15 14:26:28,763][01035] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-15 14:26:28,765][01035] RunningMeanStd input shape: (1,) | |
| [2025-01-15 14:26:28,778][01035] ConvEncoder: input_channels=3 | |
| [2025-01-15 14:26:28,880][01035] Conv encoder output size: 512 | |
| [2025-01-15 14:26:28,880][01035] Policy head output size: 512 | |
| [2025-01-15 14:26:28,933][00319] Inference worker 0-0 is ready! | |
| [2025-01-15 14:26:28,935][00319] All inference workers are ready! Signal rollout workers to start! | |
| [2025-01-15 14:26:29,150][01040] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,151][01037] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,152][01042] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,153][01039] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,165][01036] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,166][01041] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,167][01038] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,168][01043] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:26:29,871][01041] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:30,392][01039] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:30,390][01040] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:30,396][01037] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:30,547][00319] 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) | |
| [2025-01-15 14:26:30,767][01041] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:30,805][01036] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:31,126][01040] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:31,136][01039] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:31,625][01038] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:31,849][01036] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:32,152][01041] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:32,452][01037] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:32,451][01042] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:32,836][01040] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:33,256][01038] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:33,351][01039] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:33,589][01042] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:33,678][01036] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:33,800][01041] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:34,020][01043] Decorrelating experience for 0 frames... | |
| [2025-01-15 14:26:34,828][01037] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:35,192][01039] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:35,548][00319] 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) | |
| [2025-01-15 14:26:35,587][01040] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:35,740][01043] Decorrelating experience for 32 frames... | |
| [2025-01-15 14:26:35,877][01036] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:38,325][01042] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:38,883][01043] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:39,232][01037] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:40,547][00319] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 79.0. Samples: 790. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-15 14:26:40,554][00319] Avg episode reward: [(0, '2.184')] | |
| [2025-01-15 14:26:42,864][01038] Decorrelating experience for 64 frames... | |
| [2025-01-15 14:26:43,626][01020] Signal inference workers to stop experience collection... | |
| [2025-01-15 14:26:43,636][01035] InferenceWorker_p0-w0: stopping experience collection | |
| [2025-01-15 14:26:44,020][01042] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:44,208][01038] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:44,567][01043] Decorrelating experience for 96 frames... | |
| [2025-01-15 14:26:45,547][00319] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 193.7. Samples: 2906. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-01-15 14:26:45,550][00319] Avg episode reward: [(0, '3.321')] | |
| [2025-01-15 14:26:45,918][01020] Signal inference workers to resume experience collection... | |
| [2025-01-15 14:26:45,920][01035] InferenceWorker_p0-w0: resuming experience collection | |
| [2025-01-15 14:26:50,548][00319] Fps is (10 sec: 2867.1, 60 sec: 1433.6, 300 sec: 1433.6). Total num frames: 28672. Throughput: 0: 360.9. Samples: 7218. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:26:50,550][00319] Avg episode reward: [(0, '3.774')] | |
| [2025-01-15 14:26:54,601][01035] Updated weights for policy 0, policy_version 10 (0.0030) | |
| [2025-01-15 14:26:55,547][00319] Fps is (10 sec: 4096.0, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 40960. Throughput: 0: 394.2. Samples: 9856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:26:55,551][00319] Avg episode reward: [(0, '4.134')] | |
| [2025-01-15 14:27:00,548][00319] Fps is (10 sec: 2867.2, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 57344. Throughput: 0: 464.5. Samples: 13936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:27:00,554][00319] Avg episode reward: [(0, '4.416')] | |
| [2025-01-15 14:27:05,547][00319] Fps is (10 sec: 3686.4, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 579.4. Samples: 20280. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:05,551][00319] Avg episode reward: [(0, '4.450')] | |
| [2025-01-15 14:27:05,734][01035] Updated weights for policy 0, policy_version 20 (0.0018) | |
| [2025-01-15 14:27:10,548][00319] Fps is (10 sec: 4505.6, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 595.1. Samples: 23806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:10,557][00319] Avg episode reward: [(0, '4.476')] | |
| [2025-01-15 14:27:10,568][01020] Saving new best policy, reward=4.476! | |
| [2025-01-15 14:27:15,548][00319] Fps is (10 sec: 4095.9, 60 sec: 2639.6, 300 sec: 2639.6). Total num frames: 118784. Throughput: 0: 650.4. Samples: 29270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:15,552][00319] Avg episode reward: [(0, '4.329')] | |
| [2025-01-15 14:27:16,927][01035] Updated weights for policy 0, policy_version 30 (0.0037) | |
| [2025-01-15 14:27:20,548][00319] Fps is (10 sec: 3276.8, 60 sec: 2703.3, 300 sec: 2703.3). Total num frames: 135168. Throughput: 0: 757.5. Samples: 34088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:27:20,555][00319] Avg episode reward: [(0, '4.299')] | |
| [2025-01-15 14:27:25,547][00319] Fps is (10 sec: 4096.1, 60 sec: 2904.4, 300 sec: 2904.4). Total num frames: 159744. Throughput: 0: 819.8. Samples: 37682. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2025-01-15 14:27:25,553][00319] Avg episode reward: [(0, '4.481')] | |
| [2025-01-15 14:27:25,559][01020] Saving new best policy, reward=4.481! | |
| [2025-01-15 14:27:26,405][01035] Updated weights for policy 0, policy_version 40 (0.0027) | |
| [2025-01-15 14:27:30,547][00319] Fps is (10 sec: 4505.7, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 180224. Throughput: 0: 927.0. Samples: 44620. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:27:30,552][00319] Avg episode reward: [(0, '4.494')] | |
| [2025-01-15 14:27:30,565][01020] Saving new best policy, reward=4.494! | |
| [2025-01-15 14:27:35,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 2961.7). Total num frames: 192512. Throughput: 0: 925.6. Samples: 48868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:35,551][00319] Avg episode reward: [(0, '4.568')] | |
| [2025-01-15 14:27:35,555][01020] Saving new best policy, reward=4.568! | |
| [2025-01-15 14:27:38,142][01035] Updated weights for policy 0, policy_version 50 (0.0023) | |
| [2025-01-15 14:27:40,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3042.7). Total num frames: 212992. Throughput: 0: 927.6. Samples: 51596. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:40,550][00319] Avg episode reward: [(0, '4.362')] | |
| [2025-01-15 14:27:45,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3167.6). Total num frames: 237568. Throughput: 0: 998.9. Samples: 58886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:27:45,550][00319] Avg episode reward: [(0, '4.199')] | |
| [2025-01-15 14:27:46,719][01035] Updated weights for policy 0, policy_version 60 (0.0015) | |
| [2025-01-15 14:27:50,549][00319] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3174.3). Total num frames: 253952. Throughput: 0: 985.3. Samples: 64618. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:27:50,554][00319] Avg episode reward: [(0, '4.307')] | |
| [2025-01-15 14:27:55,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3180.4). Total num frames: 270336. Throughput: 0: 954.7. Samples: 66766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:27:55,550][00319] Avg episode reward: [(0, '4.514')] | |
| [2025-01-15 14:27:58,428][01035] Updated weights for policy 0, policy_version 70 (0.0041) | |
| [2025-01-15 14:28:00,547][00319] Fps is (10 sec: 4096.6, 60 sec: 3959.5, 300 sec: 3276.8). Total num frames: 294912. Throughput: 0: 971.3. Samples: 72980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:28:00,550][00319] Avg episode reward: [(0, '4.586')] | |
| [2025-01-15 14:28:00,557][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth... | |
| [2025-01-15 14:28:00,678][01020] Saving new best policy, reward=4.586! | |
| [2025-01-15 14:28:05,550][00319] Fps is (10 sec: 4913.9, 60 sec: 4027.6, 300 sec: 3362.9). Total num frames: 319488. Throughput: 0: 1022.5. Samples: 80102. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:28:05,555][00319] Avg episode reward: [(0, '4.393')] | |
| [2025-01-15 14:28:08,234][01035] Updated weights for policy 0, policy_version 80 (0.0025) | |
| [2025-01-15 14:28:10,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3317.8). Total num frames: 331776. Throughput: 0: 994.3. Samples: 82426. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:28:10,553][00319] Avg episode reward: [(0, '4.356')] | |
| [2025-01-15 14:28:15,547][00319] Fps is (10 sec: 3277.6, 60 sec: 3891.2, 300 sec: 3354.8). Total num frames: 352256. Throughput: 0: 944.1. Samples: 87104. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:28:15,550][00319] Avg episode reward: [(0, '4.479')] | |
| [2025-01-15 14:28:18,782][01035] Updated weights for policy 0, policy_version 90 (0.0025) | |
| [2025-01-15 14:28:20,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.8, 300 sec: 3425.7). Total num frames: 376832. Throughput: 0: 1009.6. Samples: 94302. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:28:20,551][00319] Avg episode reward: [(0, '4.553')] | |
| [2025-01-15 14:28:25,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3454.9). Total num frames: 397312. Throughput: 0: 1029.2. Samples: 97910. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:28:25,553][00319] Avg episode reward: [(0, '4.770')] | |
| [2025-01-15 14:28:25,558][01020] Saving new best policy, reward=4.770! | |
| [2025-01-15 14:28:29,767][01035] Updated weights for policy 0, policy_version 100 (0.0017) | |
| [2025-01-15 14:28:30,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3413.3). Total num frames: 409600. Throughput: 0: 965.1. Samples: 102316. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:28:30,554][00319] Avg episode reward: [(0, '4.890')] | |
| [2025-01-15 14:28:30,561][01020] Saving new best policy, reward=4.890! | |
| [2025-01-15 14:28:35,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3440.6). Total num frames: 430080. Throughput: 0: 963.4. Samples: 107968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:28:35,552][00319] Avg episode reward: [(0, '4.588')] | |
| [2025-01-15 14:28:39,408][01035] Updated weights for policy 0, policy_version 110 (0.0027) | |
| [2025-01-15 14:28:40,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3497.4). Total num frames: 454656. Throughput: 0: 993.2. Samples: 111460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:28:40,551][00319] Avg episode reward: [(0, '4.622')] | |
| [2025-01-15 14:28:45,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3489.2). Total num frames: 471040. Throughput: 0: 994.3. Samples: 117724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:28:45,552][00319] Avg episode reward: [(0, '4.585')] | |
| [2025-01-15 14:28:50,548][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.3, 300 sec: 3481.6). Total num frames: 487424. Throughput: 0: 932.1. Samples: 122042. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:28:50,557][00319] Avg episode reward: [(0, '4.683')] | |
| [2025-01-15 14:28:51,406][01035] Updated weights for policy 0, policy_version 120 (0.0049) | |
| [2025-01-15 14:28:55,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3531.0). Total num frames: 512000. Throughput: 0: 954.5. Samples: 125378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:28:55,551][00319] Avg episode reward: [(0, '4.827')] | |
| [2025-01-15 14:28:59,843][01035] Updated weights for policy 0, policy_version 130 (0.0015) | |
| [2025-01-15 14:29:00,549][00319] Fps is (10 sec: 4504.7, 60 sec: 3959.3, 300 sec: 3549.8). Total num frames: 532480. Throughput: 0: 1008.1. Samples: 132472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:00,554][00319] Avg episode reward: [(0, '4.696')] | |
| [2025-01-15 14:29:05,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3541.1). Total num frames: 548864. Throughput: 0: 960.7. Samples: 137532. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:05,554][00319] Avg episode reward: [(0, '5.027')] | |
| [2025-01-15 14:29:05,556][01020] Saving new best policy, reward=5.027! | |
| [2025-01-15 14:29:10,547][00319] Fps is (10 sec: 3277.5, 60 sec: 3891.2, 300 sec: 3532.8). Total num frames: 565248. Throughput: 0: 928.0. Samples: 139670. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:10,555][00319] Avg episode reward: [(0, '5.043')] | |
| [2025-01-15 14:29:10,563][01020] Saving new best policy, reward=5.043! | |
| [2025-01-15 14:29:11,729][01035] Updated weights for policy 0, policy_version 140 (0.0024) | |
| [2025-01-15 14:29:15,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3959.5, 300 sec: 3574.7). Total num frames: 589824. Throughput: 0: 983.0. Samples: 146552. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:15,554][00319] Avg episode reward: [(0, '4.671')] | |
| [2025-01-15 14:29:20,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3590.0). Total num frames: 610304. Throughput: 0: 1004.7. Samples: 153180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:29:20,551][00319] Avg episode reward: [(0, '4.508')] | |
| [2025-01-15 14:29:21,160][01035] Updated weights for policy 0, policy_version 150 (0.0020) | |
| [2025-01-15 14:29:25,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3581.1). Total num frames: 626688. Throughput: 0: 974.9. Samples: 155330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:29:25,550][00319] Avg episode reward: [(0, '4.704')] | |
| [2025-01-15 14:29:30,548][00319] Fps is (10 sec: 3686.3, 60 sec: 3959.5, 300 sec: 3595.4). Total num frames: 647168. Throughput: 0: 953.7. Samples: 160640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:29:30,555][00319] Avg episode reward: [(0, '4.693')] | |
| [2025-01-15 14:29:32,036][01035] Updated weights for policy 0, policy_version 160 (0.0030) | |
| [2025-01-15 14:29:35,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3631.0). Total num frames: 671744. Throughput: 0: 1020.3. Samples: 167956. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:29:35,556][00319] Avg episode reward: [(0, '4.748')] | |
| [2025-01-15 14:29:40,547][00319] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3621.7). Total num frames: 688128. Throughput: 0: 1017.2. Samples: 171152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:40,554][00319] Avg episode reward: [(0, '4.542')] | |
| [2025-01-15 14:29:42,708][01035] Updated weights for policy 0, policy_version 170 (0.0024) | |
| [2025-01-15 14:29:45,548][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3612.9). Total num frames: 704512. Throughput: 0: 956.0. Samples: 175490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:29:45,550][00319] Avg episode reward: [(0, '4.606')] | |
| [2025-01-15 14:29:50,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3625.0). Total num frames: 724992. Throughput: 0: 992.0. Samples: 182174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:29:50,552][00319] Avg episode reward: [(0, '4.762')] | |
| [2025-01-15 14:29:52,239][01035] Updated weights for policy 0, policy_version 180 (0.0040) | |
| [2025-01-15 14:29:55,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3656.4). Total num frames: 749568. Throughput: 0: 1024.5. Samples: 185772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:29:55,559][00319] Avg episode reward: [(0, '5.036')] | |
| [2025-01-15 14:30:00,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3891.3, 300 sec: 3647.4). Total num frames: 765952. Throughput: 0: 990.3. Samples: 191116. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:30:00,556][00319] Avg episode reward: [(0, '5.109')] | |
| [2025-01-15 14:30:00,572][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000187_765952.pth... | |
| [2025-01-15 14:30:00,754][01020] Saving new best policy, reward=5.109! | |
| [2025-01-15 14:30:03,943][01035] Updated weights for policy 0, policy_version 190 (0.0026) | |
| [2025-01-15 14:30:05,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3638.8). Total num frames: 782336. Throughput: 0: 955.6. Samples: 196184. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:30:05,553][00319] Avg episode reward: [(0, '5.293')] | |
| [2025-01-15 14:30:05,556][01020] Saving new best policy, reward=5.293! | |
| [2025-01-15 14:30:10,548][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3667.8). Total num frames: 806912. Throughput: 0: 984.7. Samples: 199640. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:30:10,553][00319] Avg episode reward: [(0, '5.671')] | |
| [2025-01-15 14:30:10,563][01020] Saving new best policy, reward=5.671! | |
| [2025-01-15 14:30:12,835][01035] Updated weights for policy 0, policy_version 200 (0.0020) | |
| [2025-01-15 14:30:15,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3677.3). Total num frames: 827392. Throughput: 0: 1019.8. Samples: 206532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:30:15,554][00319] Avg episode reward: [(0, '5.620')] | |
| [2025-01-15 14:30:20,547][00319] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3650.8). Total num frames: 839680. Throughput: 0: 950.5. Samples: 210730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:30:20,552][00319] Avg episode reward: [(0, '5.741')] | |
| [2025-01-15 14:30:20,563][01020] Saving new best policy, reward=5.741! | |
| [2025-01-15 14:30:24,619][01035] Updated weights for policy 0, policy_version 210 (0.0027) | |
| [2025-01-15 14:30:25,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3677.7). Total num frames: 864256. Throughput: 0: 941.4. Samples: 213514. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:30:25,550][00319] Avg episode reward: [(0, '5.798')] | |
| [2025-01-15 14:30:25,555][01020] Saving new best policy, reward=5.798! | |
| [2025-01-15 14:30:30,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3686.4). Total num frames: 884736. Throughput: 0: 1001.0. Samples: 220534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:30:30,557][00319] Avg episode reward: [(0, '5.834')] | |
| [2025-01-15 14:30:30,564][01020] Saving new best policy, reward=5.834! | |
| [2025-01-15 14:30:34,405][01035] Updated weights for policy 0, policy_version 220 (0.0024) | |
| [2025-01-15 14:30:35,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3678.0). Total num frames: 901120. Throughput: 0: 976.8. Samples: 226132. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:30:35,551][00319] Avg episode reward: [(0, '6.158')] | |
| [2025-01-15 14:30:35,558][01020] Saving new best policy, reward=6.158! | |
| [2025-01-15 14:30:40,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3670.0). Total num frames: 917504. Throughput: 0: 943.6. Samples: 228232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:30:40,553][00319] Avg episode reward: [(0, '6.248')] | |
| [2025-01-15 14:30:40,563][01020] Saving new best policy, reward=6.248! | |
| [2025-01-15 14:30:45,486][01035] Updated weights for policy 0, policy_version 230 (0.0031) | |
| [2025-01-15 14:30:45,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3694.4). Total num frames: 942080. Throughput: 0: 958.9. Samples: 234268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:30:45,550][00319] Avg episode reward: [(0, '5.973')] | |
| [2025-01-15 14:30:50,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3702.2). Total num frames: 962560. Throughput: 0: 1011.0. Samples: 241678. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:30:50,554][00319] Avg episode reward: [(0, '5.890')] | |
| [2025-01-15 14:30:55,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3694.1). Total num frames: 978944. Throughput: 0: 985.8. Samples: 244000. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-15 14:30:55,555][00319] Avg episode reward: [(0, '5.898')] | |
| [2025-01-15 14:30:56,223][01035] Updated weights for policy 0, policy_version 240 (0.0040) | |
| [2025-01-15 14:31:00,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3686.4). Total num frames: 995328. Throughput: 0: 933.4. Samples: 248534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:31:00,550][00319] Avg episode reward: [(0, '6.219')] | |
| [2025-01-15 14:31:05,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3708.7). Total num frames: 1019904. Throughput: 0: 1003.6. Samples: 255894. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:31:05,551][00319] Avg episode reward: [(0, '6.216')] | |
| [2025-01-15 14:31:05,611][01035] Updated weights for policy 0, policy_version 250 (0.0025) | |
| [2025-01-15 14:31:10,548][00319] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3730.3). Total num frames: 1044480. Throughput: 0: 1021.5. Samples: 259480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:31:10,550][00319] Avg episode reward: [(0, '6.386')] | |
| [2025-01-15 14:31:10,557][01020] Saving new best policy, reward=6.386! | |
| [2025-01-15 14:31:15,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3708.0). Total num frames: 1056768. Throughput: 0: 969.1. Samples: 264142. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:31:15,553][00319] Avg episode reward: [(0, '6.958')] | |
| [2025-01-15 14:31:15,561][01020] Saving new best policy, reward=6.958! | |
| [2025-01-15 14:31:17,485][01035] Updated weights for policy 0, policy_version 260 (0.0015) | |
| [2025-01-15 14:31:20,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3714.6). Total num frames: 1077248. Throughput: 0: 972.9. Samples: 269912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:31:20,557][00319] Avg episode reward: [(0, '6.633')] | |
| [2025-01-15 14:31:25,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3735.0). Total num frames: 1101824. Throughput: 0: 1005.9. Samples: 273496. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:31:25,556][00319] Avg episode reward: [(0, '6.221')] | |
| [2025-01-15 14:31:25,819][01035] Updated weights for policy 0, policy_version 270 (0.0025) | |
| [2025-01-15 14:31:30,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 1118208. Throughput: 0: 1009.5. Samples: 279694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:31:30,553][00319] Avg episode reward: [(0, '6.188')] | |
| [2025-01-15 14:31:35,549][00319] Fps is (10 sec: 3276.3, 60 sec: 3891.1, 300 sec: 3846.1). Total num frames: 1134592. Throughput: 0: 941.7. Samples: 284058. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:31:35,557][00319] Avg episode reward: [(0, '6.280')] | |
| [2025-01-15 14:31:37,844][01035] Updated weights for policy 0, policy_version 280 (0.0017) | |
| [2025-01-15 14:31:40,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1159168. Throughput: 0: 963.2. Samples: 287342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:31:40,553][00319] Avg episode reward: [(0, '6.465')] | |
| [2025-01-15 14:31:45,547][00319] Fps is (10 sec: 4916.0, 60 sec: 4027.7, 300 sec: 3915.5). Total num frames: 1183744. Throughput: 0: 1024.0. Samples: 294614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:31:45,553][00319] Avg episode reward: [(0, '6.662')] | |
| [2025-01-15 14:31:46,695][01035] Updated weights for policy 0, policy_version 290 (0.0027) | |
| [2025-01-15 14:31:50,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 1196032. Throughput: 0: 977.8. Samples: 299896. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:31:50,554][00319] Avg episode reward: [(0, '6.912')] | |
| [2025-01-15 14:31:55,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 1216512. Throughput: 0: 947.2. Samples: 302106. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:31:55,551][00319] Avg episode reward: [(0, '7.495')] | |
| [2025-01-15 14:31:55,557][01020] Saving new best policy, reward=7.495! | |
| [2025-01-15 14:31:58,008][01035] Updated weights for policy 0, policy_version 300 (0.0018) | |
| [2025-01-15 14:32:00,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1236992. Throughput: 0: 995.4. Samples: 308936. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:00,553][00319] Avg episode reward: [(0, '8.346')] | |
| [2025-01-15 14:32:00,567][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000303_1241088.pth... | |
| [2025-01-15 14:32:00,693][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000072_294912.pth | |
| [2025-01-15 14:32:00,703][01020] Saving new best policy, reward=8.346! | |
| [2025-01-15 14:32:05,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1261568. Throughput: 0: 1013.4. Samples: 315514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:05,553][00319] Avg episode reward: [(0, '8.951')] | |
| [2025-01-15 14:32:05,556][01020] Saving new best policy, reward=8.951! | |
| [2025-01-15 14:32:08,563][01035] Updated weights for policy 0, policy_version 310 (0.0021) | |
| [2025-01-15 14:32:10,553][00319] Fps is (10 sec: 3684.3, 60 sec: 3822.6, 300 sec: 3915.4). Total num frames: 1273856. Throughput: 0: 979.3. Samples: 317572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:32:10,556][00319] Avg episode reward: [(0, '8.760')] | |
| [2025-01-15 14:32:15,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 1294336. Throughput: 0: 961.0. Samples: 322938. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:15,550][00319] Avg episode reward: [(0, '9.610')] | |
| [2025-01-15 14:32:15,556][01020] Saving new best policy, reward=9.610! | |
| [2025-01-15 14:32:18,373][01035] Updated weights for policy 0, policy_version 320 (0.0026) | |
| [2025-01-15 14:32:20,547][00319] Fps is (10 sec: 4508.1, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1318912. Throughput: 0: 1027.5. Samples: 330296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:32:20,556][00319] Avg episode reward: [(0, '9.042')] | |
| [2025-01-15 14:32:25,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 1335296. Throughput: 0: 1023.2. Samples: 333384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:25,551][00319] Avg episode reward: [(0, '9.842')] | |
| [2025-01-15 14:32:25,555][01020] Saving new best policy, reward=9.842! | |
| [2025-01-15 14:32:30,096][01035] Updated weights for policy 0, policy_version 330 (0.0030) | |
| [2025-01-15 14:32:30,550][00319] Fps is (10 sec: 3276.0, 60 sec: 3891.0, 300 sec: 3929.3). Total num frames: 1351680. Throughput: 0: 958.2. Samples: 337734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:30,553][00319] Avg episode reward: [(0, '10.339')] | |
| [2025-01-15 14:32:30,565][01020] Saving new best policy, reward=10.339! | |
| [2025-01-15 14:32:35,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.8, 300 sec: 3943.3). Total num frames: 1376256. Throughput: 0: 986.1. Samples: 344270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:35,554][00319] Avg episode reward: [(0, '11.226')] | |
| [2025-01-15 14:32:35,559][01020] Saving new best policy, reward=11.226! | |
| [2025-01-15 14:32:38,740][01035] Updated weights for policy 0, policy_version 340 (0.0022) | |
| [2025-01-15 14:32:40,548][00319] Fps is (10 sec: 4506.6, 60 sec: 3959.4, 300 sec: 3929.4). Total num frames: 1396736. Throughput: 0: 1014.4. Samples: 347754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:32:40,555][00319] Avg episode reward: [(0, '12.752')] | |
| [2025-01-15 14:32:40,571][01020] Saving new best policy, reward=12.752! | |
| [2025-01-15 14:32:45,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 1413120. Throughput: 0: 985.0. Samples: 353262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:45,551][00319] Avg episode reward: [(0, '12.777')] | |
| [2025-01-15 14:32:45,561][01020] Saving new best policy, reward=12.777! | |
| [2025-01-15 14:32:50,470][01035] Updated weights for policy 0, policy_version 350 (0.0018) | |
| [2025-01-15 14:32:50,548][00319] Fps is (10 sec: 3686.3, 60 sec: 3959.4, 300 sec: 3943.3). Total num frames: 1433600. Throughput: 0: 950.4. Samples: 358284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:32:50,552][00319] Avg episode reward: [(0, '12.580')] | |
| [2025-01-15 14:32:55,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1458176. Throughput: 0: 987.2. Samples: 361992. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:32:55,551][00319] Avg episode reward: [(0, '12.216')] | |
| [2025-01-15 14:32:58,901][01035] Updated weights for policy 0, policy_version 360 (0.0013) | |
| [2025-01-15 14:33:00,551][00319] Fps is (10 sec: 4504.2, 60 sec: 4027.5, 300 sec: 3929.4). Total num frames: 1478656. Throughput: 0: 1026.8. Samples: 369148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:33:00,555][00319] Avg episode reward: [(0, '12.019')] | |
| [2025-01-15 14:33:05,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 1490944. Throughput: 0: 962.4. Samples: 373606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:33:05,551][00319] Avg episode reward: [(0, '12.435')] | |
| [2025-01-15 14:33:10,449][01035] Updated weights for policy 0, policy_version 370 (0.0045) | |
| [2025-01-15 14:33:10,547][00319] Fps is (10 sec: 3687.7, 60 sec: 4028.1, 300 sec: 3943.3). Total num frames: 1515520. Throughput: 0: 955.7. Samples: 376390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:33:10,555][00319] Avg episode reward: [(0, '12.868')] | |
| [2025-01-15 14:33:10,563][01020] Saving new best policy, reward=12.868! | |
| [2025-01-15 14:33:15,547][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3929.4). Total num frames: 1536000. Throughput: 0: 1018.9. Samples: 383580. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:33:15,556][00319] Avg episode reward: [(0, '12.594')] | |
| [2025-01-15 14:33:20,366][01035] Updated weights for policy 0, policy_version 380 (0.0013) | |
| [2025-01-15 14:33:20,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 1556480. Throughput: 0: 1006.0. Samples: 389542. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:33:20,550][00319] Avg episode reward: [(0, '13.119')] | |
| [2025-01-15 14:33:20,569][01020] Saving new best policy, reward=13.119! | |
| [2025-01-15 14:33:25,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 1568768. Throughput: 0: 973.0. Samples: 391538. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:33:25,550][00319] Avg episode reward: [(0, '13.344')] | |
| [2025-01-15 14:33:25,556][01020] Saving new best policy, reward=13.344! | |
| [2025-01-15 14:33:30,547][00319] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 3943.3). Total num frames: 1593344. Throughput: 0: 986.9. Samples: 397672. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:33:30,556][00319] Avg episode reward: [(0, '12.872')] | |
| [2025-01-15 14:33:30,977][01035] Updated weights for policy 0, policy_version 390 (0.0015) | |
| [2025-01-15 14:33:35,555][00319] Fps is (10 sec: 4911.5, 60 sec: 4027.2, 300 sec: 3943.2). Total num frames: 1617920. Throughput: 0: 1034.9. Samples: 404860. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:33:35,558][00319] Avg episode reward: [(0, '13.084')] | |
| [2025-01-15 14:33:40,548][00319] Fps is (10 sec: 3686.1, 60 sec: 3891.2, 300 sec: 3929.4). Total num frames: 1630208. Throughput: 0: 1003.2. Samples: 407136. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:33:40,551][00319] Avg episode reward: [(0, '14.340')] | |
| [2025-01-15 14:33:40,562][01020] Saving new best policy, reward=14.340! | |
| [2025-01-15 14:33:42,302][01035] Updated weights for policy 0, policy_version 400 (0.0034) | |
| [2025-01-15 14:33:45,547][00319] Fps is (10 sec: 3279.3, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1650688. Throughput: 0: 945.2. Samples: 411680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:33:45,551][00319] Avg episode reward: [(0, '13.281')] | |
| [2025-01-15 14:33:50,547][00319] Fps is (10 sec: 4505.9, 60 sec: 4027.8, 300 sec: 3943.3). Total num frames: 1675264. Throughput: 0: 1008.5. Samples: 418988. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:33:50,555][00319] Avg episode reward: [(0, '14.859')] | |
| [2025-01-15 14:33:50,566][01020] Saving new best policy, reward=14.859! | |
| [2025-01-15 14:33:51,287][01035] Updated weights for policy 0, policy_version 410 (0.0018) | |
| [2025-01-15 14:33:55,555][00319] Fps is (10 sec: 4502.2, 60 sec: 3959.0, 300 sec: 3943.2). Total num frames: 1695744. Throughput: 0: 1026.5. Samples: 422590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:33:55,565][00319] Avg episode reward: [(0, '14.835')] | |
| [2025-01-15 14:34:00,550][00319] Fps is (10 sec: 3276.0, 60 sec: 3823.0, 300 sec: 3929.3). Total num frames: 1708032. Throughput: 0: 970.7. Samples: 427262. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:34:00,563][00319] Avg episode reward: [(0, '14.581')] | |
| [2025-01-15 14:34:00,642][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_1712128.pth... | |
| [2025-01-15 14:34:00,842][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000187_765952.pth | |
| [2025-01-15 14:34:02,854][01035] Updated weights for policy 0, policy_version 420 (0.0031) | |
| [2025-01-15 14:34:05,547][00319] Fps is (10 sec: 3689.2, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 1732608. Throughput: 0: 968.9. Samples: 433142. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:34:05,556][00319] Avg episode reward: [(0, '16.013')] | |
| [2025-01-15 14:34:05,559][01020] Saving new best policy, reward=16.013! | |
| [2025-01-15 14:34:10,548][00319] Fps is (10 sec: 4506.6, 60 sec: 3959.4, 300 sec: 3943.3). Total num frames: 1753088. Throughput: 0: 1002.1. Samples: 436634. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:34:10,554][00319] Avg episode reward: [(0, '15.782')] | |
| [2025-01-15 14:34:11,489][01035] Updated weights for policy 0, policy_version 430 (0.0030) | |
| [2025-01-15 14:34:15,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1773568. Throughput: 0: 1002.6. Samples: 442790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:34:15,554][00319] Avg episode reward: [(0, '15.737')] | |
| [2025-01-15 14:34:20,547][00319] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 1785856. Throughput: 0: 942.4. Samples: 447262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:34:20,550][00319] Avg episode reward: [(0, '15.924')] | |
| [2025-01-15 14:34:23,102][01035] Updated weights for policy 0, policy_version 440 (0.0026) | |
| [2025-01-15 14:34:25,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3957.2). Total num frames: 1814528. Throughput: 0: 973.4. Samples: 450938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:34:25,550][00319] Avg episode reward: [(0, '15.102')] | |
| [2025-01-15 14:34:30,547][00319] Fps is (10 sec: 4915.2, 60 sec: 4027.7, 300 sec: 3943.3). Total num frames: 1835008. Throughput: 0: 1035.9. Samples: 458294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:34:30,550][00319] Avg episode reward: [(0, '15.279')] | |
| [2025-01-15 14:34:32,574][01035] Updated weights for policy 0, policy_version 450 (0.0026) | |
| [2025-01-15 14:34:35,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.7, 300 sec: 3943.3). Total num frames: 1851392. Throughput: 0: 980.0. Samples: 463088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:34:35,553][00319] Avg episode reward: [(0, '15.952')] | |
| [2025-01-15 14:34:40,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1867776. Throughput: 0: 949.3. Samples: 465300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:34:40,551][00319] Avg episode reward: [(0, '16.919')] | |
| [2025-01-15 14:34:40,559][01020] Saving new best policy, reward=16.919! | |
| [2025-01-15 14:34:43,354][01035] Updated weights for policy 0, policy_version 460 (0.0020) | |
| [2025-01-15 14:34:45,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 1892352. Throughput: 0: 1001.7. Samples: 472338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:34:45,551][00319] Avg episode reward: [(0, '18.907')] | |
| [2025-01-15 14:34:45,561][01020] Saving new best policy, reward=18.907! | |
| [2025-01-15 14:34:50,547][00319] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1912832. Throughput: 0: 1014.4. Samples: 478792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:34:50,556][00319] Avg episode reward: [(0, '20.573')] | |
| [2025-01-15 14:34:50,570][01020] Saving new best policy, reward=20.573! | |
| [2025-01-15 14:34:54,224][01035] Updated weights for policy 0, policy_version 470 (0.0044) | |
| [2025-01-15 14:34:55,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.7, 300 sec: 3943.3). Total num frames: 1929216. Throughput: 0: 982.5. Samples: 480848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:34:55,563][00319] Avg episode reward: [(0, '21.089')] | |
| [2025-01-15 14:34:55,576][01020] Saving new best policy, reward=21.089! | |
| [2025-01-15 14:35:00,548][00319] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 3957.2). Total num frames: 1949696. Throughput: 0: 968.0. Samples: 486352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:35:00,551][00319] Avg episode reward: [(0, '20.789')] | |
| [2025-01-15 14:35:03,710][01035] Updated weights for policy 0, policy_version 480 (0.0032) | |
| [2025-01-15 14:35:05,548][00319] Fps is (10 sec: 4505.5, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 1974272. Throughput: 0: 1030.3. Samples: 493624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:35:05,553][00319] Avg episode reward: [(0, '21.276')] | |
| [2025-01-15 14:35:05,558][01020] Saving new best policy, reward=21.276! | |
| [2025-01-15 14:35:10,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 1990656. Throughput: 0: 1015.5. Samples: 496634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:35:10,553][00319] Avg episode reward: [(0, '19.427')] | |
| [2025-01-15 14:35:15,337][01035] Updated weights for policy 0, policy_version 490 (0.0022) | |
| [2025-01-15 14:35:15,547][00319] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2007040. Throughput: 0: 949.6. Samples: 501026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:15,554][00319] Avg episode reward: [(0, '19.458')] | |
| [2025-01-15 14:35:20,548][00319] Fps is (10 sec: 4095.9, 60 sec: 4096.0, 300 sec: 3957.1). Total num frames: 2031616. Throughput: 0: 997.9. Samples: 507992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:35:20,553][00319] Avg episode reward: [(0, '18.957')] | |
| [2025-01-15 14:35:23,836][01035] Updated weights for policy 0, policy_version 500 (0.0028) | |
| [2025-01-15 14:35:25,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2052096. Throughput: 0: 1029.1. Samples: 511608. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-15 14:35:25,551][00319] Avg episode reward: [(0, '19.348')] | |
| [2025-01-15 14:35:30,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2068480. Throughput: 0: 989.3. Samples: 516856. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:30,553][00319] Avg episode reward: [(0, '19.320')] | |
| [2025-01-15 14:35:35,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2084864. Throughput: 0: 956.1. Samples: 521818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:35:35,556][00319] Avg episode reward: [(0, '19.336')] | |
| [2025-01-15 14:35:35,859][01035] Updated weights for policy 0, policy_version 510 (0.0025) | |
| [2025-01-15 14:35:40,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.8, 300 sec: 3957.2). Total num frames: 2109440. Throughput: 0: 991.7. Samples: 525476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:40,556][00319] Avg episode reward: [(0, '18.906')] | |
| [2025-01-15 14:35:44,464][01035] Updated weights for policy 0, policy_version 520 (0.0032) | |
| [2025-01-15 14:35:45,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2129920. Throughput: 0: 1030.4. Samples: 532718. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:45,559][00319] Avg episode reward: [(0, '18.916')] | |
| [2025-01-15 14:35:50,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2146304. Throughput: 0: 967.8. Samples: 537176. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:50,554][00319] Avg episode reward: [(0, '19.563')] | |
| [2025-01-15 14:35:55,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3971.0). Total num frames: 2166784. Throughput: 0: 964.9. Samples: 540054. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:35:55,554][00319] Avg episode reward: [(0, '19.285')] | |
| [2025-01-15 14:35:55,721][01035] Updated weights for policy 0, policy_version 530 (0.0018) | |
| [2025-01-15 14:36:00,548][00319] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2191360. Throughput: 0: 1030.1. Samples: 547382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:36:00,555][00319] Avg episode reward: [(0, '20.429')] | |
| [2025-01-15 14:36:00,636][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000536_2195456.pth... | |
| [2025-01-15 14:36:00,766][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000303_1241088.pth | |
| [2025-01-15 14:36:05,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2207744. Throughput: 0: 1002.0. Samples: 553080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:36:05,553][00319] Avg episode reward: [(0, '21.605')] | |
| [2025-01-15 14:36:05,563][01020] Saving new best policy, reward=21.605! | |
| [2025-01-15 14:36:05,572][01035] Updated weights for policy 0, policy_version 540 (0.0014) | |
| [2025-01-15 14:36:10,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2224128. Throughput: 0: 969.5. Samples: 555236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:36:10,555][00319] Avg episode reward: [(0, '20.959')] | |
| [2025-01-15 14:36:15,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3971.0). Total num frames: 2248704. Throughput: 0: 992.2. Samples: 561504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:36:15,555][00319] Avg episode reward: [(0, '19.412')] | |
| [2025-01-15 14:36:15,862][01035] Updated weights for policy 0, policy_version 550 (0.0019) | |
| [2025-01-15 14:36:20,547][00319] Fps is (10 sec: 4915.2, 60 sec: 4027.8, 300 sec: 3971.0). Total num frames: 2273280. Throughput: 0: 1043.3. Samples: 568768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:36:20,550][00319] Avg episode reward: [(0, '18.201')] | |
| [2025-01-15 14:36:25,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3957.2). Total num frames: 2285568. Throughput: 0: 1011.8. Samples: 571006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:36:25,550][00319] Avg episode reward: [(0, '18.842')] | |
| [2025-01-15 14:36:27,073][01035] Updated weights for policy 0, policy_version 560 (0.0031) | |
| [2025-01-15 14:36:30,548][00319] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3971.1). Total num frames: 2306048. Throughput: 0: 955.9. Samples: 575732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:36:30,554][00319] Avg episode reward: [(0, '17.511')] | |
| [2025-01-15 14:36:35,547][00319] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 3957.2). Total num frames: 2326528. Throughput: 0: 998.1. Samples: 582092. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:36:35,553][00319] Avg episode reward: [(0, '16.576')] | |
| [2025-01-15 14:36:36,810][01035] Updated weights for policy 0, policy_version 570 (0.0032) | |
| [2025-01-15 14:36:40,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3943.3). Total num frames: 2347008. Throughput: 0: 1012.3. Samples: 585606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:36:40,557][00319] Avg episode reward: [(0, '18.491')] | |
| [2025-01-15 14:36:45,551][00319] Fps is (10 sec: 3275.8, 60 sec: 3822.7, 300 sec: 3943.2). Total num frames: 2359296. Throughput: 0: 944.3. Samples: 589880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:36:45,553][00319] Avg episode reward: [(0, '21.387')] | |
| [2025-01-15 14:36:49,122][01035] Updated weights for policy 0, policy_version 580 (0.0029) | |
| [2025-01-15 14:36:50,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2379776. Throughput: 0: 945.2. Samples: 595616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:36:50,550][00319] Avg episode reward: [(0, '20.458')] | |
| [2025-01-15 14:36:55,547][00319] Fps is (10 sec: 4507.0, 60 sec: 3959.5, 300 sec: 3957.2). Total num frames: 2404352. Throughput: 0: 977.0. Samples: 599200. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:36:55,553][00319] Avg episode reward: [(0, '21.244')] | |
| [2025-01-15 14:36:57,942][01035] Updated weights for policy 0, policy_version 590 (0.0017) | |
| [2025-01-15 14:37:00,548][00319] Fps is (10 sec: 4095.7, 60 sec: 3822.9, 300 sec: 3929.4). Total num frames: 2420736. Throughput: 0: 978.3. Samples: 605530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:37:00,553][00319] Avg episode reward: [(0, '21.671')] | |
| [2025-01-15 14:37:00,643][01020] Saving new best policy, reward=21.671! | |
| [2025-01-15 14:37:05,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3943.3). Total num frames: 2437120. Throughput: 0: 908.0. Samples: 609626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:37:05,555][00319] Avg episode reward: [(0, '20.868')] | |
| [2025-01-15 14:37:09,892][01035] Updated weights for policy 0, policy_version 600 (0.0033) | |
| [2025-01-15 14:37:10,547][00319] Fps is (10 sec: 3686.6, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2457600. Throughput: 0: 927.9. Samples: 612762. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:37:10,551][00319] Avg episode reward: [(0, '18.477')] | |
| [2025-01-15 14:37:15,548][00319] Fps is (10 sec: 4505.3, 60 sec: 3891.2, 300 sec: 3943.3). Total num frames: 2482176. Throughput: 0: 972.7. Samples: 619504. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-15 14:37:15,550][00319] Avg episode reward: [(0, '19.138')] | |
| [2025-01-15 14:37:20,548][00319] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3929.4). Total num frames: 2494464. Throughput: 0: 938.5. Samples: 624326. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:37:20,553][00319] Avg episode reward: [(0, '19.477')] | |
| [2025-01-15 14:37:21,366][01035] Updated weights for policy 0, policy_version 610 (0.0028) | |
| [2025-01-15 14:37:25,547][00319] Fps is (10 sec: 2867.4, 60 sec: 3754.7, 300 sec: 3929.4). Total num frames: 2510848. Throughput: 0: 906.4. Samples: 626392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:37:25,549][00319] Avg episode reward: [(0, '19.629')] | |
| [2025-01-15 14:37:30,551][00319] Fps is (10 sec: 4094.6, 60 sec: 3822.7, 300 sec: 3929.3). Total num frames: 2535424. Throughput: 0: 958.2. Samples: 632998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:37:30,555][00319] Avg episode reward: [(0, '20.951')] | |
| [2025-01-15 14:37:31,152][01035] Updated weights for policy 0, policy_version 620 (0.0019) | |
| [2025-01-15 14:37:35,552][00319] Fps is (10 sec: 4503.5, 60 sec: 3822.6, 300 sec: 3929.3). Total num frames: 2555904. Throughput: 0: 975.2. Samples: 639504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:37:35,559][00319] Avg episode reward: [(0, '20.654')] | |
| [2025-01-15 14:37:40,548][00319] Fps is (10 sec: 3277.8, 60 sec: 3686.4, 300 sec: 3915.5). Total num frames: 2568192. Throughput: 0: 942.3. Samples: 641604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:37:40,553][00319] Avg episode reward: [(0, '20.775')] | |
| [2025-01-15 14:37:42,948][01035] Updated weights for policy 0, policy_version 630 (0.0016) | |
| [2025-01-15 14:37:45,547][00319] Fps is (10 sec: 3688.1, 60 sec: 3891.4, 300 sec: 3929.4). Total num frames: 2592768. Throughput: 0: 918.3. Samples: 646852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:37:45,550][00319] Avg episode reward: [(0, '20.850')] | |
| [2025-01-15 14:37:50,547][00319] Fps is (10 sec: 4915.3, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 2617344. Throughput: 0: 990.8. Samples: 654214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:37:50,555][00319] Avg episode reward: [(0, '20.632')] | |
| [2025-01-15 14:37:51,394][01035] Updated weights for policy 0, policy_version 640 (0.0028) | |
| [2025-01-15 14:37:55,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 2633728. Throughput: 0: 994.6. Samples: 657518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:37:55,552][00319] Avg episode reward: [(0, '20.768')] | |
| [2025-01-15 14:38:00,548][00319] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3915.5). Total num frames: 2646016. Throughput: 0: 941.2. Samples: 661858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:38:00,552][00319] Avg episode reward: [(0, '22.166')] | |
| [2025-01-15 14:38:00,637][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000647_2650112.pth... | |
| [2025-01-15 14:38:00,767][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000418_1712128.pth | |
| [2025-01-15 14:38:00,787][01020] Saving new best policy, reward=22.166! | |
| [2025-01-15 14:38:03,217][01035] Updated weights for policy 0, policy_version 650 (0.0018) | |
| [2025-01-15 14:38:05,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3915.5). Total num frames: 2670592. Throughput: 0: 976.7. Samples: 668278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:38:05,551][00319] Avg episode reward: [(0, '23.143')] | |
| [2025-01-15 14:38:05,555][01020] Saving new best policy, reward=23.143! | |
| [2025-01-15 14:38:10,548][00319] Fps is (10 sec: 4915.2, 60 sec: 3959.5, 300 sec: 3929.4). Total num frames: 2695168. Throughput: 0: 1005.0. Samples: 671616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:38:10,551][00319] Avg episode reward: [(0, '24.000')] | |
| [2025-01-15 14:38:10,559][01020] Saving new best policy, reward=24.000! | |
| [2025-01-15 14:38:13,131][01035] Updated weights for policy 0, policy_version 660 (0.0021) | |
| [2025-01-15 14:38:15,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 2707456. Throughput: 0: 978.1. Samples: 677008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:38:15,557][00319] Avg episode reward: [(0, '22.705')] | |
| [2025-01-15 14:38:20,548][00319] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3915.5). Total num frames: 2723840. Throughput: 0: 942.0. Samples: 681892. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:38:20,553][00319] Avg episode reward: [(0, '21.615')] | |
| [2025-01-15 14:38:24,391][01035] Updated weights for policy 0, policy_version 670 (0.0024) | |
| [2025-01-15 14:38:25,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3915.5). Total num frames: 2748416. Throughput: 0: 963.0. Samples: 684940. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:38:25,555][00319] Avg episode reward: [(0, '19.633')] | |
| [2025-01-15 14:38:30,547][00319] Fps is (10 sec: 4505.7, 60 sec: 3891.4, 300 sec: 3901.7). Total num frames: 2768896. Throughput: 0: 1001.2. Samples: 691906. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:38:30,553][00319] Avg episode reward: [(0, '20.233')] | |
| [2025-01-15 14:38:35,552][00319] Fps is (10 sec: 3275.3, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 2781184. Throughput: 0: 931.7. Samples: 696146. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:38:35,555][00319] Avg episode reward: [(0, '20.413')] | |
| [2025-01-15 14:38:35,935][01035] Updated weights for policy 0, policy_version 680 (0.0017) | |
| [2025-01-15 14:38:40,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 2801664. Throughput: 0: 910.6. Samples: 698494. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:38:40,550][00319] Avg episode reward: [(0, '19.494')] | |
| [2025-01-15 14:38:45,160][01035] Updated weights for policy 0, policy_version 690 (0.0019) | |
| [2025-01-15 14:38:45,547][00319] Fps is (10 sec: 4507.7, 60 sec: 3891.2, 300 sec: 3901.6). Total num frames: 2826240. Throughput: 0: 972.4. Samples: 705616. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:38:45,551][00319] Avg episode reward: [(0, '19.842')] | |
| [2025-01-15 14:38:50,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3887.8). Total num frames: 2842624. Throughput: 0: 960.6. Samples: 711504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:38:50,555][00319] Avg episode reward: [(0, '20.014')] | |
| [2025-01-15 14:38:55,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3901.6). Total num frames: 2859008. Throughput: 0: 931.6. Samples: 713540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:38:55,552][00319] Avg episode reward: [(0, '18.594')] | |
| [2025-01-15 14:38:57,555][01035] Updated weights for policy 0, policy_version 700 (0.0027) | |
| [2025-01-15 14:39:00,548][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3887.7). Total num frames: 2879488. Throughput: 0: 931.4. Samples: 718922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:39:00,553][00319] Avg episode reward: [(0, '19.298')] | |
| [2025-01-15 14:39:05,547][00319] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3887.7). Total num frames: 2899968. Throughput: 0: 968.0. Samples: 725450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:39:05,554][00319] Avg episode reward: [(0, '19.563')] | |
| [2025-01-15 14:39:07,667][01035] Updated weights for policy 0, policy_version 710 (0.0013) | |
| [2025-01-15 14:39:10,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3860.0). Total num frames: 2912256. Throughput: 0: 952.4. Samples: 727800. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:39:10,555][00319] Avg episode reward: [(0, '20.562')] | |
| [2025-01-15 14:39:15,547][00319] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3873.8). Total num frames: 2928640. Throughput: 0: 885.6. Samples: 731758. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:39:15,555][00319] Avg episode reward: [(0, '19.793')] | |
| [2025-01-15 14:39:19,660][01035] Updated weights for policy 0, policy_version 720 (0.0018) | |
| [2025-01-15 14:39:20,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 2949120. Throughput: 0: 934.1. Samples: 738178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:39:20,552][00319] Avg episode reward: [(0, '20.366')] | |
| [2025-01-15 14:39:25,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3860.0). Total num frames: 2973696. Throughput: 0: 956.6. Samples: 741542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:39:25,554][00319] Avg episode reward: [(0, '18.769')] | |
| [2025-01-15 14:39:30,548][00319] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3846.1). Total num frames: 2985984. Throughput: 0: 905.1. Samples: 746348. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:39:30,555][00319] Avg episode reward: [(0, '19.704')] | |
| [2025-01-15 14:39:31,415][01035] Updated weights for policy 0, policy_version 730 (0.0028) | |
| [2025-01-15 14:39:35,547][00319] Fps is (10 sec: 2867.2, 60 sec: 3686.7, 300 sec: 3846.1). Total num frames: 3002368. Throughput: 0: 889.4. Samples: 751526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:39:35,550][00319] Avg episode reward: [(0, '21.175')] | |
| [2025-01-15 14:39:40,548][00319] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3846.1). Total num frames: 3026944. Throughput: 0: 920.5. Samples: 754964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:39:40,551][00319] Avg episode reward: [(0, '22.870')] | |
| [2025-01-15 14:39:40,834][01035] Updated weights for policy 0, policy_version 740 (0.0028) | |
| [2025-01-15 14:39:45,550][00319] Fps is (10 sec: 4504.7, 60 sec: 3686.3, 300 sec: 3846.0). Total num frames: 3047424. Throughput: 0: 946.5. Samples: 761518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:39:45,554][00319] Avg episode reward: [(0, '23.876')] | |
| [2025-01-15 14:39:50,551][00319] Fps is (10 sec: 3275.7, 60 sec: 3617.9, 300 sec: 3832.1). Total num frames: 3059712. Throughput: 0: 893.0. Samples: 765636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:39:50,554][00319] Avg episode reward: [(0, '25.103')] | |
| [2025-01-15 14:39:50,567][01020] Saving new best policy, reward=25.103! | |
| [2025-01-15 14:39:53,081][01035] Updated weights for policy 0, policy_version 750 (0.0039) | |
| [2025-01-15 14:39:55,547][00319] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 3080192. Throughput: 0: 904.4. Samples: 768498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:39:55,550][00319] Avg episode reward: [(0, '25.903')] | |
| [2025-01-15 14:39:55,562][01020] Saving new best policy, reward=25.903! | |
| [2025-01-15 14:40:00,548][00319] Fps is (10 sec: 4507.2, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3104768. Throughput: 0: 972.9. Samples: 775540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:40:00,559][00319] Avg episode reward: [(0, '23.974')] | |
| [2025-01-15 14:40:00,566][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000758_3104768.pth... | |
| [2025-01-15 14:40:00,692][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000536_2195456.pth | |
| [2025-01-15 14:40:02,084][01035] Updated weights for policy 0, policy_version 760 (0.0040) | |
| [2025-01-15 14:40:05,548][00319] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3832.2). Total num frames: 3121152. Throughput: 0: 945.7. Samples: 780736. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:40:05,558][00319] Avg episode reward: [(0, '23.494')] | |
| [2025-01-15 14:40:10,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3832.2). Total num frames: 3137536. Throughput: 0: 917.0. Samples: 782808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:40:10,551][00319] Avg episode reward: [(0, '23.539')] | |
| [2025-01-15 14:40:13,840][01035] Updated weights for policy 0, policy_version 770 (0.0033) | |
| [2025-01-15 14:40:15,547][00319] Fps is (10 sec: 4096.1, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 3162112. Throughput: 0: 951.4. Samples: 789162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:40:15,550][00319] Avg episode reward: [(0, '22.622')] | |
| [2025-01-15 14:40:20,553][00319] Fps is (10 sec: 4503.1, 60 sec: 3890.8, 300 sec: 3832.1). Total num frames: 3182592. Throughput: 0: 991.6. Samples: 796154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:40:20,556][00319] Avg episode reward: [(0, '22.293')] | |
| [2025-01-15 14:40:24,365][01035] Updated weights for policy 0, policy_version 780 (0.0023) | |
| [2025-01-15 14:40:25,550][00319] Fps is (10 sec: 3275.9, 60 sec: 3686.2, 300 sec: 3818.3). Total num frames: 3194880. Throughput: 0: 963.3. Samples: 798314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:40:25,556][00319] Avg episode reward: [(0, '23.078')] | |
| [2025-01-15 14:40:30,547][00319] Fps is (10 sec: 3278.6, 60 sec: 3823.0, 300 sec: 3832.2). Total num frames: 3215360. Throughput: 0: 923.2. Samples: 803062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:40:30,550][00319] Avg episode reward: [(0, '23.770')] | |
| [2025-01-15 14:40:34,350][01035] Updated weights for policy 0, policy_version 790 (0.0018) | |
| [2025-01-15 14:40:35,547][00319] Fps is (10 sec: 4506.8, 60 sec: 3959.5, 300 sec: 3832.2). Total num frames: 3239936. Throughput: 0: 993.2. Samples: 810326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:40:35,551][00319] Avg episode reward: [(0, '22.298')] | |
| [2025-01-15 14:40:40,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3256320. Throughput: 0: 1004.1. Samples: 813684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:40:40,553][00319] Avg episode reward: [(0, '22.417')] | |
| [2025-01-15 14:40:45,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3818.3). Total num frames: 3272704. Throughput: 0: 938.6. Samples: 817778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:40:45,553][00319] Avg episode reward: [(0, '22.694')] | |
| [2025-01-15 14:40:46,645][01035] Updated weights for policy 0, policy_version 800 (0.0029) | |
| [2025-01-15 14:40:50,548][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.4, 300 sec: 3818.3). Total num frames: 3293184. Throughput: 0: 953.7. Samples: 823654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:40:50,552][00319] Avg episode reward: [(0, '22.257')] | |
| [2025-01-15 14:40:55,366][01035] Updated weights for policy 0, policy_version 810 (0.0022) | |
| [2025-01-15 14:40:55,548][00319] Fps is (10 sec: 4505.4, 60 sec: 3959.4, 300 sec: 3818.3). Total num frames: 3317760. Throughput: 0: 984.4. Samples: 827106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:40:55,555][00319] Avg episode reward: [(0, '21.285')] | |
| [2025-01-15 14:41:00,547][00319] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 3334144. Throughput: 0: 975.1. Samples: 833040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:41:00,553][00319] Avg episode reward: [(0, '22.298')] | |
| [2025-01-15 14:41:05,547][00319] Fps is (10 sec: 2867.3, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3346432. Throughput: 0: 915.7. Samples: 837354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:41:05,556][00319] Avg episode reward: [(0, '20.653')] | |
| [2025-01-15 14:41:07,302][01035] Updated weights for policy 0, policy_version 820 (0.0015) | |
| [2025-01-15 14:41:10,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3371008. Throughput: 0: 948.5. Samples: 840994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:41:10,555][00319] Avg episode reward: [(0, '22.123')] | |
| [2025-01-15 14:41:15,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3391488. Throughput: 0: 995.3. Samples: 847850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:41:15,556][00319] Avg episode reward: [(0, '23.431')] | |
| [2025-01-15 14:41:17,101][01035] Updated weights for policy 0, policy_version 830 (0.0024) | |
| [2025-01-15 14:41:20,548][00319] Fps is (10 sec: 3686.2, 60 sec: 3755.0, 300 sec: 3804.4). Total num frames: 3407872. Throughput: 0: 936.0. Samples: 852448. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:41:20,551][00319] Avg episode reward: [(0, '24.039')] | |
| [2025-01-15 14:41:25,547][00319] Fps is (10 sec: 3686.4, 60 sec: 3891.4, 300 sec: 3804.4). Total num frames: 3428352. Throughput: 0: 908.2. Samples: 854554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:41:25,555][00319] Avg episode reward: [(0, '24.554')] | |
| [2025-01-15 14:41:28,224][01035] Updated weights for policy 0, policy_version 840 (0.0020) | |
| [2025-01-15 14:41:30,547][00319] Fps is (10 sec: 4096.2, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3448832. Throughput: 0: 971.8. Samples: 861510. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:41:30,553][00319] Avg episode reward: [(0, '23.488')] | |
| [2025-01-15 14:41:35,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3469312. Throughput: 0: 975.3. Samples: 867542. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:41:35,554][00319] Avg episode reward: [(0, '22.519')] | |
| [2025-01-15 14:41:39,718][01035] Updated weights for policy 0, policy_version 850 (0.0016) | |
| [2025-01-15 14:41:40,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.5). Total num frames: 3481600. Throughput: 0: 943.5. Samples: 869564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:41:40,554][00319] Avg episode reward: [(0, '21.903')] | |
| [2025-01-15 14:41:45,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 3502080. Throughput: 0: 933.9. Samples: 875066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:41:45,555][00319] Avg episode reward: [(0, '21.283')] | |
| [2025-01-15 14:41:49,060][01035] Updated weights for policy 0, policy_version 860 (0.0028) | |
| [2025-01-15 14:41:50,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3526656. Throughput: 0: 995.2. Samples: 882138. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:41:50,555][00319] Avg episode reward: [(0, '23.079')] | |
| [2025-01-15 14:41:55,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3543040. Throughput: 0: 974.9. Samples: 884866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:41:55,553][00319] Avg episode reward: [(0, '24.458')] | |
| [2025-01-15 14:42:00,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3754.6, 300 sec: 3804.4). Total num frames: 3559424. Throughput: 0: 915.4. Samples: 889044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:42:00,551][00319] Avg episode reward: [(0, '26.574')] | |
| [2025-01-15 14:42:00,564][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000869_3559424.pth... | |
| [2025-01-15 14:42:00,710][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000647_2650112.pth | |
| [2025-01-15 14:42:00,731][01020] Saving new best policy, reward=26.574! | |
| [2025-01-15 14:42:01,472][01035] Updated weights for policy 0, policy_version 870 (0.0023) | |
| [2025-01-15 14:42:05,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3579904. Throughput: 0: 957.1. Samples: 895516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:42:05,554][00319] Avg episode reward: [(0, '25.814')] | |
| [2025-01-15 14:42:10,548][00319] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 3600384. Throughput: 0: 985.6. Samples: 898906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:10,557][00319] Avg episode reward: [(0, '25.924')] | |
| [2025-01-15 14:42:10,831][01035] Updated weights for policy 0, policy_version 880 (0.0019) | |
| [2025-01-15 14:42:15,548][00319] Fps is (10 sec: 3686.3, 60 sec: 3754.6, 300 sec: 3804.4). Total num frames: 3616768. Throughput: 0: 941.1. Samples: 903862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:15,556][00319] Avg episode reward: [(0, '25.199')] | |
| [2025-01-15 14:42:20,547][00319] Fps is (10 sec: 3277.0, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3633152. Throughput: 0: 919.6. Samples: 908926. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:20,554][00319] Avg episode reward: [(0, '24.154')] | |
| [2025-01-15 14:42:22,464][01035] Updated weights for policy 0, policy_version 890 (0.0031) | |
| [2025-01-15 14:42:25,547][00319] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3804.5). Total num frames: 3657728. Throughput: 0: 953.7. Samples: 912482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:25,553][00319] Avg episode reward: [(0, '23.135')] | |
| [2025-01-15 14:42:30,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3804.5). Total num frames: 3678208. Throughput: 0: 985.4. Samples: 919410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:42:30,554][00319] Avg episode reward: [(0, '23.108')] | |
| [2025-01-15 14:42:32,741][01035] Updated weights for policy 0, policy_version 900 (0.0018) | |
| [2025-01-15 14:42:35,549][00319] Fps is (10 sec: 3276.4, 60 sec: 3686.3, 300 sec: 3804.4). Total num frames: 3690496. Throughput: 0: 924.6. Samples: 923744. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-01-15 14:42:35,557][00319] Avg episode reward: [(0, '23.057')] | |
| [2025-01-15 14:42:40,548][00319] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3715072. Throughput: 0: 926.1. Samples: 926542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:40,551][00319] Avg episode reward: [(0, '23.003')] | |
| [2025-01-15 14:42:43,051][01035] Updated weights for policy 0, policy_version 910 (0.0023) | |
| [2025-01-15 14:42:45,547][00319] Fps is (10 sec: 4506.1, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3735552. Throughput: 0: 985.5. Samples: 933392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:42:45,550][00319] Avg episode reward: [(0, '22.486')] | |
| [2025-01-15 14:42:50,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 3751936. Throughput: 0: 966.8. Samples: 939022. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:42:50,554][00319] Avg episode reward: [(0, '22.578')] | |
| [2025-01-15 14:42:54,983][01035] Updated weights for policy 0, policy_version 920 (0.0034) | |
| [2025-01-15 14:42:55,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3804.4). Total num frames: 3768320. Throughput: 0: 938.0. Samples: 941114. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-01-15 14:42:55,556][00319] Avg episode reward: [(0, '22.550')] | |
| [2025-01-15 14:43:00,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 3792896. Throughput: 0: 967.5. Samples: 947400. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:43:00,552][00319] Avg episode reward: [(0, '25.572')] | |
| [2025-01-15 14:43:03,697][01035] Updated weights for policy 0, policy_version 930 (0.0025) | |
| [2025-01-15 14:43:05,547][00319] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 3813376. Throughput: 0: 1009.6. Samples: 954356. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-01-15 14:43:05,553][00319] Avg episode reward: [(0, '26.734')] | |
| [2025-01-15 14:43:05,555][01020] Saving new best policy, reward=26.734! | |
| [2025-01-15 14:43:10,551][00319] Fps is (10 sec: 3685.0, 60 sec: 3822.7, 300 sec: 3804.4). Total num frames: 3829760. Throughput: 0: 978.8. Samples: 956532. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:43:10,554][00319] Avg episode reward: [(0, '27.464')] | |
| [2025-01-15 14:43:10,570][01020] Saving new best policy, reward=27.464! | |
| [2025-01-15 14:43:15,547][00319] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 3846144. Throughput: 0: 928.2. Samples: 961178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-01-15 14:43:15,550][00319] Avg episode reward: [(0, '25.662')] | |
| [2025-01-15 14:43:15,705][01035] Updated weights for policy 0, policy_version 940 (0.0016) | |
| [2025-01-15 14:43:20,548][00319] Fps is (10 sec: 4097.4, 60 sec: 3959.4, 300 sec: 3804.4). Total num frames: 3870720. Throughput: 0: 991.5. Samples: 968362. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:43:20,555][00319] Avg episode reward: [(0, '25.439')] | |
| [2025-01-15 14:43:24,576][01035] Updated weights for policy 0, policy_version 950 (0.0025) | |
| [2025-01-15 14:43:25,549][00319] Fps is (10 sec: 4504.7, 60 sec: 3891.1, 300 sec: 3804.4). Total num frames: 3891200. Throughput: 0: 1010.3. Samples: 972006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:43:25,556][00319] Avg episode reward: [(0, '23.513')] | |
| [2025-01-15 14:43:30,547][00319] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3818.4). Total num frames: 3907584. Throughput: 0: 958.8. Samples: 976538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:43:30,555][00319] Avg episode reward: [(0, '23.840')] | |
| [2025-01-15 14:43:35,547][00319] Fps is (10 sec: 3687.1, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 3928064. Throughput: 0: 967.2. Samples: 982548. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-01-15 14:43:35,550][00319] Avg episode reward: [(0, '22.529')] | |
| [2025-01-15 14:43:35,822][01035] Updated weights for policy 0, policy_version 960 (0.0015) | |
| [2025-01-15 14:43:40,548][00319] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3818.3). Total num frames: 3952640. Throughput: 0: 998.3. Samples: 986036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-01-15 14:43:40,556][00319] Avg episode reward: [(0, '24.425')] | |
| [2025-01-15 14:43:45,547][00319] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3969024. Throughput: 0: 988.6. Samples: 991888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-01-15 14:43:45,558][00319] Avg episode reward: [(0, '23.863')] | |
| [2025-01-15 14:43:46,458][01035] Updated weights for policy 0, policy_version 970 (0.0015) | |
| [2025-01-15 14:43:50,548][00319] Fps is (10 sec: 3276.7, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 3985408. Throughput: 0: 932.0. Samples: 996298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-01-15 14:43:50,556][00319] Avg episode reward: [(0, '24.449')] | |
| [2025-01-15 14:43:54,765][00319] Component Batcher_0 stopped! | |
| [2025-01-15 14:43:54,779][01020] Stopping Batcher_0... | |
| [2025-01-15 14:43:54,779][01020] Loop batcher_evt_loop terminating... | |
| [2025-01-15 14:43:54,780][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-15 14:43:54,821][01035] Weights refcount: 2 0 | |
| [2025-01-15 14:43:54,823][01035] Stopping InferenceWorker_p0-w0... | |
| [2025-01-15 14:43:54,824][01035] Loop inference_proc0-0_evt_loop terminating... | |
| [2025-01-15 14:43:54,823][00319] Component InferenceWorker_p0-w0 stopped! | |
| [2025-01-15 14:43:54,897][01020] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000758_3104768.pth | |
| [2025-01-15 14:43:54,915][01020] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-15 14:43:55,078][00319] Component LearnerWorker_p0 stopped! | |
| [2025-01-15 14:43:55,087][01020] Stopping LearnerWorker_p0... | |
| [2025-01-15 14:43:55,088][01020] Loop learner_proc0_evt_loop terminating... | |
| [2025-01-15 14:43:55,156][00319] Component RolloutWorker_w6 stopped! | |
| [2025-01-15 14:43:55,160][01042] Stopping RolloutWorker_w6... | |
| [2025-01-15 14:43:55,170][00319] Component RolloutWorker_w2 stopped! | |
| [2025-01-15 14:43:55,166][01042] Loop rollout_proc6_evt_loop terminating... | |
| [2025-01-15 14:43:55,169][01039] Stopping RolloutWorker_w2... | |
| [2025-01-15 14:43:55,174][01039] Loop rollout_proc2_evt_loop terminating... | |
| [2025-01-15 14:43:55,189][00319] Component RolloutWorker_w4 stopped! | |
| [2025-01-15 14:43:55,191][01040] Stopping RolloutWorker_w4... | |
| [2025-01-15 14:43:55,195][01040] Loop rollout_proc4_evt_loop terminating... | |
| [2025-01-15 14:43:55,203][00319] Component RolloutWorker_w1 stopped! | |
| [2025-01-15 14:43:55,210][01036] Stopping RolloutWorker_w1... | |
| [2025-01-15 14:43:55,210][01036] Loop rollout_proc1_evt_loop terminating... | |
| [2025-01-15 14:43:55,218][01037] Stopping RolloutWorker_w0... | |
| [2025-01-15 14:43:55,218][00319] Component RolloutWorker_w0 stopped! | |
| [2025-01-15 14:43:55,225][01037] Loop rollout_proc0_evt_loop terminating... | |
| [2025-01-15 14:43:55,226][00319] Component RolloutWorker_w3 stopped! | |
| [2025-01-15 14:43:55,232][01038] Stopping RolloutWorker_w3... | |
| [2025-01-15 14:43:55,235][01038] Loop rollout_proc3_evt_loop terminating... | |
| [2025-01-15 14:43:55,238][00319] Component RolloutWorker_w7 stopped! | |
| [2025-01-15 14:43:55,243][01043] Stopping RolloutWorker_w7... | |
| [2025-01-15 14:43:55,249][00319] Component RolloutWorker_w5 stopped! | |
| [2025-01-15 14:43:55,255][00319] Waiting for process learner_proc0 to stop... | |
| [2025-01-15 14:43:55,256][01041] Stopping RolloutWorker_w5... | |
| [2025-01-15 14:43:55,245][01043] Loop rollout_proc7_evt_loop terminating... | |
| [2025-01-15 14:43:55,264][01041] Loop rollout_proc5_evt_loop terminating... | |
| [2025-01-15 14:43:56,735][00319] Waiting for process inference_proc0-0 to join... | |
| [2025-01-15 14:43:56,748][00319] Waiting for process rollout_proc0 to join... | |
| [2025-01-15 14:43:58,697][00319] Waiting for process rollout_proc1 to join... | |
| [2025-01-15 14:43:58,750][00319] Waiting for process rollout_proc2 to join... | |
| [2025-01-15 14:43:58,756][00319] Waiting for process rollout_proc3 to join... | |
| [2025-01-15 14:43:58,760][00319] Waiting for process rollout_proc4 to join... | |
| [2025-01-15 14:43:58,764][00319] Waiting for process rollout_proc5 to join... | |
| [2025-01-15 14:43:58,768][00319] Waiting for process rollout_proc6 to join... | |
| [2025-01-15 14:43:58,772][00319] Waiting for process rollout_proc7 to join... | |
| [2025-01-15 14:43:58,776][00319] Batcher 0 profile tree view: | |
| batching: 27.4826, releasing_batches: 0.0303 | |
| [2025-01-15 14:43:58,778][00319] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 418.7503 | |
| update_model: 8.5261 | |
| weight_update: 0.0030 | |
| one_step: 0.0081 | |
| handle_policy_step: 574.0382 | |
| deserialize: 14.6473, stack: 3.3419, obs_to_device_normalize: 122.9754, forward: 288.1993, send_messages: 28.4491 | |
| prepare_outputs: 87.3286 | |
| to_cpu: 52.8217 | |
| [2025-01-15 14:43:58,781][00319] Learner 0 profile tree view: | |
| misc: 0.0047, prepare_batch: 15.0550 | |
| train: 74.3916 | |
| epoch_init: 0.0057, minibatch_init: 0.0066, losses_postprocess: 0.6715, kl_divergence: 0.7288, after_optimizer: 33.4940 | |
| calculate_losses: 26.7837 | |
| losses_init: 0.0049, forward_head: 1.2731, bptt_initial: 18.0487, tail: 1.0836, advantages_returns: 0.2323, losses: 3.8355 | |
| bptt: 1.9727 | |
| bptt_forward_core: 1.8768 | |
| update: 12.0016 | |
| clip: 0.8933 | |
| [2025-01-15 14:43:58,783][00319] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3361, enqueue_policy_requests: 104.0313, env_step: 807.3174, overhead: 13.6173, complete_rollouts: 7.4427 | |
| save_policy_outputs: 21.5908 | |
| split_output_tensors: 8.4833 | |
| [2025-01-15 14:43:58,785][00319] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3348, enqueue_policy_requests: 103.1740, env_step: 807.6032, overhead: 13.3103, complete_rollouts: 6.8850 | |
| save_policy_outputs: 21.6953 | |
| split_output_tensors: 8.5687 | |
| [2025-01-15 14:43:58,787][00319] Loop Runner_EvtLoop terminating... | |
| [2025-01-15 14:43:58,790][00319] Runner profile tree view: | |
| main_loop: 1072.3200 | |
| [2025-01-15 14:43:58,792][00319] Collected {0: 4005888}, FPS: 3735.7 | |
| [2025-01-15 14:44:29,403][00319] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-15 14:44:29,406][00319] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-15 14:44:29,409][00319] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-15 14:44:29,411][00319] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-15 14:44:29,413][00319] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-15 14:44:29,415][00319] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-15 14:44:29,419][00319] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-15 14:44:29,420][00319] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-15 14:44:29,423][00319] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2025-01-15 14:44:29,426][00319] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2025-01-15 14:44:29,427][00319] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-15 14:44:29,428][00319] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-15 14:44:29,429][00319] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-15 14:44:29,431][00319] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-15 14:44:29,432][00319] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-15 14:44:29,463][00319] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-01-15 14:44:29,468][00319] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-15 14:44:29,471][00319] RunningMeanStd input shape: (1,) | |
| [2025-01-15 14:44:29,486][00319] ConvEncoder: input_channels=3 | |
| [2025-01-15 14:44:29,590][00319] Conv encoder output size: 512 | |
| [2025-01-15 14:44:29,592][00319] Policy head output size: 512 | |
| [2025-01-15 14:44:29,779][00319] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-15 14:44:30,593][00319] Num frames 100... | |
| [2025-01-15 14:44:30,721][00319] Num frames 200... | |
| [2025-01-15 14:44:30,841][00319] Num frames 300... | |
| [2025-01-15 14:44:30,962][00319] Num frames 400... | |
| [2025-01-15 14:44:31,084][00319] Num frames 500... | |
| [2025-01-15 14:44:31,202][00319] Num frames 600... | |
| [2025-01-15 14:44:31,331][00319] Num frames 700... | |
| [2025-01-15 14:44:31,447][00319] Num frames 800... | |
| [2025-01-15 14:44:31,565][00319] Num frames 900... | |
| [2025-01-15 14:44:31,683][00319] Num frames 1000... | |
| [2025-01-15 14:44:31,799][00319] Num frames 1100... | |
| [2025-01-15 14:44:31,923][00319] Num frames 1200... | |
| [2025-01-15 14:44:32,043][00319] Num frames 1300... | |
| [2025-01-15 14:44:32,170][00319] Num frames 1400... | |
| [2025-01-15 14:44:32,296][00319] Num frames 1500... | |
| [2025-01-15 14:44:32,362][00319] Avg episode rewards: #0: 33.040, true rewards: #0: 15.040 | |
| [2025-01-15 14:44:32,365][00319] Avg episode reward: 33.040, avg true_objective: 15.040 | |
| [2025-01-15 14:44:32,478][00319] Num frames 1600... | |
| [2025-01-15 14:44:32,597][00319] Num frames 1700... | |
| [2025-01-15 14:44:32,718][00319] Num frames 1800... | |
| [2025-01-15 14:44:32,843][00319] Num frames 1900... | |
| [2025-01-15 14:44:32,963][00319] Num frames 2000... | |
| [2025-01-15 14:44:33,086][00319] Num frames 2100... | |
| [2025-01-15 14:44:33,211][00319] Num frames 2200... | |
| [2025-01-15 14:44:33,342][00319] Num frames 2300... | |
| [2025-01-15 14:44:33,404][00319] Avg episode rewards: #0: 26.020, true rewards: #0: 11.520 | |
| [2025-01-15 14:44:33,406][00319] Avg episode reward: 26.020, avg true_objective: 11.520 | |
| [2025-01-15 14:44:33,522][00319] Num frames 2400... | |
| [2025-01-15 14:44:33,646][00319] Num frames 2500... | |
| [2025-01-15 14:44:33,773][00319] Num frames 2600... | |
| [2025-01-15 14:44:33,892][00319] Num frames 2700... | |
| [2025-01-15 14:44:34,010][00319] Num frames 2800... | |
| [2025-01-15 14:44:34,137][00319] Num frames 2900... | |
| [2025-01-15 14:44:34,257][00319] Num frames 3000... | |
| [2025-01-15 14:44:34,385][00319] Num frames 3100... | |
| [2025-01-15 14:44:34,505][00319] Num frames 3200... | |
| [2025-01-15 14:44:34,630][00319] Num frames 3300... | |
| [2025-01-15 14:44:34,752][00319] Num frames 3400... | |
| [2025-01-15 14:44:34,837][00319] Avg episode rewards: #0: 25.077, true rewards: #0: 11.410 | |
| [2025-01-15 14:44:34,839][00319] Avg episode reward: 25.077, avg true_objective: 11.410 | |
| [2025-01-15 14:44:34,932][00319] Num frames 3500... | |
| [2025-01-15 14:44:35,052][00319] Num frames 3600... | |
| [2025-01-15 14:44:35,180][00319] Num frames 3700... | |
| [2025-01-15 14:44:35,300][00319] Num frames 3800... | |
| [2025-01-15 14:44:35,432][00319] Num frames 3900... | |
| [2025-01-15 14:44:35,554][00319] Num frames 4000... | |
| [2025-01-15 14:44:35,676][00319] Num frames 4100... | |
| [2025-01-15 14:44:35,799][00319] Num frames 4200... | |
| [2025-01-15 14:44:35,920][00319] Num frames 4300... | |
| [2025-01-15 14:44:36,042][00319] Num frames 4400... | |
| [2025-01-15 14:44:36,202][00319] Num frames 4500... | |
| [2025-01-15 14:44:36,374][00319] Num frames 4600... | |
| [2025-01-15 14:44:36,545][00319] Num frames 4700... | |
| [2025-01-15 14:44:36,710][00319] Num frames 4800... | |
| [2025-01-15 14:44:36,873][00319] Num frames 4900... | |
| [2025-01-15 14:44:37,042][00319] Num frames 5000... | |
| [2025-01-15 14:44:37,208][00319] Num frames 5100... | |
| [2025-01-15 14:44:37,371][00319] Num frames 5200... | |
| [2025-01-15 14:44:37,555][00319] Num frames 5300... | |
| [2025-01-15 14:44:37,727][00319] Num frames 5400... | |
| [2025-01-15 14:44:37,888][00319] Num frames 5500... | |
| [2025-01-15 14:44:37,986][00319] Avg episode rewards: #0: 32.807, true rewards: #0: 13.807 | |
| [2025-01-15 14:44:37,989][00319] Avg episode reward: 32.807, avg true_objective: 13.807 | |
| [2025-01-15 14:44:38,130][00319] Num frames 5600... | |
| [2025-01-15 14:44:38,302][00319] Num frames 5700... | |
| [2025-01-15 14:44:38,469][00319] Num frames 5800... | |
| [2025-01-15 14:44:38,645][00319] Num frames 5900... | |
| [2025-01-15 14:44:38,823][00319] Num frames 6000... | |
| [2025-01-15 14:44:39,020][00319] Num frames 6100... | |
| [2025-01-15 14:44:39,193][00319] Num frames 6200... | |
| [2025-01-15 14:44:39,362][00319] Num frames 6300... | |
| [2025-01-15 14:44:39,486][00319] Num frames 6400... | |
| [2025-01-15 14:44:39,607][00319] Avg episode rewards: #0: 30.702, true rewards: #0: 12.902 | |
| [2025-01-15 14:44:39,609][00319] Avg episode reward: 30.702, avg true_objective: 12.902 | |
| [2025-01-15 14:44:39,670][00319] Num frames 6500... | |
| [2025-01-15 14:44:39,788][00319] Num frames 6600... | |
| [2025-01-15 14:44:39,906][00319] Num frames 6700... | |
| [2025-01-15 14:44:40,041][00319] Num frames 6800... | |
| [2025-01-15 14:44:40,168][00319] Num frames 6900... | |
| [2025-01-15 14:44:40,265][00319] Avg episode rewards: #0: 27.218, true rewards: #0: 11.552 | |
| [2025-01-15 14:44:40,267][00319] Avg episode reward: 27.218, avg true_objective: 11.552 | |
| [2025-01-15 14:44:40,349][00319] Num frames 7000... | |
| [2025-01-15 14:44:40,470][00319] Num frames 7100... | |
| [2025-01-15 14:44:40,601][00319] Num frames 7200... | |
| [2025-01-15 14:44:40,719][00319] Num frames 7300... | |
| [2025-01-15 14:44:40,836][00319] Num frames 7400... | |
| [2025-01-15 14:44:40,953][00319] Num frames 7500... | |
| [2025-01-15 14:44:41,077][00319] Num frames 7600... | |
| [2025-01-15 14:44:41,130][00319] Avg episode rewards: #0: 25.143, true rewards: #0: 10.857 | |
| [2025-01-15 14:44:41,132][00319] Avg episode reward: 25.143, avg true_objective: 10.857 | |
| [2025-01-15 14:44:41,251][00319] Num frames 7700... | |
| [2025-01-15 14:44:41,370][00319] Num frames 7800... | |
| [2025-01-15 14:44:41,490][00319] Num frames 7900... | |
| [2025-01-15 14:44:41,617][00319] Num frames 8000... | |
| [2025-01-15 14:44:41,731][00319] Avg episode rewards: #0: 23.060, true rewards: #0: 10.060 | |
| [2025-01-15 14:44:41,734][00319] Avg episode reward: 23.060, avg true_objective: 10.060 | |
| [2025-01-15 14:44:41,797][00319] Num frames 8100... | |
| [2025-01-15 14:44:41,914][00319] Num frames 8200... | |
| [2025-01-15 14:44:42,035][00319] Num frames 8300... | |
| [2025-01-15 14:44:42,192][00319] Num frames 8400... | |
| [2025-01-15 14:44:42,308][00319] Num frames 8500... | |
| [2025-01-15 14:44:42,429][00319] Num frames 8600... | |
| [2025-01-15 14:44:42,548][00319] Num frames 8700... | |
| [2025-01-15 14:44:42,632][00319] Avg episode rewards: #0: 21.803, true rewards: #0: 9.692 | |
| [2025-01-15 14:44:42,635][00319] Avg episode reward: 21.803, avg true_objective: 9.692 | |
| [2025-01-15 14:44:42,735][00319] Num frames 8800... | |
| [2025-01-15 14:44:42,854][00319] Num frames 8900... | |
| [2025-01-15 14:44:42,974][00319] Num frames 9000... | |
| [2025-01-15 14:44:43,098][00319] Num frames 9100... | |
| [2025-01-15 14:44:43,222][00319] Num frames 9200... | |
| [2025-01-15 14:44:43,341][00319] Num frames 9300... | |
| [2025-01-15 14:44:43,460][00319] Num frames 9400... | |
| [2025-01-15 14:44:43,583][00319] Num frames 9500... | |
| [2025-01-15 14:44:43,715][00319] Num frames 9600... | |
| [2025-01-15 14:44:43,836][00319] Num frames 9700... | |
| [2025-01-15 14:44:43,959][00319] Num frames 9800... | |
| [2025-01-15 14:44:44,083][00319] Num frames 9900... | |
| [2025-01-15 14:44:44,208][00319] Num frames 10000... | |
| [2025-01-15 14:44:44,329][00319] Num frames 10100... | |
| [2025-01-15 14:44:44,454][00319] Num frames 10200... | |
| [2025-01-15 14:44:44,575][00319] Num frames 10300... | |
| [2025-01-15 14:44:44,706][00319] Num frames 10400... | |
| [2025-01-15 14:44:44,829][00319] Num frames 10500... | |
| [2025-01-15 14:44:44,959][00319] Num frames 10600... | |
| [2025-01-15 14:44:45,085][00319] Num frames 10700... | |
| [2025-01-15 14:44:45,208][00319] Num frames 10800... | |
| [2025-01-15 14:44:45,294][00319] Avg episode rewards: #0: 25.223, true rewards: #0: 10.823 | |
| [2025-01-15 14:44:45,296][00319] Avg episode reward: 25.223, avg true_objective: 10.823 | |
| [2025-01-15 14:45:52,412][00319] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2025-01-15 14:46:49,681][00319] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-01-15 14:46:49,684][00319] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-01-15 14:46:49,686][00319] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-01-15 14:46:49,689][00319] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-01-15 14:46:49,691][00319] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-01-15 14:46:49,696][00319] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-01-15 14:46:49,698][00319] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-01-15 14:46:49,700][00319] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-01-15 14:46:49,705][00319] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-01-15 14:46:49,707][00319] Adding new argument 'hf_repository'='Stoub/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-01-15 14:46:49,709][00319] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-01-15 14:46:49,710][00319] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-01-15 14:46:49,711][00319] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-01-15 14:46:49,714][00319] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-01-15 14:46:49,715][00319] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-01-15 14:46:49,758][00319] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-01-15 14:46:49,762][00319] RunningMeanStd input shape: (1,) | |
| [2025-01-15 14:46:49,781][00319] ConvEncoder: input_channels=3 | |
| [2025-01-15 14:46:49,843][00319] Conv encoder output size: 512 | |
| [2025-01-15 14:46:49,854][00319] Policy head output size: 512 | |
| [2025-01-15 14:46:49,883][00319] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-01-15 14:46:50,562][00319] Num frames 100... | |
| [2025-01-15 14:46:50,737][00319] Num frames 200... | |
| [2025-01-15 14:46:50,911][00319] Num frames 300... | |
| [2025-01-15 14:46:51,085][00319] Num frames 400... | |
| [2025-01-15 14:46:51,254][00319] Num frames 500... | |
| [2025-01-15 14:46:51,422][00319] Num frames 600... | |
| [2025-01-15 14:46:51,588][00319] Num frames 700... | |
| [2025-01-15 14:46:51,765][00319] Num frames 800... | |
| [2025-01-15 14:46:51,937][00319] Num frames 900... | |
| [2025-01-15 14:46:52,088][00319] Num frames 1000... | |
| [2025-01-15 14:46:52,212][00319] Avg episode rewards: #0: 24.560, true rewards: #0: 10.560 | |
| [2025-01-15 14:46:52,214][00319] Avg episode reward: 24.560, avg true_objective: 10.560 | |
| [2025-01-15 14:46:52,270][00319] Num frames 1100... | |
| [2025-01-15 14:46:52,394][00319] Num frames 1200... | |
| [2025-01-15 14:46:52,522][00319] Num frames 1300... | |
| [2025-01-15 14:46:52,641][00319] Num frames 1400... | |
| [2025-01-15 14:46:52,766][00319] Num frames 1500... | |
| [2025-01-15 14:46:52,892][00319] Num frames 1600... | |
| [2025-01-15 14:46:53,014][00319] Num frames 1700... | |
| [2025-01-15 14:46:53,140][00319] Num frames 1800... | |
| [2025-01-15 14:46:53,266][00319] Num frames 1900... | |
| [2025-01-15 14:46:53,381][00319] Num frames 2000... | |
| [2025-01-15 14:46:53,508][00319] Num frames 2100... | |
| [2025-01-15 14:46:53,625][00319] Num frames 2200... | |
| [2025-01-15 14:46:53,744][00319] Num frames 2300... | |
| [2025-01-15 14:46:53,878][00319] Avg episode rewards: #0: 27.840, true rewards: #0: 11.840 | |
| [2025-01-15 14:46:53,880][00319] Avg episode reward: 27.840, avg true_objective: 11.840 | |
| [2025-01-15 14:46:53,923][00319] Num frames 2400... | |
| [2025-01-15 14:46:54,043][00319] Num frames 2500... | |
| [2025-01-15 14:46:54,173][00319] Num frames 2600... | |
| [2025-01-15 14:46:54,290][00319] Num frames 2700... | |
| [2025-01-15 14:46:54,407][00319] Num frames 2800... | |
| [2025-01-15 14:46:54,535][00319] Num frames 2900... | |
| [2025-01-15 14:46:54,654][00319] Num frames 3000... | |
| [2025-01-15 14:46:54,772][00319] Num frames 3100... | |
| [2025-01-15 14:46:54,889][00319] Num frames 3200... | |
| [2025-01-15 14:46:55,018][00319] Num frames 3300... | |
| [2025-01-15 14:46:55,147][00319] Num frames 3400... | |
| [2025-01-15 14:46:55,268][00319] Num frames 3500... | |
| [2025-01-15 14:46:55,389][00319] Num frames 3600... | |
| [2025-01-15 14:46:55,511][00319] Num frames 3700... | |
| [2025-01-15 14:46:55,642][00319] Num frames 3800... | |
| [2025-01-15 14:46:55,761][00319] Num frames 3900... | |
| [2025-01-15 14:46:55,878][00319] Num frames 4000... | |
| [2025-01-15 14:46:56,003][00319] Num frames 4100... | |
| [2025-01-15 14:46:56,131][00319] Num frames 4200... | |
| [2025-01-15 14:46:56,252][00319] Num frames 4300... | |
| [2025-01-15 14:46:56,373][00319] Num frames 4400... | |
| [2025-01-15 14:46:56,516][00319] Avg episode rewards: #0: 37.893, true rewards: #0: 14.893 | |
| [2025-01-15 14:46:56,518][00319] Avg episode reward: 37.893, avg true_objective: 14.893 | |
| [2025-01-15 14:46:56,561][00319] Num frames 4500... | |
| [2025-01-15 14:46:56,683][00319] Num frames 4600... | |
| [2025-01-15 14:46:56,801][00319] Num frames 4700... | |
| [2025-01-15 14:46:56,924][00319] Num frames 4800... | |
| [2025-01-15 14:46:57,045][00319] Num frames 4900... | |
| [2025-01-15 14:46:57,174][00319] Num frames 5000... | |
| [2025-01-15 14:46:57,294][00319] Num frames 5100... | |
| [2025-01-15 14:46:57,418][00319] Num frames 5200... | |
| [2025-01-15 14:46:57,538][00319] Num frames 5300... | |
| [2025-01-15 14:46:57,668][00319] Num frames 5400... | |
| [2025-01-15 14:46:57,794][00319] Num frames 5500... | |
| [2025-01-15 14:46:57,916][00319] Num frames 5600... | |
| [2025-01-15 14:46:58,039][00319] Num frames 5700... | |
| [2025-01-15 14:46:58,164][00319] Num frames 5800... | |
| [2025-01-15 14:46:58,286][00319] Num frames 5900... | |
| [2025-01-15 14:46:58,406][00319] Num frames 6000... | |
| [2025-01-15 14:46:58,522][00319] Num frames 6100... | |
| [2025-01-15 14:46:58,652][00319] Num frames 6200... | |
| [2025-01-15 14:46:58,774][00319] Num frames 6300... | |
| [2025-01-15 14:46:58,894][00319] Num frames 6400... | |
| [2025-01-15 14:46:59,020][00319] Num frames 6500... | |
| [2025-01-15 14:46:59,162][00319] Avg episode rewards: #0: 41.420, true rewards: #0: 16.420 | |
| [2025-01-15 14:46:59,164][00319] Avg episode reward: 41.420, avg true_objective: 16.420 | |
| [2025-01-15 14:46:59,207][00319] Num frames 6600... | |
| [2025-01-15 14:46:59,322][00319] Num frames 6700... | |
| [2025-01-15 14:46:59,441][00319] Num frames 6800... | |
| [2025-01-15 14:46:59,560][00319] Num frames 6900... | |
| [2025-01-15 14:46:59,689][00319] Num frames 7000... | |
| [2025-01-15 14:46:59,808][00319] Num frames 7100... | |
| [2025-01-15 14:46:59,935][00319] Num frames 7200... | |
| [2025-01-15 14:47:00,057][00319] Num frames 7300... | |
| [2025-01-15 14:47:00,185][00319] Num frames 7400... | |
| [2025-01-15 14:47:00,304][00319] Num frames 7500... | |
| [2025-01-15 14:47:00,421][00319] Num frames 7600... | |
| [2025-01-15 14:47:00,541][00319] Num frames 7700... | |
| [2025-01-15 14:47:00,622][00319] Avg episode rewards: #0: 38.840, true rewards: #0: 15.440 | |
| [2025-01-15 14:47:00,624][00319] Avg episode reward: 38.840, avg true_objective: 15.440 | |
| [2025-01-15 14:47:00,732][00319] Num frames 7800... | |
| [2025-01-15 14:47:00,854][00319] Num frames 7900... | |
| [2025-01-15 14:47:00,981][00319] Num frames 8000... | |
| [2025-01-15 14:47:01,110][00319] Num frames 8100... | |
| [2025-01-15 14:47:01,232][00319] Num frames 8200... | |
| [2025-01-15 14:47:01,352][00319] Num frames 8300... | |
| [2025-01-15 14:47:01,471][00319] Num frames 8400... | |
| [2025-01-15 14:47:01,568][00319] Avg episode rewards: #0: 35.055, true rewards: #0: 14.055 | |
| [2025-01-15 14:47:01,570][00319] Avg episode reward: 35.055, avg true_objective: 14.055 | |
| [2025-01-15 14:47:01,650][00319] Num frames 8500... | |
| [2025-01-15 14:47:01,778][00319] Num frames 8600... | |
| [2025-01-15 14:47:01,899][00319] Num frames 8700... | |
| [2025-01-15 14:47:02,032][00319] Num frames 8800... | |
| [2025-01-15 14:47:02,203][00319] Num frames 8900... | |
| [2025-01-15 14:47:02,369][00319] Num frames 9000... | |
| [2025-01-15 14:47:02,535][00319] Num frames 9100... | |
| [2025-01-15 14:47:02,694][00319] Num frames 9200... | |
| [2025-01-15 14:47:02,864][00319] Num frames 9300... | |
| [2025-01-15 14:47:03,027][00319] Avg episode rewards: #0: 33.087, true rewards: #0: 13.373 | |
| [2025-01-15 14:47:03,030][00319] Avg episode reward: 33.087, avg true_objective: 13.373 | |
| [2025-01-15 14:47:03,106][00319] Num frames 9400... | |
| [2025-01-15 14:47:03,265][00319] Num frames 9500... | |
| [2025-01-15 14:47:03,429][00319] Num frames 9600... | |
| [2025-01-15 14:47:03,590][00319] Num frames 9700... | |
| [2025-01-15 14:47:03,757][00319] Num frames 9800... | |
| [2025-01-15 14:47:03,928][00319] Num frames 9900... | |
| [2025-01-15 14:47:04,101][00319] Num frames 10000... | |
| [2025-01-15 14:47:04,275][00319] Num frames 10100... | |
| [2025-01-15 14:47:04,439][00319] Num frames 10200... | |
| [2025-01-15 14:47:04,612][00319] Num frames 10300... | |
| [2025-01-15 14:47:04,767][00319] Avg episode rewards: #0: 31.566, true rewards: #0: 12.941 | |
| [2025-01-15 14:47:04,769][00319] Avg episode reward: 31.566, avg true_objective: 12.941 | |
| [2025-01-15 14:47:04,865][00319] Num frames 10400... | |
| [2025-01-15 14:47:05,043][00319] Num frames 10500... | |
| [2025-01-15 14:47:05,223][00319] Num frames 10600... | |
| [2025-01-15 14:47:05,391][00319] Num frames 10700... | |
| [2025-01-15 14:47:05,567][00319] Num frames 10800... | |
| [2025-01-15 14:47:05,711][00319] Num frames 10900... | |
| [2025-01-15 14:47:05,831][00319] Num frames 11000... | |
| [2025-01-15 14:47:05,960][00319] Num frames 11100... | |
| [2025-01-15 14:47:06,084][00319] Num frames 11200... | |
| [2025-01-15 14:47:06,208][00319] Num frames 11300... | |
| [2025-01-15 14:47:06,326][00319] Num frames 11400... | |
| [2025-01-15 14:47:06,447][00319] Num frames 11500... | |
| [2025-01-15 14:47:06,511][00319] Avg episode rewards: #0: 31.228, true rewards: #0: 12.783 | |
| [2025-01-15 14:47:06,513][00319] Avg episode reward: 31.228, avg true_objective: 12.783 | |
| [2025-01-15 14:47:06,624][00319] Num frames 11600... | |
| [2025-01-15 14:47:06,747][00319] Num frames 11700... | |
| [2025-01-15 14:47:06,863][00319] Num frames 11800... | |
| [2025-01-15 14:47:06,994][00319] Num frames 11900... | |
| [2025-01-15 14:47:07,121][00319] Num frames 12000... | |
| [2025-01-15 14:47:07,244][00319] Num frames 12100... | |
| [2025-01-15 14:47:07,365][00319] Num frames 12200... | |
| [2025-01-15 14:47:07,484][00319] Num frames 12300... | |
| [2025-01-15 14:47:07,606][00319] Num frames 12400... | |
| [2025-01-15 14:47:07,729][00319] Num frames 12500... | |
| [2025-01-15 14:47:07,849][00319] Num frames 12600... | |
| [2025-01-15 14:47:07,980][00319] Num frames 12700... | |
| [2025-01-15 14:47:08,109][00319] Num frames 12800... | |
| [2025-01-15 14:47:08,229][00319] Num frames 12900... | |
| [2025-01-15 14:47:08,347][00319] Num frames 13000... | |
| [2025-01-15 14:47:08,415][00319] Avg episode rewards: #0: 31.209, true rewards: #0: 13.009 | |
| [2025-01-15 14:47:08,417][00319] Avg episode reward: 31.209, avg true_objective: 13.009 | |
| [2025-01-15 14:48:28,537][00319] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |