| [2025-03-06 21:44:12,880][00284] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2025-03-06 21:44:12,882][00284] Rollout worker 0 uses device cpu | |
| [2025-03-06 21:44:12,882][00284] Rollout worker 1 uses device cpu | |
| [2025-03-06 21:44:12,884][00284] Rollout worker 2 uses device cpu | |
| [2025-03-06 21:44:12,885][00284] Rollout worker 3 uses device cpu | |
| [2025-03-06 21:44:12,886][00284] Rollout worker 4 uses device cpu | |
| [2025-03-06 21:44:12,887][00284] Rollout worker 5 uses device cpu | |
| [2025-03-06 21:44:12,888][00284] Rollout worker 6 uses device cpu | |
| [2025-03-06 21:44:12,889][00284] Rollout worker 7 uses device cpu | |
| [2025-03-06 21:44:13,139][00284] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-03-06 21:44:13,140][00284] InferenceWorker_p0-w0: min num requests: 2 | |
| [2025-03-06 21:44:13,174][00284] Starting all processes... | |
| [2025-03-06 21:44:13,174][00284] Starting process learner_proc0 | |
| [2025-03-06 21:44:13,233][00284] Starting all processes... | |
| [2025-03-06 21:44:13,242][00284] Starting process inference_proc0-0 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc0 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc1 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc2 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc3 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc4 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc5 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc6 | |
| [2025-03-06 21:44:13,242][00284] Starting process rollout_proc7 | |
| [2025-03-06 21:44:29,617][05512] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-03-06 21:44:29,617][05512] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2025-03-06 21:44:29,622][05529] Worker 3 uses CPU cores [1] | |
| [2025-03-06 21:44:29,706][05512] Num visible devices: 1 | |
| [2025-03-06 21:44:29,724][05512] Starting seed is not provided | |
| [2025-03-06 21:44:29,727][05512] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-03-06 21:44:29,728][05512] Initializing actor-critic model on device cuda:0 | |
| [2025-03-06 21:44:29,731][05512] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-03-06 21:44:29,734][05512] RunningMeanStd input shape: (1,) | |
| [2025-03-06 21:44:29,791][05512] ConvEncoder: input_channels=3 | |
| [2025-03-06 21:44:29,810][05533] Worker 7 uses CPU cores [1] | |
| [2025-03-06 21:44:29,967][05525] Worker 0 uses CPU cores [0] | |
| [2025-03-06 21:44:30,017][05531] Worker 5 uses CPU cores [1] | |
| [2025-03-06 21:44:30,041][05527] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-03-06 21:44:30,043][05527] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2025-03-06 21:44:30,092][05527] Num visible devices: 1 | |
| [2025-03-06 21:44:30,100][05526] Worker 1 uses CPU cores [1] | |
| [2025-03-06 21:44:30,111][05532] Worker 6 uses CPU cores [0] | |
| [2025-03-06 21:44:30,153][05530] Worker 4 uses CPU cores [0] | |
| [2025-03-06 21:44:30,162][05528] Worker 2 uses CPU cores [0] | |
| [2025-03-06 21:44:30,238][05512] Conv encoder output size: 512 | |
| [2025-03-06 21:44:30,238][05512] Policy head output size: 512 | |
| [2025-03-06 21:44:30,293][05512] Created Actor Critic model with architecture: | |
| [2025-03-06 21:44:30,293][05512] 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) | |
| ) | |
| ) | |
| [2025-03-06 21:44:30,627][05512] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2025-03-06 21:44:33,139][00284] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2025-03-06 21:44:33,148][00284] Heartbeat connected on RolloutWorker_w0 | |
| [2025-03-06 21:44:33,151][00284] Heartbeat connected on RolloutWorker_w1 | |
| [2025-03-06 21:44:33,158][00284] Heartbeat connected on RolloutWorker_w2 | |
| [2025-03-06 21:44:33,159][00284] Heartbeat connected on RolloutWorker_w3 | |
| [2025-03-06 21:44:33,165][00284] Heartbeat connected on RolloutWorker_w4 | |
| [2025-03-06 21:44:33,166][00284] Heartbeat connected on RolloutWorker_w5 | |
| [2025-03-06 21:44:33,170][00284] Heartbeat connected on RolloutWorker_w6 | |
| [2025-03-06 21:44:33,173][00284] Heartbeat connected on RolloutWorker_w7 | |
| [2025-03-06 21:44:33,417][00284] Heartbeat connected on Batcher_0 | |
| [2025-03-06 21:44:35,325][05512] No checkpoints found | |
| [2025-03-06 21:44:35,325][05512] Did not load from checkpoint, starting from scratch! | |
| [2025-03-06 21:44:35,326][05512] Initialized policy 0 weights for model version 0 | |
| [2025-03-06 21:44:35,328][05512] LearnerWorker_p0 finished initialization! | |
| [2025-03-06 21:44:35,329][00284] Heartbeat connected on LearnerWorker_p0 | |
| [2025-03-06 21:44:35,332][05512] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2025-03-06 21:44:35,553][05527] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-03-06 21:44:35,555][05527] RunningMeanStd input shape: (1,) | |
| [2025-03-06 21:44:35,566][05527] ConvEncoder: input_channels=3 | |
| [2025-03-06 21:44:35,667][05527] Conv encoder output size: 512 | |
| [2025-03-06 21:44:35,667][05527] Policy head output size: 512 | |
| [2025-03-06 21:44:35,702][00284] Inference worker 0-0 is ready! | |
| [2025-03-06 21:44:35,702][00284] All inference workers are ready! Signal rollout workers to start! | |
| [2025-03-06 21:44:35,996][05530] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:35,993][05532] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,000][05525] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,026][05528] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,031][05531] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,040][05526] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,048][05533] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:36,110][05529] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 21:44:37,326][00284] 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) | |
| [2025-03-06 21:44:37,402][05531] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:37,400][05526] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:37,556][05525] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:37,558][05532] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:37,560][05530] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:37,572][05528] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:38,378][05528] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:38,376][05530] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:38,731][05526] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:38,735][05531] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:39,128][05529] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:39,163][05533] Decorrelating experience for 0 frames... | |
| [2025-03-06 21:44:39,684][05530] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:39,687][05528] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:39,941][05532] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:40,532][05529] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:40,556][05533] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:40,606][05531] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:41,142][05528] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:41,145][05530] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:41,571][05526] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:41,994][05525] Decorrelating experience for 32 frames... | |
| [2025-03-06 21:44:42,326][00284] 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) | |
| [2025-03-06 21:44:42,991][05532] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:43,142][05531] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:43,446][05529] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:43,448][05533] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:43,761][05526] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:45,349][05532] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:46,171][05525] Decorrelating experience for 64 frames... | |
| [2025-03-06 21:44:47,326][00284] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 107.4. Samples: 1074. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2025-03-06 21:44:47,333][00284] Avg episode reward: [(0, '2.547')] | |
| [2025-03-06 21:44:48,211][05512] Signal inference workers to stop experience collection... | |
| [2025-03-06 21:44:48,236][05527] InferenceWorker_p0-w0: stopping experience collection | |
| [2025-03-06 21:44:49,386][05525] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:49,428][05512] Signal inference workers to resume experience collection... | |
| [2025-03-06 21:44:49,431][05527] InferenceWorker_p0-w0: resuming experience collection | |
| [2025-03-06 21:44:49,570][05529] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:50,027][05533] Decorrelating experience for 96 frames... | |
| [2025-03-06 21:44:52,326][00284] Fps is (10 sec: 1638.4, 60 sec: 1092.3, 300 sec: 1092.3). Total num frames: 16384. Throughput: 0: 222.4. Samples: 3336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:44:52,328][00284] Avg episode reward: [(0, '3.200')] | |
| [2025-03-06 21:44:57,135][05527] Updated weights for policy 0, policy_version 10 (0.0164) | |
| [2025-03-06 21:44:57,326][00284] Fps is (10 sec: 4095.9, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 40960. Throughput: 0: 514.3. Samples: 10286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:44:57,329][00284] Avg episode reward: [(0, '3.829')] | |
| [2025-03-06 21:45:02,326][00284] Fps is (10 sec: 4095.8, 60 sec: 2293.7, 300 sec: 2293.7). Total num frames: 57344. Throughput: 0: 546.0. Samples: 13650. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:45:02,329][00284] Avg episode reward: [(0, '4.276')] | |
| [2025-03-06 21:45:07,326][00284] Fps is (10 sec: 3686.5, 60 sec: 2594.1, 300 sec: 2594.1). Total num frames: 77824. Throughput: 0: 625.1. Samples: 18754. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:45:07,327][00284] Avg episode reward: [(0, '4.509')] | |
| [2025-03-06 21:45:07,622][05527] Updated weights for policy 0, policy_version 20 (0.0028) | |
| [2025-03-06 21:45:12,326][00284] Fps is (10 sec: 4505.7, 60 sec: 2925.7, 300 sec: 2925.7). Total num frames: 102400. Throughput: 0: 740.4. Samples: 25914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:45:12,331][00284] Avg episode reward: [(0, '4.480')] | |
| [2025-03-06 21:45:12,334][05512] Saving new best policy, reward=4.480! | |
| [2025-03-06 21:45:17,326][00284] Fps is (10 sec: 4096.0, 60 sec: 2969.6, 300 sec: 2969.6). Total num frames: 118784. Throughput: 0: 718.1. Samples: 28724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:45:17,329][00284] Avg episode reward: [(0, '4.511')] | |
| [2025-03-06 21:45:17,336][05512] Saving new best policy, reward=4.511! | |
| [2025-03-06 21:45:18,259][05527] Updated weights for policy 0, policy_version 30 (0.0022) | |
| [2025-03-06 21:45:22,326][00284] Fps is (10 sec: 3686.5, 60 sec: 3094.8, 300 sec: 3094.8). Total num frames: 139264. Throughput: 0: 755.4. Samples: 33994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:45:22,327][00284] Avg episode reward: [(0, '4.553')] | |
| [2025-03-06 21:45:22,330][05512] Saving new best policy, reward=4.553! | |
| [2025-03-06 21:45:27,061][05527] Updated weights for policy 0, policy_version 40 (0.0013) | |
| [2025-03-06 21:45:27,326][00284] Fps is (10 sec: 4505.6, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 163840. Throughput: 0: 911.1. Samples: 40998. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:45:27,327][00284] Avg episode reward: [(0, '4.523')] | |
| [2025-03-06 21:45:32,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 180224. Throughput: 0: 954.2. Samples: 44014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:45:32,327][00284] Avg episode reward: [(0, '4.659')] | |
| [2025-03-06 21:45:32,329][05512] Saving new best policy, reward=4.659! | |
| [2025-03-06 21:45:37,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3345.1). Total num frames: 200704. Throughput: 0: 1025.7. Samples: 49492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:45:37,327][00284] Avg episode reward: [(0, '4.493')] | |
| [2025-03-06 21:45:37,625][05527] Updated weights for policy 0, policy_version 50 (0.0023) | |
| [2025-03-06 21:45:42,326][00284] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3465.8). Total num frames: 225280. Throughput: 0: 1027.7. Samples: 56532. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:45:42,327][00284] Avg episode reward: [(0, '4.595')] | |
| [2025-03-06 21:45:47,328][00284] Fps is (10 sec: 4095.3, 60 sec: 4027.6, 300 sec: 3452.3). Total num frames: 241664. Throughput: 0: 1015.0. Samples: 59326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:45:47,329][00284] Avg episode reward: [(0, '4.761')] | |
| [2025-03-06 21:45:47,337][05512] Saving new best policy, reward=4.761! | |
| [2025-03-06 21:45:48,353][05527] Updated weights for policy 0, policy_version 60 (0.0021) | |
| [2025-03-06 21:45:52,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3495.3). Total num frames: 262144. Throughput: 0: 1020.7. Samples: 64684. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:45:52,331][00284] Avg episode reward: [(0, '5.052')] | |
| [2025-03-06 21:45:52,333][05512] Saving new best policy, reward=5.052! | |
| [2025-03-06 21:45:57,326][00284] Fps is (10 sec: 4096.7, 60 sec: 4027.8, 300 sec: 3532.8). Total num frames: 282624. Throughput: 0: 1014.9. Samples: 71586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:45:57,329][00284] Avg episode reward: [(0, '5.056')] | |
| [2025-03-06 21:45:57,348][05512] Saving new best policy, reward=5.056! | |
| [2025-03-06 21:45:57,364][05527] Updated weights for policy 0, policy_version 70 (0.0024) | |
| [2025-03-06 21:46:02,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3517.7). Total num frames: 299008. Throughput: 0: 1011.5. Samples: 74242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:46:02,329][00284] Avg episode reward: [(0, '4.768')] | |
| [2025-03-06 21:46:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3595.4). Total num frames: 323584. Throughput: 0: 1021.2. Samples: 79946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:46:07,330][00284] Avg episode reward: [(0, '4.862')] | |
| [2025-03-06 21:46:07,336][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000079_323584.pth... | |
| [2025-03-06 21:46:07,937][05527] Updated weights for policy 0, policy_version 80 (0.0014) | |
| [2025-03-06 21:46:12,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3664.8). Total num frames: 348160. Throughput: 0: 1021.5. Samples: 86964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:46:12,330][00284] Avg episode reward: [(0, '4.927')] | |
| [2025-03-06 21:46:17,326][00284] Fps is (10 sec: 3686.3, 60 sec: 4027.7, 300 sec: 3604.5). Total num frames: 360448. Throughput: 0: 1009.5. Samples: 89442. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:46:17,329][00284] Avg episode reward: [(0, '4.912')] | |
| [2025-03-06 21:46:18,416][05527] Updated weights for policy 0, policy_version 90 (0.0024) | |
| [2025-03-06 21:46:22,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3666.9). Total num frames: 385024. Throughput: 0: 1020.7. Samples: 95424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:46:22,327][00284] Avg episode reward: [(0, '5.152')] | |
| [2025-03-06 21:46:22,332][05512] Saving new best policy, reward=5.152! | |
| [2025-03-06 21:46:27,199][05527] Updated weights for policy 0, policy_version 100 (0.0022) | |
| [2025-03-06 21:46:27,326][00284] Fps is (10 sec: 4915.3, 60 sec: 4096.0, 300 sec: 3723.6). Total num frames: 409600. Throughput: 0: 1019.2. Samples: 102396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:46:27,328][00284] Avg episode reward: [(0, '5.568')] | |
| [2025-03-06 21:46:27,335][05512] Saving new best policy, reward=5.568! | |
| [2025-03-06 21:46:32,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3668.6). Total num frames: 421888. Throughput: 0: 1010.7. Samples: 104806. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:46:32,329][00284] Avg episode reward: [(0, '5.449')] | |
| [2025-03-06 21:46:37,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3720.5). Total num frames: 446464. Throughput: 0: 1025.6. Samples: 110834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:46:37,332][00284] Avg episode reward: [(0, '5.251')] | |
| [2025-03-06 21:46:37,747][05527] Updated weights for policy 0, policy_version 110 (0.0018) | |
| [2025-03-06 21:46:42,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4096.0, 300 sec: 3768.3). Total num frames: 471040. Throughput: 0: 1028.8. Samples: 117884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:46:42,329][00284] Avg episode reward: [(0, '5.581')] | |
| [2025-03-06 21:46:42,333][05512] Saving new best policy, reward=5.581! | |
| [2025-03-06 21:46:47,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 3717.9). Total num frames: 483328. Throughput: 0: 1014.7. Samples: 119902. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:46:47,332][00284] Avg episode reward: [(0, '5.433')] | |
| [2025-03-06 21:46:48,626][05527] Updated weights for policy 0, policy_version 120 (0.0013) | |
| [2025-03-06 21:46:52,326][00284] Fps is (10 sec: 3686.3, 60 sec: 4096.0, 300 sec: 3762.2). Total num frames: 507904. Throughput: 0: 1022.3. Samples: 125948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:46:52,327][00284] Avg episode reward: [(0, '5.223')] | |
| [2025-03-06 21:46:57,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3774.2). Total num frames: 528384. Throughput: 0: 1023.6. Samples: 133024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:46:57,330][00284] Avg episode reward: [(0, '5.316')] | |
| [2025-03-06 21:46:57,587][05527] Updated weights for policy 0, policy_version 130 (0.0019) | |
| [2025-03-06 21:47:02,326][00284] Fps is (10 sec: 3686.5, 60 sec: 4096.0, 300 sec: 3757.0). Total num frames: 544768. Throughput: 0: 1016.2. Samples: 135172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:02,329][00284] Avg episode reward: [(0, '5.484')] | |
| [2025-03-06 21:47:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 3795.6). Total num frames: 569344. Throughput: 0: 1027.6. Samples: 141664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:07,329][00284] Avg episode reward: [(0, '5.505')] | |
| [2025-03-06 21:47:07,602][05527] Updated weights for policy 0, policy_version 140 (0.0023) | |
| [2025-03-06 21:47:12,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3805.3). Total num frames: 589824. Throughput: 0: 1022.0. Samples: 148388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:12,330][00284] Avg episode reward: [(0, '5.503')] | |
| [2025-03-06 21:47:17,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 3788.8). Total num frames: 606208. Throughput: 0: 1015.7. Samples: 150512. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:47:17,330][00284] Avg episode reward: [(0, '5.423')] | |
| [2025-03-06 21:47:19,295][05527] Updated weights for policy 0, policy_version 150 (0.0020) | |
| [2025-03-06 21:47:22,326][00284] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 3773.3). Total num frames: 622592. Throughput: 0: 984.8. Samples: 155152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:22,331][00284] Avg episode reward: [(0, '5.288')] | |
| [2025-03-06 21:47:27,331][00284] Fps is (10 sec: 3684.6, 60 sec: 3890.9, 300 sec: 3782.7). Total num frames: 643072. Throughput: 0: 969.5. Samples: 161518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:27,335][00284] Avg episode reward: [(0, '5.906')] | |
| [2025-03-06 21:47:27,341][05512] Saving new best policy, reward=5.906! | |
| [2025-03-06 21:47:30,674][05527] Updated weights for policy 0, policy_version 160 (0.0020) | |
| [2025-03-06 21:47:32,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3768.3). Total num frames: 659456. Throughput: 0: 969.2. Samples: 163518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:47:32,332][00284] Avg episode reward: [(0, '6.224')] | |
| [2025-03-06 21:47:32,376][05512] Saving new best policy, reward=6.224! | |
| [2025-03-06 21:47:37,326][00284] Fps is (10 sec: 4098.0, 60 sec: 3959.5, 300 sec: 3800.2). Total num frames: 684032. Throughput: 0: 980.4. Samples: 170066. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:47:37,330][00284] Avg episode reward: [(0, '6.654')] | |
| [2025-03-06 21:47:37,337][05512] Saving new best policy, reward=6.654! | |
| [2025-03-06 21:47:39,700][05527] Updated weights for policy 0, policy_version 170 (0.0022) | |
| [2025-03-06 21:47:42,327][00284] Fps is (10 sec: 4505.3, 60 sec: 3891.2, 300 sec: 3808.2). Total num frames: 704512. Throughput: 0: 965.4. Samples: 176466. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:47:42,329][00284] Avg episode reward: [(0, '6.795')] | |
| [2025-03-06 21:47:42,333][05512] Saving new best policy, reward=6.795! | |
| [2025-03-06 21:47:47,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3794.2). Total num frames: 720896. Throughput: 0: 961.2. Samples: 178426. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:47:47,327][00284] Avg episode reward: [(0, '6.200')] | |
| [2025-03-06 21:47:50,497][05527] Updated weights for policy 0, policy_version 180 (0.0015) | |
| [2025-03-06 21:47:52,326][00284] Fps is (10 sec: 4096.3, 60 sec: 3959.5, 300 sec: 3822.9). Total num frames: 745472. Throughput: 0: 969.7. Samples: 185302. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:47:52,327][00284] Avg episode reward: [(0, '6.439')] | |
| [2025-03-06 21:47:57,326][00284] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3829.8). Total num frames: 765952. Throughput: 0: 961.6. Samples: 191658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:47:57,329][00284] Avg episode reward: [(0, '7.198')] | |
| [2025-03-06 21:47:57,336][05512] Saving new best policy, reward=7.198! | |
| [2025-03-06 21:48:00,722][05527] Updated weights for policy 0, policy_version 190 (0.0014) | |
| [2025-03-06 21:48:02,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3816.3). Total num frames: 782336. Throughput: 0: 964.9. Samples: 193932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:02,330][00284] Avg episode reward: [(0, '7.643')] | |
| [2025-03-06 21:48:02,351][05512] Saving new best policy, reward=7.643! | |
| [2025-03-06 21:48:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3842.4). Total num frames: 806912. Throughput: 0: 1017.6. Samples: 200946. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:48:07,330][00284] Avg episode reward: [(0, '7.582')] | |
| [2025-03-06 21:48:07,337][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000197_806912.pth... | |
| [2025-03-06 21:48:09,503][05527] Updated weights for policy 0, policy_version 200 (0.0016) | |
| [2025-03-06 21:48:12,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3829.3). Total num frames: 823296. Throughput: 0: 1007.0. Samples: 206828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:12,330][00284] Avg episode reward: [(0, '7.730')] | |
| [2025-03-06 21:48:12,362][05512] Saving new best policy, reward=7.730! | |
| [2025-03-06 21:48:17,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 3835.3). Total num frames: 843776. Throughput: 0: 1017.2. Samples: 209294. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:48:17,327][00284] Avg episode reward: [(0, '7.373')] | |
| [2025-03-06 21:48:20,263][05527] Updated weights for policy 0, policy_version 210 (0.0031) | |
| [2025-03-06 21:48:22,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3859.3). Total num frames: 868352. Throughput: 0: 1026.8. Samples: 216270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:48:22,327][00284] Avg episode reward: [(0, '7.667')] | |
| [2025-03-06 21:48:27,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4028.1, 300 sec: 3846.7). Total num frames: 884736. Throughput: 0: 1013.0. Samples: 222052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:27,329][00284] Avg episode reward: [(0, '7.780')] | |
| [2025-03-06 21:48:27,336][05512] Saving new best policy, reward=7.780! | |
| [2025-03-06 21:48:30,594][05527] Updated weights for policy 0, policy_version 220 (0.0023) | |
| [2025-03-06 21:48:32,328][00284] Fps is (10 sec: 4095.3, 60 sec: 4164.2, 300 sec: 3869.4). Total num frames: 909312. Throughput: 0: 1029.9. Samples: 224774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:32,332][00284] Avg episode reward: [(0, '7.487')] | |
| [2025-03-06 21:48:37,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 3874.1). Total num frames: 929792. Throughput: 0: 1036.6. Samples: 231950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:37,331][00284] Avg episode reward: [(0, '7.210')] | |
| [2025-03-06 21:48:39,744][05527] Updated weights for policy 0, policy_version 230 (0.0021) | |
| [2025-03-06 21:48:42,327][00284] Fps is (10 sec: 3686.7, 60 sec: 4027.7, 300 sec: 3861.9). Total num frames: 946176. Throughput: 0: 1018.2. Samples: 237478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:42,328][00284] Avg episode reward: [(0, '7.005')] | |
| [2025-03-06 21:48:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3883.0). Total num frames: 970752. Throughput: 0: 1036.4. Samples: 240572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:48:47,331][00284] Avg episode reward: [(0, '7.294')] | |
| [2025-03-06 21:48:49,617][05527] Updated weights for policy 0, policy_version 240 (0.0013) | |
| [2025-03-06 21:48:52,326][00284] Fps is (10 sec: 4915.5, 60 sec: 4164.3, 300 sec: 3903.2). Total num frames: 995328. Throughput: 0: 1037.0. Samples: 247610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:48:52,327][00284] Avg episode reward: [(0, '7.593')] | |
| [2025-03-06 21:48:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 3875.4). Total num frames: 1007616. Throughput: 0: 1024.8. Samples: 252946. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:48:57,329][00284] Avg episode reward: [(0, '7.966')] | |
| [2025-03-06 21:48:57,336][05512] Saving new best policy, reward=7.966! | |
| [2025-03-06 21:49:00,030][05527] Updated weights for policy 0, policy_version 250 (0.0020) | |
| [2025-03-06 21:49:02,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 3895.1). Total num frames: 1032192. Throughput: 0: 1042.8. Samples: 256218. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:49:02,329][00284] Avg episode reward: [(0, '7.862')] | |
| [2025-03-06 21:49:07,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 3914.0). Total num frames: 1056768. Throughput: 0: 1047.0. Samples: 263386. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:49:07,330][00284] Avg episode reward: [(0, '7.465')] | |
| [2025-03-06 21:49:09,390][05527] Updated weights for policy 0, policy_version 260 (0.0025) | |
| [2025-03-06 21:49:12,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 3902.4). Total num frames: 1073152. Throughput: 0: 1030.0. Samples: 268402. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:49:12,327][00284] Avg episode reward: [(0, '7.885')] | |
| [2025-03-06 21:49:17,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 3920.5). Total num frames: 1097728. Throughput: 0: 1047.8. Samples: 271922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:49:17,330][00284] Avg episode reward: [(0, '8.194')] | |
| [2025-03-06 21:49:17,337][05512] Saving new best policy, reward=8.194! | |
| [2025-03-06 21:49:19,253][05527] Updated weights for policy 0, policy_version 270 (0.0020) | |
| [2025-03-06 21:49:22,326][00284] Fps is (10 sec: 4505.5, 60 sec: 4164.2, 300 sec: 3923.5). Total num frames: 1118208. Throughput: 0: 1043.6. Samples: 278912. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:49:22,333][00284] Avg episode reward: [(0, '8.755')] | |
| [2025-03-06 21:49:22,335][05512] Saving new best policy, reward=8.755! | |
| [2025-03-06 21:49:27,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 3912.4). Total num frames: 1134592. Throughput: 0: 1027.9. Samples: 283734. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:49:27,327][00284] Avg episode reward: [(0, '8.414')] | |
| [2025-03-06 21:49:29,626][05527] Updated weights for policy 0, policy_version 280 (0.0014) | |
| [2025-03-06 21:49:32,326][00284] Fps is (10 sec: 4096.1, 60 sec: 4164.4, 300 sec: 3929.4). Total num frames: 1159168. Throughput: 0: 1039.6. Samples: 287352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:49:32,327][00284] Avg episode reward: [(0, '8.877')] | |
| [2025-03-06 21:49:32,329][05512] Saving new best policy, reward=8.877! | |
| [2025-03-06 21:49:37,333][00284] Fps is (10 sec: 4502.6, 60 sec: 4163.8, 300 sec: 3998.7). Total num frames: 1179648. Throughput: 0: 1041.6. Samples: 294490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:49:37,339][00284] Avg episode reward: [(0, '8.751')] | |
| [2025-03-06 21:49:39,645][05527] Updated weights for policy 0, policy_version 290 (0.0015) | |
| [2025-03-06 21:49:42,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4054.3). Total num frames: 1196032. Throughput: 0: 1034.6. Samples: 299504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:49:42,331][00284] Avg episode reward: [(0, '9.381')] | |
| [2025-03-06 21:49:42,334][05512] Saving new best policy, reward=9.381! | |
| [2025-03-06 21:49:47,326][00284] Fps is (10 sec: 4098.7, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 1220608. Throughput: 0: 1039.1. Samples: 302978. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:49:47,333][00284] Avg episode reward: [(0, '9.253')] | |
| [2025-03-06 21:49:48,951][05527] Updated weights for policy 0, policy_version 300 (0.0019) | |
| [2025-03-06 21:49:52,328][00284] Fps is (10 sec: 4504.9, 60 sec: 4095.9, 300 sec: 4068.2). Total num frames: 1241088. Throughput: 0: 1033.6. Samples: 309900. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:49:52,329][00284] Avg episode reward: [(0, '9.265')] | |
| [2025-03-06 21:49:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 1257472. Throughput: 0: 1029.4. Samples: 314726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:49:57,330][00284] Avg episode reward: [(0, '8.786')] | |
| [2025-03-06 21:49:59,430][05527] Updated weights for policy 0, policy_version 310 (0.0024) | |
| [2025-03-06 21:50:02,326][00284] Fps is (10 sec: 4096.7, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 1282048. Throughput: 0: 1030.3. Samples: 318284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:50:02,327][00284] Avg episode reward: [(0, '8.889')] | |
| [2025-03-06 21:50:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 1298432. Throughput: 0: 1026.1. Samples: 325086. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:50:07,327][00284] Avg episode reward: [(0, '9.107')] | |
| [2025-03-06 21:50:07,408][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000318_1302528.pth... | |
| [2025-03-06 21:50:07,587][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000079_323584.pth | |
| [2025-03-06 21:50:10,196][05527] Updated weights for policy 0, policy_version 320 (0.0022) | |
| [2025-03-06 21:50:12,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 1318912. Throughput: 0: 1030.0. Samples: 330086. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-03-06 21:50:12,327][00284] Avg episode reward: [(0, '10.126')] | |
| [2025-03-06 21:50:12,329][05512] Saving new best policy, reward=10.126! | |
| [2025-03-06 21:50:17,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 1339392. Throughput: 0: 1027.2. Samples: 333576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:50:17,331][00284] Avg episode reward: [(0, '10.962')] | |
| [2025-03-06 21:50:17,338][05512] Saving new best policy, reward=10.962! | |
| [2025-03-06 21:50:19,350][05527] Updated weights for policy 0, policy_version 330 (0.0024) | |
| [2025-03-06 21:50:22,327][00284] Fps is (10 sec: 4095.6, 60 sec: 4027.7, 300 sec: 4054.3). Total num frames: 1359872. Throughput: 0: 1007.1. Samples: 339806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:50:22,329][00284] Avg episode reward: [(0, '11.477')] | |
| [2025-03-06 21:50:22,331][05512] Saving new best policy, reward=11.477! | |
| [2025-03-06 21:50:27,326][00284] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 1372160. Throughput: 0: 983.0. Samples: 343738. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:50:27,329][00284] Avg episode reward: [(0, '10.827')] | |
| [2025-03-06 21:50:31,783][05527] Updated weights for policy 0, policy_version 340 (0.0029) | |
| [2025-03-06 21:50:32,326][00284] Fps is (10 sec: 3277.1, 60 sec: 3891.2, 300 sec: 4040.5). Total num frames: 1392640. Throughput: 0: 964.7. Samples: 346388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:50:32,329][00284] Avg episode reward: [(0, '11.490')] | |
| [2025-03-06 21:50:32,336][05512] Saving new best policy, reward=11.490! | |
| [2025-03-06 21:50:37,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3891.6, 300 sec: 4026.6). Total num frames: 1413120. Throughput: 0: 956.4. Samples: 352936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:50:37,330][00284] Avg episode reward: [(0, '11.775')] | |
| [2025-03-06 21:50:37,336][05512] Saving new best policy, reward=11.775! | |
| [2025-03-06 21:50:42,289][05527] Updated weights for policy 0, policy_version 350 (0.0017) | |
| [2025-03-06 21:50:42,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4040.5). Total num frames: 1433600. Throughput: 0: 970.7. Samples: 358408. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:50:42,327][00284] Avg episode reward: [(0, '11.750')] | |
| [2025-03-06 21:50:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 4040.5). Total num frames: 1454080. Throughput: 0: 970.8. Samples: 361970. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:50:47,327][00284] Avg episode reward: [(0, '12.017')] | |
| [2025-03-06 21:50:47,337][05512] Saving new best policy, reward=12.017! | |
| [2025-03-06 21:50:52,248][05527] Updated weights for policy 0, policy_version 360 (0.0020) | |
| [2025-03-06 21:50:52,326][00284] Fps is (10 sec: 4095.8, 60 sec: 3891.3, 300 sec: 4040.5). Total num frames: 1474560. Throughput: 0: 960.7. Samples: 368320. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2025-03-06 21:50:52,331][00284] Avg episode reward: [(0, '11.011')] | |
| [2025-03-06 21:50:57,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 1495040. Throughput: 0: 976.6. Samples: 374034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:50:57,331][00284] Avg episode reward: [(0, '11.489')] | |
| [2025-03-06 21:51:01,429][05527] Updated weights for policy 0, policy_version 370 (0.0013) | |
| [2025-03-06 21:51:02,326][00284] Fps is (10 sec: 4505.8, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 1519616. Throughput: 0: 976.7. Samples: 377526. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:51:02,330][00284] Avg episode reward: [(0, '11.117')] | |
| [2025-03-06 21:51:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4026.6). Total num frames: 1536000. Throughput: 0: 973.0. Samples: 383588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:51:07,330][00284] Avg episode reward: [(0, '11.774')] | |
| [2025-03-06 21:51:12,126][05527] Updated weights for policy 0, policy_version 380 (0.0020) | |
| [2025-03-06 21:51:12,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 1556480. Throughput: 0: 1013.4. Samples: 389340. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:51:12,327][00284] Avg episode reward: [(0, '11.080')] | |
| [2025-03-06 21:51:17,326][00284] Fps is (10 sec: 4095.9, 60 sec: 3959.4, 300 sec: 4040.5). Total num frames: 1576960. Throughput: 0: 1031.9. Samples: 392824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:51:17,331][00284] Avg episode reward: [(0, '11.145')] | |
| [2025-03-06 21:51:22,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3891.3, 300 sec: 4012.7). Total num frames: 1593344. Throughput: 0: 1020.4. Samples: 398852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:51:22,330][00284] Avg episode reward: [(0, '11.433')] | |
| [2025-03-06 21:51:22,338][05527] Updated weights for policy 0, policy_version 390 (0.0024) | |
| [2025-03-06 21:51:27,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 1617920. Throughput: 0: 1032.2. Samples: 404856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:51:27,330][00284] Avg episode reward: [(0, '12.549')] | |
| [2025-03-06 21:51:27,335][05512] Saving new best policy, reward=12.549! | |
| [2025-03-06 21:51:31,096][05527] Updated weights for policy 0, policy_version 400 (0.0013) | |
| [2025-03-06 21:51:32,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4054.3). Total num frames: 1642496. Throughput: 0: 1031.5. Samples: 408388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:51:32,330][00284] Avg episode reward: [(0, '14.013')] | |
| [2025-03-06 21:51:32,334][05512] Saving new best policy, reward=14.013! | |
| [2025-03-06 21:51:37,326][00284] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 4026.6). Total num frames: 1658880. Throughput: 0: 1022.2. Samples: 414320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:51:37,327][00284] Avg episode reward: [(0, '13.872')] | |
| [2025-03-06 21:51:41,572][05527] Updated weights for policy 0, policy_version 410 (0.0014) | |
| [2025-03-06 21:51:42,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 1679360. Throughput: 0: 1033.5. Samples: 420540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:51:42,332][00284] Avg episode reward: [(0, '13.710')] | |
| [2025-03-06 21:51:47,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4054.3). Total num frames: 1703936. Throughput: 0: 1038.2. Samples: 424244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:51:47,330][00284] Avg episode reward: [(0, '13.187')] | |
| [2025-03-06 21:51:52,089][05527] Updated weights for policy 0, policy_version 420 (0.0011) | |
| [2025-03-06 21:51:52,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 1720320. Throughput: 0: 1024.7. Samples: 429700. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:51:52,331][00284] Avg episode reward: [(0, '11.931')] | |
| [2025-03-06 21:51:57,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 1744896. Throughput: 0: 1043.6. Samples: 436304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:51:57,327][00284] Avg episode reward: [(0, '11.280')] | |
| [2025-03-06 21:52:00,440][05527] Updated weights for policy 0, policy_version 430 (0.0021) | |
| [2025-03-06 21:52:02,327][00284] Fps is (10 sec: 4505.3, 60 sec: 4096.0, 300 sec: 4054.3). Total num frames: 1765376. Throughput: 0: 1045.9. Samples: 439890. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:52:02,331][00284] Avg episode reward: [(0, '12.172')] | |
| [2025-03-06 21:52:07,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4040.5). Total num frames: 1781760. Throughput: 0: 1032.2. Samples: 445300. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:52:07,329][00284] Avg episode reward: [(0, '12.866')] | |
| [2025-03-06 21:52:07,337][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000435_1781760.pth... | |
| [2025-03-06 21:52:07,456][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000197_806912.pth | |
| [2025-03-06 21:52:11,021][05527] Updated weights for policy 0, policy_version 440 (0.0028) | |
| [2025-03-06 21:52:12,326][00284] Fps is (10 sec: 4096.3, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 1806336. Throughput: 0: 1049.5. Samples: 452084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:52:12,328][00284] Avg episode reward: [(0, '13.416')] | |
| [2025-03-06 21:52:17,326][00284] Fps is (10 sec: 4914.9, 60 sec: 4232.5, 300 sec: 4096.0). Total num frames: 1830912. Throughput: 0: 1050.1. Samples: 455644. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:52:17,328][00284] Avg episode reward: [(0, '13.705')] | |
| [2025-03-06 21:52:21,359][05527] Updated weights for policy 0, policy_version 450 (0.0026) | |
| [2025-03-06 21:52:22,326][00284] Fps is (10 sec: 4095.9, 60 sec: 4232.5, 300 sec: 4082.2). Total num frames: 1847296. Throughput: 0: 1032.4. Samples: 460780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:52:22,330][00284] Avg episode reward: [(0, '12.748')] | |
| [2025-03-06 21:52:27,326][00284] Fps is (10 sec: 4096.2, 60 sec: 4232.6, 300 sec: 4109.9). Total num frames: 1871872. Throughput: 0: 1051.6. Samples: 467864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:52:27,330][00284] Avg episode reward: [(0, '12.531')] | |
| [2025-03-06 21:52:29,783][05527] Updated weights for policy 0, policy_version 460 (0.0012) | |
| [2025-03-06 21:52:32,326][00284] Fps is (10 sec: 4505.7, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 1892352. Throughput: 0: 1051.5. Samples: 471562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:52:32,331][00284] Avg episode reward: [(0, '13.184')] | |
| [2025-03-06 21:52:37,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 1908736. Throughput: 0: 1042.2. Samples: 476600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:52:37,331][00284] Avg episode reward: [(0, '14.160')] | |
| [2025-03-06 21:52:37,346][05512] Saving new best policy, reward=14.160! | |
| [2025-03-06 21:52:40,120][05527] Updated weights for policy 0, policy_version 470 (0.0013) | |
| [2025-03-06 21:52:42,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 4109.9). Total num frames: 1933312. Throughput: 0: 1053.1. Samples: 483692. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:52:42,327][00284] Avg episode reward: [(0, '14.281')] | |
| [2025-03-06 21:52:42,332][05512] Saving new best policy, reward=14.281! | |
| [2025-03-06 21:52:47,329][00284] Fps is (10 sec: 4504.4, 60 sec: 4164.1, 300 sec: 4096.0). Total num frames: 1953792. Throughput: 0: 1050.8. Samples: 487180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:52:47,332][00284] Avg episode reward: [(0, '15.758')] | |
| [2025-03-06 21:52:47,340][05512] Saving new best policy, reward=15.758! | |
| [2025-03-06 21:52:50,864][05527] Updated weights for policy 0, policy_version 480 (0.0016) | |
| [2025-03-06 21:52:52,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 1970176. Throughput: 0: 1034.6. Samples: 491858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:52:52,332][00284] Avg episode reward: [(0, '16.919')] | |
| [2025-03-06 21:52:52,336][05512] Saving new best policy, reward=16.919! | |
| [2025-03-06 21:52:57,326][00284] Fps is (10 sec: 4097.0, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 1994752. Throughput: 0: 1041.1. Samples: 498934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:52:57,328][00284] Avg episode reward: [(0, '17.791')] | |
| [2025-03-06 21:52:57,332][05512] Saving new best policy, reward=17.791! | |
| [2025-03-06 21:52:59,665][05527] Updated weights for policy 0, policy_version 490 (0.0012) | |
| [2025-03-06 21:53:02,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 2015232. Throughput: 0: 1040.7. Samples: 502474. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:53:02,332][00284] Avg episode reward: [(0, '17.876')] | |
| [2025-03-06 21:53:02,335][05512] Saving new best policy, reward=17.876! | |
| [2025-03-06 21:53:07,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 2031616. Throughput: 0: 1036.8. Samples: 507438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:53:07,331][00284] Avg episode reward: [(0, '18.474')] | |
| [2025-03-06 21:53:07,338][05512] Saving new best policy, reward=18.474! | |
| [2025-03-06 21:53:10,120][05527] Updated weights for policy 0, policy_version 500 (0.0012) | |
| [2025-03-06 21:53:12,326][00284] Fps is (10 sec: 4095.9, 60 sec: 4164.2, 300 sec: 4109.9). Total num frames: 2056192. Throughput: 0: 1039.1. Samples: 514622. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:53:12,328][00284] Avg episode reward: [(0, '17.447')] | |
| [2025-03-06 21:53:17,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2076672. Throughput: 0: 1034.5. Samples: 518114. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:53:17,327][00284] Avg episode reward: [(0, '17.310')] | |
| [2025-03-06 21:53:20,529][05527] Updated weights for policy 0, policy_version 510 (0.0043) | |
| [2025-03-06 21:53:22,326][00284] Fps is (10 sec: 4096.2, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2097152. Throughput: 0: 1031.2. Samples: 523006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:53:22,330][00284] Avg episode reward: [(0, '16.963')] | |
| [2025-03-06 21:53:27,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2113536. Throughput: 0: 1001.6. Samples: 528762. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:53:27,327][00284] Avg episode reward: [(0, '16.914')] | |
| [2025-03-06 21:53:31,759][05527] Updated weights for policy 0, policy_version 520 (0.0039) | |
| [2025-03-06 21:53:32,326][00284] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2129920. Throughput: 0: 982.1. Samples: 531372. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:53:32,327][00284] Avg episode reward: [(0, '16.786')] | |
| [2025-03-06 21:53:37,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2150400. Throughput: 0: 992.0. Samples: 536500. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:53:37,330][00284] Avg episode reward: [(0, '17.039')] | |
| [2025-03-06 21:53:41,487][05527] Updated weights for policy 0, policy_version 530 (0.0023) | |
| [2025-03-06 21:53:42,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2170880. Throughput: 0: 995.1. Samples: 543714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:53:42,330][00284] Avg episode reward: [(0, '17.432')] | |
| [2025-03-06 21:53:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.6, 300 sec: 4054.3). Total num frames: 2191360. Throughput: 0: 992.2. Samples: 547122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:53:47,327][00284] Avg episode reward: [(0, '17.092')] | |
| [2025-03-06 21:53:51,973][05527] Updated weights for policy 0, policy_version 540 (0.0014) | |
| [2025-03-06 21:53:52,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2211840. Throughput: 0: 994.0. Samples: 552166. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:53:52,327][00284] Avg episode reward: [(0, '17.631')] | |
| [2025-03-06 21:53:57,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2236416. Throughput: 0: 995.3. Samples: 559410. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:53:57,331][00284] Avg episode reward: [(0, '18.083')] | |
| [2025-03-06 21:54:01,486][05527] Updated weights for policy 0, policy_version 550 (0.0016) | |
| [2025-03-06 21:54:02,326][00284] Fps is (10 sec: 4095.8, 60 sec: 3959.4, 300 sec: 4054.3). Total num frames: 2252800. Throughput: 0: 989.6. Samples: 562648. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:54:02,332][00284] Avg episode reward: [(0, '18.491')] | |
| [2025-03-06 21:54:02,335][05512] Saving new best policy, reward=18.491! | |
| [2025-03-06 21:54:07,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4068.2). Total num frames: 2273280. Throughput: 0: 998.9. Samples: 567958. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:54:07,330][00284] Avg episode reward: [(0, '20.189')] | |
| [2025-03-06 21:54:07,337][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000555_2273280.pth... | |
| [2025-03-06 21:54:07,481][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000318_1302528.pth | |
| [2025-03-06 21:54:07,499][05512] Saving new best policy, reward=20.189! | |
| [2025-03-06 21:54:11,029][05527] Updated weights for policy 0, policy_version 560 (0.0020) | |
| [2025-03-06 21:54:12,326][00284] Fps is (10 sec: 4505.8, 60 sec: 4027.8, 300 sec: 4068.2). Total num frames: 2297856. Throughput: 0: 1024.4. Samples: 574860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:54:12,329][00284] Avg episode reward: [(0, '19.002')] | |
| [2025-03-06 21:54:17,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 4054.3). Total num frames: 2314240. Throughput: 0: 1031.2. Samples: 577776. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:54:17,330][00284] Avg episode reward: [(0, '19.212')] | |
| [2025-03-06 21:54:21,554][05527] Updated weights for policy 0, policy_version 570 (0.0012) | |
| [2025-03-06 21:54:22,326][00284] Fps is (10 sec: 3686.4, 60 sec: 3959.5, 300 sec: 4068.2). Total num frames: 2334720. Throughput: 0: 1038.8. Samples: 583244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:54:22,327][00284] Avg episode reward: [(0, '19.942')] | |
| [2025-03-06 21:54:27,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 2359296. Throughput: 0: 1037.1. Samples: 590384. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:54:27,327][00284] Avg episode reward: [(0, '19.243')] | |
| [2025-03-06 21:54:31,555][05527] Updated weights for policy 0, policy_version 580 (0.0024) | |
| [2025-03-06 21:54:32,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.0, 300 sec: 4054.4). Total num frames: 2375680. Throughput: 0: 1023.7. Samples: 593188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:54:32,332][00284] Avg episode reward: [(0, '20.204')] | |
| [2025-03-06 21:54:32,337][05512] Saving new best policy, reward=20.204! | |
| [2025-03-06 21:54:37,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 2400256. Throughput: 0: 1039.6. Samples: 598946. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:54:37,330][00284] Avg episode reward: [(0, '18.833')] | |
| [2025-03-06 21:54:40,568][05527] Updated weights for policy 0, policy_version 590 (0.0012) | |
| [2025-03-06 21:54:42,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4068.2). Total num frames: 2420736. Throughput: 0: 1036.8. Samples: 606066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:54:42,331][00284] Avg episode reward: [(0, '19.910')] | |
| [2025-03-06 21:54:47,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4054.4). Total num frames: 2437120. Throughput: 0: 1020.1. Samples: 608552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:54:47,327][00284] Avg episode reward: [(0, '19.504')] | |
| [2025-03-06 21:54:51,131][05527] Updated weights for policy 0, policy_version 600 (0.0013) | |
| [2025-03-06 21:54:52,330][00284] Fps is (10 sec: 4094.5, 60 sec: 4164.0, 300 sec: 4082.1). Total num frames: 2461696. Throughput: 0: 1033.4. Samples: 614466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:54:52,334][00284] Avg episode reward: [(0, '20.323')] | |
| [2025-03-06 21:54:52,341][05512] Saving new best policy, reward=20.323! | |
| [2025-03-06 21:54:57,326][00284] Fps is (10 sec: 4505.5, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 2482176. Throughput: 0: 1037.6. Samples: 621550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:54:57,329][00284] Avg episode reward: [(0, '20.523')] | |
| [2025-03-06 21:54:57,335][05512] Saving new best policy, reward=20.523! | |
| [2025-03-06 21:55:01,731][05527] Updated weights for policy 0, policy_version 610 (0.0020) | |
| [2025-03-06 21:55:02,326][00284] Fps is (10 sec: 3687.7, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 2498560. Throughput: 0: 1021.9. Samples: 623762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:55:02,330][00284] Avg episode reward: [(0, '21.010')] | |
| [2025-03-06 21:55:02,336][05512] Saving new best policy, reward=21.010! | |
| [2025-03-06 21:55:07,326][00284] Fps is (10 sec: 4096.1, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 2523136. Throughput: 0: 1038.4. Samples: 629970. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-03-06 21:55:07,330][00284] Avg episode reward: [(0, '21.060')] | |
| [2025-03-06 21:55:07,337][05512] Saving new best policy, reward=21.060! | |
| [2025-03-06 21:55:10,437][05527] Updated weights for policy 0, policy_version 620 (0.0013) | |
| [2025-03-06 21:55:12,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4096.0, 300 sec: 4082.1). Total num frames: 2543616. Throughput: 0: 1032.3. Samples: 636836. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:55:12,330][00284] Avg episode reward: [(0, '21.648')] | |
| [2025-03-06 21:55:12,332][05512] Saving new best policy, reward=21.648! | |
| [2025-03-06 21:55:17,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 2560000. Throughput: 0: 1016.1. Samples: 638912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:17,330][00284] Avg episode reward: [(0, '21.132')] | |
| [2025-03-06 21:55:20,905][05527] Updated weights for policy 0, policy_version 630 (0.0028) | |
| [2025-03-06 21:55:22,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2584576. Throughput: 0: 1033.2. Samples: 645438. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:55:22,330][00284] Avg episode reward: [(0, '21.135')] | |
| [2025-03-06 21:55:27,329][00284] Fps is (10 sec: 4504.4, 60 sec: 4095.8, 300 sec: 4109.8). Total num frames: 2605056. Throughput: 0: 1023.0. Samples: 652102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:27,331][00284] Avg episode reward: [(0, '21.777')] | |
| [2025-03-06 21:55:27,342][05512] Saving new best policy, reward=21.777! | |
| [2025-03-06 21:55:31,445][05527] Updated weights for policy 0, policy_version 640 (0.0018) | |
| [2025-03-06 21:55:32,329][00284] Fps is (10 sec: 3685.4, 60 sec: 4095.8, 300 sec: 4096.0). Total num frames: 2621440. Throughput: 0: 1014.0. Samples: 654186. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2025-03-06 21:55:32,330][00284] Avg episode reward: [(0, '21.340')] | |
| [2025-03-06 21:55:37,326][00284] Fps is (10 sec: 4097.1, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 2646016. Throughput: 0: 1033.4. Samples: 660964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:37,327][00284] Avg episode reward: [(0, '20.669')] | |
| [2025-03-06 21:55:40,056][05527] Updated weights for policy 0, policy_version 650 (0.0019) | |
| [2025-03-06 21:55:42,326][00284] Fps is (10 sec: 4506.7, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 2666496. Throughput: 0: 1020.8. Samples: 667486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:42,328][00284] Avg episode reward: [(0, '20.822')] | |
| [2025-03-06 21:55:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2686976. Throughput: 0: 1019.1. Samples: 669622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:47,330][00284] Avg episode reward: [(0, '21.058')] | |
| [2025-03-06 21:55:50,699][05527] Updated weights for policy 0, policy_version 660 (0.0012) | |
| [2025-03-06 21:55:52,327][00284] Fps is (10 sec: 4505.2, 60 sec: 4164.4, 300 sec: 4123.8). Total num frames: 2711552. Throughput: 0: 1034.5. Samples: 676526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:55:52,331][00284] Avg episode reward: [(0, '19.703')] | |
| [2025-03-06 21:55:57,327][00284] Fps is (10 sec: 4095.8, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 2727936. Throughput: 0: 1022.4. Samples: 682846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:55:57,328][00284] Avg episode reward: [(0, '19.872')] | |
| [2025-03-06 21:56:01,023][05527] Updated weights for policy 0, policy_version 670 (0.0026) | |
| [2025-03-06 21:56:02,326][00284] Fps is (10 sec: 3686.9, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 2748416. Throughput: 0: 1027.9. Samples: 685166. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:56:02,328][00284] Avg episode reward: [(0, '19.514')] | |
| [2025-03-06 21:56:07,326][00284] Fps is (10 sec: 4505.9, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2772992. Throughput: 0: 1042.0. Samples: 692326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:56:07,328][00284] Avg episode reward: [(0, '18.793')] | |
| [2025-03-06 21:56:07,334][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000677_2772992.pth... | |
| [2025-03-06 21:56:07,453][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000435_1781760.pth | |
| [2025-03-06 21:56:09,893][05527] Updated weights for policy 0, policy_version 680 (0.0018) | |
| [2025-03-06 21:56:12,328][00284] Fps is (10 sec: 4095.0, 60 sec: 4095.8, 300 sec: 4109.9). Total num frames: 2789376. Throughput: 0: 1028.5. Samples: 698382. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-03-06 21:56:12,330][00284] Avg episode reward: [(0, '20.132')] | |
| [2025-03-06 21:56:17,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 2809856. Throughput: 0: 1036.8. Samples: 700840. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:56:17,332][00284] Avg episode reward: [(0, '20.152')] | |
| [2025-03-06 21:56:20,299][05527] Updated weights for policy 0, policy_version 690 (0.0017) | |
| [2025-03-06 21:56:22,327][00284] Fps is (10 sec: 4506.3, 60 sec: 4164.2, 300 sec: 4123.8). Total num frames: 2834432. Throughput: 0: 1041.3. Samples: 707822. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:56:22,331][00284] Avg episode reward: [(0, '19.486')] | |
| [2025-03-06 21:56:27,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.9, 300 sec: 4082.1). Total num frames: 2846720. Throughput: 0: 996.6. Samples: 712334. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:56:27,327][00284] Avg episode reward: [(0, '19.606')] | |
| [2025-03-06 21:56:32,326][00284] Fps is (10 sec: 2867.4, 60 sec: 4027.9, 300 sec: 4082.1). Total num frames: 2863104. Throughput: 0: 992.7. Samples: 714294. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0) | |
| [2025-03-06 21:56:32,331][00284] Avg episode reward: [(0, '18.865')] | |
| [2025-03-06 21:56:32,550][05527] Updated weights for policy 0, policy_version 700 (0.0023) | |
| [2025-03-06 21:56:37,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2887680. Throughput: 0: 998.2. Samples: 721446. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:56:37,327][00284] Avg episode reward: [(0, '17.369')] | |
| [2025-03-06 21:56:41,584][05527] Updated weights for policy 0, policy_version 710 (0.0025) | |
| [2025-03-06 21:56:42,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.8, 300 sec: 4082.1). Total num frames: 2908160. Throughput: 0: 997.8. Samples: 727746. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:56:42,333][00284] Avg episode reward: [(0, '18.083')] | |
| [2025-03-06 21:56:47,327][00284] Fps is (10 sec: 4095.7, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2928640. Throughput: 0: 997.0. Samples: 730032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:56:47,328][00284] Avg episode reward: [(0, '18.153')] | |
| [2025-03-06 21:56:51,395][05527] Updated weights for policy 0, policy_version 720 (0.0014) | |
| [2025-03-06 21:56:52,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.8, 300 sec: 4096.0). Total num frames: 2953216. Throughput: 0: 992.4. Samples: 736986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:56:52,333][00284] Avg episode reward: [(0, '18.547')] | |
| [2025-03-06 21:56:57,327][00284] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 4082.1). Total num frames: 2969600. Throughput: 0: 993.4. Samples: 743084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:56:57,328][00284] Avg episode reward: [(0, '19.105')] | |
| [2025-03-06 21:57:01,863][05527] Updated weights for policy 0, policy_version 730 (0.0014) | |
| [2025-03-06 21:57:02,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 2990080. Throughput: 0: 993.8. Samples: 745562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:57:02,330][00284] Avg episode reward: [(0, '19.863')] | |
| [2025-03-06 21:57:07,326][00284] Fps is (10 sec: 4506.0, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3014656. Throughput: 0: 997.2. Samples: 752694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:57:07,331][00284] Avg episode reward: [(0, '20.207')] | |
| [2025-03-06 21:57:11,244][05527] Updated weights for policy 0, policy_version 740 (0.0025) | |
| [2025-03-06 21:57:12,328][00284] Fps is (10 sec: 4095.3, 60 sec: 4027.8, 300 sec: 4068.2). Total num frames: 3031040. Throughput: 0: 1027.2. Samples: 758558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:57:12,329][00284] Avg episode reward: [(0, '19.897')] | |
| [2025-03-06 21:57:17,326][00284] Fps is (10 sec: 4096.1, 60 sec: 4096.0, 300 sec: 4096.0). Total num frames: 3055616. Throughput: 0: 1044.3. Samples: 761288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:57:17,329][00284] Avg episode reward: [(0, '20.314')] | |
| [2025-03-06 21:57:20,838][05527] Updated weights for policy 0, policy_version 750 (0.0014) | |
| [2025-03-06 21:57:22,326][00284] Fps is (10 sec: 4506.3, 60 sec: 4027.8, 300 sec: 4082.1). Total num frames: 3076096. Throughput: 0: 1044.6. Samples: 768452. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:57:22,331][00284] Avg episode reward: [(0, '19.914')] | |
| [2025-03-06 21:57:27,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.2). Total num frames: 3092480. Throughput: 0: 1027.5. Samples: 773984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:57:27,331][00284] Avg episode reward: [(0, '20.428')] | |
| [2025-03-06 21:57:31,180][05527] Updated weights for policy 0, policy_version 760 (0.0013) | |
| [2025-03-06 21:57:32,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4232.5, 300 sec: 4096.0). Total num frames: 3117056. Throughput: 0: 1042.4. Samples: 776940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:57:32,331][00284] Avg episode reward: [(0, '20.782')] | |
| [2025-03-06 21:57:37,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4082.1). Total num frames: 3137536. Throughput: 0: 1047.2. Samples: 784108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:57:37,327][00284] Avg episode reward: [(0, '21.563')] | |
| [2025-03-06 21:57:41,220][05527] Updated weights for policy 0, policy_version 770 (0.0015) | |
| [2025-03-06 21:57:42,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4068.3). Total num frames: 3153920. Throughput: 0: 1031.4. Samples: 789496. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:57:42,332][00284] Avg episode reward: [(0, '20.920')] | |
| [2025-03-06 21:57:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3178496. Throughput: 0: 1047.1. Samples: 792682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 21:57:47,330][00284] Avg episode reward: [(0, '19.304')] | |
| [2025-03-06 21:57:50,466][05527] Updated weights for policy 0, policy_version 780 (0.0012) | |
| [2025-03-06 21:57:52,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3203072. Throughput: 0: 1043.4. Samples: 799646. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:57:52,327][00284] Avg episode reward: [(0, '18.421')] | |
| [2025-03-06 21:57:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.1, 300 sec: 4068.2). Total num frames: 3215360. Throughput: 0: 1031.2. Samples: 804962. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:57:57,327][00284] Avg episode reward: [(0, '18.534')] | |
| [2025-03-06 21:58:00,781][05527] Updated weights for policy 0, policy_version 790 (0.0013) | |
| [2025-03-06 21:58:02,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3239936. Throughput: 0: 1046.0. Samples: 808360. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:58:02,328][00284] Avg episode reward: [(0, '17.764')] | |
| [2025-03-06 21:58:07,326][00284] Fps is (10 sec: 4915.2, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3264512. Throughput: 0: 1046.4. Samples: 815542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:58:07,330][00284] Avg episode reward: [(0, '19.941')] | |
| [2025-03-06 21:58:07,338][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000797_3264512.pth... | |
| [2025-03-06 21:58:07,513][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000555_2273280.pth | |
| [2025-03-06 21:58:10,754][05527] Updated weights for policy 0, policy_version 800 (0.0021) | |
| [2025-03-06 21:58:12,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.4, 300 sec: 4082.1). Total num frames: 3280896. Throughput: 0: 1032.3. Samples: 820436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:58:12,327][00284] Avg episode reward: [(0, '20.868')] | |
| [2025-03-06 21:58:17,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3305472. Throughput: 0: 1042.9. Samples: 823870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:58:17,327][00284] Avg episode reward: [(0, '22.142')] | |
| [2025-03-06 21:58:17,333][05512] Saving new best policy, reward=22.142! | |
| [2025-03-06 21:58:19,922][05527] Updated weights for policy 0, policy_version 810 (0.0012) | |
| [2025-03-06 21:58:22,326][00284] Fps is (10 sec: 4505.5, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 3325952. Throughput: 0: 1039.1. Samples: 830866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:58:22,327][00284] Avg episode reward: [(0, '22.135')] | |
| [2025-03-06 21:58:27,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 3342336. Throughput: 0: 1028.2. Samples: 835764. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:58:27,327][00284] Avg episode reward: [(0, '21.854')] | |
| [2025-03-06 21:58:30,590][05527] Updated weights for policy 0, policy_version 820 (0.0022) | |
| [2025-03-06 21:58:32,326][00284] Fps is (10 sec: 4096.1, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 3366912. Throughput: 0: 1034.9. Samples: 839254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:58:32,327][00284] Avg episode reward: [(0, '21.274')] | |
| [2025-03-06 21:58:37,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 3387392. Throughput: 0: 1036.0. Samples: 846264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:58:37,329][00284] Avg episode reward: [(0, '20.273')] | |
| [2025-03-06 21:58:41,120][05527] Updated weights for policy 0, policy_version 830 (0.0021) | |
| [2025-03-06 21:58:42,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 3403776. Throughput: 0: 1027.3. Samples: 851190. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:58:42,331][00284] Avg episode reward: [(0, '19.817')] | |
| [2025-03-06 21:58:47,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4123.8). Total num frames: 3428352. Throughput: 0: 1029.6. Samples: 854690. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2025-03-06 21:58:47,331][00284] Avg episode reward: [(0, '21.408')] | |
| [2025-03-06 21:58:49,807][05527] Updated weights for policy 0, policy_version 840 (0.0022) | |
| [2025-03-06 21:58:52,331][00284] Fps is (10 sec: 4503.5, 60 sec: 4095.7, 300 sec: 4109.8). Total num frames: 3448832. Throughput: 0: 1029.7. Samples: 861884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:58:52,332][00284] Avg episode reward: [(0, '22.210')] | |
| [2025-03-06 21:58:52,333][05512] Saving new best policy, reward=22.210! | |
| [2025-03-06 21:58:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4109.9). Total num frames: 3465216. Throughput: 0: 1027.5. Samples: 866672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:58:57,327][00284] Avg episode reward: [(0, '23.802')] | |
| [2025-03-06 21:58:57,333][05512] Saving new best policy, reward=23.802! | |
| [2025-03-06 21:59:00,493][05527] Updated weights for policy 0, policy_version 850 (0.0020) | |
| [2025-03-06 21:59:02,326][00284] Fps is (10 sec: 4097.8, 60 sec: 4164.2, 300 sec: 4123.8). Total num frames: 3489792. Throughput: 0: 1027.5. Samples: 870106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:59:02,331][00284] Avg episode reward: [(0, '23.467')] | |
| [2025-03-06 21:59:07,331][00284] Fps is (10 sec: 4503.5, 60 sec: 4095.7, 300 sec: 4109.8). Total num frames: 3510272. Throughput: 0: 1029.1. Samples: 877178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:59:07,332][00284] Avg episode reward: [(0, '22.427')] | |
| [2025-03-06 21:59:10,876][05527] Updated weights for policy 0, policy_version 860 (0.0018) | |
| [2025-03-06 21:59:12,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 3526656. Throughput: 0: 1034.2. Samples: 882304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:59:12,331][00284] Avg episode reward: [(0, '21.617')] | |
| [2025-03-06 21:59:17,326][00284] Fps is (10 sec: 4097.9, 60 sec: 4096.0, 300 sec: 4123.8). Total num frames: 3551232. Throughput: 0: 1035.8. Samples: 885864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2025-03-06 21:59:17,330][00284] Avg episode reward: [(0, '20.779')] | |
| [2025-03-06 21:59:19,506][05527] Updated weights for policy 0, policy_version 870 (0.0018) | |
| [2025-03-06 21:59:22,326][00284] Fps is (10 sec: 4505.7, 60 sec: 4096.0, 300 sec: 4109.9). Total num frames: 3571712. Throughput: 0: 1032.5. Samples: 892726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 21:59:22,335][00284] Avg episode reward: [(0, '19.088')] | |
| [2025-03-06 21:59:27,328][00284] Fps is (10 sec: 3685.8, 60 sec: 4095.9, 300 sec: 4109.9). Total num frames: 3588096. Throughput: 0: 1033.4. Samples: 897694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:59:27,329][00284] Avg episode reward: [(0, '19.864')] | |
| [2025-03-06 21:59:31,758][05527] Updated weights for policy 0, policy_version 880 (0.0036) | |
| [2025-03-06 21:59:32,326][00284] Fps is (10 sec: 3276.8, 60 sec: 3959.5, 300 sec: 4082.1). Total num frames: 3604480. Throughput: 0: 1003.5. Samples: 899848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:59:32,330][00284] Avg episode reward: [(0, '20.025')] | |
| [2025-03-06 21:59:37,327][00284] Fps is (10 sec: 3686.7, 60 sec: 3959.4, 300 sec: 4082.1). Total num frames: 3624960. Throughput: 0: 980.8. Samples: 906014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:59:37,329][00284] Avg episode reward: [(0, '19.292')] | |
| [2025-03-06 21:59:42,095][05527] Updated weights for policy 0, policy_version 890 (0.0025) | |
| [2025-03-06 21:59:42,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3645440. Throughput: 0: 995.6. Samples: 911474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 21:59:42,330][00284] Avg episode reward: [(0, '17.989')] | |
| [2025-03-06 21:59:47,326][00284] Fps is (10 sec: 4505.9, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3670016. Throughput: 0: 997.7. Samples: 915002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:59:47,330][00284] Avg episode reward: [(0, '19.125')] | |
| [2025-03-06 21:59:51,354][05527] Updated weights for policy 0, policy_version 900 (0.0013) | |
| [2025-03-06 21:59:52,327][00284] Fps is (10 sec: 4095.4, 60 sec: 3959.7, 300 sec: 4082.1). Total num frames: 3686400. Throughput: 0: 987.3. Samples: 921604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 21:59:52,330][00284] Avg episode reward: [(0, '18.844')] | |
| [2025-03-06 21:59:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3706880. Throughput: 0: 997.3. Samples: 927180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2025-03-06 21:59:57,327][00284] Avg episode reward: [(0, '18.285')] | |
| [2025-03-06 22:00:00,975][05527] Updated weights for policy 0, policy_version 910 (0.0017) | |
| [2025-03-06 22:00:02,326][00284] Fps is (10 sec: 4506.3, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3731456. Throughput: 0: 997.9. Samples: 930770. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 22:00:02,333][00284] Avg episode reward: [(0, '20.598')] | |
| [2025-03-06 22:00:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 3959.8, 300 sec: 4082.1). Total num frames: 3747840. Throughput: 0: 989.1. Samples: 937236. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 22:00:07,330][00284] Avg episode reward: [(0, '20.032')] | |
| [2025-03-06 22:00:07,344][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000915_3747840.pth... | |
| [2025-03-06 22:00:07,540][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000677_2772992.pth | |
| [2025-03-06 22:00:11,549][05527] Updated weights for policy 0, policy_version 920 (0.0012) | |
| [2025-03-06 22:00:12,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4027.8, 300 sec: 4096.0). Total num frames: 3768320. Throughput: 0: 1005.5. Samples: 942938. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:12,327][00284] Avg episode reward: [(0, '20.978')] | |
| [2025-03-06 22:00:17,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3792896. Throughput: 0: 1037.9. Samples: 946554. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:17,327][00284] Avg episode reward: [(0, '21.240')] | |
| [2025-03-06 22:00:20,659][05527] Updated weights for policy 0, policy_version 930 (0.0023) | |
| [2025-03-06 22:00:22,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 4096.0). Total num frames: 3813376. Throughput: 0: 1039.1. Samples: 952774. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2025-03-06 22:00:22,327][00284] Avg episode reward: [(0, '22.221')] | |
| [2025-03-06 22:00:27,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4096.1, 300 sec: 4109.9). Total num frames: 3833856. Throughput: 0: 1050.0. Samples: 958726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:27,330][00284] Avg episode reward: [(0, '22.875')] | |
| [2025-03-06 22:00:30,447][05527] Updated weights for policy 0, policy_version 940 (0.0025) | |
| [2025-03-06 22:00:32,326][00284] Fps is (10 sec: 4505.5, 60 sec: 4232.5, 300 sec: 4109.9). Total num frames: 3858432. Throughput: 0: 1051.5. Samples: 962320. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:32,330][00284] Avg episode reward: [(0, '22.181')] | |
| [2025-03-06 22:00:37,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3874816. Throughput: 0: 1036.7. Samples: 968254. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:37,327][00284] Avg episode reward: [(0, '22.350')] | |
| [2025-03-06 22:00:40,854][05527] Updated weights for policy 0, policy_version 950 (0.0014) | |
| [2025-03-06 22:00:42,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3895296. Throughput: 0: 1049.8. Samples: 974420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 22:00:42,332][00284] Avg episode reward: [(0, '22.411')] | |
| [2025-03-06 22:00:47,326][00284] Fps is (10 sec: 4505.6, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3919872. Throughput: 0: 1048.2. Samples: 977938. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 22:00:47,327][00284] Avg episode reward: [(0, '22.473')] | |
| [2025-03-06 22:00:50,606][05527] Updated weights for policy 0, policy_version 960 (0.0018) | |
| [2025-03-06 22:00:52,331][00284] Fps is (10 sec: 4094.1, 60 sec: 4164.0, 300 sec: 4095.9). Total num frames: 3936256. Throughput: 0: 1031.6. Samples: 983662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 22:00:52,332][00284] Avg episode reward: [(0, '22.517')] | |
| [2025-03-06 22:00:57,326][00284] Fps is (10 sec: 3686.4, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3956736. Throughput: 0: 1043.7. Samples: 989904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2025-03-06 22:00:57,327][00284] Avg episode reward: [(0, '21.807')] | |
| [2025-03-06 22:01:00,109][05527] Updated weights for policy 0, policy_version 970 (0.0029) | |
| [2025-03-06 22:01:02,329][00284] Fps is (10 sec: 4506.5, 60 sec: 4164.1, 300 sec: 4096.0). Total num frames: 3981312. Throughput: 0: 1042.6. Samples: 993472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2025-03-06 22:01:02,333][00284] Avg episode reward: [(0, '21.546')] | |
| [2025-03-06 22:01:07,326][00284] Fps is (10 sec: 4096.0, 60 sec: 4164.3, 300 sec: 4096.0). Total num frames: 3997696. Throughput: 0: 1027.0. Samples: 998990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2025-03-06 22:01:07,331][00284] Avg episode reward: [(0, '21.481')] | |
| [2025-03-06 22:01:08,667][05512] Stopping Batcher_0... | |
| [2025-03-06 22:01:08,667][05512] Loop batcher_evt_loop terminating... | |
| [2025-03-06 22:01:08,673][00284] Component Batcher_0 stopped! | |
| [2025-03-06 22:01:08,681][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-03-06 22:01:08,730][05527] Weights refcount: 2 0 | |
| [2025-03-06 22:01:08,734][05527] Stopping InferenceWorker_p0-w0... | |
| [2025-03-06 22:01:08,735][05527] Loop inference_proc0-0_evt_loop terminating... | |
| [2025-03-06 22:01:08,734][00284] Component InferenceWorker_p0-w0 stopped! | |
| [2025-03-06 22:01:08,814][05512] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000797_3264512.pth | |
| [2025-03-06 22:01:08,832][05512] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-03-06 22:01:08,986][05512] Stopping LearnerWorker_p0... | |
| [2025-03-06 22:01:08,986][00284] Component LearnerWorker_p0 stopped! | |
| [2025-03-06 22:01:08,991][05512] Loop learner_proc0_evt_loop terminating... | |
| [2025-03-06 22:01:09,060][05529] Stopping RolloutWorker_w3... | |
| [2025-03-06 22:01:09,059][00284] Component RolloutWorker_w3 stopped! | |
| [2025-03-06 22:01:09,061][05529] Loop rollout_proc3_evt_loop terminating... | |
| [2025-03-06 22:01:09,078][00284] Component RolloutWorker_w7 stopped! | |
| [2025-03-06 22:01:09,081][00284] Component RolloutWorker_w5 stopped! | |
| [2025-03-06 22:01:09,080][05531] Stopping RolloutWorker_w5... | |
| [2025-03-06 22:01:09,078][05533] Stopping RolloutWorker_w7... | |
| [2025-03-06 22:01:09,085][05531] Loop rollout_proc5_evt_loop terminating... | |
| [2025-03-06 22:01:09,090][05533] Loop rollout_proc7_evt_loop terminating... | |
| [2025-03-06 22:01:09,105][00284] Component RolloutWorker_w1 stopped! | |
| [2025-03-06 22:01:09,106][05526] Stopping RolloutWorker_w1... | |
| [2025-03-06 22:01:09,108][05526] Loop rollout_proc1_evt_loop terminating... | |
| [2025-03-06 22:01:09,146][05530] Stopping RolloutWorker_w4... | |
| [2025-03-06 22:01:09,146][00284] Component RolloutWorker_w4 stopped! | |
| [2025-03-06 22:01:09,151][05530] Loop rollout_proc4_evt_loop terminating... | |
| [2025-03-06 22:01:09,156][05528] Stopping RolloutWorker_w2... | |
| [2025-03-06 22:01:09,156][00284] Component RolloutWorker_w2 stopped! | |
| [2025-03-06 22:01:09,162][05528] Loop rollout_proc2_evt_loop terminating... | |
| [2025-03-06 22:01:09,180][00284] Component RolloutWorker_w6 stopped! | |
| [2025-03-06 22:01:09,180][05532] Stopping RolloutWorker_w6... | |
| [2025-03-06 22:01:09,186][00284] Component RolloutWorker_w0 stopped! | |
| [2025-03-06 22:01:09,187][00284] Waiting for process learner_proc0 to stop... | |
| [2025-03-06 22:01:09,186][05525] Stopping RolloutWorker_w0... | |
| [2025-03-06 22:01:09,184][05532] Loop rollout_proc6_evt_loop terminating... | |
| [2025-03-06 22:01:09,203][05525] Loop rollout_proc0_evt_loop terminating... | |
| [2025-03-06 22:01:10,884][00284] Waiting for process inference_proc0-0 to join... | |
| [2025-03-06 22:01:10,886][00284] Waiting for process rollout_proc0 to join... | |
| [2025-03-06 22:01:12,918][00284] Waiting for process rollout_proc1 to join... | |
| [2025-03-06 22:01:12,919][00284] Waiting for process rollout_proc2 to join... | |
| [2025-03-06 22:01:12,920][00284] Waiting for process rollout_proc3 to join... | |
| [2025-03-06 22:01:12,921][00284] Waiting for process rollout_proc4 to join... | |
| [2025-03-06 22:01:12,922][00284] Waiting for process rollout_proc5 to join... | |
| [2025-03-06 22:01:12,924][00284] Waiting for process rollout_proc6 to join... | |
| [2025-03-06 22:01:12,925][00284] Waiting for process rollout_proc7 to join... | |
| [2025-03-06 22:01:12,928][00284] Batcher 0 profile tree view: | |
| batching: 25.4308, releasing_batches: 0.0268 | |
| [2025-03-06 22:01:12,929][00284] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0001 | |
| wait_policy_total: 400.7710 | |
| update_model: 8.0843 | |
| weight_update: 0.0033 | |
| one_step: 0.0132 | |
| handle_policy_step: 547.9427 | |
| deserialize: 13.2473, stack: 3.0099, obs_to_device_normalize: 116.1650, forward: 281.0652, send_messages: 26.8386 | |
| prepare_outputs: 83.6460 | |
| to_cpu: 51.4727 | |
| [2025-03-06 22:01:12,930][00284] Learner 0 profile tree view: | |
| misc: 0.0042, prepare_batch: 12.8300 | |
| train: 72.0384 | |
| epoch_init: 0.0065, minibatch_init: 0.0054, losses_postprocess: 0.6873, kl_divergence: 0.5710, after_optimizer: 33.4718 | |
| calculate_losses: 25.3359 | |
| losses_init: 0.0091, forward_head: 1.3617, bptt_initial: 16.6307, tail: 1.0562, advantages_returns: 0.2803, losses: 3.8496 | |
| bptt: 1.8815 | |
| bptt_forward_core: 1.8118 | |
| update: 11.3776 | |
| clip: 0.8626 | |
| [2025-03-06 22:01:12,934][00284] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.2633, enqueue_policy_requests: 97.2257, env_step: 781.7387, overhead: 11.2096, complete_rollouts: 7.0124 | |
| save_policy_outputs: 17.1345 | |
| split_output_tensors: 6.5462 | |
| [2025-03-06 22:01:12,935][00284] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.2340, enqueue_policy_requests: 97.3959, env_step: 781.4050, overhead: 11.2650, complete_rollouts: 6.0488 | |
| save_policy_outputs: 17.3161 | |
| split_output_tensors: 6.6509 | |
| [2025-03-06 22:01:12,936][00284] Loop Runner_EvtLoop terminating... | |
| [2025-03-06 22:01:12,938][00284] Runner profile tree view: | |
| main_loop: 1019.7643 | |
| [2025-03-06 22:01:12,938][00284] Collected {0: 4005888}, FPS: 3928.2 | |
| [2025-03-06 22:03:33,283][00284] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-03-06 22:03:33,284][00284] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-03-06 22:03:33,285][00284] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-03-06 22:03:33,285][00284] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-03-06 22:03:33,286][00284] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-03-06 22:03:33,287][00284] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-03-06 22:03:33,288][00284] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-03-06 22:03:33,289][00284] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-03-06 22:03:33,290][00284] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2025-03-06 22:03:33,291][00284] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2025-03-06 22:03:33,292][00284] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-03-06 22:03:33,293][00284] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-03-06 22:03:33,293][00284] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-03-06 22:03:33,294][00284] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-03-06 22:03:33,295][00284] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-03-06 22:03:33,337][00284] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2025-03-06 22:03:33,340][00284] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-03-06 22:03:33,341][00284] RunningMeanStd input shape: (1,) | |
| [2025-03-06 22:03:33,360][00284] ConvEncoder: input_channels=3 | |
| [2025-03-06 22:03:33,510][00284] Conv encoder output size: 512 | |
| [2025-03-06 22:03:33,511][00284] Policy head output size: 512 | |
| [2025-03-06 22:03:33,825][00284] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-03-06 22:03:34,871][00284] Num frames 100... | |
| [2025-03-06 22:03:35,002][00284] Num frames 200... | |
| [2025-03-06 22:03:35,132][00284] Num frames 300... | |
| [2025-03-06 22:03:35,271][00284] Num frames 400... | |
| [2025-03-06 22:03:35,403][00284] Num frames 500... | |
| [2025-03-06 22:03:35,534][00284] Num frames 600... | |
| [2025-03-06 22:03:35,665][00284] Num frames 700... | |
| [2025-03-06 22:03:35,731][00284] Avg episode rewards: #0: 12.080, true rewards: #0: 7.080 | |
| [2025-03-06 22:03:35,732][00284] Avg episode reward: 12.080, avg true_objective: 7.080 | |
| [2025-03-06 22:03:35,851][00284] Num frames 800... | |
| [2025-03-06 22:03:35,981][00284] Num frames 900... | |
| [2025-03-06 22:03:36,120][00284] Num frames 1000... | |
| [2025-03-06 22:03:36,260][00284] Num frames 1100... | |
| [2025-03-06 22:03:36,400][00284] Num frames 1200... | |
| [2025-03-06 22:03:36,531][00284] Num frames 1300... | |
| [2025-03-06 22:03:36,661][00284] Num frames 1400... | |
| [2025-03-06 22:03:36,792][00284] Num frames 1500... | |
| [2025-03-06 22:03:36,923][00284] Num frames 1600... | |
| [2025-03-06 22:03:37,062][00284] Num frames 1700... | |
| [2025-03-06 22:03:37,193][00284] Num frames 1800... | |
| [2025-03-06 22:03:37,334][00284] Num frames 1900... | |
| [2025-03-06 22:03:37,466][00284] Num frames 2000... | |
| [2025-03-06 22:03:37,597][00284] Num frames 2100... | |
| [2025-03-06 22:03:37,730][00284] Num frames 2200... | |
| [2025-03-06 22:03:37,846][00284] Avg episode rewards: #0: 26.735, true rewards: #0: 11.235 | |
| [2025-03-06 22:03:37,847][00284] Avg episode reward: 26.735, avg true_objective: 11.235 | |
| [2025-03-06 22:03:37,917][00284] Num frames 2300... | |
| [2025-03-06 22:03:38,050][00284] Num frames 2400... | |
| [2025-03-06 22:03:38,181][00284] Num frames 2500... | |
| [2025-03-06 22:03:38,313][00284] Num frames 2600... | |
| [2025-03-06 22:03:38,453][00284] Num frames 2700... | |
| [2025-03-06 22:03:38,584][00284] Num frames 2800... | |
| [2025-03-06 22:03:38,716][00284] Num frames 2900... | |
| [2025-03-06 22:03:38,850][00284] Num frames 3000... | |
| [2025-03-06 22:03:38,984][00284] Num frames 3100... | |
| [2025-03-06 22:03:39,121][00284] Num frames 3200... | |
| [2025-03-06 22:03:39,251][00284] Num frames 3300... | |
| [2025-03-06 22:03:39,387][00284] Num frames 3400... | |
| [2025-03-06 22:03:39,519][00284] Num frames 3500... | |
| [2025-03-06 22:03:39,653][00284] Num frames 3600... | |
| [2025-03-06 22:03:39,786][00284] Num frames 3700... | |
| [2025-03-06 22:03:39,915][00284] Num frames 3800... | |
| [2025-03-06 22:03:40,046][00284] Num frames 3900... | |
| [2025-03-06 22:03:40,179][00284] Num frames 4000... | |
| [2025-03-06 22:03:40,317][00284] Num frames 4100... | |
| [2025-03-06 22:03:40,454][00284] Num frames 4200... | |
| [2025-03-06 22:03:40,585][00284] Num frames 4300... | |
| [2025-03-06 22:03:40,676][00284] Avg episode rewards: #0: 33.756, true rewards: #0: 14.423 | |
| [2025-03-06 22:03:40,677][00284] Avg episode reward: 33.756, avg true_objective: 14.423 | |
| [2025-03-06 22:03:40,772][00284] Num frames 4400... | |
| [2025-03-06 22:03:40,903][00284] Num frames 4500... | |
| [2025-03-06 22:03:41,034][00284] Num frames 4600... | |
| [2025-03-06 22:03:41,168][00284] Num frames 4700... | |
| [2025-03-06 22:03:41,298][00284] Num frames 4800... | |
| [2025-03-06 22:03:41,435][00284] Num frames 4900... | |
| [2025-03-06 22:03:41,564][00284] Num frames 5000... | |
| [2025-03-06 22:03:41,699][00284] Num frames 5100... | |
| [2025-03-06 22:03:41,833][00284] Num frames 5200... | |
| [2025-03-06 22:03:41,966][00284] Num frames 5300... | |
| [2025-03-06 22:03:42,107][00284] Num frames 5400... | |
| [2025-03-06 22:03:42,239][00284] Num frames 5500... | |
| [2025-03-06 22:03:42,370][00284] Num frames 5600... | |
| [2025-03-06 22:03:42,510][00284] Num frames 5700... | |
| [2025-03-06 22:03:42,648][00284] Num frames 5800... | |
| [2025-03-06 22:03:42,779][00284] Num frames 5900... | |
| [2025-03-06 22:03:42,870][00284] Avg episode rewards: #0: 34.817, true rewards: #0: 14.817 | |
| [2025-03-06 22:03:42,871][00284] Avg episode reward: 34.817, avg true_objective: 14.817 | |
| [2025-03-06 22:03:42,967][00284] Num frames 6000... | |
| [2025-03-06 22:03:43,102][00284] Num frames 6100... | |
| [2025-03-06 22:03:43,229][00284] Num frames 6200... | |
| [2025-03-06 22:03:43,359][00284] Num frames 6300... | |
| [2025-03-06 22:03:43,499][00284] Num frames 6400... | |
| [2025-03-06 22:03:43,628][00284] Num frames 6500... | |
| [2025-03-06 22:03:43,764][00284] Num frames 6600... | |
| [2025-03-06 22:03:43,892][00284] Num frames 6700... | |
| [2025-03-06 22:03:44,024][00284] Num frames 6800... | |
| [2025-03-06 22:03:44,194][00284] Avg episode rewards: #0: 31.774, true rewards: #0: 13.774 | |
| [2025-03-06 22:03:44,195][00284] Avg episode reward: 31.774, avg true_objective: 13.774 | |
| [2025-03-06 22:03:44,216][00284] Num frames 6900... | |
| [2025-03-06 22:03:44,355][00284] Num frames 7000... | |
| [2025-03-06 22:03:44,493][00284] Num frames 7100... | |
| [2025-03-06 22:03:44,648][00284] Num frames 7200... | |
| [2025-03-06 22:03:44,831][00284] Num frames 7300... | |
| [2025-03-06 22:03:44,998][00284] Num frames 7400... | |
| [2025-03-06 22:03:45,170][00284] Num frames 7500... | |
| [2025-03-06 22:03:45,339][00284] Num frames 7600... | |
| [2025-03-06 22:03:45,509][00284] Num frames 7700... | |
| [2025-03-06 22:03:45,679][00284] Num frames 7800... | |
| [2025-03-06 22:03:45,844][00284] Num frames 7900... | |
| [2025-03-06 22:03:46,018][00284] Num frames 8000... | |
| [2025-03-06 22:03:46,145][00284] Avg episode rewards: #0: 30.398, true rewards: #0: 13.398 | |
| [2025-03-06 22:03:46,147][00284] Avg episode reward: 30.398, avg true_objective: 13.398 | |
| [2025-03-06 22:03:46,253][00284] Num frames 8100... | |
| [2025-03-06 22:03:46,427][00284] Num frames 8200... | |
| [2025-03-06 22:03:46,613][00284] Num frames 8300... | |
| [2025-03-06 22:03:46,768][00284] Num frames 8400... | |
| [2025-03-06 22:03:46,898][00284] Num frames 8500... | |
| [2025-03-06 22:03:47,033][00284] Num frames 8600... | |
| [2025-03-06 22:03:47,168][00284] Num frames 8700... | |
| [2025-03-06 22:03:47,302][00284] Num frames 8800... | |
| [2025-03-06 22:03:47,432][00284] Num frames 8900... | |
| [2025-03-06 22:03:47,563][00284] Num frames 9000... | |
| [2025-03-06 22:03:47,696][00284] Num frames 9100... | |
| [2025-03-06 22:03:47,825][00284] Num frames 9200... | |
| [2025-03-06 22:03:47,955][00284] Num frames 9300... | |
| [2025-03-06 22:03:48,086][00284] Num frames 9400... | |
| [2025-03-06 22:03:48,219][00284] Num frames 9500... | |
| [2025-03-06 22:03:48,349][00284] Num frames 9600... | |
| [2025-03-06 22:03:48,479][00284] Num frames 9700... | |
| [2025-03-06 22:03:48,606][00284] Num frames 9800... | |
| [2025-03-06 22:03:48,744][00284] Num frames 9900... | |
| [2025-03-06 22:03:48,874][00284] Num frames 10000... | |
| [2025-03-06 22:03:49,007][00284] Num frames 10100... | |
| [2025-03-06 22:03:49,119][00284] Avg episode rewards: #0: 33.484, true rewards: #0: 14.484 | |
| [2025-03-06 22:03:49,119][00284] Avg episode reward: 33.484, avg true_objective: 14.484 | |
| [2025-03-06 22:03:49,198][00284] Num frames 10200... | |
| [2025-03-06 22:03:49,330][00284] Num frames 10300... | |
| [2025-03-06 22:03:49,508][00284] Avg episode rewards: #0: 29.619, true rewards: #0: 12.994 | |
| [2025-03-06 22:03:49,509][00284] Avg episode reward: 29.619, avg true_objective: 12.994 | |
| [2025-03-06 22:03:49,518][00284] Num frames 10400... | |
| [2025-03-06 22:03:49,646][00284] Num frames 10500... | |
| [2025-03-06 22:03:49,794][00284] Num frames 10600... | |
| [2025-03-06 22:03:49,945][00284] Num frames 10700... | |
| [2025-03-06 22:03:50,079][00284] Num frames 10800... | |
| [2025-03-06 22:03:50,210][00284] Num frames 10900... | |
| [2025-03-06 22:03:50,341][00284] Num frames 11000... | |
| [2025-03-06 22:03:50,470][00284] Num frames 11100... | |
| [2025-03-06 22:03:50,599][00284] Num frames 11200... | |
| [2025-03-06 22:03:50,733][00284] Num frames 11300... | |
| [2025-03-06 22:03:50,865][00284] Num frames 11400... | |
| [2025-03-06 22:03:50,994][00284] Num frames 11500... | |
| [2025-03-06 22:03:51,124][00284] Num frames 11600... | |
| [2025-03-06 22:03:51,252][00284] Num frames 11700... | |
| [2025-03-06 22:03:51,378][00284] Num frames 11800... | |
| [2025-03-06 22:03:51,506][00284] Num frames 11900... | |
| [2025-03-06 22:03:51,634][00284] Num frames 12000... | |
| [2025-03-06 22:03:51,770][00284] Num frames 12100... | |
| [2025-03-06 22:03:51,901][00284] Num frames 12200... | |
| [2025-03-06 22:03:52,034][00284] Num frames 12300... | |
| [2025-03-06 22:03:52,170][00284] Num frames 12400... | |
| [2025-03-06 22:03:52,347][00284] Avg episode rewards: #0: 33.105, true rewards: #0: 13.883 | |
| [2025-03-06 22:03:52,348][00284] Avg episode reward: 33.105, avg true_objective: 13.883 | |
| [2025-03-06 22:03:52,358][00284] Num frames 12500... | |
| [2025-03-06 22:03:52,485][00284] Num frames 12600... | |
| [2025-03-06 22:03:52,615][00284] Num frames 12700... | |
| [2025-03-06 22:03:52,749][00284] Num frames 12800... | |
| [2025-03-06 22:03:52,884][00284] Num frames 12900... | |
| [2025-03-06 22:03:53,035][00284] Num frames 13000... | |
| [2025-03-06 22:03:53,172][00284] Num frames 13100... | |
| [2025-03-06 22:03:53,299][00284] Num frames 13200... | |
| [2025-03-06 22:03:53,427][00284] Num frames 13300... | |
| [2025-03-06 22:03:53,552][00284] Num frames 13400... | |
| [2025-03-06 22:03:53,680][00284] Num frames 13500... | |
| [2025-03-06 22:03:53,816][00284] Num frames 13600... | |
| [2025-03-06 22:03:53,945][00284] Num frames 13700... | |
| [2025-03-06 22:03:54,096][00284] Avg episode rewards: #0: 32.375, true rewards: #0: 13.775 | |
| [2025-03-06 22:03:54,097][00284] Avg episode reward: 32.375, avg true_objective: 13.775 | |
| [2025-03-06 22:05:10,972][00284] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2025-03-06 22:08:42,286][00284] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-03-06 22:08:42,287][00284] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-03-06 22:08:42,288][00284] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-03-06 22:08:42,289][00284] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-03-06 22:08:42,290][00284] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-03-06 22:08:42,290][00284] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-03-06 22:08:42,291][00284] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-03-06 22:08:42,292][00284] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-03-06 22:08:42,293][00284] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-03-06 22:08:42,294][00284] Adding new argument 'hf_repository'='taha454/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-03-06 22:08:42,294][00284] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-03-06 22:08:42,295][00284] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-03-06 22:08:42,296][00284] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-03-06 22:08:42,297][00284] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-03-06 22:08:42,298][00284] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-03-06 22:08:42,324][00284] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-03-06 22:08:42,325][00284] RunningMeanStd input shape: (1,) | |
| [2025-03-06 22:08:42,336][00284] ConvEncoder: input_channels=3 | |
| [2025-03-06 22:08:42,368][00284] Conv encoder output size: 512 | |
| [2025-03-06 22:08:42,369][00284] Policy head output size: 512 | |
| [2025-03-06 22:08:42,387][00284] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-03-06 22:08:42,824][00284] Num frames 100... | |
| [2025-03-06 22:08:42,950][00284] Num frames 200... | |
| [2025-03-06 22:08:43,092][00284] Num frames 300... | |
| [2025-03-06 22:08:43,223][00284] Num frames 400... | |
| [2025-03-06 22:08:43,347][00284] Num frames 500... | |
| [2025-03-06 22:08:43,473][00284] Num frames 600... | |
| [2025-03-06 22:08:43,599][00284] Num frames 700... | |
| [2025-03-06 22:08:43,725][00284] Num frames 800... | |
| [2025-03-06 22:08:43,849][00284] Num frames 900... | |
| [2025-03-06 22:08:43,977][00284] Num frames 1000... | |
| [2025-03-06 22:08:44,115][00284] Num frames 1100... | |
| [2025-03-06 22:08:44,241][00284] Num frames 1200... | |
| [2025-03-06 22:08:44,365][00284] Num frames 1300... | |
| [2025-03-06 22:08:44,491][00284] Num frames 1400... | |
| [2025-03-06 22:08:44,619][00284] Num frames 1500... | |
| [2025-03-06 22:08:44,747][00284] Num frames 1600... | |
| [2025-03-06 22:08:44,877][00284] Num frames 1700... | |
| [2025-03-06 22:08:45,007][00284] Num frames 1800... | |
| [2025-03-06 22:08:45,147][00284] Num frames 1900... | |
| [2025-03-06 22:08:45,281][00284] Num frames 2000... | |
| [2025-03-06 22:08:45,413][00284] Num frames 2100... | |
| [2025-03-06 22:08:45,466][00284] Avg episode rewards: #0: 53.999, true rewards: #0: 21.000 | |
| [2025-03-06 22:08:45,467][00284] Avg episode reward: 53.999, avg true_objective: 21.000 | |
| [2025-03-06 22:08:45,596][00284] Num frames 2200... | |
| [2025-03-06 22:08:45,724][00284] Num frames 2300... | |
| [2025-03-06 22:08:45,848][00284] Num frames 2400... | |
| [2025-03-06 22:08:45,975][00284] Num frames 2500... | |
| [2025-03-06 22:08:46,108][00284] Num frames 2600... | |
| [2025-03-06 22:08:46,278][00284] Num frames 2700... | |
| [2025-03-06 22:08:46,405][00284] Avg episode rewards: #0: 32.709, true rewards: #0: 13.710 | |
| [2025-03-06 22:08:46,406][00284] Avg episode reward: 32.709, avg true_objective: 13.710 | |
| [2025-03-06 22:08:46,504][00284] Num frames 2800... | |
| [2025-03-06 22:08:46,669][00284] Num frames 2900... | |
| [2025-03-06 22:08:46,835][00284] Num frames 3000... | |
| [2025-03-06 22:08:47,004][00284] Num frames 3100... | |
| [2025-03-06 22:08:47,191][00284] Num frames 3200... | |
| [2025-03-06 22:08:47,354][00284] Num frames 3300... | |
| [2025-03-06 22:08:47,527][00284] Num frames 3400... | |
| [2025-03-06 22:08:47,703][00284] Num frames 3500... | |
| [2025-03-06 22:08:47,874][00284] Num frames 3600... | |
| [2025-03-06 22:08:48,058][00284] Num frames 3700... | |
| [2025-03-06 22:08:48,120][00284] Avg episode rewards: #0: 29.336, true rewards: #0: 12.337 | |
| [2025-03-06 22:08:48,120][00284] Avg episode reward: 29.336, avg true_objective: 12.337 | |
| [2025-03-06 22:08:48,263][00284] Num frames 3800... | |
| [2025-03-06 22:08:48,389][00284] Num frames 3900... | |
| [2025-03-06 22:08:48,519][00284] Num frames 4000... | |
| [2025-03-06 22:08:48,650][00284] Num frames 4100... | |
| [2025-03-06 22:08:48,777][00284] Num frames 4200... | |
| [2025-03-06 22:08:48,849][00284] Avg episode rewards: #0: 24.032, true rewards: #0: 10.533 | |
| [2025-03-06 22:08:48,850][00284] Avg episode reward: 24.032, avg true_objective: 10.533 | |
| [2025-03-06 22:08:48,961][00284] Num frames 4300... | |
| [2025-03-06 22:08:49,094][00284] Num frames 4400... | |
| [2025-03-06 22:08:49,219][00284] Num frames 4500... | |
| [2025-03-06 22:08:49,354][00284] Num frames 4600... | |
| [2025-03-06 22:08:49,484][00284] Num frames 4700... | |
| [2025-03-06 22:08:49,613][00284] Num frames 4800... | |
| [2025-03-06 22:08:49,778][00284] Avg episode rewards: #0: 21.570, true rewards: #0: 9.770 | |
| [2025-03-06 22:08:49,779][00284] Avg episode reward: 21.570, avg true_objective: 9.770 | |
| [2025-03-06 22:08:49,799][00284] Num frames 4900... | |
| [2025-03-06 22:08:49,927][00284] Num frames 5000... | |
| [2025-03-06 22:08:50,062][00284] Num frames 5100... | |
| [2025-03-06 22:08:50,190][00284] Num frames 5200... | |
| [2025-03-06 22:08:50,330][00284] Num frames 5300... | |
| [2025-03-06 22:08:50,462][00284] Num frames 5400... | |
| [2025-03-06 22:08:50,607][00284] Num frames 5500... | |
| [2025-03-06 22:08:50,736][00284] Num frames 5600... | |
| [2025-03-06 22:08:50,866][00284] Num frames 5700... | |
| [2025-03-06 22:08:50,996][00284] Num frames 5800... | |
| [2025-03-06 22:08:51,128][00284] Num frames 5900... | |
| [2025-03-06 22:08:51,257][00284] Num frames 6000... | |
| [2025-03-06 22:08:51,393][00284] Num frames 6100... | |
| [2025-03-06 22:08:51,529][00284] Num frames 6200... | |
| [2025-03-06 22:08:51,664][00284] Num frames 6300... | |
| [2025-03-06 22:08:51,794][00284] Num frames 6400... | |
| [2025-03-06 22:08:51,878][00284] Avg episode rewards: #0: 24.870, true rewards: #0: 10.703 | |
| [2025-03-06 22:08:51,879][00284] Avg episode reward: 24.870, avg true_objective: 10.703 | |
| [2025-03-06 22:08:51,981][00284] Num frames 6500... | |
| [2025-03-06 22:08:52,114][00284] Num frames 6600... | |
| [2025-03-06 22:08:52,241][00284] Num frames 6700... | |
| [2025-03-06 22:08:52,377][00284] Num frames 6800... | |
| [2025-03-06 22:08:52,506][00284] Num frames 6900... | |
| [2025-03-06 22:08:52,633][00284] Num frames 7000... | |
| [2025-03-06 22:08:52,806][00284] Avg episode rewards: #0: 23.563, true rewards: #0: 10.134 | |
| [2025-03-06 22:08:52,807][00284] Avg episode reward: 23.563, avg true_objective: 10.134 | |
| [2025-03-06 22:08:52,818][00284] Num frames 7100... | |
| [2025-03-06 22:08:52,942][00284] Num frames 7200... | |
| [2025-03-06 22:08:53,085][00284] Num frames 7300... | |
| [2025-03-06 22:08:53,210][00284] Num frames 7400... | |
| [2025-03-06 22:08:53,343][00284] Num frames 7500... | |
| [2025-03-06 22:08:53,475][00284] Num frames 7600... | |
| [2025-03-06 22:08:53,603][00284] Num frames 7700... | |
| [2025-03-06 22:08:53,733][00284] Num frames 7800... | |
| [2025-03-06 22:08:53,863][00284] Num frames 7900... | |
| [2025-03-06 22:08:53,997][00284] Num frames 8000... | |
| [2025-03-06 22:08:54,160][00284] Num frames 8100... | |
| [2025-03-06 22:08:54,292][00284] Num frames 8200... | |
| [2025-03-06 22:08:54,431][00284] Num frames 8300... | |
| [2025-03-06 22:08:54,609][00284] Avg episode rewards: #0: 25.115, true rewards: #0: 10.490 | |
| [2025-03-06 22:08:54,610][00284] Avg episode reward: 25.115, avg true_objective: 10.490 | |
| [2025-03-06 22:08:54,622][00284] Num frames 8400... | |
| [2025-03-06 22:08:54,755][00284] Num frames 8500... | |
| [2025-03-06 22:08:54,887][00284] Num frames 8600... | |
| [2025-03-06 22:08:55,015][00284] Num frames 8700... | |
| [2025-03-06 22:08:55,155][00284] Num frames 8800... | |
| [2025-03-06 22:08:55,297][00284] Num frames 8900... | |
| [2025-03-06 22:08:55,435][00284] Num frames 9000... | |
| [2025-03-06 22:08:55,566][00284] Num frames 9100... | |
| [2025-03-06 22:08:55,696][00284] Num frames 9200... | |
| [2025-03-06 22:08:55,824][00284] Num frames 9300... | |
| [2025-03-06 22:08:55,950][00284] Num frames 9400... | |
| [2025-03-06 22:08:56,082][00284] Num frames 9500... | |
| [2025-03-06 22:08:56,210][00284] Num frames 9600... | |
| [2025-03-06 22:08:56,336][00284] Num frames 9700... | |
| [2025-03-06 22:08:56,471][00284] Num frames 9800... | |
| [2025-03-06 22:08:56,533][00284] Avg episode rewards: #0: 26.115, true rewards: #0: 10.893 | |
| [2025-03-06 22:08:56,534][00284] Avg episode reward: 26.115, avg true_objective: 10.893 | |
| [2025-03-06 22:08:56,658][00284] Num frames 9900... | |
| [2025-03-06 22:08:56,787][00284] Num frames 10000... | |
| [2025-03-06 22:08:56,914][00284] Num frames 10100... | |
| [2025-03-06 22:08:57,042][00284] Num frames 10200... | |
| [2025-03-06 22:08:57,170][00284] Num frames 10300... | |
| [2025-03-06 22:08:57,231][00284] Avg episode rewards: #0: 24.504, true rewards: #0: 10.304 | |
| [2025-03-06 22:08:57,231][00284] Avg episode reward: 24.504, avg true_objective: 10.304 | |
| [2025-03-06 22:09:55,046][00284] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2025-03-06 22:17:30,140][00284] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2025-03-06 22:17:30,141][00284] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2025-03-06 22:17:30,142][00284] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2025-03-06 22:17:30,143][00284] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2025-03-06 22:17:30,145][00284] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2025-03-06 22:17:30,146][00284] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2025-03-06 22:17:30,147][00284] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2025-03-06 22:17:30,147][00284] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2025-03-06 22:17:30,148][00284] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2025-03-06 22:17:30,149][00284] Adding new argument 'hf_repository'='taha454/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2025-03-06 22:17:30,150][00284] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2025-03-06 22:17:30,151][00284] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2025-03-06 22:17:30,152][00284] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2025-03-06 22:17:30,153][00284] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2025-03-06 22:17:30,154][00284] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2025-03-06 22:17:30,177][00284] RunningMeanStd input shape: (3, 72, 128) | |
| [2025-03-06 22:17:30,179][00284] RunningMeanStd input shape: (1,) | |
| [2025-03-06 22:17:30,190][00284] ConvEncoder: input_channels=3 | |
| [2025-03-06 22:17:30,223][00284] Conv encoder output size: 512 | |
| [2025-03-06 22:17:30,224][00284] Policy head output size: 512 | |
| [2025-03-06 22:17:30,242][00284] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2025-03-06 22:17:30,687][00284] Num frames 100... | |
| [2025-03-06 22:17:30,816][00284] Num frames 200... | |
| [2025-03-06 22:17:30,950][00284] Num frames 300... | |
| [2025-03-06 22:17:31,098][00284] Num frames 400... | |
| [2025-03-06 22:17:31,230][00284] Num frames 500... | |
| [2025-03-06 22:17:31,362][00284] Num frames 600... | |
| [2025-03-06 22:17:31,491][00284] Num frames 700... | |
| [2025-03-06 22:17:31,618][00284] Num frames 800... | |
| [2025-03-06 22:17:31,746][00284] Num frames 900... | |
| [2025-03-06 22:17:31,876][00284] Num frames 1000... | |
| [2025-03-06 22:17:32,014][00284] Num frames 1100... | |
| [2025-03-06 22:17:32,158][00284] Num frames 1200... | |
| [2025-03-06 22:17:32,275][00284] Avg episode rewards: #0: 28.480, true rewards: #0: 12.480 | |
| [2025-03-06 22:17:32,276][00284] Avg episode reward: 28.480, avg true_objective: 12.480 | |
| [2025-03-06 22:17:32,345][00284] Num frames 1300... | |
| [2025-03-06 22:17:32,473][00284] Num frames 1400... | |
| [2025-03-06 22:17:32,610][00284] Num frames 1500... | |
| [2025-03-06 22:17:32,793][00284] Num frames 1600... | |
| [2025-03-06 22:17:32,970][00284] Num frames 1700... | |
| [2025-03-06 22:17:33,150][00284] Num frames 1800... | |
| [2025-03-06 22:17:33,324][00284] Num frames 1900... | |
| [2025-03-06 22:17:33,494][00284] Num frames 2000... | |
| [2025-03-06 22:17:33,654][00284] Num frames 2100... | |
| [2025-03-06 22:17:33,821][00284] Num frames 2200... | |
| [2025-03-06 22:17:34,011][00284] Num frames 2300... | |
| [2025-03-06 22:17:34,192][00284] Num frames 2400... | |
| [2025-03-06 22:17:34,377][00284] Num frames 2500... | |
| [2025-03-06 22:17:34,566][00284] Num frames 2600... | |
| [2025-03-06 22:17:34,741][00284] Num frames 2700... | |
| [2025-03-06 22:17:34,869][00284] Num frames 2800... | |
| [2025-03-06 22:17:34,997][00284] Num frames 2900... | |
| [2025-03-06 22:17:35,126][00284] Num frames 3000... | |
| [2025-03-06 22:17:35,263][00284] Num frames 3100... | |
| [2025-03-06 22:17:35,405][00284] Num frames 3200... | |
| [2025-03-06 22:17:35,539][00284] Num frames 3300... | |
| [2025-03-06 22:17:35,659][00284] Avg episode rewards: #0: 39.740, true rewards: #0: 16.740 | |
| [2025-03-06 22:17:35,660][00284] Avg episode reward: 39.740, avg true_objective: 16.740 | |
| [2025-03-06 22:17:35,731][00284] Num frames 3400... | |
| [2025-03-06 22:17:35,860][00284] Num frames 3500... | |
| [2025-03-06 22:17:35,998][00284] Num frames 3600... | |
| [2025-03-06 22:17:36,130][00284] Num frames 3700... | |
| [2025-03-06 22:17:36,260][00284] Num frames 3800... | |
| [2025-03-06 22:17:36,397][00284] Num frames 3900... | |
| [2025-03-06 22:17:36,536][00284] Num frames 4000... | |
| [2025-03-06 22:17:36,667][00284] Num frames 4100... | |
| [2025-03-06 22:17:36,805][00284] Num frames 4200... | |
| [2025-03-06 22:17:36,877][00284] Avg episode rewards: #0: 32.706, true rewards: #0: 14.040 | |
| [2025-03-06 22:17:36,878][00284] Avg episode reward: 32.706, avg true_objective: 14.040 | |
| [2025-03-06 22:17:37,001][00284] Num frames 4300... | |
| [2025-03-06 22:17:37,137][00284] Num frames 4400... | |
| [2025-03-06 22:17:37,270][00284] Num frames 4500... | |
| [2025-03-06 22:17:37,417][00284] Num frames 4600... | |
| [2025-03-06 22:17:37,552][00284] Num frames 4700... | |
| [2025-03-06 22:17:37,681][00284] Num frames 4800... | |
| [2025-03-06 22:17:37,816][00284] Num frames 4900... | |
| [2025-03-06 22:17:37,954][00284] Num frames 5000... | |
| [2025-03-06 22:17:38,089][00284] Num frames 5100... | |
| [2025-03-06 22:17:38,228][00284] Num frames 5200... | |
| [2025-03-06 22:17:38,363][00284] Avg episode rewards: #0: 30.897, true rewards: #0: 13.147 | |
| [2025-03-06 22:17:38,365][00284] Avg episode reward: 30.897, avg true_objective: 13.147 | |
| [2025-03-06 22:17:38,421][00284] Num frames 5300... | |
| [2025-03-06 22:17:38,553][00284] Num frames 5400... | |
| [2025-03-06 22:17:38,688][00284] Num frames 5500... | |
| [2025-03-06 22:17:38,822][00284] Num frames 5600... | |
| [2025-03-06 22:17:38,963][00284] Num frames 5700... | |
| [2025-03-06 22:17:39,114][00284] Num frames 5800... | |
| [2025-03-06 22:17:39,248][00284] Num frames 5900... | |
| [2025-03-06 22:17:39,391][00284] Num frames 6000... | |
| [2025-03-06 22:17:39,528][00284] Num frames 6100... | |
| [2025-03-06 22:17:39,663][00284] Num frames 6200... | |
| [2025-03-06 22:17:39,794][00284] Num frames 6300... | |
| [2025-03-06 22:17:39,869][00284] Avg episode rewards: #0: 28.830, true rewards: #0: 12.630 | |
| [2025-03-06 22:17:39,870][00284] Avg episode reward: 28.830, avg true_objective: 12.630 | |
| [2025-03-06 22:17:39,983][00284] Num frames 6400... | |
| [2025-03-06 22:17:40,129][00284] Num frames 6500... | |
| [2025-03-06 22:17:40,262][00284] Num frames 6600... | |
| [2025-03-06 22:17:40,401][00284] Num frames 6700... | |
| [2025-03-06 22:17:40,541][00284] Num frames 6800... | |
| [2025-03-06 22:17:40,674][00284] Num frames 6900... | |
| [2025-03-06 22:17:40,805][00284] Num frames 7000... | |
| [2025-03-06 22:17:40,942][00284] Num frames 7100... | |
| [2025-03-06 22:17:41,061][00284] Avg episode rewards: #0: 27.078, true rewards: #0: 11.912 | |
| [2025-03-06 22:17:41,062][00284] Avg episode reward: 27.078, avg true_objective: 11.912 | |
| [2025-03-06 22:17:41,133][00284] Num frames 7200... | |
| [2025-03-06 22:17:41,268][00284] Num frames 7300... | |
| [2025-03-06 22:17:41,398][00284] Num frames 7400... | |
| [2025-03-06 22:17:41,542][00284] Num frames 7500... | |
| [2025-03-06 22:17:41,684][00284] Num frames 7600... | |
| [2025-03-06 22:17:41,817][00284] Num frames 7700... | |
| [2025-03-06 22:17:41,948][00284] Num frames 7800... | |
| [2025-03-06 22:17:42,090][00284] Num frames 7900... | |
| [2025-03-06 22:17:42,224][00284] Num frames 8000... | |
| [2025-03-06 22:17:42,359][00284] Num frames 8100... | |
| [2025-03-06 22:17:42,506][00284] Num frames 8200... | |
| [2025-03-06 22:17:42,650][00284] Num frames 8300... | |
| [2025-03-06 22:17:42,791][00284] Num frames 8400... | |
| [2025-03-06 22:17:42,923][00284] Num frames 8500... | |
| [2025-03-06 22:17:43,058][00284] Num frames 8600... | |
| [2025-03-06 22:17:43,186][00284] Num frames 8700... | |
| [2025-03-06 22:17:43,316][00284] Num frames 8800... | |
| [2025-03-06 22:17:43,444][00284] Num frames 8900... | |
| [2025-03-06 22:17:43,583][00284] Num frames 9000... | |
| [2025-03-06 22:17:43,712][00284] Num frames 9100... | |
| [2025-03-06 22:17:43,810][00284] Avg episode rewards: #0: 30.758, true rewards: #0: 13.044 | |
| [2025-03-06 22:17:43,811][00284] Avg episode reward: 30.758, avg true_objective: 13.044 | |
| [2025-03-06 22:17:43,902][00284] Num frames 9200... | |
| [2025-03-06 22:17:44,034][00284] Num frames 9300... | |
| [2025-03-06 22:17:44,178][00284] Num frames 9400... | |
| [2025-03-06 22:17:44,311][00284] Num frames 9500... | |
| [2025-03-06 22:17:44,440][00284] Num frames 9600... | |
| [2025-03-06 22:17:44,602][00284] Avg episode rewards: #0: 28.344, true rewards: #0: 12.094 | |
| [2025-03-06 22:17:44,603][00284] Avg episode reward: 28.344, avg true_objective: 12.094 | |
| [2025-03-06 22:17:44,638][00284] Num frames 9700... | |
| [2025-03-06 22:17:44,787][00284] Num frames 9800... | |
| [2025-03-06 22:17:44,965][00284] Num frames 9900... | |
| [2025-03-06 22:17:45,147][00284] Num frames 10000... | |
| [2025-03-06 22:17:45,324][00284] Num frames 10100... | |
| [2025-03-06 22:17:45,500][00284] Num frames 10200... | |
| [2025-03-06 22:17:45,690][00284] Num frames 10300... | |
| [2025-03-06 22:17:45,867][00284] Num frames 10400... | |
| [2025-03-06 22:17:46,053][00284] Num frames 10500... | |
| [2025-03-06 22:17:46,260][00284] Avg episode rewards: #0: 27.644, true rewards: #0: 11.756 | |
| [2025-03-06 22:17:46,261][00284] Avg episode reward: 27.644, avg true_objective: 11.756 | |
| [2025-03-06 22:17:46,300][00284] Num frames 10600... | |
| [2025-03-06 22:17:46,481][00284] Num frames 10700... | |
| [2025-03-06 22:17:46,683][00284] Num frames 10800... | |
| [2025-03-06 22:17:46,875][00284] Num frames 10900... | |
| [2025-03-06 22:17:47,024][00284] Num frames 11000... | |
| [2025-03-06 22:17:47,159][00284] Num frames 11100... | |
| [2025-03-06 22:17:47,297][00284] Num frames 11200... | |
| [2025-03-06 22:17:47,428][00284] Num frames 11300... | |
| [2025-03-06 22:17:47,566][00284] Num frames 11400... | |
| [2025-03-06 22:17:47,713][00284] Num frames 11500... | |
| [2025-03-06 22:17:47,847][00284] Num frames 11600... | |
| [2025-03-06 22:17:47,982][00284] Num frames 11700... | |
| [2025-03-06 22:17:48,123][00284] Num frames 11800... | |
| [2025-03-06 22:17:48,257][00284] Num frames 11900... | |
| [2025-03-06 22:17:48,393][00284] Num frames 12000... | |
| [2025-03-06 22:17:48,533][00284] Num frames 12100... | |
| [2025-03-06 22:17:48,610][00284] Avg episode rewards: #0: 28.716, true rewards: #0: 12.116 | |
| [2025-03-06 22:17:48,611][00284] Avg episode reward: 28.716, avg true_objective: 12.116 | |
| [2025-03-06 22:18:57,702][00284] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |