| [2024-09-07 05:36:19,875][01890] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2024-09-07 05:36:19,878][01890] Rollout worker 0 uses device cpu | |
| [2024-09-07 05:36:19,879][01890] Rollout worker 1 uses device cpu | |
| [2024-09-07 05:36:19,880][01890] Rollout worker 2 uses device cpu | |
| [2024-09-07 05:36:19,882][01890] Rollout worker 3 uses device cpu | |
| [2024-09-07 05:36:19,883][01890] Rollout worker 4 uses device cpu | |
| [2024-09-07 05:36:19,885][01890] Rollout worker 5 uses device cpu | |
| [2024-09-07 05:36:19,886][01890] Rollout worker 6 uses device cpu | |
| [2024-09-07 05:36:19,887][01890] Rollout worker 7 uses device cpu | |
| [2024-09-07 05:36:20,042][01890] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-09-07 05:36:20,043][01890] InferenceWorker_p0-w0: min num requests: 2 | |
| [2024-09-07 05:36:20,075][01890] Starting all processes... | |
| [2024-09-07 05:36:20,077][01890] Starting process learner_proc0 | |
| [2024-09-07 05:36:20,793][01890] Starting all processes... | |
| [2024-09-07 05:36:20,807][01890] Starting process inference_proc0-0 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc0 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc2 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc3 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc4 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc5 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc6 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc7 | |
| [2024-09-07 05:36:20,808][01890] Starting process rollout_proc1 | |
| [2024-09-07 05:36:36,325][04362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-09-07 05:36:36,334][04362] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2024-09-07 05:36:36,395][04362] Num visible devices: 1 | |
| [2024-09-07 05:36:36,458][04376] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-09-07 05:36:36,459][04376] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2024-09-07 05:36:36,465][04362] Starting seed is not provided | |
| [2024-09-07 05:36:36,465][04362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-09-07 05:36:36,466][04362] Initializing actor-critic model on device cuda:0 | |
| [2024-09-07 05:36:36,467][04362] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-09-07 05:36:36,470][04362] RunningMeanStd input shape: (1,) | |
| [2024-09-07 05:36:36,549][04362] ConvEncoder: input_channels=3 | |
| [2024-09-07 05:36:36,558][04376] Num visible devices: 1 | |
| [2024-09-07 05:36:36,604][04375] Worker 0 uses CPU cores [0] | |
| [2024-09-07 05:36:36,693][04378] Worker 4 uses CPU cores [0] | |
| [2024-09-07 05:36:37,036][04381] Worker 6 uses CPU cores [0] | |
| [2024-09-07 05:36:37,076][04382] Worker 7 uses CPU cores [1] | |
| [2024-09-07 05:36:37,113][04377] Worker 2 uses CPU cores [0] | |
| [2024-09-07 05:36:37,163][04379] Worker 3 uses CPU cores [1] | |
| [2024-09-07 05:36:37,169][04380] Worker 5 uses CPU cores [1] | |
| [2024-09-07 05:36:37,188][04362] Conv encoder output size: 512 | |
| [2024-09-07 05:36:37,190][04362] Policy head output size: 512 | |
| [2024-09-07 05:36:37,213][04383] Worker 1 uses CPU cores [1] | |
| [2024-09-07 05:36:37,256][04362] Created Actor Critic model with architecture: | |
| [2024-09-07 05:36:37,257][04362] ActorCriticSharedWeights( | |
| (obs_normalizer): ObservationNormalizer( | |
| (running_mean_std): RunningMeanStdDictInPlace( | |
| (running_mean_std): ModuleDict( | |
| (obs): RunningMeanStdInPlace() | |
| ) | |
| ) | |
| ) | |
| (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) | |
| (encoder): VizdoomEncoder( | |
| (basic_encoder): ConvEncoder( | |
| (enc): RecursiveScriptModule( | |
| original_name=ConvEncoderImpl | |
| (conv_head): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Conv2d) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| (2): RecursiveScriptModule(original_name=Conv2d) | |
| (3): RecursiveScriptModule(original_name=ELU) | |
| (4): RecursiveScriptModule(original_name=Conv2d) | |
| (5): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| (mlp_layers): RecursiveScriptModule( | |
| original_name=Sequential | |
| (0): RecursiveScriptModule(original_name=Linear) | |
| (1): RecursiveScriptModule(original_name=ELU) | |
| ) | |
| ) | |
| ) | |
| ) | |
| (core): ModelCoreRNN( | |
| (core): GRU(512, 512) | |
| ) | |
| (decoder): MlpDecoder( | |
| (mlp): Identity() | |
| ) | |
| (critic_linear): Linear(in_features=512, out_features=1, bias=True) | |
| (action_parameterization): ActionParameterizationDefault( | |
| (distribution_linear): Linear(in_features=512, out_features=5, bias=True) | |
| ) | |
| ) | |
| [2024-09-07 05:36:37,670][04362] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2024-09-07 05:36:38,361][04362] No checkpoints found | |
| [2024-09-07 05:36:38,361][04362] Did not load from checkpoint, starting from scratch! | |
| [2024-09-07 05:36:38,362][04362] Initialized policy 0 weights for model version 0 | |
| [2024-09-07 05:36:38,367][04362] LearnerWorker_p0 finished initialization! | |
| [2024-09-07 05:36:38,368][04362] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2024-09-07 05:36:38,563][04376] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-09-07 05:36:38,564][04376] RunningMeanStd input shape: (1,) | |
| [2024-09-07 05:36:38,576][04376] ConvEncoder: input_channels=3 | |
| [2024-09-07 05:36:38,680][04376] Conv encoder output size: 512 | |
| [2024-09-07 05:36:38,681][04376] Policy head output size: 512 | |
| [2024-09-07 05:36:38,732][01890] Inference worker 0-0 is ready! | |
| [2024-09-07 05:36:38,734][01890] All inference workers are ready! Signal rollout workers to start! | |
| [2024-09-07 05:36:38,929][04381] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,932][04382] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,926][04378] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,930][04375] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,935][04379] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,928][04377] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,936][04380] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:38,937][04383] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:36:39,621][01890] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-09-07 05:36:40,034][01890] Heartbeat connected on Batcher_0 | |
| [2024-09-07 05:36:40,040][01890] Heartbeat connected on LearnerWorker_p0 | |
| [2024-09-07 05:36:40,082][01890] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2024-09-07 05:36:40,356][04375] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:40,357][04381] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:40,358][04377] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:40,358][04382] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:40,356][04383] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:40,361][04380] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:41,094][04383] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:41,103][04382] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:41,548][04375] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:41,551][04381] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:41,560][04377] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:42,949][04379] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:42,956][04380] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:43,518][04382] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:43,754][04378] Decorrelating experience for 0 frames... | |
| [2024-09-07 05:36:44,368][04375] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:44,370][04377] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:44,627][01890] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-09-07 05:36:44,737][04379] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:45,182][04382] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:45,589][01890] Heartbeat connected on RolloutWorker_w7 | |
| [2024-09-07 05:36:45,839][04378] Decorrelating experience for 32 frames... | |
| [2024-09-07 05:36:45,841][04381] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:46,473][04377] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:46,873][04383] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:46,950][01890] Heartbeat connected on RolloutWorker_w2 | |
| [2024-09-07 05:36:47,326][04379] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:48,239][04381] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:48,772][01890] Heartbeat connected on RolloutWorker_w6 | |
| [2024-09-07 05:36:48,960][04383] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:49,007][04378] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:49,214][01890] Heartbeat connected on RolloutWorker_w1 | |
| [2024-09-07 05:36:49,367][04379] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:49,510][04375] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:49,622][01890] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 1.2. Samples: 12. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-09-07 05:36:49,626][01890] Avg episode reward: [(0, '1.850')] | |
| [2024-09-07 05:36:49,679][01890] Heartbeat connected on RolloutWorker_w0 | |
| [2024-09-07 05:36:49,710][01890] Heartbeat connected on RolloutWorker_w3 | |
| [2024-09-07 05:36:51,337][04380] Decorrelating experience for 64 frames... | |
| [2024-09-07 05:36:52,512][04362] Signal inference workers to stop experience collection... | |
| [2024-09-07 05:36:52,520][04376] InferenceWorker_p0-w0: stopping experience collection | |
| [2024-09-07 05:36:52,922][04380] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:53,040][01890] Heartbeat connected on RolloutWorker_w5 | |
| [2024-09-07 05:36:53,058][04378] Decorrelating experience for 96 frames... | |
| [2024-09-07 05:36:53,141][01890] Heartbeat connected on RolloutWorker_w4 | |
| [2024-09-07 05:36:54,622][01890] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 166.1. Samples: 2492. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2024-09-07 05:36:54,623][01890] Avg episode reward: [(0, '2.762')] | |
| [2024-09-07 05:36:55,538][04362] Signal inference workers to resume experience collection... | |
| [2024-09-07 05:36:55,541][04376] InferenceWorker_p0-w0: resuming experience collection | |
| [2024-09-07 05:36:59,628][01890] Fps is (10 sec: 2046.8, 60 sec: 1023.7, 300 sec: 1023.7). Total num frames: 20480. Throughput: 0: 172.4. Samples: 3450. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:36:59,639][01890] Avg episode reward: [(0, '3.473')] | |
| [2024-09-07 05:37:04,625][01890] Fps is (10 sec: 3275.7, 60 sec: 1310.5, 300 sec: 1310.5). Total num frames: 32768. Throughput: 0: 326.2. Samples: 8156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:04,628][01890] Avg episode reward: [(0, '3.705')] | |
| [2024-09-07 05:37:06,607][04376] Updated weights for policy 0, policy_version 10 (0.0169) | |
| [2024-09-07 05:37:09,622][01890] Fps is (10 sec: 3279.0, 60 sec: 1774.9, 300 sec: 1774.9). Total num frames: 53248. Throughput: 0: 440.4. Samples: 13212. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:09,628][01890] Avg episode reward: [(0, '4.268')] | |
| [2024-09-07 05:37:14,622][01890] Fps is (10 sec: 4097.2, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 73728. Throughput: 0: 471.5. Samples: 16502. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:37:14,625][01890] Avg episode reward: [(0, '4.337')] | |
| [2024-09-07 05:37:16,590][04376] Updated weights for policy 0, policy_version 20 (0.0021) | |
| [2024-09-07 05:37:19,622][01890] Fps is (10 sec: 3276.8, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 86016. Throughput: 0: 546.5. Samples: 21862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:37:19,624][01890] Avg episode reward: [(0, '4.333')] | |
| [2024-09-07 05:37:24,622][01890] Fps is (10 sec: 2867.2, 60 sec: 2275.5, 300 sec: 2275.5). Total num frames: 102400. Throughput: 0: 579.6. Samples: 26084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:37:24,627][01890] Avg episode reward: [(0, '4.399')] | |
| [2024-09-07 05:37:24,635][04362] Saving new best policy, reward=4.399! | |
| [2024-09-07 05:37:28,583][04376] Updated weights for policy 0, policy_version 30 (0.0019) | |
| [2024-09-07 05:37:29,622][01890] Fps is (10 sec: 4096.0, 60 sec: 2539.5, 300 sec: 2539.5). Total num frames: 126976. Throughput: 0: 651.1. Samples: 29294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:37:29,624][01890] Avg episode reward: [(0, '4.460')] | |
| [2024-09-07 05:37:29,627][04362] Saving new best policy, reward=4.460! | |
| [2024-09-07 05:37:34,627][01890] Fps is (10 sec: 3684.6, 60 sec: 2531.8, 300 sec: 2531.8). Total num frames: 139264. Throughput: 0: 784.5. Samples: 35318. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:37:34,630][01890] Avg episode reward: [(0, '4.455')] | |
| [2024-09-07 05:37:39,622][01890] Fps is (10 sec: 2457.6, 60 sec: 2525.9, 300 sec: 2525.9). Total num frames: 151552. Throughput: 0: 797.8. Samples: 38394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:39,625][01890] Avg episode reward: [(0, '4.473')] | |
| [2024-09-07 05:37:39,630][04362] Saving new best policy, reward=4.473! | |
| [2024-09-07 05:37:43,457][04376] Updated weights for policy 0, policy_version 40 (0.0031) | |
| [2024-09-07 05:37:44,622][01890] Fps is (10 sec: 2868.7, 60 sec: 2799.2, 300 sec: 2583.6). Total num frames: 167936. Throughput: 0: 811.2. Samples: 39948. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:44,625][01890] Avg episode reward: [(0, '4.378')] | |
| [2024-09-07 05:37:49,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 2691.7). Total num frames: 188416. Throughput: 0: 837.7. Samples: 45852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:49,628][01890] Avg episode reward: [(0, '4.388')] | |
| [2024-09-07 05:37:53,171][04376] Updated weights for policy 0, policy_version 50 (0.0031) | |
| [2024-09-07 05:37:54,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 2730.7). Total num frames: 204800. Throughput: 0: 862.5. Samples: 52024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:37:54,625][01890] Avg episode reward: [(0, '4.424')] | |
| [2024-09-07 05:37:59,625][01890] Fps is (10 sec: 2866.3, 60 sec: 3277.0, 300 sec: 2713.5). Total num frames: 217088. Throughput: 0: 830.2. Samples: 53864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:37:59,630][01890] Avg episode reward: [(0, '4.328')] | |
| [2024-09-07 05:38:04,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 2843.1). Total num frames: 241664. Throughput: 0: 827.6. Samples: 59106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:38:04,628][01890] Avg episode reward: [(0, '4.207')] | |
| [2024-09-07 05:38:05,331][04376] Updated weights for policy 0, policy_version 60 (0.0018) | |
| [2024-09-07 05:38:09,622][01890] Fps is (10 sec: 4507.0, 60 sec: 3481.6, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 882.4. Samples: 65790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:38:09,624][01890] Avg episode reward: [(0, '4.259')] | |
| [2024-09-07 05:38:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 2888.8). Total num frames: 274432. Throughput: 0: 861.6. Samples: 68066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:38:14,623][01890] Avg episode reward: [(0, '4.571')] | |
| [2024-09-07 05:38:14,640][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth... | |
| [2024-09-07 05:38:14,833][04362] Saving new best policy, reward=4.571! | |
| [2024-09-07 05:38:17,972][04376] Updated weights for policy 0, policy_version 70 (0.0014) | |
| [2024-09-07 05:38:19,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 2908.2). Total num frames: 290816. Throughput: 0: 815.7. Samples: 72020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:38:19,624][01890] Avg episode reward: [(0, '4.775')] | |
| [2024-09-07 05:38:19,629][04362] Saving new best policy, reward=4.775! | |
| [2024-09-07 05:38:24,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 2964.7). Total num frames: 311296. Throughput: 0: 884.6. Samples: 78202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:38:24,624][01890] Avg episode reward: [(0, '4.487')] | |
| [2024-09-07 05:38:28,293][04376] Updated weights for policy 0, policy_version 80 (0.0023) | |
| [2024-09-07 05:38:29,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 2978.9). Total num frames: 327680. Throughput: 0: 920.4. Samples: 81368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:38:29,626][01890] Avg episode reward: [(0, '4.407')] | |
| [2024-09-07 05:38:34,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.6, 300 sec: 2991.9). Total num frames: 344064. Throughput: 0: 872.8. Samples: 85126. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:38:34,624][01890] Avg episode reward: [(0, '4.394')] | |
| [2024-09-07 05:38:39,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3037.9). Total num frames: 364544. Throughput: 0: 867.6. Samples: 91068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:38:39,624][01890] Avg episode reward: [(0, '4.668')] | |
| [2024-09-07 05:38:40,177][04376] Updated weights for policy 0, policy_version 90 (0.0042) | |
| [2024-09-07 05:38:44,622][01890] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3080.2). Total num frames: 385024. Throughput: 0: 898.3. Samples: 94286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:38:44,627][01890] Avg episode reward: [(0, '4.856')] | |
| [2024-09-07 05:38:44,637][04362] Saving new best policy, reward=4.856! | |
| [2024-09-07 05:38:49,623][01890] Fps is (10 sec: 3276.3, 60 sec: 3481.5, 300 sec: 3056.2). Total num frames: 397312. Throughput: 0: 883.7. Samples: 98874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:38:49,629][01890] Avg episode reward: [(0, '4.928')] | |
| [2024-09-07 05:38:49,636][04362] Saving new best policy, reward=4.928! | |
| [2024-09-07 05:38:53,095][04376] Updated weights for policy 0, policy_version 100 (0.0027) | |
| [2024-09-07 05:38:54,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3064.4). Total num frames: 413696. Throughput: 0: 844.8. Samples: 103808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:38:54,624][01890] Avg episode reward: [(0, '4.801')] | |
| [2024-09-07 05:38:59,622][01890] Fps is (10 sec: 3686.9, 60 sec: 3618.3, 300 sec: 3101.3). Total num frames: 434176. Throughput: 0: 866.6. Samples: 107062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:38:59,628][01890] Avg episode reward: [(0, '4.648')] | |
| [2024-09-07 05:39:03,847][04376] Updated weights for policy 0, policy_version 110 (0.0024) | |
| [2024-09-07 05:39:04,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3107.3). Total num frames: 450560. Throughput: 0: 900.2. Samples: 112528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:39:04,627][01890] Avg episode reward: [(0, '4.483')] | |
| [2024-09-07 05:39:09,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3113.0). Total num frames: 466944. Throughput: 0: 852.0. Samples: 116544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:39:09,623][01890] Avg episode reward: [(0, '4.399')] | |
| [2024-09-07 05:39:14,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3144.7). Total num frames: 487424. Throughput: 0: 849.7. Samples: 119604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:39:14,624][01890] Avg episode reward: [(0, '4.463')] | |
| [2024-09-07 05:39:15,474][04376] Updated weights for policy 0, policy_version 120 (0.0021) | |
| [2024-09-07 05:39:19,622][01890] Fps is (10 sec: 3686.1, 60 sec: 3549.8, 300 sec: 3148.8). Total num frames: 503808. Throughput: 0: 905.2. Samples: 125862. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-09-07 05:39:19,625][01890] Avg episode reward: [(0, '4.878')] | |
| [2024-09-07 05:39:24,622][01890] Fps is (10 sec: 2867.0, 60 sec: 3413.3, 300 sec: 3127.8). Total num frames: 516096. Throughput: 0: 857.9. Samples: 129676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:39:24,626][01890] Avg episode reward: [(0, '4.973')] | |
| [2024-09-07 05:39:24,636][04362] Saving new best policy, reward=4.973! | |
| [2024-09-07 05:39:28,048][04376] Updated weights for policy 0, policy_version 130 (0.0047) | |
| [2024-09-07 05:39:29,622][01890] Fps is (10 sec: 3277.0, 60 sec: 3481.6, 300 sec: 3156.3). Total num frames: 536576. Throughput: 0: 848.8. Samples: 132480. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:39:29,630][01890] Avg episode reward: [(0, '5.119')] | |
| [2024-09-07 05:39:29,632][04362] Saving new best policy, reward=5.119! | |
| [2024-09-07 05:39:34,622][01890] Fps is (10 sec: 4096.3, 60 sec: 3549.9, 300 sec: 3183.2). Total num frames: 557056. Throughput: 0: 889.9. Samples: 138918. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-09-07 05:39:34,636][01890] Avg episode reward: [(0, '5.254')] | |
| [2024-09-07 05:39:34,645][04362] Saving new best policy, reward=5.254! | |
| [2024-09-07 05:39:39,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3163.0). Total num frames: 569344. Throughput: 0: 862.4. Samples: 142618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:39:39,624][01890] Avg episode reward: [(0, '5.231')] | |
| [2024-09-07 05:39:41,334][04376] Updated weights for policy 0, policy_version 140 (0.0039) | |
| [2024-09-07 05:39:44,623][01890] Fps is (10 sec: 2047.8, 60 sec: 3208.5, 300 sec: 3121.8). Total num frames: 577536. Throughput: 0: 824.4. Samples: 144162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:39:44,625][01890] Avg episode reward: [(0, '5.305')] | |
| [2024-09-07 05:39:44,638][04362] Saving new best policy, reward=5.305! | |
| [2024-09-07 05:39:49,621][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.2, 300 sec: 3147.5). Total num frames: 598016. Throughput: 0: 807.2. Samples: 148852. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:39:49,628][01890] Avg episode reward: [(0, '4.984')] | |
| [2024-09-07 05:39:52,703][04376] Updated weights for policy 0, policy_version 150 (0.0037) | |
| [2024-09-07 05:39:54,622][01890] Fps is (10 sec: 4096.5, 60 sec: 3413.3, 300 sec: 3171.8). Total num frames: 618496. Throughput: 0: 861.9. Samples: 155328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:39:54,628][01890] Avg episode reward: [(0, '5.003')] | |
| [2024-09-07 05:39:59,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3174.4). Total num frames: 634880. Throughput: 0: 848.1. Samples: 157768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:39:59,632][01890] Avg episode reward: [(0, '5.086')] | |
| [2024-09-07 05:40:04,622][01890] Fps is (10 sec: 3276.7, 60 sec: 3345.0, 300 sec: 3176.9). Total num frames: 651264. Throughput: 0: 807.8. Samples: 162212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:40:04,627][01890] Avg episode reward: [(0, '5.174')] | |
| [2024-09-07 05:40:04,924][04376] Updated weights for policy 0, policy_version 160 (0.0027) | |
| [2024-09-07 05:40:09,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3218.3). Total num frames: 675840. Throughput: 0: 870.0. Samples: 168824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:40:09,625][01890] Avg episode reward: [(0, '5.492')] | |
| [2024-09-07 05:40:09,627][04362] Saving new best policy, reward=5.492! | |
| [2024-09-07 05:40:14,622][01890] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3219.6). Total num frames: 692224. Throughput: 0: 879.5. Samples: 172056. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:40:14,624][01890] Avg episode reward: [(0, '5.750')] | |
| [2024-09-07 05:40:14,642][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000169_692224.pth... | |
| [2024-09-07 05:40:14,866][04362] Saving new best policy, reward=5.750! | |
| [2024-09-07 05:40:15,958][04376] Updated weights for policy 0, policy_version 170 (0.0016) | |
| [2024-09-07 05:40:19,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3202.3). Total num frames: 704512. Throughput: 0: 817.9. Samples: 175722. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:40:19,628][01890] Avg episode reward: [(0, '5.957')] | |
| [2024-09-07 05:40:19,632][04362] Saving new best policy, reward=5.957! | |
| [2024-09-07 05:40:24,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3222.2). Total num frames: 724992. Throughput: 0: 870.5. Samples: 181790. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:40:24,624][01890] Avg episode reward: [(0, '5.779')] | |
| [2024-09-07 05:40:26,367][04376] Updated weights for policy 0, policy_version 180 (0.0047) | |
| [2024-09-07 05:40:29,621][01890] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3241.2). Total num frames: 745472. Throughput: 0: 911.0. Samples: 185158. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:40:29,624][01890] Avg episode reward: [(0, '5.958')] | |
| [2024-09-07 05:40:29,626][04362] Saving new best policy, reward=5.958! | |
| [2024-09-07 05:40:34,622][01890] Fps is (10 sec: 3276.6, 60 sec: 3345.0, 300 sec: 3224.5). Total num frames: 757760. Throughput: 0: 909.2. Samples: 189768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:40:34,624][01890] Avg episode reward: [(0, '6.446')] | |
| [2024-09-07 05:40:34,656][04362] Saving new best policy, reward=6.446! | |
| [2024-09-07 05:40:38,772][04376] Updated weights for policy 0, policy_version 190 (0.0048) | |
| [2024-09-07 05:40:39,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3242.7). Total num frames: 778240. Throughput: 0: 883.1. Samples: 195066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:40:39,628][01890] Avg episode reward: [(0, '6.717')] | |
| [2024-09-07 05:40:39,631][04362] Saving new best policy, reward=6.717! | |
| [2024-09-07 05:40:44,622][01890] Fps is (10 sec: 4505.9, 60 sec: 3754.7, 300 sec: 3276.8). Total num frames: 802816. Throughput: 0: 899.6. Samples: 198250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:40:44,625][01890] Avg episode reward: [(0, '7.069')] | |
| [2024-09-07 05:40:44,634][04362] Saving new best policy, reward=7.069! | |
| [2024-09-07 05:40:49,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3260.4). Total num frames: 815104. Throughput: 0: 923.0. Samples: 203746. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:40:49,628][01890] Avg episode reward: [(0, '7.100')] | |
| [2024-09-07 05:40:49,634][04362] Saving new best policy, reward=7.100! | |
| [2024-09-07 05:40:50,481][04376] Updated weights for policy 0, policy_version 200 (0.0039) | |
| [2024-09-07 05:40:54,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3260.7). Total num frames: 831488. Throughput: 0: 870.3. Samples: 207986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:40:54,625][01890] Avg episode reward: [(0, '7.279')] | |
| [2024-09-07 05:40:54,634][04362] Saving new best policy, reward=7.279! | |
| [2024-09-07 05:40:59,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 851968. Throughput: 0: 870.7. Samples: 211236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:40:59,627][01890] Avg episode reward: [(0, '7.404')] | |
| [2024-09-07 05:40:59,629][04362] Saving new best policy, reward=7.404! | |
| [2024-09-07 05:41:00,692][04376] Updated weights for policy 0, policy_version 210 (0.0018) | |
| [2024-09-07 05:41:04,622][01890] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3292.3). Total num frames: 872448. Throughput: 0: 931.9. Samples: 217658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:41:04,629][01890] Avg episode reward: [(0, '7.280')] | |
| [2024-09-07 05:41:09,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 884736. Throughput: 0: 882.1. Samples: 221486. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:41:09,626][01890] Avg episode reward: [(0, '6.951')] | |
| [2024-09-07 05:41:12,996][04376] Updated weights for policy 0, policy_version 220 (0.0029) | |
| [2024-09-07 05:41:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3291.7). Total num frames: 905216. Throughput: 0: 873.9. Samples: 224484. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:41:14,628][01890] Avg episode reward: [(0, '6.884')] | |
| [2024-09-07 05:41:19,623][01890] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3306.0). Total num frames: 925696. Throughput: 0: 917.1. Samples: 231038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:41:19,629][01890] Avg episode reward: [(0, '7.346')] | |
| [2024-09-07 05:41:24,401][04376] Updated weights for policy 0, policy_version 230 (0.0021) | |
| [2024-09-07 05:41:24,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3305.5). Total num frames: 942080. Throughput: 0: 897.4. Samples: 235450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:41:24,627][01890] Avg episode reward: [(0, '7.849')] | |
| [2024-09-07 05:41:24,638][04362] Saving new best policy, reward=7.849! | |
| [2024-09-07 05:41:29,622][01890] Fps is (10 sec: 3277.2, 60 sec: 3549.9, 300 sec: 3305.0). Total num frames: 958464. Throughput: 0: 873.2. Samples: 237544. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-09-07 05:41:29,629][01890] Avg episode reward: [(0, '8.405')] | |
| [2024-09-07 05:41:29,632][04362] Saving new best policy, reward=8.405! | |
| [2024-09-07 05:41:34,622][01890] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3318.5). Total num frames: 978944. Throughput: 0: 895.3. Samples: 244036. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:41:34,624][01890] Avg episode reward: [(0, '8.219')] | |
| [2024-09-07 05:41:34,773][04376] Updated weights for policy 0, policy_version 240 (0.0037) | |
| [2024-09-07 05:41:39,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3360.2). Total num frames: 991232. Throughput: 0: 909.3. Samples: 248904. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:41:39,626][01890] Avg episode reward: [(0, '7.683')] | |
| [2024-09-07 05:41:44,622][01890] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 1003520. Throughput: 0: 871.1. Samples: 250436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:41:44,624][01890] Avg episode reward: [(0, '7.704')] | |
| [2024-09-07 05:41:49,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 810.9. Samples: 254148. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:41:49,624][01890] Avg episode reward: [(0, '7.348')] | |
| [2024-09-07 05:41:50,092][04376] Updated weights for policy 0, policy_version 250 (0.0051) | |
| [2024-09-07 05:41:54,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3457.4). Total num frames: 1040384. Throughput: 0: 867.5. Samples: 260522. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:41:54,626][01890] Avg episode reward: [(0, '7.574')] | |
| [2024-09-07 05:41:59,621][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 1056768. Throughput: 0: 871.7. Samples: 263710. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:41:59,627][01890] Avg episode reward: [(0, '7.357')] | |
| [2024-09-07 05:42:01,587][04376] Updated weights for policy 0, policy_version 260 (0.0025) | |
| [2024-09-07 05:42:04,622][01890] Fps is (10 sec: 3276.7, 60 sec: 3345.1, 300 sec: 3457.3). Total num frames: 1073152. Throughput: 0: 812.4. Samples: 267596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:42:04,624][01890] Avg episode reward: [(0, '7.297')] | |
| [2024-09-07 05:42:09,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1093632. Throughput: 0: 851.2. Samples: 273752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:42:09,628][01890] Avg episode reward: [(0, '7.781')] | |
| [2024-09-07 05:42:11,881][04376] Updated weights for policy 0, policy_version 270 (0.0023) | |
| [2024-09-07 05:42:14,622][01890] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 1114112. Throughput: 0: 875.8. Samples: 276956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:14,625][01890] Avg episode reward: [(0, '8.837')] | |
| [2024-09-07 05:42:14,636][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000272_1114112.pth... | |
| [2024-09-07 05:42:14,793][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000067_274432.pth | |
| [2024-09-07 05:42:14,818][04362] Saving new best policy, reward=8.837! | |
| [2024-09-07 05:42:19,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3471.2). Total num frames: 1126400. Throughput: 0: 832.9. Samples: 281518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:19,624][01890] Avg episode reward: [(0, '9.212')] | |
| [2024-09-07 05:42:19,633][04362] Saving new best policy, reward=9.212! | |
| [2024-09-07 05:42:24,381][04376] Updated weights for policy 0, policy_version 280 (0.0017) | |
| [2024-09-07 05:42:24,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 1146880. Throughput: 0: 837.8. Samples: 286606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:24,628][01890] Avg episode reward: [(0, '9.455')] | |
| [2024-09-07 05:42:24,637][04362] Saving new best policy, reward=9.455! | |
| [2024-09-07 05:42:29,622][01890] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 1167360. Throughput: 0: 878.1. Samples: 289950. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:29,628][01890] Avg episode reward: [(0, '8.891')] | |
| [2024-09-07 05:42:34,625][01890] Fps is (10 sec: 3685.2, 60 sec: 3413.2, 300 sec: 3498.9). Total num frames: 1183744. Throughput: 0: 921.0. Samples: 295594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:42:34,627][01890] Avg episode reward: [(0, '9.099')] | |
| [2024-09-07 05:42:35,647][04376] Updated weights for policy 0, policy_version 290 (0.0031) | |
| [2024-09-07 05:42:39,622][01890] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1200128. Throughput: 0: 876.8. Samples: 299976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:42:39,628][01890] Avg episode reward: [(0, '8.685')] | |
| [2024-09-07 05:42:44,622][01890] Fps is (10 sec: 3687.6, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1220608. Throughput: 0: 880.1. Samples: 303314. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:42:44,628][01890] Avg episode reward: [(0, '9.341')] | |
| [2024-09-07 05:42:45,883][04376] Updated weights for policy 0, policy_version 300 (0.0032) | |
| [2024-09-07 05:42:49,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3512.8). Total num frames: 1241088. Throughput: 0: 937.3. Samples: 309776. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:42:49,624][01890] Avg episode reward: [(0, '9.428')] | |
| [2024-09-07 05:42:54,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 1253376. Throughput: 0: 884.1. Samples: 313536. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:54,626][01890] Avg episode reward: [(0, '10.147')] | |
| [2024-09-07 05:42:54,635][04362] Saving new best policy, reward=10.147! | |
| [2024-09-07 05:42:58,316][04376] Updated weights for policy 0, policy_version 310 (0.0021) | |
| [2024-09-07 05:42:59,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1273856. Throughput: 0: 874.1. Samples: 316292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:42:59,625][01890] Avg episode reward: [(0, '10.428')] | |
| [2024-09-07 05:42:59,630][04362] Saving new best policy, reward=10.428! | |
| [2024-09-07 05:43:04,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3499.0). Total num frames: 1294336. Throughput: 0: 918.4. Samples: 322844. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:43:04,629][01890] Avg episode reward: [(0, '10.575')] | |
| [2024-09-07 05:43:04,645][04362] Saving new best policy, reward=10.575! | |
| [2024-09-07 05:43:09,623][01890] Fps is (10 sec: 3276.4, 60 sec: 3549.8, 300 sec: 3498.9). Total num frames: 1306624. Throughput: 0: 906.0. Samples: 327378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:43:09,625][01890] Avg episode reward: [(0, '10.060')] | |
| [2024-09-07 05:43:09,954][04376] Updated weights for policy 0, policy_version 320 (0.0036) | |
| [2024-09-07 05:43:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1327104. Throughput: 0: 876.3. Samples: 329384. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:43:14,629][01890] Avg episode reward: [(0, '10.555')] | |
| [2024-09-07 05:43:19,622][01890] Fps is (10 sec: 4096.5, 60 sec: 3686.4, 300 sec: 3512.8). Total num frames: 1347584. Throughput: 0: 896.4. Samples: 335928. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:43:19,624][01890] Avg episode reward: [(0, '11.843')] | |
| [2024-09-07 05:43:19,630][04362] Saving new best policy, reward=11.843! | |
| [2024-09-07 05:43:20,190][04376] Updated weights for policy 0, policy_version 330 (0.0019) | |
| [2024-09-07 05:43:24,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1363968. Throughput: 0: 920.1. Samples: 341382. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:43:24,625][01890] Avg episode reward: [(0, '12.107')] | |
| [2024-09-07 05:43:24,638][04362] Saving new best policy, reward=12.107! | |
| [2024-09-07 05:43:29,622][01890] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1376256. Throughput: 0: 886.9. Samples: 343224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:43:29,627][01890] Avg episode reward: [(0, '13.134')] | |
| [2024-09-07 05:43:29,630][04362] Saving new best policy, reward=13.134! | |
| [2024-09-07 05:43:32,631][04376] Updated weights for policy 0, policy_version 340 (0.0023) | |
| [2024-09-07 05:43:34,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3618.3, 300 sec: 3512.8). Total num frames: 1400832. Throughput: 0: 868.5. Samples: 348860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:43:34,630][01890] Avg episode reward: [(0, '14.184')] | |
| [2024-09-07 05:43:34,639][04362] Saving new best policy, reward=14.184! | |
| [2024-09-07 05:43:39,622][01890] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1417216. Throughput: 0: 922.4. Samples: 355046. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:43:39,624][01890] Avg episode reward: [(0, '14.754')] | |
| [2024-09-07 05:43:39,628][04362] Saving new best policy, reward=14.754! | |
| [2024-09-07 05:43:44,622][01890] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1429504. Throughput: 0: 895.8. Samples: 356604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:43:44,624][01890] Avg episode reward: [(0, '14.040')] | |
| [2024-09-07 05:43:46,493][04376] Updated weights for policy 0, policy_version 350 (0.0037) | |
| [2024-09-07 05:43:49,622][01890] Fps is (10 sec: 2048.0, 60 sec: 3276.8, 300 sec: 3471.2). Total num frames: 1437696. Throughput: 0: 819.4. Samples: 359718. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:43:49,624][01890] Avg episode reward: [(0, '13.829')] | |
| [2024-09-07 05:43:54,622][01890] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 1462272. Throughput: 0: 846.9. Samples: 365486. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:43:54,624][01890] Avg episode reward: [(0, '12.480')] | |
| [2024-09-07 05:43:57,167][04376] Updated weights for policy 0, policy_version 360 (0.0035) | |
| [2024-09-07 05:43:59,622][01890] Fps is (10 sec: 4505.6, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1482752. Throughput: 0: 874.4. Samples: 368730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:43:59,630][01890] Avg episode reward: [(0, '11.750')] | |
| [2024-09-07 05:44:04,628][01890] Fps is (10 sec: 3274.9, 60 sec: 3344.7, 300 sec: 3485.0). Total num frames: 1495040. Throughput: 0: 836.1. Samples: 373556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:44:04,630][01890] Avg episode reward: [(0, '11.973')] | |
| [2024-09-07 05:44:09,606][04376] Updated weights for policy 0, policy_version 370 (0.0023) | |
| [2024-09-07 05:44:09,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3485.1). Total num frames: 1515520. Throughput: 0: 825.2. Samples: 378518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:44:09,625][01890] Avg episode reward: [(0, '12.862')] | |
| [2024-09-07 05:44:14,622][01890] Fps is (10 sec: 4098.5, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 1536000. Throughput: 0: 855.5. Samples: 381720. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:44:14,626][01890] Avg episode reward: [(0, '13.192')] | |
| [2024-09-07 05:44:14,636][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000375_1536000.pth... | |
| [2024-09-07 05:44:14,775][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000169_692224.pth | |
| [2024-09-07 05:44:19,622][01890] Fps is (10 sec: 3686.2, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 1552384. Throughput: 0: 860.5. Samples: 387584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:44:19,624][01890] Avg episode reward: [(0, '13.260')] | |
| [2024-09-07 05:44:21,096][04376] Updated weights for policy 0, policy_version 380 (0.0035) | |
| [2024-09-07 05:44:24,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 1564672. Throughput: 0: 814.0. Samples: 391678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:44:24,629][01890] Avg episode reward: [(0, '13.966')] | |
| [2024-09-07 05:44:29,621][01890] Fps is (10 sec: 3686.6, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 1589248. Throughput: 0: 853.3. Samples: 395004. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:44:29,630][01890] Avg episode reward: [(0, '12.682')] | |
| [2024-09-07 05:44:31,540][04376] Updated weights for policy 0, policy_version 390 (0.0029) | |
| [2024-09-07 05:44:34,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3413.4, 300 sec: 3512.8). Total num frames: 1605632. Throughput: 0: 921.6. Samples: 401188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:44:34,624][01890] Avg episode reward: [(0, '12.543')] | |
| [2024-09-07 05:44:39,621][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3526.7). Total num frames: 1617920. Throughput: 0: 883.9. Samples: 405262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:44:39,624][01890] Avg episode reward: [(0, '11.922')] | |
| [2024-09-07 05:44:44,140][04376] Updated weights for policy 0, policy_version 400 (0.0038) | |
| [2024-09-07 05:44:44,622][01890] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 1638400. Throughput: 0: 868.7. Samples: 407824. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:44:44,625][01890] Avg episode reward: [(0, '11.373')] | |
| [2024-09-07 05:44:49,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3526.7). Total num frames: 1658880. Throughput: 0: 903.0. Samples: 414184. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:44:49,625][01890] Avg episode reward: [(0, '12.816')] | |
| [2024-09-07 05:44:54,622][01890] Fps is (10 sec: 3686.6, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 1675264. Throughput: 0: 902.4. Samples: 419126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:44:54,625][01890] Avg episode reward: [(0, '13.106')] | |
| [2024-09-07 05:44:55,783][04376] Updated weights for policy 0, policy_version 410 (0.0033) | |
| [2024-09-07 05:44:59,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 1691648. Throughput: 0: 874.0. Samples: 421050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:44:59,628][01890] Avg episode reward: [(0, '13.845')] | |
| [2024-09-07 05:45:04,624][01890] Fps is (10 sec: 3685.6, 60 sec: 3618.4, 300 sec: 3512.8). Total num frames: 1712128. Throughput: 0: 880.3. Samples: 427200. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:45:04,629][01890] Avg episode reward: [(0, '16.133')] | |
| [2024-09-07 05:45:04,638][04362] Saving new best policy, reward=16.133! | |
| [2024-09-07 05:45:06,004][04376] Updated weights for policy 0, policy_version 420 (0.0025) | |
| [2024-09-07 05:45:09,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1728512. Throughput: 0: 917.6. Samples: 432972. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:45:09,624][01890] Avg episode reward: [(0, '16.215')] | |
| [2024-09-07 05:45:09,707][04362] Saving new best policy, reward=16.215! | |
| [2024-09-07 05:45:14,622][01890] Fps is (10 sec: 2867.8, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 1740800. Throughput: 0: 884.0. Samples: 434782. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:45:14,632][01890] Avg episode reward: [(0, '16.375')] | |
| [2024-09-07 05:45:14,651][04362] Saving new best policy, reward=16.375! | |
| [2024-09-07 05:45:18,713][04376] Updated weights for policy 0, policy_version 430 (0.0047) | |
| [2024-09-07 05:45:19,621][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 1761280. Throughput: 0: 858.1. Samples: 439802. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:45:19,624][01890] Avg episode reward: [(0, '16.410')] | |
| [2024-09-07 05:45:19,689][04362] Saving new best policy, reward=16.410! | |
| [2024-09-07 05:45:24,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1781760. Throughput: 0: 902.9. Samples: 445894. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:45:24,629][01890] Avg episode reward: [(0, '16.551')] | |
| [2024-09-07 05:45:24,639][04362] Saving new best policy, reward=16.551! | |
| [2024-09-07 05:45:29,622][01890] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 1794048. Throughput: 0: 894.5. Samples: 448074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:45:29,624][01890] Avg episode reward: [(0, '15.780')] | |
| [2024-09-07 05:45:31,615][04376] Updated weights for policy 0, policy_version 440 (0.0047) | |
| [2024-09-07 05:45:34,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 1814528. Throughput: 0: 850.3. Samples: 452446. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:45:34,634][01890] Avg episode reward: [(0, '16.334')] | |
| [2024-09-07 05:45:39,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1835008. Throughput: 0: 887.6. Samples: 459068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:45:39,628][01890] Avg episode reward: [(0, '15.390')] | |
| [2024-09-07 05:45:41,057][04376] Updated weights for policy 0, policy_version 450 (0.0015) | |
| [2024-09-07 05:45:44,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1851392. Throughput: 0: 910.3. Samples: 462014. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:45:44,627][01890] Avg episode reward: [(0, '15.899')] | |
| [2024-09-07 05:45:49,622][01890] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 1859584. Throughput: 0: 845.3. Samples: 465238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:45:49,627][01890] Avg episode reward: [(0, '15.713')] | |
| [2024-09-07 05:45:54,622][01890] Fps is (10 sec: 2457.5, 60 sec: 3345.0, 300 sec: 3471.2). Total num frames: 1875968. Throughput: 0: 798.2. Samples: 468892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:45:54,628][01890] Avg episode reward: [(0, '15.833')] | |
| [2024-09-07 05:45:56,089][04376] Updated weights for policy 0, policy_version 460 (0.0037) | |
| [2024-09-07 05:45:59,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 1896448. Throughput: 0: 831.5. Samples: 472198. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:45:59,624][01890] Avg episode reward: [(0, '15.926')] | |
| [2024-09-07 05:46:04,621][01890] Fps is (10 sec: 3686.5, 60 sec: 3345.2, 300 sec: 3485.1). Total num frames: 1912832. Throughput: 0: 845.9. Samples: 477866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:46:04,627][01890] Avg episode reward: [(0, '16.564')] | |
| [2024-09-07 05:46:04,637][04362] Saving new best policy, reward=16.564! | |
| [2024-09-07 05:46:08,564][04376] Updated weights for policy 0, policy_version 470 (0.0035) | |
| [2024-09-07 05:46:09,621][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3471.2). Total num frames: 1929216. Throughput: 0: 801.0. Samples: 481940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:46:09,626][01890] Avg episode reward: [(0, '16.978')] | |
| [2024-09-07 05:46:09,630][04362] Saving new best policy, reward=16.978! | |
| [2024-09-07 05:46:14,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1949696. Throughput: 0: 824.5. Samples: 485178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:46:14,627][01890] Avg episode reward: [(0, '18.169')] | |
| [2024-09-07 05:46:14,641][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000476_1949696.pth... | |
| [2024-09-07 05:46:14,776][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000272_1114112.pth | |
| [2024-09-07 05:46:14,788][04362] Saving new best policy, reward=18.169! | |
| [2024-09-07 05:46:18,687][04376] Updated weights for policy 0, policy_version 480 (0.0021) | |
| [2024-09-07 05:46:19,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 1966080. Throughput: 0: 864.5. Samples: 491348. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:46:19,627][01890] Avg episode reward: [(0, '18.688')] | |
| [2024-09-07 05:46:19,629][04362] Saving new best policy, reward=18.688! | |
| [2024-09-07 05:46:24,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3457.3). Total num frames: 1978368. Throughput: 0: 802.5. Samples: 495182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:46:24,624][01890] Avg episode reward: [(0, '18.970')] | |
| [2024-09-07 05:46:24,636][04362] Saving new best policy, reward=18.970! | |
| [2024-09-07 05:46:29,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 1998848. Throughput: 0: 789.8. Samples: 497554. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:46:29,628][01890] Avg episode reward: [(0, '18.053')] | |
| [2024-09-07 05:46:31,379][04376] Updated weights for policy 0, policy_version 490 (0.0034) | |
| [2024-09-07 05:46:34,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 2019328. Throughput: 0: 858.6. Samples: 503874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:46:34,628][01890] Avg episode reward: [(0, '17.090')] | |
| [2024-09-07 05:46:39,626][01890] Fps is (10 sec: 3275.4, 60 sec: 3276.6, 300 sec: 3485.0). Total num frames: 2031616. Throughput: 0: 885.3. Samples: 508732. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:46:39,632][01890] Avg episode reward: [(0, '16.688')] | |
| [2024-09-07 05:46:43,649][04376] Updated weights for policy 0, policy_version 500 (0.0018) | |
| [2024-09-07 05:46:44,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3485.1). Total num frames: 2048000. Throughput: 0: 854.4. Samples: 510646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:46:44,624][01890] Avg episode reward: [(0, '17.035')] | |
| [2024-09-07 05:46:49,622][01890] Fps is (10 sec: 4097.8, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2072576. Throughput: 0: 866.8. Samples: 516874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:46:49,629][01890] Avg episode reward: [(0, '17.314')] | |
| [2024-09-07 05:46:53,747][04376] Updated weights for policy 0, policy_version 510 (0.0018) | |
| [2024-09-07 05:46:54,622][01890] Fps is (10 sec: 4095.9, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2088960. Throughput: 0: 905.1. Samples: 522668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:46:54,627][01890] Avg episode reward: [(0, '18.070')] | |
| [2024-09-07 05:46:59,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 2101248. Throughput: 0: 874.6. Samples: 524534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:46:59,624][01890] Avg episode reward: [(0, '18.443')] | |
| [2024-09-07 05:47:04,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 2121728. Throughput: 0: 855.0. Samples: 529822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:04,629][01890] Avg episode reward: [(0, '18.299')] | |
| [2024-09-07 05:47:05,724][04376] Updated weights for policy 0, policy_version 520 (0.0020) | |
| [2024-09-07 05:47:09,622][01890] Fps is (10 sec: 4505.5, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2146304. Throughput: 0: 913.5. Samples: 536290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:09,627][01890] Avg episode reward: [(0, '17.602')] | |
| [2024-09-07 05:47:14,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 2158592. Throughput: 0: 908.8. Samples: 538452. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:47:14,623][01890] Avg episode reward: [(0, '17.342')] | |
| [2024-09-07 05:47:18,205][04376] Updated weights for policy 0, policy_version 530 (0.0021) | |
| [2024-09-07 05:47:19,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 2174976. Throughput: 0: 866.0. Samples: 542846. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:19,624][01890] Avg episode reward: [(0, '17.616')] | |
| [2024-09-07 05:47:24,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3485.1). Total num frames: 2195456. Throughput: 0: 901.3. Samples: 549286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:24,630][01890] Avg episode reward: [(0, '17.622')] | |
| [2024-09-07 05:47:28,413][04376] Updated weights for policy 0, policy_version 540 (0.0040) | |
| [2024-09-07 05:47:29,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 2211840. Throughput: 0: 927.4. Samples: 552378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:47:29,627][01890] Avg episode reward: [(0, '17.418')] | |
| [2024-09-07 05:47:34,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 2228224. Throughput: 0: 874.5. Samples: 556226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:34,627][01890] Avg episode reward: [(0, '16.883')] | |
| [2024-09-07 05:47:39,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3618.4, 300 sec: 3485.1). Total num frames: 2248704. Throughput: 0: 886.7. Samples: 562568. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:39,626][01890] Avg episode reward: [(0, '16.304')] | |
| [2024-09-07 05:47:39,955][04376] Updated weights for policy 0, policy_version 550 (0.0038) | |
| [2024-09-07 05:47:44,623][01890] Fps is (10 sec: 4095.6, 60 sec: 3686.3, 300 sec: 3485.1). Total num frames: 2269184. Throughput: 0: 916.1. Samples: 565760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:44,628][01890] Avg episode reward: [(0, '17.321')] | |
| [2024-09-07 05:47:49,625][01890] Fps is (10 sec: 3275.8, 60 sec: 3481.4, 300 sec: 3485.0). Total num frames: 2281472. Throughput: 0: 894.8. Samples: 570092. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:47:49,628][01890] Avg episode reward: [(0, '17.437')] | |
| [2024-09-07 05:47:54,622][01890] Fps is (10 sec: 2048.2, 60 sec: 3345.1, 300 sec: 3443.4). Total num frames: 2289664. Throughput: 0: 819.9. Samples: 573186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:54,626][01890] Avg episode reward: [(0, '18.262')] | |
| [2024-09-07 05:47:54,845][04376] Updated weights for policy 0, policy_version 560 (0.0035) | |
| [2024-09-07 05:47:59,622][01890] Fps is (10 sec: 2868.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 2310144. Throughput: 0: 827.3. Samples: 575682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:47:59,624][01890] Avg episode reward: [(0, '16.758')] | |
| [2024-09-07 05:48:04,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 2330624. Throughput: 0: 874.6. Samples: 582204. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-09-07 05:48:04,625][01890] Avg episode reward: [(0, '17.472')] | |
| [2024-09-07 05:48:05,593][04376] Updated weights for policy 0, policy_version 570 (0.0031) | |
| [2024-09-07 05:48:09,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3443.4). Total num frames: 2342912. Throughput: 0: 818.8. Samples: 586130. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:48:09,625][01890] Avg episode reward: [(0, '16.832')] | |
| [2024-09-07 05:48:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 2363392. Throughput: 0: 813.4. Samples: 588982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:48:14,630][01890] Avg episode reward: [(0, '17.480')] | |
| [2024-09-07 05:48:14,640][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000577_2363392.pth... | |
| [2024-09-07 05:48:14,787][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000375_1536000.pth | |
| [2024-09-07 05:48:16,760][04376] Updated weights for policy 0, policy_version 580 (0.0024) | |
| [2024-09-07 05:48:19,621][01890] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 2383872. Throughput: 0: 870.0. Samples: 595376. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-09-07 05:48:19,623][01890] Avg episode reward: [(0, '17.128')] | |
| [2024-09-07 05:48:24,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3457.3). Total num frames: 2396160. Throughput: 0: 833.2. Samples: 600062. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:48:24,629][01890] Avg episode reward: [(0, '18.314')] | |
| [2024-09-07 05:48:29,301][04376] Updated weights for policy 0, policy_version 590 (0.0029) | |
| [2024-09-07 05:48:29,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 2416640. Throughput: 0: 807.0. Samples: 602076. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:48:29,624][01890] Avg episode reward: [(0, '19.407')] | |
| [2024-09-07 05:48:29,628][04362] Saving new best policy, reward=19.407! | |
| [2024-09-07 05:48:34,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 2437120. Throughput: 0: 853.7. Samples: 608506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:48:34,629][01890] Avg episode reward: [(0, '18.722')] | |
| [2024-09-07 05:48:39,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 2453504. Throughput: 0: 912.5. Samples: 614250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:48:39,625][01890] Avg episode reward: [(0, '18.241')] | |
| [2024-09-07 05:48:39,893][04376] Updated weights for policy 0, policy_version 600 (0.0044) | |
| [2024-09-07 05:48:44,621][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3499.0). Total num frames: 2469888. Throughput: 0: 900.8. Samples: 616218. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:48:44,624][01890] Avg episode reward: [(0, '18.651')] | |
| [2024-09-07 05:48:49,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3485.1). Total num frames: 2490368. Throughput: 0: 880.1. Samples: 621810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:48:49,624][01890] Avg episode reward: [(0, '17.141')] | |
| [2024-09-07 05:48:50,903][04376] Updated weights for policy 0, policy_version 610 (0.0020) | |
| [2024-09-07 05:48:54,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3485.1). Total num frames: 2510848. Throughput: 0: 936.0. Samples: 628248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:48:54,623][01890] Avg episode reward: [(0, '18.186')] | |
| [2024-09-07 05:48:59,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 2523136. Throughput: 0: 915.3. Samples: 630170. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2024-09-07 05:48:59,624][01890] Avg episode reward: [(0, '19.037')] | |
| [2024-09-07 05:49:03,321][04376] Updated weights for policy 0, policy_version 620 (0.0040) | |
| [2024-09-07 05:49:04,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 2543616. Throughput: 0: 878.9. Samples: 634928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:49:04,624][01890] Avg episode reward: [(0, '20.489')] | |
| [2024-09-07 05:49:04,634][04362] Saving new best policy, reward=20.489! | |
| [2024-09-07 05:49:09,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3485.1). Total num frames: 2564096. Throughput: 0: 917.0. Samples: 641326. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:49:09,624][01890] Avg episode reward: [(0, '21.777')] | |
| [2024-09-07 05:49:09,627][04362] Saving new best policy, reward=21.777! | |
| [2024-09-07 05:49:13,944][04376] Updated weights for policy 0, policy_version 630 (0.0019) | |
| [2024-09-07 05:49:14,624][01890] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3485.1). Total num frames: 2580480. Throughput: 0: 936.2. Samples: 644208. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:49:14,631][01890] Avg episode reward: [(0, '22.185')] | |
| [2024-09-07 05:49:14,648][04362] Saving new best policy, reward=22.185! | |
| [2024-09-07 05:49:19,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 2596864. Throughput: 0: 879.9. Samples: 648100. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:49:19,627][01890] Avg episode reward: [(0, '21.241')] | |
| [2024-09-07 05:49:24,622][01890] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3485.1). Total num frames: 2617344. Throughput: 0: 894.7. Samples: 654510. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:49:24,624][01890] Avg episode reward: [(0, '21.475')] | |
| [2024-09-07 05:49:25,155][04376] Updated weights for policy 0, policy_version 640 (0.0032) | |
| [2024-09-07 05:49:29,621][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3499.0). Total num frames: 2637824. Throughput: 0: 919.5. Samples: 657596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:49:29,627][01890] Avg episode reward: [(0, '19.202')] | |
| [2024-09-07 05:49:34,623][01890] Fps is (10 sec: 3276.3, 60 sec: 3549.8, 300 sec: 3498.9). Total num frames: 2650112. Throughput: 0: 893.6. Samples: 662024. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:49:34,626][01890] Avg episode reward: [(0, '17.781')] | |
| [2024-09-07 05:49:37,611][04376] Updated weights for policy 0, policy_version 650 (0.0035) | |
| [2024-09-07 05:49:39,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 2670592. Throughput: 0: 873.4. Samples: 667552. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:49:39,631][01890] Avg episode reward: [(0, '16.565')] | |
| [2024-09-07 05:49:44,622][01890] Fps is (10 sec: 4096.5, 60 sec: 3686.4, 300 sec: 3499.0). Total num frames: 2691072. Throughput: 0: 901.2. Samples: 670724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:49:44,624][01890] Avg episode reward: [(0, '17.578')] | |
| [2024-09-07 05:49:48,475][04376] Updated weights for policy 0, policy_version 660 (0.0023) | |
| [2024-09-07 05:49:49,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 2703360. Throughput: 0: 911.2. Samples: 675930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:49:49,629][01890] Avg episode reward: [(0, '17.716')] | |
| [2024-09-07 05:49:54,622][01890] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 2715648. Throughput: 0: 840.3. Samples: 679140. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:49:54,623][01890] Avg episode reward: [(0, '17.514')] | |
| [2024-09-07 05:49:59,622][01890] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 2727936. Throughput: 0: 816.2. Samples: 680936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:49:59,624][01890] Avg episode reward: [(0, '18.089')] | |
| [2024-09-07 05:50:02,525][04376] Updated weights for policy 0, policy_version 670 (0.0053) | |
| [2024-09-07 05:50:04,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 2748416. Throughput: 0: 860.7. Samples: 686832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:04,625][01890] Avg episode reward: [(0, '19.172')] | |
| [2024-09-07 05:50:09,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3457.3). Total num frames: 2760704. Throughput: 0: 805.7. Samples: 690766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:09,625][01890] Avg episode reward: [(0, '19.952')] | |
| [2024-09-07 05:50:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.2, 300 sec: 3457.3). Total num frames: 2781184. Throughput: 0: 793.2. Samples: 693288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:14,627][01890] Avg episode reward: [(0, '19.837')] | |
| [2024-09-07 05:50:14,637][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth... | |
| [2024-09-07 05:50:14,760][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000476_1949696.pth | |
| [2024-09-07 05:50:15,400][04376] Updated weights for policy 0, policy_version 680 (0.0020) | |
| [2024-09-07 05:50:19,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3457.3). Total num frames: 2801664. Throughput: 0: 831.6. Samples: 699444. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:50:19,629][01890] Avg episode reward: [(0, '20.780')] | |
| [2024-09-07 05:50:24,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3457.3). Total num frames: 2813952. Throughput: 0: 815.1. Samples: 704230. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:24,624][01890] Avg episode reward: [(0, '21.113')] | |
| [2024-09-07 05:50:28,145][04376] Updated weights for policy 0, policy_version 690 (0.0029) | |
| [2024-09-07 05:50:29,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3443.4). Total num frames: 2830336. Throughput: 0: 786.8. Samples: 706128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:50:29,628][01890] Avg episode reward: [(0, '21.577')] | |
| [2024-09-07 05:50:34,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3443.4). Total num frames: 2850816. Throughput: 0: 801.7. Samples: 712008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:34,624][01890] Avg episode reward: [(0, '22.913')] | |
| [2024-09-07 05:50:34,635][04362] Saving new best policy, reward=22.913! | |
| [2024-09-07 05:50:38,234][04376] Updated weights for policy 0, policy_version 700 (0.0020) | |
| [2024-09-07 05:50:39,624][01890] Fps is (10 sec: 3685.4, 60 sec: 3276.7, 300 sec: 3443.4). Total num frames: 2867200. Throughput: 0: 858.7. Samples: 717784. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:50:39,627][01890] Avg episode reward: [(0, '22.878')] | |
| [2024-09-07 05:50:44,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3471.2). Total num frames: 2883584. Throughput: 0: 859.3. Samples: 719606. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:44,628][01890] Avg episode reward: [(0, '23.068')] | |
| [2024-09-07 05:50:44,637][04362] Saving new best policy, reward=23.068! | |
| [2024-09-07 05:50:49,621][01890] Fps is (10 sec: 3687.4, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 2904064. Throughput: 0: 842.4. Samples: 724738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:49,625][01890] Avg episode reward: [(0, '23.693')] | |
| [2024-09-07 05:50:49,634][04362] Saving new best policy, reward=23.693! | |
| [2024-09-07 05:50:50,513][04376] Updated weights for policy 0, policy_version 710 (0.0014) | |
| [2024-09-07 05:50:54,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 2924544. Throughput: 0: 894.7. Samples: 731026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:50:54,627][01890] Avg episode reward: [(0, '24.409')] | |
| [2024-09-07 05:50:54,639][04362] Saving new best policy, reward=24.409! | |
| [2024-09-07 05:50:59,623][01890] Fps is (10 sec: 3276.4, 60 sec: 3481.5, 300 sec: 3471.2). Total num frames: 2936832. Throughput: 0: 886.2. Samples: 733168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:50:59,625][01890] Avg episode reward: [(0, '23.731')] | |
| [2024-09-07 05:51:03,132][04376] Updated weights for policy 0, policy_version 720 (0.0017) | |
| [2024-09-07 05:51:04,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 2953216. Throughput: 0: 844.4. Samples: 737444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:51:04,624][01890] Avg episode reward: [(0, '24.200')] | |
| [2024-09-07 05:51:09,622][01890] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 2973696. Throughput: 0: 879.3. Samples: 743798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:51:09,629][01890] Avg episode reward: [(0, '24.586')] | |
| [2024-09-07 05:51:09,632][04362] Saving new best policy, reward=24.586! | |
| [2024-09-07 05:51:13,742][04376] Updated weights for policy 0, policy_version 730 (0.0045) | |
| [2024-09-07 05:51:14,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 2990080. Throughput: 0: 903.7. Samples: 746794. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-09-07 05:51:14,628][01890] Avg episode reward: [(0, '24.462')] | |
| [2024-09-07 05:51:19,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 3006464. Throughput: 0: 858.6. Samples: 750644. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:51:19,628][01890] Avg episode reward: [(0, '24.146')] | |
| [2024-09-07 05:51:24,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 3026944. Throughput: 0: 861.9. Samples: 756566. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:51:24,630][01890] Avg episode reward: [(0, '24.571')] | |
| [2024-09-07 05:51:25,511][04376] Updated weights for policy 0, policy_version 740 (0.0014) | |
| [2024-09-07 05:51:29,621][01890] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3043328. Throughput: 0: 885.7. Samples: 759464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:51:29,629][01890] Avg episode reward: [(0, '25.675')] | |
| [2024-09-07 05:51:29,634][04362] Saving new best policy, reward=25.675! | |
| [2024-09-07 05:51:34,622][01890] Fps is (10 sec: 2867.3, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 3055616. Throughput: 0: 870.1. Samples: 763892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:51:34,624][01890] Avg episode reward: [(0, '25.417')] | |
| [2024-09-07 05:51:38,136][04376] Updated weights for policy 0, policy_version 750 (0.0025) | |
| [2024-09-07 05:51:39,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3481.8, 300 sec: 3485.1). Total num frames: 3076096. Throughput: 0: 849.9. Samples: 769270. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:51:39,624][01890] Avg episode reward: [(0, '25.079')] | |
| [2024-09-07 05:51:44,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 3096576. Throughput: 0: 871.4. Samples: 772382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:51:44,631][01890] Avg episode reward: [(0, '25.585')] | |
| [2024-09-07 05:51:49,616][04376] Updated weights for policy 0, policy_version 760 (0.0053) | |
| [2024-09-07 05:51:49,621][01890] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 3112960. Throughput: 0: 892.2. Samples: 777594. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:51:49,627][01890] Avg episode reward: [(0, '25.448')] | |
| [2024-09-07 05:51:54,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3471.2). Total num frames: 3125248. Throughput: 0: 842.9. Samples: 781730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:51:54,631][01890] Avg episode reward: [(0, '24.653')] | |
| [2024-09-07 05:51:59,622][01890] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3443.4). Total num frames: 3137536. Throughput: 0: 816.0. Samples: 783514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:51:59,627][01890] Avg episode reward: [(0, '24.403')] | |
| [2024-09-07 05:52:04,107][04376] Updated weights for policy 0, policy_version 770 (0.0048) | |
| [2024-09-07 05:52:04,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 3153920. Throughput: 0: 834.2. Samples: 788182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:52:04,626][01890] Avg episode reward: [(0, '25.560')] | |
| [2024-09-07 05:52:09,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3415.6). Total num frames: 3166208. Throughput: 0: 787.5. Samples: 792004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:52:09,623][01890] Avg episode reward: [(0, '25.869')] | |
| [2024-09-07 05:52:09,634][04362] Saving new best policy, reward=25.869! | |
| [2024-09-07 05:52:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3429.5). Total num frames: 3186688. Throughput: 0: 789.2. Samples: 794976. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:52:14,626][01890] Avg episode reward: [(0, '25.897')] | |
| [2024-09-07 05:52:14,634][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000778_3186688.pth... | |
| [2024-09-07 05:52:14,766][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000577_2363392.pth | |
| [2024-09-07 05:52:14,780][04362] Saving new best policy, reward=25.897! | |
| [2024-09-07 05:52:16,069][04376] Updated weights for policy 0, policy_version 780 (0.0031) | |
| [2024-09-07 05:52:19,625][01890] Fps is (10 sec: 4094.7, 60 sec: 3344.9, 300 sec: 3429.5). Total num frames: 3207168. Throughput: 0: 826.0. Samples: 801066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:52:19,627][01890] Avg episode reward: [(0, '24.865')] | |
| [2024-09-07 05:52:24,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3208.6, 300 sec: 3415.6). Total num frames: 3219456. Throughput: 0: 802.3. Samples: 805372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:52:24,624][01890] Avg episode reward: [(0, '24.333')] | |
| [2024-09-07 05:52:28,722][04376] Updated weights for policy 0, policy_version 790 (0.0034) | |
| [2024-09-07 05:52:29,622][01890] Fps is (10 sec: 2868.1, 60 sec: 3208.5, 300 sec: 3415.6). Total num frames: 3235840. Throughput: 0: 779.7. Samples: 807470. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2024-09-07 05:52:29,624][01890] Avg episode reward: [(0, '23.879')] | |
| [2024-09-07 05:52:34,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 3256320. Throughput: 0: 802.0. Samples: 813686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:52:34,625][01890] Avg episode reward: [(0, '21.796')] | |
| [2024-09-07 05:52:39,624][01890] Fps is (10 sec: 3685.5, 60 sec: 3276.7, 300 sec: 3401.7). Total num frames: 3272704. Throughput: 0: 828.9. Samples: 819034. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:52:39,627][01890] Avg episode reward: [(0, '22.784')] | |
| [2024-09-07 05:52:39,947][04376] Updated weights for policy 0, policy_version 800 (0.0033) | |
| [2024-09-07 05:52:44,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3415.7). Total num frames: 3289088. Throughput: 0: 829.7. Samples: 820852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:52:44,624][01890] Avg episode reward: [(0, '22.326')] | |
| [2024-09-07 05:52:49,622][01890] Fps is (10 sec: 3687.3, 60 sec: 3276.8, 300 sec: 3457.3). Total num frames: 3309568. Throughput: 0: 852.3. Samples: 826536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:52:49,628][01890] Avg episode reward: [(0, '22.412')] | |
| [2024-09-07 05:52:51,196][04376] Updated weights for policy 0, policy_version 810 (0.0029) | |
| [2024-09-07 05:52:54,623][01890] Fps is (10 sec: 4095.2, 60 sec: 3413.2, 300 sec: 3457.3). Total num frames: 3330048. Throughput: 0: 901.0. Samples: 832552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:52:54,628][01890] Avg episode reward: [(0, '22.849')] | |
| [2024-09-07 05:52:59,628][01890] Fps is (10 sec: 3274.8, 60 sec: 3413.0, 300 sec: 3429.5). Total num frames: 3342336. Throughput: 0: 876.4. Samples: 834418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:52:59,630][01890] Avg episode reward: [(0, '23.451')] | |
| [2024-09-07 05:53:03,642][04376] Updated weights for policy 0, policy_version 820 (0.0021) | |
| [2024-09-07 05:53:04,622][01890] Fps is (10 sec: 3277.4, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 3362816. Throughput: 0: 846.5. Samples: 839158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:53:04,629][01890] Avg episode reward: [(0, '23.950')] | |
| [2024-09-07 05:53:09,622][01890] Fps is (10 sec: 4098.4, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 3383296. Throughput: 0: 896.0. Samples: 845692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:53:09,629][01890] Avg episode reward: [(0, '24.182')] | |
| [2024-09-07 05:53:14,627][01890] Fps is (10 sec: 3275.1, 60 sec: 3481.3, 300 sec: 3429.5). Total num frames: 3395584. Throughput: 0: 907.6. Samples: 848318. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:53:14,633][01890] Avg episode reward: [(0, '23.527')] | |
| [2024-09-07 05:53:15,658][04376] Updated weights for policy 0, policy_version 830 (0.0037) | |
| [2024-09-07 05:53:19,622][01890] Fps is (10 sec: 2867.3, 60 sec: 3413.5, 300 sec: 3443.4). Total num frames: 3411968. Throughput: 0: 853.1. Samples: 852076. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:53:19,624][01890] Avg episode reward: [(0, '23.190')] | |
| [2024-09-07 05:53:24,622][01890] Fps is (10 sec: 3688.3, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 3432448. Throughput: 0: 871.0. Samples: 858226. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:53:24,627][01890] Avg episode reward: [(0, '23.432')] | |
| [2024-09-07 05:53:26,248][04376] Updated weights for policy 0, policy_version 840 (0.0030) | |
| [2024-09-07 05:53:29,625][01890] Fps is (10 sec: 3685.3, 60 sec: 3549.7, 300 sec: 3429.5). Total num frames: 3448832. Throughput: 0: 898.6. Samples: 861292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:53:29,627][01890] Avg episode reward: [(0, '22.865')] | |
| [2024-09-07 05:53:34,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3461120. Throughput: 0: 858.5. Samples: 865168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:53:34,624][01890] Avg episode reward: [(0, '22.110')] | |
| [2024-09-07 05:53:39,004][04376] Updated weights for policy 0, policy_version 850 (0.0018) | |
| [2024-09-07 05:53:39,622][01890] Fps is (10 sec: 3277.8, 60 sec: 3481.7, 300 sec: 3429.5). Total num frames: 3481600. Throughput: 0: 847.9. Samples: 870706. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:53:39,624][01890] Avg episode reward: [(0, '22.662')] | |
| [2024-09-07 05:53:44,622][01890] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3443.4). Total num frames: 3506176. Throughput: 0: 877.3. Samples: 873890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:53:44,624][01890] Avg episode reward: [(0, '23.945')] | |
| [2024-09-07 05:53:49,626][01890] Fps is (10 sec: 3684.9, 60 sec: 3481.4, 300 sec: 3415.6). Total num frames: 3518464. Throughput: 0: 886.1. Samples: 879034. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2024-09-07 05:53:49,630][01890] Avg episode reward: [(0, '24.316')] | |
| [2024-09-07 05:53:50,829][04376] Updated weights for policy 0, policy_version 860 (0.0030) | |
| [2024-09-07 05:53:54,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3429.5). Total num frames: 3534848. Throughput: 0: 847.9. Samples: 883848. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:53:54,625][01890] Avg episode reward: [(0, '23.793')] | |
| [2024-09-07 05:53:59,625][01890] Fps is (10 sec: 3277.1, 60 sec: 3481.8, 300 sec: 3415.6). Total num frames: 3551232. Throughput: 0: 859.3. Samples: 886986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:53:59,631][01890] Avg episode reward: [(0, '25.714')] | |
| [2024-09-07 05:54:04,137][04376] Updated weights for policy 0, policy_version 870 (0.0030) | |
| [2024-09-07 05:54:04,622][01890] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 3563520. Throughput: 0: 859.6. Samples: 890760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:54:04,624][01890] Avg episode reward: [(0, '25.788')] | |
| [2024-09-07 05:54:09,622][01890] Fps is (10 sec: 2458.4, 60 sec: 3208.5, 300 sec: 3374.0). Total num frames: 3575808. Throughput: 0: 802.6. Samples: 894342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:54:09,624][01890] Avg episode reward: [(0, '25.445')] | |
| [2024-09-07 05:54:14,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3345.4, 300 sec: 3387.9). Total num frames: 3596288. Throughput: 0: 797.2. Samples: 897162. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:14,627][01890] Avg episode reward: [(0, '25.311')] | |
| [2024-09-07 05:54:14,637][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000878_3596288.pth... | |
| [2024-09-07 05:54:14,762][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000679_2781184.pth | |
| [2024-09-07 05:54:16,070][04376] Updated weights for policy 0, policy_version 880 (0.0015) | |
| [2024-09-07 05:54:19,624][01890] Fps is (10 sec: 4095.1, 60 sec: 3413.2, 300 sec: 3387.9). Total num frames: 3616768. Throughput: 0: 858.0. Samples: 903780. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:19,626][01890] Avg episode reward: [(0, '23.770')] | |
| [2024-09-07 05:54:24,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 3633152. Throughput: 0: 841.2. Samples: 908558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:24,635][01890] Avg episode reward: [(0, '24.585')] | |
| [2024-09-07 05:54:28,232][04376] Updated weights for policy 0, policy_version 890 (0.0027) | |
| [2024-09-07 05:54:29,622][01890] Fps is (10 sec: 3277.6, 60 sec: 3345.2, 300 sec: 3387.9). Total num frames: 3649536. Throughput: 0: 812.4. Samples: 910446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:29,629][01890] Avg episode reward: [(0, '23.938')] | |
| [2024-09-07 05:54:34,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3670016. Throughput: 0: 839.7. Samples: 916818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:34,624][01890] Avg episode reward: [(0, '22.582')] | |
| [2024-09-07 05:54:38,302][04376] Updated weights for policy 0, policy_version 900 (0.0022) | |
| [2024-09-07 05:54:39,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 3686400. Throughput: 0: 858.7. Samples: 922490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:54:39,630][01890] Avg episode reward: [(0, '22.497')] | |
| [2024-09-07 05:54:44,622][01890] Fps is (10 sec: 3276.9, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 3702784. Throughput: 0: 831.3. Samples: 924390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:54:44,624][01890] Avg episode reward: [(0, '22.170')] | |
| [2024-09-07 05:54:49,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3413.6, 300 sec: 3415.6). Total num frames: 3723264. Throughput: 0: 872.8. Samples: 930036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:54:49,625][01890] Avg episode reward: [(0, '21.048')] | |
| [2024-09-07 05:54:49,996][04376] Updated weights for policy 0, policy_version 910 (0.0049) | |
| [2024-09-07 05:54:54,624][01890] Fps is (10 sec: 4095.1, 60 sec: 3481.5, 300 sec: 3443.4). Total num frames: 3743744. Throughput: 0: 942.4. Samples: 936750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:54:54,626][01890] Avg episode reward: [(0, '21.763')] | |
| [2024-09-07 05:54:59,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3413.5, 300 sec: 3415.6). Total num frames: 3756032. Throughput: 0: 923.6. Samples: 938724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:54:59,628][01890] Avg episode reward: [(0, '21.854')] | |
| [2024-09-07 05:55:02,153][04376] Updated weights for policy 0, policy_version 920 (0.0038) | |
| [2024-09-07 05:55:04,622][01890] Fps is (10 sec: 3277.5, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 3776512. Throughput: 0: 877.0. Samples: 943242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:55:04,627][01890] Avg episode reward: [(0, '23.224')] | |
| [2024-09-07 05:55:09,621][01890] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3457.3). Total num frames: 3801088. Throughput: 0: 918.1. Samples: 949874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:55:09,629][01890] Avg episode reward: [(0, '23.435')] | |
| [2024-09-07 05:55:11,716][04376] Updated weights for policy 0, policy_version 930 (0.0021) | |
| [2024-09-07 05:55:14,623][01890] Fps is (10 sec: 3685.9, 60 sec: 3618.0, 300 sec: 3429.5). Total num frames: 3813376. Throughput: 0: 942.2. Samples: 952848. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:55:14,627][01890] Avg episode reward: [(0, '24.736')] | |
| [2024-09-07 05:55:19,621][01890] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3443.4). Total num frames: 3829760. Throughput: 0: 889.2. Samples: 956834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:55:19,628][01890] Avg episode reward: [(0, '25.039')] | |
| [2024-09-07 05:55:23,704][04376] Updated weights for policy 0, policy_version 940 (0.0019) | |
| [2024-09-07 05:55:24,621][01890] Fps is (10 sec: 4096.6, 60 sec: 3686.4, 300 sec: 3471.2). Total num frames: 3854336. Throughput: 0: 908.1. Samples: 963354. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2024-09-07 05:55:24,628][01890] Avg episode reward: [(0, '24.306')] | |
| [2024-09-07 05:55:29,622][01890] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3457.3). Total num frames: 3870720. Throughput: 0: 939.9. Samples: 966686. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:55:29,628][01890] Avg episode reward: [(0, '24.106')] | |
| [2024-09-07 05:55:34,625][01890] Fps is (10 sec: 2866.3, 60 sec: 3549.7, 300 sec: 3443.4). Total num frames: 3883008. Throughput: 0: 912.2. Samples: 971090. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2024-09-07 05:55:34,627][01890] Avg episode reward: [(0, '23.336')] | |
| [2024-09-07 05:55:35,839][04376] Updated weights for policy 0, policy_version 950 (0.0015) | |
| [2024-09-07 05:55:39,622][01890] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3471.2). Total num frames: 3907584. Throughput: 0: 886.2. Samples: 976626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:55:39,625][01890] Avg episode reward: [(0, '21.915')] | |
| [2024-09-07 05:55:44,622][01890] Fps is (10 sec: 4507.0, 60 sec: 3754.7, 300 sec: 3471.2). Total num frames: 3928064. Throughput: 0: 915.1. Samples: 979902. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:55:44,628][01890] Avg episode reward: [(0, '22.196')] | |
| [2024-09-07 05:55:44,994][04376] Updated weights for policy 0, policy_version 960 (0.0017) | |
| [2024-09-07 05:55:49,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3443.4). Total num frames: 3940352. Throughput: 0: 935.9. Samples: 985356. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2024-09-07 05:55:49,628][01890] Avg episode reward: [(0, '22.403')] | |
| [2024-09-07 05:55:54,622][01890] Fps is (10 sec: 3276.8, 60 sec: 3618.3, 300 sec: 3471.2). Total num frames: 3960832. Throughput: 0: 894.2. Samples: 990112. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2024-09-07 05:55:54,624][01890] Avg episode reward: [(0, '23.391')] | |
| [2024-09-07 05:55:57,231][04376] Updated weights for policy 0, policy_version 970 (0.0033) | |
| [2024-09-07 05:55:59,624][01890] Fps is (10 sec: 4095.1, 60 sec: 3754.5, 300 sec: 3485.0). Total num frames: 3981312. Throughput: 0: 901.7. Samples: 993424. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2024-09-07 05:55:59,626][01890] Avg episode reward: [(0, '25.307')] | |
| [2024-09-07 05:56:04,622][01890] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3471.2). Total num frames: 3997696. Throughput: 0: 938.1. Samples: 999050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2024-09-07 05:56:04,626][01890] Avg episode reward: [(0, '25.365')] | |
| [2024-09-07 05:56:08,431][04362] Stopping Batcher_0... | |
| [2024-09-07 05:56:08,431][04362] Loop batcher_evt_loop terminating... | |
| [2024-09-07 05:56:08,431][01890] Component Batcher_0 stopped! | |
| [2024-09-07 05:56:08,442][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-09-07 05:56:08,572][04376] Weights refcount: 2 0 | |
| [2024-09-07 05:56:08,609][01890] Component InferenceWorker_p0-w0 stopped! | |
| [2024-09-07 05:56:08,616][04376] Stopping InferenceWorker_p0-w0... | |
| [2024-09-07 05:56:08,617][04376] Loop inference_proc0-0_evt_loop terminating... | |
| [2024-09-07 05:56:08,676][04362] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000778_3186688.pth | |
| [2024-09-07 05:56:08,703][04362] Saving new best policy, reward=26.381! | |
| [2024-09-07 05:56:08,859][04362] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-09-07 05:56:09,184][04362] Stopping LearnerWorker_p0... | |
| [2024-09-07 05:56:09,185][04362] Loop learner_proc0_evt_loop terminating... | |
| [2024-09-07 05:56:09,186][01890] Component LearnerWorker_p0 stopped! | |
| [2024-09-07 05:56:09,268][01890] Component RolloutWorker_w3 stopped! | |
| [2024-09-07 05:56:09,270][04379] Stopping RolloutWorker_w3... | |
| [2024-09-07 05:56:09,271][04379] Loop rollout_proc3_evt_loop terminating... | |
| [2024-09-07 05:56:09,311][01890] Component RolloutWorker_w2 stopped! | |
| [2024-09-07 05:56:09,319][01890] Component RolloutWorker_w5 stopped! | |
| [2024-09-07 05:56:09,324][04380] Stopping RolloutWorker_w5... | |
| [2024-09-07 05:56:09,311][04377] Stopping RolloutWorker_w2... | |
| [2024-09-07 05:56:09,328][04377] Loop rollout_proc2_evt_loop terminating... | |
| [2024-09-07 05:56:09,329][04380] Loop rollout_proc5_evt_loop terminating... | |
| [2024-09-07 05:56:09,349][01890] Component RolloutWorker_w7 stopped! | |
| [2024-09-07 05:56:09,349][04382] Stopping RolloutWorker_w7... | |
| [2024-09-07 05:56:09,356][04375] Stopping RolloutWorker_w0... | |
| [2024-09-07 05:56:09,356][01890] Component RolloutWorker_w0 stopped! | |
| [2024-09-07 05:56:09,368][04375] Loop rollout_proc0_evt_loop terminating... | |
| [2024-09-07 05:56:09,371][04382] Loop rollout_proc7_evt_loop terminating... | |
| [2024-09-07 05:56:09,387][04378] Stopping RolloutWorker_w4... | |
| [2024-09-07 05:56:09,388][04378] Loop rollout_proc4_evt_loop terminating... | |
| [2024-09-07 05:56:09,387][01890] Component RolloutWorker_w4 stopped! | |
| [2024-09-07 05:56:09,401][04383] Stopping RolloutWorker_w1... | |
| [2024-09-07 05:56:09,401][01890] Component RolloutWorker_w1 stopped! | |
| [2024-09-07 05:56:09,407][04383] Loop rollout_proc1_evt_loop terminating... | |
| [2024-09-07 05:56:09,447][04381] Stopping RolloutWorker_w6... | |
| [2024-09-07 05:56:09,447][01890] Component RolloutWorker_w6 stopped! | |
| [2024-09-07 05:56:09,450][01890] Waiting for process learner_proc0 to stop... | |
| [2024-09-07 05:56:09,448][04381] Loop rollout_proc6_evt_loop terminating... | |
| [2024-09-07 05:56:11,291][01890] Waiting for process inference_proc0-0 to join... | |
| [2024-09-07 05:56:11,352][01890] Waiting for process rollout_proc0 to join... | |
| [2024-09-07 05:56:13,615][01890] Waiting for process rollout_proc1 to join... | |
| [2024-09-07 05:56:13,619][01890] Waiting for process rollout_proc2 to join... | |
| [2024-09-07 05:56:13,623][01890] Waiting for process rollout_proc3 to join... | |
| [2024-09-07 05:56:13,627][01890] Waiting for process rollout_proc4 to join... | |
| [2024-09-07 05:56:13,630][01890] Waiting for process rollout_proc5 to join... | |
| [2024-09-07 05:56:13,634][01890] Waiting for process rollout_proc6 to join... | |
| [2024-09-07 05:56:13,639][01890] Waiting for process rollout_proc7 to join... | |
| [2024-09-07 05:56:13,642][01890] Batcher 0 profile tree view: | |
| batching: 27.6691, releasing_batches: 0.0385 | |
| [2024-09-07 05:56:13,644][01890] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 440.4912 | |
| update_model: 10.5348 | |
| weight_update: 0.0056 | |
| one_step: 0.0265 | |
| handle_policy_step: 668.5203 | |
| deserialize: 17.1593, stack: 3.4427, obs_to_device_normalize: 132.3903, forward: 361.8378, send_messages: 31.9472 | |
| prepare_outputs: 89.7982 | |
| to_cpu: 50.4306 | |
| [2024-09-07 05:56:13,648][01890] Learner 0 profile tree view: | |
| misc: 0.0058, prepare_batch: 13.5921 | |
| train: 74.2079 | |
| epoch_init: 0.0096, minibatch_init: 0.0068, losses_postprocess: 0.6468, kl_divergence: 0.6943, after_optimizer: 33.8487 | |
| calculate_losses: 26.3669 | |
| losses_init: 0.0037, forward_head: 1.2687, bptt_initial: 17.4777, tail: 1.1175, advantages_returns: 0.2948, losses: 3.8414 | |
| bptt: 1.9891 | |
| bptt_forward_core: 1.9013 | |
| update: 11.9017 | |
| clip: 0.9526 | |
| [2024-09-07 05:56:13,651][01890] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.4061, enqueue_policy_requests: 118.2825, env_step: 898.0010, overhead: 18.3171, complete_rollouts: 7.2837 | |
| save_policy_outputs: 24.6316 | |
| split_output_tensors: 9.8048 | |
| [2024-09-07 05:56:13,653][01890] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3023, enqueue_policy_requests: 118.3455, env_step: 896.0656, overhead: 17.7915, complete_rollouts: 7.7283 | |
| save_policy_outputs: 24.4692 | |
| split_output_tensors: 9.5431 | |
| [2024-09-07 05:56:13,654][01890] Loop Runner_EvtLoop terminating... | |
| [2024-09-07 05:56:13,656][01890] Runner profile tree view: | |
| main_loop: 1193.5814 | |
| [2024-09-07 05:56:13,658][01890] Collected {0: 4005888}, FPS: 3356.2 | |
| [2024-09-07 05:57:08,317][01890] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-09-07 05:57:08,319][01890] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-09-07 05:57:08,321][01890] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-09-07 05:57:08,323][01890] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-09-07 05:57:08,325][01890] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-09-07 05:57:08,326][01890] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-09-07 05:57:08,328][01890] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-09-07 05:57:08,329][01890] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-09-07 05:57:08,330][01890] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2024-09-07 05:57:08,331][01890] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2024-09-07 05:57:08,332][01890] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-09-07 05:57:08,334][01890] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-09-07 05:57:08,335][01890] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-09-07 05:57:08,336][01890] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-09-07 05:57:08,337][01890] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-09-07 05:57:08,373][01890] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2024-09-07 05:57:08,377][01890] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-09-07 05:57:08,379][01890] RunningMeanStd input shape: (1,) | |
| [2024-09-07 05:57:08,396][01890] ConvEncoder: input_channels=3 | |
| [2024-09-07 05:57:08,500][01890] Conv encoder output size: 512 | |
| [2024-09-07 05:57:08,502][01890] Policy head output size: 512 | |
| [2024-09-07 05:57:08,786][01890] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-09-07 05:57:09,600][01890] Num frames 100... | |
| [2024-09-07 05:57:09,721][01890] Num frames 200... | |
| [2024-09-07 05:57:09,853][01890] Num frames 300... | |
| [2024-09-07 05:57:09,995][01890] Num frames 400... | |
| [2024-09-07 05:57:10,131][01890] Num frames 500... | |
| [2024-09-07 05:57:10,252][01890] Num frames 600... | |
| [2024-09-07 05:57:10,380][01890] Num frames 700... | |
| [2024-09-07 05:57:10,501][01890] Num frames 800... | |
| [2024-09-07 05:57:10,624][01890] Num frames 900... | |
| [2024-09-07 05:57:10,745][01890] Num frames 1000... | |
| [2024-09-07 05:57:10,877][01890] Num frames 1100... | |
| [2024-09-07 05:57:10,999][01890] Num frames 1200... | |
| [2024-09-07 05:57:11,123][01890] Num frames 1300... | |
| [2024-09-07 05:57:11,245][01890] Num frames 1400... | |
| [2024-09-07 05:57:11,376][01890] Num frames 1500... | |
| [2024-09-07 05:57:11,500][01890] Num frames 1600... | |
| [2024-09-07 05:57:11,552][01890] Avg episode rewards: #0: 41.000, true rewards: #0: 16.000 | |
| [2024-09-07 05:57:11,554][01890] Avg episode reward: 41.000, avg true_objective: 16.000 | |
| [2024-09-07 05:57:11,677][01890] Num frames 1700... | |
| [2024-09-07 05:57:11,802][01890] Num frames 1800... | |
| [2024-09-07 05:57:11,932][01890] Num frames 1900... | |
| [2024-09-07 05:57:12,051][01890] Num frames 2000... | |
| [2024-09-07 05:57:12,174][01890] Num frames 2100... | |
| [2024-09-07 05:57:12,297][01890] Num frames 2200... | |
| [2024-09-07 05:57:12,401][01890] Avg episode rewards: #0: 26.155, true rewards: #0: 11.155 | |
| [2024-09-07 05:57:12,403][01890] Avg episode reward: 26.155, avg true_objective: 11.155 | |
| [2024-09-07 05:57:12,487][01890] Num frames 2300... | |
| [2024-09-07 05:57:12,608][01890] Num frames 2400... | |
| [2024-09-07 05:57:12,735][01890] Num frames 2500... | |
| [2024-09-07 05:57:12,872][01890] Num frames 2600... | |
| [2024-09-07 05:57:12,998][01890] Num frames 2700... | |
| [2024-09-07 05:57:13,121][01890] Num frames 2800... | |
| [2024-09-07 05:57:13,262][01890] Avg episode rewards: #0: 22.237, true rewards: #0: 9.570 | |
| [2024-09-07 05:57:13,264][01890] Avg episode reward: 22.237, avg true_objective: 9.570 | |
| [2024-09-07 05:57:13,303][01890] Num frames 2900... | |
| [2024-09-07 05:57:13,438][01890] Num frames 3000... | |
| [2024-09-07 05:57:13,560][01890] Num frames 3100... | |
| [2024-09-07 05:57:13,680][01890] Num frames 3200... | |
| [2024-09-07 05:57:13,802][01890] Num frames 3300... | |
| [2024-09-07 05:57:13,933][01890] Num frames 3400... | |
| [2024-09-07 05:57:14,054][01890] Num frames 3500... | |
| [2024-09-07 05:57:14,175][01890] Num frames 3600... | |
| [2024-09-07 05:57:14,298][01890] Num frames 3700... | |
| [2024-09-07 05:57:14,431][01890] Num frames 3800... | |
| [2024-09-07 05:57:14,490][01890] Avg episode rewards: #0: 21.255, true rewards: #0: 9.505 | |
| [2024-09-07 05:57:14,492][01890] Avg episode reward: 21.255, avg true_objective: 9.505 | |
| [2024-09-07 05:57:14,610][01890] Num frames 3900... | |
| [2024-09-07 05:57:14,730][01890] Num frames 4000... | |
| [2024-09-07 05:57:14,819][01890] Avg episode rewards: #0: 17.652, true rewards: #0: 8.052 | |
| [2024-09-07 05:57:14,820][01890] Avg episode reward: 17.652, avg true_objective: 8.052 | |
| [2024-09-07 05:57:14,919][01890] Num frames 4100... | |
| [2024-09-07 05:57:15,055][01890] Num frames 4200... | |
| [2024-09-07 05:57:15,177][01890] Num frames 4300... | |
| [2024-09-07 05:57:15,295][01890] Num frames 4400... | |
| [2024-09-07 05:57:15,424][01890] Num frames 4500... | |
| [2024-09-07 05:57:15,541][01890] Num frames 4600... | |
| [2024-09-07 05:57:15,659][01890] Num frames 4700... | |
| [2024-09-07 05:57:15,781][01890] Num frames 4800... | |
| [2024-09-07 05:57:15,905][01890] Num frames 4900... | |
| [2024-09-07 05:57:16,039][01890] Num frames 5000... | |
| [2024-09-07 05:57:16,160][01890] Num frames 5100... | |
| [2024-09-07 05:57:16,282][01890] Num frames 5200... | |
| [2024-09-07 05:57:16,412][01890] Num frames 5300... | |
| [2024-09-07 05:57:16,530][01890] Num frames 5400... | |
| [2024-09-07 05:57:16,633][01890] Avg episode rewards: #0: 20.563, true rewards: #0: 9.063 | |
| [2024-09-07 05:57:16,634][01890] Avg episode reward: 20.563, avg true_objective: 9.063 | |
| [2024-09-07 05:57:16,711][01890] Num frames 5500... | |
| [2024-09-07 05:57:16,837][01890] Num frames 5600... | |
| [2024-09-07 05:57:16,957][01890] Num frames 5700... | |
| [2024-09-07 05:57:17,088][01890] Num frames 5800... | |
| [2024-09-07 05:57:17,212][01890] Num frames 5900... | |
| [2024-09-07 05:57:17,341][01890] Num frames 6000... | |
| [2024-09-07 05:57:17,460][01890] Num frames 6100... | |
| [2024-09-07 05:57:17,580][01890] Num frames 6200... | |
| [2024-09-07 05:57:17,701][01890] Num frames 6300... | |
| [2024-09-07 05:57:17,824][01890] Num frames 6400... | |
| [2024-09-07 05:57:17,944][01890] Num frames 6500... | |
| [2024-09-07 05:57:18,072][01890] Num frames 6600... | |
| [2024-09-07 05:57:18,196][01890] Num frames 6700... | |
| [2024-09-07 05:57:18,365][01890] Num frames 6800... | |
| [2024-09-07 05:57:18,533][01890] Num frames 6900... | |
| [2024-09-07 05:57:18,695][01890] Num frames 7000... | |
| [2024-09-07 05:57:18,867][01890] Num frames 7100... | |
| [2024-09-07 05:57:19,029][01890] Num frames 7200... | |
| [2024-09-07 05:57:19,197][01890] Num frames 7300... | |
| [2024-09-07 05:57:19,369][01890] Num frames 7400... | |
| [2024-09-07 05:57:19,537][01890] Num frames 7500... | |
| [2024-09-07 05:57:19,662][01890] Avg episode rewards: #0: 25.768, true rewards: #0: 10.769 | |
| [2024-09-07 05:57:19,664][01890] Avg episode reward: 25.768, avg true_objective: 10.769 | |
| [2024-09-07 05:57:19,776][01890] Num frames 7600... | |
| [2024-09-07 05:57:19,944][01890] Num frames 7700... | |
| [2024-09-07 05:57:20,118][01890] Num frames 7800... | |
| [2024-09-07 05:57:20,296][01890] Num frames 7900... | |
| [2024-09-07 05:57:20,480][01890] Num frames 8000... | |
| [2024-09-07 05:57:20,655][01890] Num frames 8100... | |
| [2024-09-07 05:57:20,777][01890] Num frames 8200... | |
| [2024-09-07 05:57:20,896][01890] Num frames 8300... | |
| [2024-09-07 05:57:21,015][01890] Num frames 8400... | |
| [2024-09-07 05:57:21,168][01890] Avg episode rewards: #0: 24.976, true rewards: #0: 10.601 | |
| [2024-09-07 05:57:21,171][01890] Avg episode reward: 24.976, avg true_objective: 10.601 | |
| [2024-09-07 05:57:21,196][01890] Num frames 8500... | |
| [2024-09-07 05:57:21,314][01890] Num frames 8600... | |
| [2024-09-07 05:57:21,438][01890] Num frames 8700... | |
| [2024-09-07 05:57:21,557][01890] Num frames 8800... | |
| [2024-09-07 05:57:21,681][01890] Num frames 8900... | |
| [2024-09-07 05:57:21,808][01890] Num frames 9000... | |
| [2024-09-07 05:57:21,925][01890] Num frames 9100... | |
| [2024-09-07 05:57:22,041][01890] Num frames 9200... | |
| [2024-09-07 05:57:22,171][01890] Num frames 9300... | |
| [2024-09-07 05:57:22,293][01890] Num frames 9400... | |
| [2024-09-07 05:57:22,417][01890] Num frames 9500... | |
| [2024-09-07 05:57:22,539][01890] Num frames 9600... | |
| [2024-09-07 05:57:22,662][01890] Num frames 9700... | |
| [2024-09-07 05:57:22,788][01890] Num frames 9800... | |
| [2024-09-07 05:57:22,907][01890] Num frames 9900... | |
| [2024-09-07 05:57:23,026][01890] Num frames 10000... | |
| [2024-09-07 05:57:23,179][01890] Avg episode rewards: #0: 27.189, true rewards: #0: 11.189 | |
| [2024-09-07 05:57:23,180][01890] Avg episode reward: 27.189, avg true_objective: 11.189 | |
| [2024-09-07 05:57:23,220][01890] Num frames 10100... | |
| [2024-09-07 05:57:23,345][01890] Num frames 10200... | |
| [2024-09-07 05:57:23,469][01890] Num frames 10300... | |
| [2024-09-07 05:57:23,594][01890] Num frames 10400... | |
| [2024-09-07 05:57:23,714][01890] Num frames 10500... | |
| [2024-09-07 05:57:23,834][01890] Num frames 10600... | |
| [2024-09-07 05:57:23,953][01890] Num frames 10700... | |
| [2024-09-07 05:57:24,076][01890] Num frames 10800... | |
| [2024-09-07 05:57:24,204][01890] Num frames 10900... | |
| [2024-09-07 05:57:24,331][01890] Num frames 11000... | |
| [2024-09-07 05:57:24,452][01890] Num frames 11100... | |
| [2024-09-07 05:57:24,580][01890] Avg episode rewards: #0: 26.858, true rewards: #0: 11.158 | |
| [2024-09-07 05:57:24,582][01890] Avg episode reward: 26.858, avg true_objective: 11.158 | |
| [2024-09-07 05:58:28,539][01890] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2024-09-07 06:03:17,638][01890] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2024-09-07 06:03:17,640][01890] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2024-09-07 06:03:17,642][01890] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2024-09-07 06:03:17,644][01890] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2024-09-07 06:03:17,646][01890] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2024-09-07 06:03:17,647][01890] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2024-09-07 06:03:17,649][01890] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2024-09-07 06:03:17,650][01890] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2024-09-07 06:03:17,651][01890] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2024-09-07 06:03:17,652][01890] Adding new argument 'hf_repository'='waready/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2024-09-07 06:03:17,653][01890] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2024-09-07 06:03:17,654][01890] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2024-09-07 06:03:17,655][01890] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2024-09-07 06:03:17,656][01890] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2024-09-07 06:03:17,657][01890] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2024-09-07 06:03:17,698][01890] RunningMeanStd input shape: (3, 72, 128) | |
| [2024-09-07 06:03:17,700][01890] RunningMeanStd input shape: (1,) | |
| [2024-09-07 06:03:17,713][01890] ConvEncoder: input_channels=3 | |
| [2024-09-07 06:03:17,750][01890] Conv encoder output size: 512 | |
| [2024-09-07 06:03:17,751][01890] Policy head output size: 512 | |
| [2024-09-07 06:03:17,770][01890] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2024-09-07 06:03:18,185][01890] Num frames 100... | |
| [2024-09-07 06:03:18,308][01890] Num frames 200... | |
| [2024-09-07 06:03:18,445][01890] Num frames 300... | |
| [2024-09-07 06:03:18,564][01890] Num frames 400... | |
| [2024-09-07 06:03:18,683][01890] Num frames 500... | |
| [2024-09-07 06:03:18,810][01890] Num frames 600... | |
| [2024-09-07 06:03:18,929][01890] Avg episode rewards: #0: 14.540, true rewards: #0: 6.540 | |
| [2024-09-07 06:03:18,932][01890] Avg episode reward: 14.540, avg true_objective: 6.540 | |
| [2024-09-07 06:03:18,987][01890] Num frames 700... | |
| [2024-09-07 06:03:19,112][01890] Num frames 800... | |
| [2024-09-07 06:03:19,236][01890] Num frames 900... | |
| [2024-09-07 06:03:19,369][01890] Num frames 1000... | |
| [2024-09-07 06:03:19,489][01890] Num frames 1100... | |
| [2024-09-07 06:03:19,611][01890] Num frames 1200... | |
| [2024-09-07 06:03:19,733][01890] Num frames 1300... | |
| [2024-09-07 06:03:19,858][01890] Num frames 1400... | |
| [2024-09-07 06:03:20,015][01890] Avg episode rewards: #0: 16.930, true rewards: #0: 7.430 | |
| [2024-09-07 06:03:20,016][01890] Avg episode reward: 16.930, avg true_objective: 7.430 | |
| [2024-09-07 06:03:20,037][01890] Num frames 1500... | |
| [2024-09-07 06:03:20,159][01890] Num frames 1600... | |
| [2024-09-07 06:03:20,278][01890] Num frames 1700... | |
| [2024-09-07 06:03:20,406][01890] Num frames 1800... | |
| [2024-09-07 06:03:20,526][01890] Num frames 1900... | |
| [2024-09-07 06:03:20,645][01890] Num frames 2000... | |
| [2024-09-07 06:03:20,738][01890] Avg episode rewards: #0: 13.767, true rewards: #0: 6.767 | |
| [2024-09-07 06:03:20,740][01890] Avg episode reward: 13.767, avg true_objective: 6.767 | |
| [2024-09-07 06:03:20,836][01890] Num frames 2100... | |
| [2024-09-07 06:03:20,956][01890] Num frames 2200... | |
| [2024-09-07 06:03:21,081][01890] Num frames 2300... | |
| [2024-09-07 06:03:21,202][01890] Num frames 2400... | |
| [2024-09-07 06:03:21,325][01890] Num frames 2500... | |
| [2024-09-07 06:03:21,452][01890] Num frames 2600... | |
| [2024-09-07 06:03:21,530][01890] Avg episode rewards: #0: 13.533, true rewards: #0: 6.532 | |
| [2024-09-07 06:03:21,531][01890] Avg episode reward: 13.533, avg true_objective: 6.532 | |
| [2024-09-07 06:03:21,637][01890] Num frames 2700... | |
| [2024-09-07 06:03:21,758][01890] Num frames 2800... | |
| [2024-09-07 06:03:21,886][01890] Num frames 2900... | |
| [2024-09-07 06:03:22,008][01890] Num frames 3000... | |
| [2024-09-07 06:03:22,102][01890] Avg episode rewards: #0: 12.058, true rewards: #0: 6.058 | |
| [2024-09-07 06:03:22,104][01890] Avg episode reward: 12.058, avg true_objective: 6.058 | |
| [2024-09-07 06:03:22,193][01890] Num frames 3100... | |
| [2024-09-07 06:03:22,313][01890] Num frames 3200... | |
| [2024-09-07 06:03:22,440][01890] Num frames 3300... | |
| [2024-09-07 06:03:22,562][01890] Num frames 3400... | |
| [2024-09-07 06:03:22,682][01890] Num frames 3500... | |
| [2024-09-07 06:03:22,805][01890] Num frames 3600... | |
| [2024-09-07 06:03:22,950][01890] Num frames 3700... | |
| [2024-09-07 06:03:23,123][01890] Num frames 3800... | |
| [2024-09-07 06:03:23,333][01890] Avg episode rewards: #0: 13.817, true rewards: #0: 6.483 | |
| [2024-09-07 06:03:23,336][01890] Avg episode reward: 13.817, avg true_objective: 6.483 | |
| [2024-09-07 06:03:23,358][01890] Num frames 3900... | |
| [2024-09-07 06:03:23,522][01890] Num frames 4000... | |
| [2024-09-07 06:03:23,692][01890] Num frames 4100... | |
| [2024-09-07 06:03:23,855][01890] Num frames 4200... | |
| [2024-09-07 06:03:24,018][01890] Num frames 4300... | |
| [2024-09-07 06:03:24,195][01890] Num frames 4400... | |
| [2024-09-07 06:03:24,379][01890] Num frames 4500... | |
| [2024-09-07 06:03:24,549][01890] Num frames 4600... | |
| [2024-09-07 06:03:24,722][01890] Num frames 4700... | |
| [2024-09-07 06:03:24,904][01890] Num frames 4800... | |
| [2024-09-07 06:03:25,082][01890] Num frames 4900... | |
| [2024-09-07 06:03:25,256][01890] Num frames 5000... | |
| [2024-09-07 06:03:25,450][01890] Num frames 5100... | |
| [2024-09-07 06:03:25,578][01890] Num frames 5200... | |
| [2024-09-07 06:03:25,701][01890] Num frames 5300... | |
| [2024-09-07 06:03:25,822][01890] Num frames 5400... | |
| [2024-09-07 06:03:25,947][01890] Num frames 5500... | |
| [2024-09-07 06:03:26,080][01890] Num frames 5600... | |
| [2024-09-07 06:03:26,204][01890] Num frames 5700... | |
| [2024-09-07 06:03:26,338][01890] Avg episode rewards: #0: 18.804, true rewards: #0: 8.233 | |
| [2024-09-07 06:03:26,340][01890] Avg episode reward: 18.804, avg true_objective: 8.233 | |
| [2024-09-07 06:03:26,389][01890] Num frames 5800... | |
| [2024-09-07 06:03:26,511][01890] Num frames 5900... | |
| [2024-09-07 06:03:26,631][01890] Num frames 6000... | |
| [2024-09-07 06:03:26,751][01890] Num frames 6100... | |
| [2024-09-07 06:03:26,887][01890] Num frames 6200... | |
| [2024-09-07 06:03:27,016][01890] Num frames 6300... | |
| [2024-09-07 06:03:27,144][01890] Num frames 6400... | |
| [2024-09-07 06:03:27,266][01890] Num frames 6500... | |
| [2024-09-07 06:03:27,395][01890] Num frames 6600... | |
| [2024-09-07 06:03:27,522][01890] Num frames 6700... | |
| [2024-09-07 06:03:27,643][01890] Num frames 6800... | |
| [2024-09-07 06:03:27,768][01890] Num frames 6900... | |
| [2024-09-07 06:03:27,896][01890] Num frames 7000... | |
| [2024-09-07 06:03:28,027][01890] Num frames 7100... | |
| [2024-09-07 06:03:28,130][01890] Avg episode rewards: #0: 20.919, true rewards: #0: 8.919 | |
| [2024-09-07 06:03:28,131][01890] Avg episode reward: 20.919, avg true_objective: 8.919 | |
| [2024-09-07 06:03:28,214][01890] Num frames 7200... | |
| [2024-09-07 06:03:28,345][01890] Num frames 7300... | |
| [2024-09-07 06:03:28,467][01890] Num frames 7400... | |
| [2024-09-07 06:03:28,586][01890] Num frames 7500... | |
| [2024-09-07 06:03:28,705][01890] Num frames 7600... | |
| [2024-09-07 06:03:28,828][01890] Num frames 7700... | |
| [2024-09-07 06:03:28,946][01890] Num frames 7800... | |
| [2024-09-07 06:03:29,074][01890] Num frames 7900... | |
| [2024-09-07 06:03:29,200][01890] Num frames 8000... | |
| [2024-09-07 06:03:29,328][01890] Num frames 8100... | |
| [2024-09-07 06:03:29,451][01890] Num frames 8200... | |
| [2024-09-07 06:03:29,535][01890] Avg episode rewards: #0: 20.914, true rewards: #0: 9.137 | |
| [2024-09-07 06:03:29,537][01890] Avg episode reward: 20.914, avg true_objective: 9.137 | |
| [2024-09-07 06:03:29,633][01890] Num frames 8300... | |
| [2024-09-07 06:03:29,758][01890] Num frames 8400... | |
| [2024-09-07 06:03:29,880][01890] Num frames 8500... | |
| [2024-09-07 06:03:30,002][01890] Num frames 8600... | |
| [2024-09-07 06:03:30,136][01890] Num frames 8700... | |
| [2024-09-07 06:03:30,262][01890] Num frames 8800... | |
| [2024-09-07 06:03:30,390][01890] Num frames 8900... | |
| [2024-09-07 06:03:30,512][01890] Num frames 9000... | |
| [2024-09-07 06:03:30,634][01890] Num frames 9100... | |
| [2024-09-07 06:03:30,757][01890] Num frames 9200... | |
| [2024-09-07 06:03:30,884][01890] Num frames 9300... | |
| [2024-09-07 06:03:31,006][01890] Num frames 9400... | |
| [2024-09-07 06:03:31,142][01890] Num frames 9500... | |
| [2024-09-07 06:03:31,272][01890] Num frames 9600... | |
| [2024-09-07 06:03:31,406][01890] Num frames 9700... | |
| [2024-09-07 06:03:31,530][01890] Num frames 9800... | |
| [2024-09-07 06:03:31,682][01890] Num frames 9900... | |
| [2024-09-07 06:03:31,810][01890] Num frames 10000... | |
| [2024-09-07 06:03:31,933][01890] Num frames 10100... | |
| [2024-09-07 06:03:32,057][01890] Num frames 10200... | |
| [2024-09-07 06:03:32,142][01890] Avg episode rewards: #0: 24.624, true rewards: #0: 10.224 | |
| [2024-09-07 06:03:32,145][01890] Avg episode reward: 24.624, avg true_objective: 10.224 | |
| [2024-09-07 06:04:29,572][01890] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |