| [2023-02-25 14:10:34,782][00869] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-25 14:10:34,787][00869] Rollout worker 0 uses device cpu | |
| [2023-02-25 14:10:34,791][00869] Rollout worker 1 uses device cpu | |
| [2023-02-25 14:10:34,795][00869] Rollout worker 2 uses device cpu | |
| [2023-02-25 14:10:34,797][00869] Rollout worker 3 uses device cpu | |
| [2023-02-25 14:10:34,798][00869] Rollout worker 4 uses device cpu | |
| [2023-02-25 14:10:34,799][00869] Rollout worker 5 uses device cpu | |
| [2023-02-25 14:10:34,800][00869] Rollout worker 6 uses device cpu | |
| [2023-02-25 14:10:34,801][00869] Rollout worker 7 uses device cpu | |
| [2023-02-25 14:10:35,068][00869] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:10:35,071][00869] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-25 14:10:35,125][00869] Starting all processes... | |
| [2023-02-25 14:10:35,127][00869] Starting process learner_proc0 | |
| [2023-02-25 14:10:35,219][00869] Starting all processes... | |
| [2023-02-25 14:10:35,298][00869] Starting process inference_proc0-0 | |
| [2023-02-25 14:10:35,306][00869] Starting process rollout_proc0 | |
| [2023-02-25 14:10:35,306][00869] Starting process rollout_proc1 | |
| [2023-02-25 14:10:35,306][00869] Starting process rollout_proc2 | |
| [2023-02-25 14:10:35,309][00869] Starting process rollout_proc3 | |
| [2023-02-25 14:10:35,309][00869] Starting process rollout_proc4 | |
| [2023-02-25 14:10:35,311][00869] Starting process rollout_proc5 | |
| [2023-02-25 14:10:35,311][00869] Starting process rollout_proc6 | |
| [2023-02-25 14:10:35,311][00869] Starting process rollout_proc7 | |
| [2023-02-25 14:10:45,716][10866] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:10:45,720][10866] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-25 14:10:48,473][10884] Worker 3 uses CPU cores [1] | |
| [2023-02-25 14:10:48,869][10882] Worker 1 uses CPU cores [1] | |
| [2023-02-25 14:10:48,875][10887] Worker 6 uses CPU cores [0] | |
| [2023-02-25 14:10:49,038][10866] Num visible devices: 1 | |
| [2023-02-25 14:10:49,067][10866] Starting seed is not provided | |
| [2023-02-25 14:10:49,068][10866] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:10:49,069][10866] Initializing actor-critic model on device cuda:0 | |
| [2023-02-25 14:10:49,070][10866] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:10:49,073][10866] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:10:49,109][10886] Worker 5 uses CPU cores [1] | |
| [2023-02-25 14:10:49,116][10883] Worker 2 uses CPU cores [0] | |
| [2023-02-25 14:10:49,165][10881] Worker 0 uses CPU cores [0] | |
| [2023-02-25 14:10:49,197][10866] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:10:49,283][10880] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:10:49,285][10880] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-25 14:10:49,294][10885] Worker 4 uses CPU cores [0] | |
| [2023-02-25 14:10:49,322][10888] Worker 7 uses CPU cores [1] | |
| [2023-02-25 14:10:49,326][10880] Num visible devices: 1 | |
| [2023-02-25 14:10:49,760][10866] Conv encoder output size: 512 | |
| [2023-02-25 14:10:49,761][10866] Policy head output size: 512 | |
| [2023-02-25 14:10:49,834][10866] Created Actor Critic model with architecture: | |
| [2023-02-25 14:10:49,835][10866] 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) | |
| ) | |
| ) | |
| [2023-02-25 14:10:55,058][00869] Heartbeat connected on Batcher_0 | |
| [2023-02-25 14:10:55,069][00869] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-25 14:10:55,079][00869] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-25 14:10:55,083][00869] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-25 14:10:55,088][00869] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-25 14:10:55,092][00869] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-25 14:10:55,096][00869] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-25 14:10:55,104][00869] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-25 14:10:55,118][00869] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-25 14:10:55,124][00869] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-25 14:10:57,017][10866] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-25 14:10:57,018][10866] No checkpoints found | |
| [2023-02-25 14:10:57,018][10866] Did not load from checkpoint, starting from scratch! | |
| [2023-02-25 14:10:57,019][10866] Initialized policy 0 weights for model version 0 | |
| [2023-02-25 14:10:57,021][10866] LearnerWorker_p0 finished initialization! | |
| [2023-02-25 14:10:57,025][10866] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:10:57,022][00869] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-25 14:10:57,224][10880] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:10:57,226][10880] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:10:57,240][10880] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:10:57,337][10880] Conv encoder output size: 512 | |
| [2023-02-25 14:10:57,338][10880] Policy head output size: 512 | |
| [2023-02-25 14:10:57,797][00869] 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) | |
| [2023-02-25 14:10:59,581][00869] Inference worker 0-0 is ready! | |
| [2023-02-25 14:10:59,583][00869] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-25 14:10:59,699][10887] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,715][10881] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,723][10883] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,736][10884] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,735][10888] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,747][10882] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,753][10885] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:10:59,764][10886] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:11:00,667][10884] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:00,669][10886] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:01,537][10887] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:01,550][10883] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:01,568][10881] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:01,593][10885] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:01,668][10884] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:02,654][10885] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:02,749][10883] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:02,797][00869] 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) | |
| [2023-02-25 14:11:03,188][10882] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:03,301][10888] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:11:03,428][10886] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:03,663][10884] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:04,748][10883] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:05,009][10882] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:05,007][10887] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:05,146][10888] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:05,499][10885] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:05,515][10886] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:05,656][10884] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:06,613][10882] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:06,750][10888] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:07,378][10881] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:11:07,485][10882] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:07,801][00869] 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) | |
| [2023-02-25 14:11:07,878][10886] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:08,120][10887] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:08,302][10888] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:08,307][10883] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:08,444][10885] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:08,961][10881] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:11:09,065][10887] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:09,394][10881] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:11:12,605][10866] Signal inference workers to stop experience collection... | |
| [2023-02-25 14:11:12,613][10880] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-25 14:11:12,797][00869] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 105.9. Samples: 1588. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-25 14:11:12,799][00869] Avg episode reward: [(0, '1.901')] | |
| [2023-02-25 14:11:14,944][10866] Signal inference workers to resume experience collection... | |
| [2023-02-25 14:11:14,945][10880] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-25 14:11:17,797][00869] Fps is (10 sec: 1639.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 16384. Throughput: 0: 222.5. Samples: 4450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:11:17,802][00869] Avg episode reward: [(0, '3.277')] | |
| [2023-02-25 14:11:22,797][00869] Fps is (10 sec: 2867.2, 60 sec: 1146.9, 300 sec: 1146.9). Total num frames: 28672. Throughput: 0: 267.4. Samples: 6684. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-25 14:11:22,803][00869] Avg episode reward: [(0, '3.820')] | |
| [2023-02-25 14:11:25,946][10880] Updated weights for policy 0, policy_version 10 (0.0018) | |
| [2023-02-25 14:11:27,797][00869] Fps is (10 sec: 2867.2, 60 sec: 1501.9, 300 sec: 1501.9). Total num frames: 45056. Throughput: 0: 372.9. Samples: 11186. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:11:27,799][00869] Avg episode reward: [(0, '4.325')] | |
| [2023-02-25 14:11:32,797][00869] Fps is (10 sec: 4096.0, 60 sec: 1989.5, 300 sec: 1989.5). Total num frames: 69632. Throughput: 0: 516.2. Samples: 18066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:11:32,798][00869] Avg episode reward: [(0, '4.403')] | |
| [2023-02-25 14:11:35,049][10880] Updated weights for policy 0, policy_version 20 (0.0016) | |
| [2023-02-25 14:11:37,797][00869] Fps is (10 sec: 4505.4, 60 sec: 2252.8, 300 sec: 2252.8). Total num frames: 90112. Throughput: 0: 540.9. Samples: 21638. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:11:37,801][00869] Avg episode reward: [(0, '4.304')] | |
| [2023-02-25 14:11:42,797][00869] Fps is (10 sec: 3686.4, 60 sec: 2366.6, 300 sec: 2366.6). Total num frames: 106496. Throughput: 0: 596.7. Samples: 26852. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:11:42,799][00869] Avg episode reward: [(0, '4.234')] | |
| [2023-02-25 14:11:42,801][10866] Saving new best policy, reward=4.234! | |
| [2023-02-25 14:11:47,369][10880] Updated weights for policy 0, policy_version 30 (0.0042) | |
| [2023-02-25 14:11:47,797][00869] Fps is (10 sec: 3276.9, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 122880. Throughput: 0: 705.0. Samples: 31726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:11:47,804][00869] Avg episode reward: [(0, '4.236')] | |
| [2023-02-25 14:11:47,814][10866] Saving new best policy, reward=4.236! | |
| [2023-02-25 14:11:52,797][00869] Fps is (10 sec: 4096.0, 60 sec: 2681.0, 300 sec: 2681.0). Total num frames: 147456. Throughput: 0: 784.7. Samples: 35310. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-25 14:11:52,799][00869] Avg episode reward: [(0, '4.222')] | |
| [2023-02-25 14:11:55,740][10880] Updated weights for policy 0, policy_version 40 (0.0014) | |
| [2023-02-25 14:11:57,797][00869] Fps is (10 sec: 4505.6, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 907.8. Samples: 42440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:11:57,806][00869] Avg episode reward: [(0, '4.356')] | |
| [2023-02-25 14:11:57,908][10866] Saving new best policy, reward=4.356! | |
| [2023-02-25 14:12:02,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3003.7, 300 sec: 2772.7). Total num frames: 180224. Throughput: 0: 929.6. Samples: 46282. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:12:02,802][00869] Avg episode reward: [(0, '4.235')] | |
| [2023-02-25 14:12:07,797][00869] Fps is (10 sec: 2457.6, 60 sec: 3208.8, 300 sec: 2750.2). Total num frames: 192512. Throughput: 0: 909.3. Samples: 47602. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:12:07,799][00869] Avg episode reward: [(0, '4.222')] | |
| [2023-02-25 14:12:12,142][10880] Updated weights for policy 0, policy_version 50 (0.0027) | |
| [2023-02-25 14:12:12,797][00869] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 2730.7). Total num frames: 204800. Throughput: 0: 889.6. Samples: 51216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:12:12,803][00869] Avg episode reward: [(0, '4.205')] | |
| [2023-02-25 14:12:17,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 2867.2). Total num frames: 229376. Throughput: 0: 890.4. Samples: 58134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:12:17,799][00869] Avg episode reward: [(0, '4.345')] | |
| [2023-02-25 14:12:21,221][10880] Updated weights for policy 0, policy_version 60 (0.0024) | |
| [2023-02-25 14:12:22,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 2939.5). Total num frames: 249856. Throughput: 0: 890.9. Samples: 61730. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:12:22,803][00869] Avg episode reward: [(0, '4.548')] | |
| [2023-02-25 14:12:22,806][10866] Saving new best policy, reward=4.548! | |
| [2023-02-25 14:12:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 2912.7). Total num frames: 262144. Throughput: 0: 871.7. Samples: 66078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:12:27,800][00869] Avg episode reward: [(0, '4.497')] | |
| [2023-02-25 14:12:27,817][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth... | |
| [2023-02-25 14:12:32,797][00869] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 2975.0). Total num frames: 282624. Throughput: 0: 885.2. Samples: 71560. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:12:32,801][00869] Avg episode reward: [(0, '4.391')] | |
| [2023-02-25 14:12:33,190][10880] Updated weights for policy 0, policy_version 70 (0.0036) | |
| [2023-02-25 14:12:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3072.0). Total num frames: 307200. Throughput: 0: 880.2. Samples: 74918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:12:37,799][00869] Avg episode reward: [(0, '4.391')] | |
| [2023-02-25 14:12:42,797][00869] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3081.8). Total num frames: 323584. Throughput: 0: 865.1. Samples: 81368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:12:42,799][00869] Avg episode reward: [(0, '4.431')] | |
| [2023-02-25 14:12:43,232][10880] Updated weights for policy 0, policy_version 80 (0.0014) | |
| [2023-02-25 14:12:47,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3090.6). Total num frames: 339968. Throughput: 0: 873.7. Samples: 85598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:12:47,800][00869] Avg episode reward: [(0, '4.305')] | |
| [2023-02-25 14:12:52,799][00869] Fps is (10 sec: 3685.6, 60 sec: 3549.7, 300 sec: 3134.3). Total num frames: 360448. Throughput: 0: 900.8. Samples: 88142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:12:52,802][00869] Avg episode reward: [(0, '4.326')] | |
| [2023-02-25 14:12:54,581][10880] Updated weights for policy 0, policy_version 90 (0.0036) | |
| [2023-02-25 14:12:57,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3174.4). Total num frames: 380928. Throughput: 0: 972.9. Samples: 94998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:12:57,805][00869] Avg episode reward: [(0, '4.393')] | |
| [2023-02-25 14:13:02,797][00869] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3178.5). Total num frames: 397312. Throughput: 0: 939.2. Samples: 100398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:13:02,801][00869] Avg episode reward: [(0, '4.378')] | |
| [2023-02-25 14:13:06,177][10880] Updated weights for policy 0, policy_version 100 (0.0011) | |
| [2023-02-25 14:13:07,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3182.3). Total num frames: 413696. Throughput: 0: 906.0. Samples: 102500. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:13:07,803][00869] Avg episode reward: [(0, '4.464')] | |
| [2023-02-25 14:13:12,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3216.1). Total num frames: 434176. Throughput: 0: 929.8. Samples: 107920. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:13:12,803][00869] Avg episode reward: [(0, '4.392')] | |
| [2023-02-25 14:13:16,035][10880] Updated weights for policy 0, policy_version 110 (0.0021) | |
| [2023-02-25 14:13:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 458752. Throughput: 0: 963.6. Samples: 114922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:13:17,799][00869] Avg episode reward: [(0, '4.398')] | |
| [2023-02-25 14:13:22,797][00869] Fps is (10 sec: 4095.8, 60 sec: 3754.6, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 955.8. Samples: 117930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:13:22,803][00869] Avg episode reward: [(0, '4.502')] | |
| [2023-02-25 14:13:27,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3249.5). Total num frames: 487424. Throughput: 0: 910.0. Samples: 122316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:13:27,802][00869] Avg episode reward: [(0, '4.451')] | |
| [2023-02-25 14:13:27,950][10880] Updated weights for policy 0, policy_version 120 (0.0023) | |
| [2023-02-25 14:13:32,800][00869] Fps is (10 sec: 3685.3, 60 sec: 3822.7, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 949.1. Samples: 128310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:13:32,803][00869] Avg episode reward: [(0, '4.635')] | |
| [2023-02-25 14:13:32,813][10866] Saving new best policy, reward=4.635! | |
| [2023-02-25 14:13:37,224][10880] Updated weights for policy 0, policy_version 130 (0.0023) | |
| [2023-02-25 14:13:37,802][00869] Fps is (10 sec: 4503.4, 60 sec: 3754.4, 300 sec: 3327.9). Total num frames: 532480. Throughput: 0: 966.7. Samples: 131644. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:13:37,804][00869] Avg episode reward: [(0, '4.633')] | |
| [2023-02-25 14:13:42,803][00869] Fps is (10 sec: 3685.3, 60 sec: 3754.3, 300 sec: 3326.3). Total num frames: 548864. Throughput: 0: 943.8. Samples: 137476. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:13:42,806][00869] Avg episode reward: [(0, '4.481')] | |
| [2023-02-25 14:13:47,797][00869] Fps is (10 sec: 3278.2, 60 sec: 3754.6, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 920.8. Samples: 141836. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:13:47,801][00869] Avg episode reward: [(0, '4.402')] | |
| [2023-02-25 14:13:49,764][10880] Updated weights for policy 0, policy_version 140 (0.0013) | |
| [2023-02-25 14:13:52,797][00869] Fps is (10 sec: 3688.8, 60 sec: 3754.8, 300 sec: 3347.0). Total num frames: 585728. Throughput: 0: 940.1. Samples: 144806. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:13:52,806][00869] Avg episode reward: [(0, '4.349')] | |
| [2023-02-25 14:13:57,797][00869] Fps is (10 sec: 4505.8, 60 sec: 3822.9, 300 sec: 3390.6). Total num frames: 610304. Throughput: 0: 974.4. Samples: 151770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:13:57,799][00869] Avg episode reward: [(0, '4.285')] | |
| [2023-02-25 14:13:58,669][10880] Updated weights for policy 0, policy_version 150 (0.0016) | |
| [2023-02-25 14:14:02,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3387.5). Total num frames: 626688. Throughput: 0: 938.1. Samples: 157138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:14:02,804][00869] Avg episode reward: [(0, '4.453')] | |
| [2023-02-25 14:14:07,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3363.0). Total num frames: 638976. Throughput: 0: 919.5. Samples: 159306. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:14:07,803][00869] Avg episode reward: [(0, '4.510')] | |
| [2023-02-25 14:14:11,129][10880] Updated weights for policy 0, policy_version 160 (0.0020) | |
| [2023-02-25 14:14:12,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3381.8). Total num frames: 659456. Throughput: 0: 948.9. Samples: 165018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:12,800][00869] Avg episode reward: [(0, '4.592')] | |
| [2023-02-25 14:14:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 968.9. Samples: 171908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:14:17,802][00869] Avg episode reward: [(0, '4.643')] | |
| [2023-02-25 14:14:17,813][10866] Saving new best policy, reward=4.643! | |
| [2023-02-25 14:14:21,010][10880] Updated weights for policy 0, policy_version 170 (0.0012) | |
| [2023-02-25 14:14:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 951.6. Samples: 174462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:22,800][00869] Avg episode reward: [(0, '4.356')] | |
| [2023-02-25 14:14:27,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 917.3. Samples: 178748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:27,802][00869] Avg episode reward: [(0, '4.419')] | |
| [2023-02-25 14:14:27,821][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth... | |
| [2023-02-25 14:14:32,599][10880] Updated weights for policy 0, policy_version 180 (0.0016) | |
| [2023-02-25 14:14:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3429.2). Total num frames: 737280. Throughput: 0: 957.2. Samples: 184908. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:32,799][00869] Avg episode reward: [(0, '4.470')] | |
| [2023-02-25 14:14:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3755.0, 300 sec: 3444.4). Total num frames: 757760. Throughput: 0: 967.9. Samples: 188362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:14:37,801][00869] Avg episode reward: [(0, '4.714')] | |
| [2023-02-25 14:14:37,819][10866] Saving new best policy, reward=4.714! | |
| [2023-02-25 14:14:42,799][00869] Fps is (10 sec: 3685.4, 60 sec: 3754.9, 300 sec: 3440.6). Total num frames: 774144. Throughput: 0: 934.2. Samples: 193810. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:14:42,803][00869] Avg episode reward: [(0, '4.617')] | |
| [2023-02-25 14:14:43,443][10880] Updated weights for policy 0, policy_version 190 (0.0013) | |
| [2023-02-25 14:14:47,797][00869] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3437.1). Total num frames: 790528. Throughput: 0: 912.4. Samples: 198194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:14:47,806][00869] Avg episode reward: [(0, '4.775')] | |
| [2023-02-25 14:14:47,817][10866] Saving new best policy, reward=4.775! | |
| [2023-02-25 14:14:52,797][00869] Fps is (10 sec: 3687.4, 60 sec: 3754.7, 300 sec: 3451.1). Total num frames: 811008. Throughput: 0: 934.5. Samples: 201358. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:52,805][00869] Avg episode reward: [(0, '4.456')] | |
| [2023-02-25 14:14:54,218][10880] Updated weights for policy 0, policy_version 200 (0.0014) | |
| [2023-02-25 14:14:57,799][00869] Fps is (10 sec: 4504.5, 60 sec: 3754.5, 300 sec: 3481.6). Total num frames: 835584. Throughput: 0: 962.6. Samples: 208336. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:14:57,804][00869] Avg episode reward: [(0, '4.336')] | |
| [2023-02-25 14:15:02,799][00869] Fps is (10 sec: 3685.5, 60 sec: 3686.3, 300 sec: 3460.7). Total num frames: 847872. Throughput: 0: 919.2. Samples: 213272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:15:02,804][00869] Avg episode reward: [(0, '4.364')] | |
| [2023-02-25 14:15:05,787][10880] Updated weights for policy 0, policy_version 210 (0.0012) | |
| [2023-02-25 14:15:07,797][00869] Fps is (10 sec: 2867.9, 60 sec: 3754.7, 300 sec: 3457.0). Total num frames: 864256. Throughput: 0: 910.9. Samples: 215454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:15:07,802][00869] Avg episode reward: [(0, '4.440')] | |
| [2023-02-25 14:15:12,797][00869] Fps is (10 sec: 4096.8, 60 sec: 3822.9, 300 sec: 3485.6). Total num frames: 888832. Throughput: 0: 952.5. Samples: 221612. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:15:12,803][00869] Avg episode reward: [(0, '4.897')] | |
| [2023-02-25 14:15:12,806][10866] Saving new best policy, reward=4.897! | |
| [2023-02-25 14:15:15,420][10880] Updated weights for policy 0, policy_version 220 (0.0016) | |
| [2023-02-25 14:15:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3497.4). Total num frames: 909312. Throughput: 0: 967.2. Samples: 228430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:15:17,801][00869] Avg episode reward: [(0, '4.827')] | |
| [2023-02-25 14:15:22,797][00869] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3493.2). Total num frames: 925696. Throughput: 0: 941.4. Samples: 230726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:15:22,804][00869] Avg episode reward: [(0, '4.535')] | |
| [2023-02-25 14:15:27,677][10880] Updated weights for policy 0, policy_version 230 (0.0041) | |
| [2023-02-25 14:15:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3489.2). Total num frames: 942080. Throughput: 0: 918.9. Samples: 235156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:15:27,799][00869] Avg episode reward: [(0, '4.378')] | |
| [2023-02-25 14:15:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3500.2). Total num frames: 962560. Throughput: 0: 966.5. Samples: 241686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:15:32,799][00869] Avg episode reward: [(0, '4.495')] | |
| [2023-02-25 14:15:37,798][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3496.2). Total num frames: 978944. Throughput: 0: 961.4. Samples: 244620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:15:37,804][00869] Avg episode reward: [(0, '4.352')] | |
| [2023-02-25 14:15:37,981][10880] Updated weights for policy 0, policy_version 240 (0.0025) | |
| [2023-02-25 14:15:42,802][00869] Fps is (10 sec: 2865.6, 60 sec: 3618.0, 300 sec: 3477.9). Total num frames: 991232. Throughput: 0: 888.2. Samples: 248308. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:15:42,804][00869] Avg episode reward: [(0, '4.413')] | |
| [2023-02-25 14:15:47,797][00869] Fps is (10 sec: 2457.5, 60 sec: 3549.9, 300 sec: 3460.4). Total num frames: 1003520. Throughput: 0: 853.4. Samples: 251672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:15:47,804][00869] Avg episode reward: [(0, '4.375')] | |
| [2023-02-25 14:15:52,797][00869] Fps is (10 sec: 2868.8, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 851.6. Samples: 253778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:15:52,799][00869] Avg episode reward: [(0, '4.556')] | |
| [2023-02-25 14:15:53,006][10880] Updated weights for policy 0, policy_version 250 (0.0012) | |
| [2023-02-25 14:15:57,797][00869] Fps is (10 sec: 4096.1, 60 sec: 3481.7, 300 sec: 3540.6). Total num frames: 1044480. Throughput: 0: 865.9. Samples: 260578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:15:57,799][00869] Avg episode reward: [(0, '4.631')] | |
| [2023-02-25 14:16:02,700][10880] Updated weights for policy 0, policy_version 260 (0.0011) | |
| [2023-02-25 14:16:02,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3618.3, 300 sec: 3610.1). Total num frames: 1064960. Throughput: 0: 849.4. Samples: 266652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:16:02,801][00869] Avg episode reward: [(0, '4.712')] | |
| [2023-02-25 14:16:07,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1077248. Throughput: 0: 846.3. Samples: 268808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:16:07,799][00869] Avg episode reward: [(0, '4.650')] | |
| [2023-02-25 14:16:12,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1097728. Throughput: 0: 857.3. Samples: 273736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:16:12,799][00869] Avg episode reward: [(0, '4.730')] | |
| [2023-02-25 14:16:14,595][10880] Updated weights for policy 0, policy_version 270 (0.0013) | |
| [2023-02-25 14:16:17,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 1118208. Throughput: 0: 865.6. Samples: 280640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:16:17,799][00869] Avg episode reward: [(0, '4.560')] | |
| [2023-02-25 14:16:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3707.2). Total num frames: 1138688. Throughput: 0: 875.3. Samples: 284010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:16:22,801][00869] Avg episode reward: [(0, '4.659')] | |
| [2023-02-25 14:16:25,133][10880] Updated weights for policy 0, policy_version 280 (0.0024) | |
| [2023-02-25 14:16:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1150976. Throughput: 0: 889.8. Samples: 288344. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:16:27,804][00869] Avg episode reward: [(0, '4.722')] | |
| [2023-02-25 14:16:27,851][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000282_1155072.pth... | |
| [2023-02-25 14:16:27,987][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000064_262144.pth | |
| [2023-02-25 14:16:32,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1171456. Throughput: 0: 933.9. Samples: 293696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:16:32,805][00869] Avg episode reward: [(0, '4.911')] | |
| [2023-02-25 14:16:32,810][10866] Saving new best policy, reward=4.911! | |
| [2023-02-25 14:16:35,929][10880] Updated weights for policy 0, policy_version 290 (0.0019) | |
| [2023-02-25 14:16:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 1196032. Throughput: 0: 960.9. Samples: 297020. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:16:37,799][00869] Avg episode reward: [(0, '4.733')] | |
| [2023-02-25 14:16:42,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3693.3). Total num frames: 1212416. Throughput: 0: 948.3. Samples: 303250. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:16:42,803][00869] Avg episode reward: [(0, '4.732')] | |
| [2023-02-25 14:16:47,802][00869] Fps is (10 sec: 2865.8, 60 sec: 3686.1, 300 sec: 3651.6). Total num frames: 1224704. Throughput: 0: 908.8. Samples: 307552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:16:47,810][00869] Avg episode reward: [(0, '4.777')] | |
| [2023-02-25 14:16:48,052][10880] Updated weights for policy 0, policy_version 300 (0.0022) | |
| [2023-02-25 14:16:52,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1245184. Throughput: 0: 916.9. Samples: 310068. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:16:52,802][00869] Avg episode reward: [(0, '4.865')] | |
| [2023-02-25 14:16:57,797][00869] Fps is (10 sec: 4098.1, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1265664. Throughput: 0: 954.1. Samples: 316670. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:16:57,804][00869] Avg episode reward: [(0, '4.829')] | |
| [2023-02-25 14:16:57,837][10880] Updated weights for policy 0, policy_version 310 (0.0030) | |
| [2023-02-25 14:17:02,798][00869] Fps is (10 sec: 4095.4, 60 sec: 3686.3, 300 sec: 3707.2). Total num frames: 1286144. Throughput: 0: 921.3. Samples: 322098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:17:02,804][00869] Avg episode reward: [(0, '5.038')] | |
| [2023-02-25 14:17:02,808][10866] Saving new best policy, reward=5.038! | |
| [2023-02-25 14:17:07,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1298432. Throughput: 0: 892.2. Samples: 324158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:17:07,803][00869] Avg episode reward: [(0, '5.227')] | |
| [2023-02-25 14:17:07,821][10866] Saving new best policy, reward=5.227! | |
| [2023-02-25 14:17:10,602][10880] Updated weights for policy 0, policy_version 320 (0.0024) | |
| [2023-02-25 14:17:12,797][00869] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1318912. Throughput: 0: 914.2. Samples: 329482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:17:12,799][00869] Avg episode reward: [(0, '5.404')] | |
| [2023-02-25 14:17:12,807][10866] Saving new best policy, reward=5.404! | |
| [2023-02-25 14:17:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1343488. Throughput: 0: 952.8. Samples: 336572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:17:17,802][00869] Avg episode reward: [(0, '5.184')] | |
| [2023-02-25 14:17:19,289][10880] Updated weights for policy 0, policy_version 330 (0.0012) | |
| [2023-02-25 14:17:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 1359872. Throughput: 0: 946.4. Samples: 339610. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:17:22,804][00869] Avg episode reward: [(0, '5.135')] | |
| [2023-02-25 14:17:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1376256. Throughput: 0: 909.1. Samples: 344160. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:17:27,800][00869] Avg episode reward: [(0, '5.558')] | |
| [2023-02-25 14:17:27,813][10866] Saving new best policy, reward=5.558! | |
| [2023-02-25 14:17:31,330][10880] Updated weights for policy 0, policy_version 340 (0.0020) | |
| [2023-02-25 14:17:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1396736. Throughput: 0: 947.2. Samples: 350170. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:17:32,799][00869] Avg episode reward: [(0, '5.400')] | |
| [2023-02-25 14:17:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1421312. Throughput: 0: 968.2. Samples: 353638. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:17:37,799][00869] Avg episode reward: [(0, '5.048')] | |
| [2023-02-25 14:17:40,452][10880] Updated weights for policy 0, policy_version 350 (0.0017) | |
| [2023-02-25 14:17:42,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1437696. Throughput: 0: 957.3. Samples: 359748. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:17:42,800][00869] Avg episode reward: [(0, '4.961')] | |
| [2023-02-25 14:17:47,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.3, 300 sec: 3707.3). Total num frames: 1454080. Throughput: 0: 936.5. Samples: 364238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:17:47,803][00869] Avg episode reward: [(0, '5.058')] | |
| [2023-02-25 14:17:52,234][10880] Updated weights for policy 0, policy_version 360 (0.0021) | |
| [2023-02-25 14:17:52,799][00869] Fps is (10 sec: 3685.6, 60 sec: 3822.8, 300 sec: 3707.2). Total num frames: 1474560. Throughput: 0: 955.2. Samples: 367142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:17:52,807][00869] Avg episode reward: [(0, '5.536')] | |
| [2023-02-25 14:17:57,797][00869] Fps is (10 sec: 4505.5, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 1499136. Throughput: 0: 992.4. Samples: 374138. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:17:57,804][00869] Avg episode reward: [(0, '5.489')] | |
| [2023-02-25 14:18:02,607][10880] Updated weights for policy 0, policy_version 370 (0.0013) | |
| [2023-02-25 14:18:02,799][00869] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1515520. Throughput: 0: 954.7. Samples: 379538. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:18:02,808][00869] Avg episode reward: [(0, '5.563')] | |
| [2023-02-25 14:18:02,815][10866] Saving new best policy, reward=5.563! | |
| [2023-02-25 14:18:07,797][00869] Fps is (10 sec: 2867.3, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1527808. Throughput: 0: 934.8. Samples: 381678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:18:07,806][00869] Avg episode reward: [(0, '5.742')] | |
| [2023-02-25 14:18:07,820][10866] Saving new best policy, reward=5.742! | |
| [2023-02-25 14:18:12,797][00869] Fps is (10 sec: 3687.3, 60 sec: 3891.2, 300 sec: 3707.2). Total num frames: 1552384. Throughput: 0: 958.6. Samples: 387296. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:18:12,804][00869] Avg episode reward: [(0, '6.126')] | |
| [2023-02-25 14:18:12,808][10866] Saving new best policy, reward=6.126! | |
| [2023-02-25 14:18:13,784][10880] Updated weights for policy 0, policy_version 380 (0.0012) | |
| [2023-02-25 14:18:17,800][00869] Fps is (10 sec: 4504.2, 60 sec: 3822.7, 300 sec: 3721.1). Total num frames: 1572864. Throughput: 0: 978.8. Samples: 394220. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:18:17,802][00869] Avg episode reward: [(0, '6.725')] | |
| [2023-02-25 14:18:17,819][10866] Saving new best policy, reward=6.725! | |
| [2023-02-25 14:18:22,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 1589248. Throughput: 0: 961.6. Samples: 396908. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:18:22,801][00869] Avg episode reward: [(0, '6.577')] | |
| [2023-02-25 14:18:24,729][10880] Updated weights for policy 0, policy_version 390 (0.0016) | |
| [2023-02-25 14:18:27,797][00869] Fps is (10 sec: 3277.9, 60 sec: 3822.9, 300 sec: 3707.3). Total num frames: 1605632. Throughput: 0: 923.8. Samples: 401318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:18:27,799][00869] Avg episode reward: [(0, '6.363')] | |
| [2023-02-25 14:18:27,807][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000392_1605632.pth... | |
| [2023-02-25 14:18:27,973][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth | |
| [2023-02-25 14:18:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3707.3). Total num frames: 1626112. Throughput: 0: 959.1. Samples: 407396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:18:32,802][00869] Avg episode reward: [(0, '6.888')] | |
| [2023-02-25 14:18:32,808][10866] Saving new best policy, reward=6.888! | |
| [2023-02-25 14:18:34,875][10880] Updated weights for policy 0, policy_version 400 (0.0021) | |
| [2023-02-25 14:18:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3735.1). Total num frames: 1650688. Throughput: 0: 969.5. Samples: 410766. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:18:37,802][00869] Avg episode reward: [(0, '7.576')] | |
| [2023-02-25 14:18:37,814][10866] Saving new best policy, reward=7.576! | |
| [2023-02-25 14:18:42,800][00869] Fps is (10 sec: 4094.5, 60 sec: 3822.7, 300 sec: 3735.0). Total num frames: 1667072. Throughput: 0: 936.6. Samples: 416290. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:18:42,806][00869] Avg episode reward: [(0, '7.583')] | |
| [2023-02-25 14:18:42,809][10866] Saving new best policy, reward=7.583! | |
| [2023-02-25 14:18:47,224][10880] Updated weights for policy 0, policy_version 410 (0.0026) | |
| [2023-02-25 14:18:47,798][00869] Fps is (10 sec: 2866.8, 60 sec: 3754.6, 300 sec: 3707.2). Total num frames: 1679360. Throughput: 0: 913.0. Samples: 420622. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:18:47,805][00869] Avg episode reward: [(0, '7.331')] | |
| [2023-02-25 14:18:52,797][00869] Fps is (10 sec: 3277.9, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 1699840. Throughput: 0: 934.8. Samples: 423746. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:18:52,804][00869] Avg episode reward: [(0, '7.185')] | |
| [2023-02-25 14:18:56,510][10880] Updated weights for policy 0, policy_version 420 (0.0022) | |
| [2023-02-25 14:18:57,797][00869] Fps is (10 sec: 4506.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1724416. Throughput: 0: 965.1. Samples: 430724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:18:57,799][00869] Avg episode reward: [(0, '7.023')] | |
| [2023-02-25 14:19:02,797][00869] Fps is (10 sec: 4095.8, 60 sec: 3754.8, 300 sec: 3735.0). Total num frames: 1740800. Throughput: 0: 925.4. Samples: 435862. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:19:02,802][00869] Avg episode reward: [(0, '7.321')] | |
| [2023-02-25 14:19:07,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1753088. Throughput: 0: 913.7. Samples: 438026. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:07,810][00869] Avg episode reward: [(0, '7.775')] | |
| [2023-02-25 14:19:07,821][10866] Saving new best policy, reward=7.775! | |
| [2023-02-25 14:19:09,021][10880] Updated weights for policy 0, policy_version 430 (0.0044) | |
| [2023-02-25 14:19:12,797][00869] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1777664. Throughput: 0: 946.3. Samples: 443902. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:19:12,806][00869] Avg episode reward: [(0, '8.114')] | |
| [2023-02-25 14:19:12,810][10866] Saving new best policy, reward=8.114! | |
| [2023-02-25 14:19:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3754.9, 300 sec: 3721.1). Total num frames: 1798144. Throughput: 0: 964.1. Samples: 450780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:19:17,804][00869] Avg episode reward: [(0, '9.286')] | |
| [2023-02-25 14:19:17,820][10866] Saving new best policy, reward=9.286! | |
| [2023-02-25 14:19:18,138][10880] Updated weights for policy 0, policy_version 440 (0.0022) | |
| [2023-02-25 14:19:22,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 1814528. Throughput: 0: 940.7. Samples: 453098. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-25 14:19:22,807][00869] Avg episode reward: [(0, '9.391')] | |
| [2023-02-25 14:19:22,814][10866] Saving new best policy, reward=9.391! | |
| [2023-02-25 14:19:27,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1826816. Throughput: 0: 916.7. Samples: 457538. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-25 14:19:27,801][00869] Avg episode reward: [(0, '9.945')] | |
| [2023-02-25 14:19:27,909][10866] Saving new best policy, reward=9.945! | |
| [2023-02-25 14:19:30,560][10880] Updated weights for policy 0, policy_version 450 (0.0025) | |
| [2023-02-25 14:19:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1851392. Throughput: 0: 953.3. Samples: 463518. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:19:32,799][00869] Avg episode reward: [(0, '9.842')] | |
| [2023-02-25 14:19:37,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3693.4). Total num frames: 1863680. Throughput: 0: 929.8. Samples: 465586. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:37,799][00869] Avg episode reward: [(0, '9.690')] | |
| [2023-02-25 14:19:42,800][00869] Fps is (10 sec: 2456.7, 60 sec: 3481.6, 300 sec: 3679.4). Total num frames: 1875968. Throughput: 0: 860.8. Samples: 469462. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:42,804][00869] Avg episode reward: [(0, '9.212')] | |
| [2023-02-25 14:19:44,785][10880] Updated weights for policy 0, policy_version 460 (0.0020) | |
| [2023-02-25 14:19:47,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1892352. Throughput: 0: 837.7. Samples: 473560. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:47,800][00869] Avg episode reward: [(0, '9.005')] | |
| [2023-02-25 14:19:52,797][00869] Fps is (10 sec: 3278.0, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1908736. Throughput: 0: 849.3. Samples: 476244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:52,799][00869] Avg episode reward: [(0, '8.747')] | |
| [2023-02-25 14:19:55,334][10880] Updated weights for policy 0, policy_version 470 (0.0019) | |
| [2023-02-25 14:19:57,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 1933312. Throughput: 0: 877.9. Samples: 483408. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:19:57,802][00869] Avg episode reward: [(0, '9.162')] | |
| [2023-02-25 14:20:02,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 1953792. Throughput: 0: 849.3. Samples: 488998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:20:02,802][00869] Avg episode reward: [(0, '9.239')] | |
| [2023-02-25 14:20:06,973][10880] Updated weights for policy 0, policy_version 480 (0.0013) | |
| [2023-02-25 14:20:07,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 1966080. Throughput: 0: 845.2. Samples: 491132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:20:07,803][00869] Avg episode reward: [(0, '9.224')] | |
| [2023-02-25 14:20:12,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 1986560. Throughput: 0: 870.4. Samples: 496708. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:20:12,800][00869] Avg episode reward: [(0, '9.736')] | |
| [2023-02-25 14:20:16,279][10880] Updated weights for policy 0, policy_version 490 (0.0024) | |
| [2023-02-25 14:20:17,797][00869] Fps is (10 sec: 4505.5, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2011136. Throughput: 0: 893.0. Samples: 503702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:20:17,799][00869] Avg episode reward: [(0, '10.480')] | |
| [2023-02-25 14:20:17,816][10866] Saving new best policy, reward=10.480! | |
| [2023-02-25 14:20:22,798][00869] Fps is (10 sec: 4095.7, 60 sec: 3549.8, 300 sec: 3679.4). Total num frames: 2027520. Throughput: 0: 907.3. Samples: 506416. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:20:22,799][00869] Avg episode reward: [(0, '10.989')] | |
| [2023-02-25 14:20:22,803][10866] Saving new best policy, reward=10.989! | |
| [2023-02-25 14:20:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2043904. Throughput: 0: 918.9. Samples: 510808. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:20:27,800][00869] Avg episode reward: [(0, '10.774')] | |
| [2023-02-25 14:20:27,808][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000499_2043904.pth... | |
| [2023-02-25 14:20:28,014][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000282_1155072.pth | |
| [2023-02-25 14:20:28,852][10880] Updated weights for policy 0, policy_version 500 (0.0021) | |
| [2023-02-25 14:20:32,797][00869] Fps is (10 sec: 3686.7, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 2064384. Throughput: 0: 961.1. Samples: 516810. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:20:32,800][00869] Avg episode reward: [(0, '10.623')] | |
| [2023-02-25 14:20:37,783][10880] Updated weights for policy 0, policy_version 510 (0.0017) | |
| [2023-02-25 14:20:37,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3721.2). Total num frames: 2088960. Throughput: 0: 978.3. Samples: 520266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:20:37,799][00869] Avg episode reward: [(0, '11.155')] | |
| [2023-02-25 14:20:37,808][10866] Saving new best policy, reward=11.155! | |
| [2023-02-25 14:20:42,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.2, 300 sec: 3735.0). Total num frames: 2105344. Throughput: 0: 945.4. Samples: 525950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:20:42,803][00869] Avg episode reward: [(0, '12.215')] | |
| [2023-02-25 14:20:42,805][10866] Saving new best policy, reward=12.215! | |
| [2023-02-25 14:20:47,797][00869] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2117632. Throughput: 0: 920.5. Samples: 530422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:20:47,801][00869] Avg episode reward: [(0, '12.576')] | |
| [2023-02-25 14:20:47,813][10866] Saving new best policy, reward=12.576! | |
| [2023-02-25 14:20:50,292][10880] Updated weights for policy 0, policy_version 520 (0.0013) | |
| [2023-02-25 14:20:52,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 2138112. Throughput: 0: 939.1. Samples: 533392. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:20:52,803][00869] Avg episode reward: [(0, '11.429')] | |
| [2023-02-25 14:20:57,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2162688. Throughput: 0: 971.2. Samples: 540414. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:20:57,801][00869] Avg episode reward: [(0, '10.668')] | |
| [2023-02-25 14:20:59,263][10880] Updated weights for policy 0, policy_version 530 (0.0012) | |
| [2023-02-25 14:21:02,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2179072. Throughput: 0: 930.4. Samples: 545572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:21:02,799][00869] Avg episode reward: [(0, '11.095')] | |
| [2023-02-25 14:21:07,797][00869] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3707.2). Total num frames: 2191360. Throughput: 0: 918.4. Samples: 547742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:21:07,807][00869] Avg episode reward: [(0, '10.997')] | |
| [2023-02-25 14:21:11,523][10880] Updated weights for policy 0, policy_version 540 (0.0027) | |
| [2023-02-25 14:21:12,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2215936. Throughput: 0: 950.1. Samples: 553562. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:21:12,804][00869] Avg episode reward: [(0, '11.660')] | |
| [2023-02-25 14:21:17,797][00869] Fps is (10 sec: 4915.5, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 2240512. Throughput: 0: 976.8. Samples: 560766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:21:17,799][00869] Avg episode reward: [(0, '12.335')] | |
| [2023-02-25 14:21:21,362][10880] Updated weights for policy 0, policy_version 550 (0.0026) | |
| [2023-02-25 14:21:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 2256896. Throughput: 0: 953.8. Samples: 563188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:21:22,800][00869] Avg episode reward: [(0, '11.839')] | |
| [2023-02-25 14:21:27,797][00869] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2269184. Throughput: 0: 925.4. Samples: 567592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:21:27,799][00869] Avg episode reward: [(0, '12.035')] | |
| [2023-02-25 14:21:32,654][10880] Updated weights for policy 0, policy_version 560 (0.0013) | |
| [2023-02-25 14:21:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2293760. Throughput: 0: 967.7. Samples: 573968. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:21:32,800][00869] Avg episode reward: [(0, '13.546')] | |
| [2023-02-25 14:21:32,801][10866] Saving new best policy, reward=13.546! | |
| [2023-02-25 14:21:37,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2314240. Throughput: 0: 976.3. Samples: 577324. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:21:37,802][00869] Avg episode reward: [(0, '13.323')] | |
| [2023-02-25 14:21:42,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2330624. Throughput: 0: 942.2. Samples: 582812. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:21:42,801][00869] Avg episode reward: [(0, '14.215')] | |
| [2023-02-25 14:21:42,806][10866] Saving new best policy, reward=14.215! | |
| [2023-02-25 14:21:43,623][10880] Updated weights for policy 0, policy_version 570 (0.0013) | |
| [2023-02-25 14:21:47,800][00869] Fps is (10 sec: 3275.7, 60 sec: 3822.7, 300 sec: 3735.0). Total num frames: 2347008. Throughput: 0: 924.0. Samples: 587154. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:21:47,805][00869] Avg episode reward: [(0, '16.039')] | |
| [2023-02-25 14:21:47,819][10866] Saving new best policy, reward=16.039! | |
| [2023-02-25 14:21:52,797][00869] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 2367488. Throughput: 0: 948.7. Samples: 590434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:21:52,806][00869] Avg episode reward: [(0, '16.511')] | |
| [2023-02-25 14:21:52,809][10866] Saving new best policy, reward=16.511! | |
| [2023-02-25 14:21:54,135][10880] Updated weights for policy 0, policy_version 580 (0.0016) | |
| [2023-02-25 14:21:57,797][00869] Fps is (10 sec: 4507.1, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 2392064. Throughput: 0: 971.8. Samples: 597292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:21:57,802][00869] Avg episode reward: [(0, '17.123')] | |
| [2023-02-25 14:21:57,813][10866] Saving new best policy, reward=17.123! | |
| [2023-02-25 14:22:02,797][00869] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2404352. Throughput: 0: 918.9. Samples: 602118. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:22:02,804][00869] Avg episode reward: [(0, '17.584')] | |
| [2023-02-25 14:22:02,809][10866] Saving new best policy, reward=17.584! | |
| [2023-02-25 14:22:06,621][10880] Updated weights for policy 0, policy_version 590 (0.0013) | |
| [2023-02-25 14:22:07,797][00869] Fps is (10 sec: 2457.6, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2416640. Throughput: 0: 909.6. Samples: 604118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:22:07,805][00869] Avg episode reward: [(0, '17.414')] | |
| [2023-02-25 14:22:12,797][00869] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2441216. Throughput: 0: 944.0. Samples: 610070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:22:12,799][00869] Avg episode reward: [(0, '16.833')] | |
| [2023-02-25 14:22:15,887][10880] Updated weights for policy 0, policy_version 600 (0.0014) | |
| [2023-02-25 14:22:17,797][00869] Fps is (10 sec: 4915.2, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2465792. Throughput: 0: 957.2. Samples: 617040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:22:17,800][00869] Avg episode reward: [(0, '16.683')] | |
| [2023-02-25 14:22:22,800][00869] Fps is (10 sec: 3685.2, 60 sec: 3686.2, 300 sec: 3735.0). Total num frames: 2478080. Throughput: 0: 930.4. Samples: 619196. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:22:22,803][00869] Avg episode reward: [(0, '16.506')] | |
| [2023-02-25 14:22:27,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2494464. Throughput: 0: 904.8. Samples: 623530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:22:27,799][00869] Avg episode reward: [(0, '15.938')] | |
| [2023-02-25 14:22:27,813][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000609_2494464.pth... | |
| [2023-02-25 14:22:27,935][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000392_1605632.pth | |
| [2023-02-25 14:22:28,424][10880] Updated weights for policy 0, policy_version 610 (0.0012) | |
| [2023-02-25 14:22:32,797][00869] Fps is (10 sec: 4097.5, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2519040. Throughput: 0: 956.4. Samples: 630188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:22:32,804][00869] Avg episode reward: [(0, '15.992')] | |
| [2023-02-25 14:22:37,023][10880] Updated weights for policy 0, policy_version 620 (0.0012) | |
| [2023-02-25 14:22:37,802][00869] Fps is (10 sec: 4503.1, 60 sec: 3754.3, 300 sec: 3734.9). Total num frames: 2539520. Throughput: 0: 959.7. Samples: 633626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:22:37,809][00869] Avg episode reward: [(0, '15.959')] | |
| [2023-02-25 14:22:42,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2555904. Throughput: 0: 920.1. Samples: 638698. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:22:42,799][00869] Avg episode reward: [(0, '15.717')] | |
| [2023-02-25 14:22:47,797][00869] Fps is (10 sec: 3278.6, 60 sec: 3754.9, 300 sec: 3721.1). Total num frames: 2572288. Throughput: 0: 919.6. Samples: 643498. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:22:47,799][00869] Avg episode reward: [(0, '16.029')] | |
| [2023-02-25 14:22:49,523][10880] Updated weights for policy 0, policy_version 630 (0.0037) | |
| [2023-02-25 14:22:52,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2592768. Throughput: 0: 951.6. Samples: 646942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:22:52,803][00869] Avg episode reward: [(0, '15.959')] | |
| [2023-02-25 14:22:57,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2613248. Throughput: 0: 974.4. Samples: 653918. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:22:57,799][00869] Avg episode reward: [(0, '16.744')] | |
| [2023-02-25 14:22:59,165][10880] Updated weights for policy 0, policy_version 640 (0.0013) | |
| [2023-02-25 14:23:02,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2629632. Throughput: 0: 918.2. Samples: 658360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:23:02,802][00869] Avg episode reward: [(0, '17.564')] | |
| [2023-02-25 14:23:07,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 2646016. Throughput: 0: 919.8. Samples: 660584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:23:07,799][00869] Avg episode reward: [(0, '18.772')] | |
| [2023-02-25 14:23:07,814][10866] Saving new best policy, reward=18.772! | |
| [2023-02-25 14:23:10,943][10880] Updated weights for policy 0, policy_version 650 (0.0016) | |
| [2023-02-25 14:23:12,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 2666496. Throughput: 0: 966.1. Samples: 667004. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:23:12,809][00869] Avg episode reward: [(0, '19.958')] | |
| [2023-02-25 14:23:12,849][10866] Saving new best policy, reward=19.958! | |
| [2023-02-25 14:23:17,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2691072. Throughput: 0: 963.4. Samples: 673542. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:23:17,800][00869] Avg episode reward: [(0, '20.410')] | |
| [2023-02-25 14:23:17,816][10866] Saving new best policy, reward=20.410! | |
| [2023-02-25 14:23:21,373][10880] Updated weights for policy 0, policy_version 660 (0.0029) | |
| [2023-02-25 14:23:22,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.9, 300 sec: 3721.1). Total num frames: 2703360. Throughput: 0: 935.3. Samples: 675708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:23:22,800][00869] Avg episode reward: [(0, '19.885')] | |
| [2023-02-25 14:23:27,798][00869] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3707.2). Total num frames: 2719744. Throughput: 0: 918.7. Samples: 680040. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:23:27,805][00869] Avg episode reward: [(0, '20.939')] | |
| [2023-02-25 14:23:27,895][10866] Saving new best policy, reward=20.939! | |
| [2023-02-25 14:23:32,381][10880] Updated weights for policy 0, policy_version 670 (0.0039) | |
| [2023-02-25 14:23:32,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2744320. Throughput: 0: 967.5. Samples: 687036. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:23:32,798][00869] Avg episode reward: [(0, '19.562')] | |
| [2023-02-25 14:23:37,797][00869] Fps is (10 sec: 4505.9, 60 sec: 3755.0, 300 sec: 3721.2). Total num frames: 2764800. Throughput: 0: 967.7. Samples: 690490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:23:37,800][00869] Avg episode reward: [(0, '17.542')] | |
| [2023-02-25 14:23:42,802][00869] Fps is (10 sec: 3684.4, 60 sec: 3754.3, 300 sec: 3734.9). Total num frames: 2781184. Throughput: 0: 919.9. Samples: 695320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:23:42,806][00869] Avg episode reward: [(0, '18.462')] | |
| [2023-02-25 14:23:43,837][10880] Updated weights for policy 0, policy_version 680 (0.0038) | |
| [2023-02-25 14:23:47,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2797568. Throughput: 0: 929.5. Samples: 700186. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:23:47,799][00869] Avg episode reward: [(0, '18.920')] | |
| [2023-02-25 14:23:52,797][00869] Fps is (10 sec: 4098.3, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 2822144. Throughput: 0: 957.2. Samples: 703656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:23:52,804][00869] Avg episode reward: [(0, '19.371')] | |
| [2023-02-25 14:23:53,776][10880] Updated weights for policy 0, policy_version 690 (0.0013) | |
| [2023-02-25 14:23:57,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2838528. Throughput: 0: 954.8. Samples: 709970. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:23:57,804][00869] Avg episode reward: [(0, '19.194')] | |
| [2023-02-25 14:24:02,798][00869] Fps is (10 sec: 2867.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2850816. Throughput: 0: 882.4. Samples: 713252. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:24:02,803][00869] Avg episode reward: [(0, '20.239')] | |
| [2023-02-25 14:24:07,797][00869] Fps is (10 sec: 2457.5, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2863104. Throughput: 0: 872.6. Samples: 714974. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:24:07,801][00869] Avg episode reward: [(0, '20.843')] | |
| [2023-02-25 14:24:09,566][10880] Updated weights for policy 0, policy_version 700 (0.0030) | |
| [2023-02-25 14:24:12,797][00869] Fps is (10 sec: 2867.4, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 2879488. Throughput: 0: 873.8. Samples: 719360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:24:12,799][00869] Avg episode reward: [(0, '20.546')] | |
| [2023-02-25 14:24:17,797][00869] Fps is (10 sec: 3686.6, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 2899968. Throughput: 0: 873.8. Samples: 726356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:24:17,799][00869] Avg episode reward: [(0, '18.792')] | |
| [2023-02-25 14:24:18,737][10880] Updated weights for policy 0, policy_version 710 (0.0025) | |
| [2023-02-25 14:24:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 2920448. Throughput: 0: 870.6. Samples: 729666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:24:22,799][00869] Avg episode reward: [(0, '18.789')] | |
| [2023-02-25 14:24:27,799][00869] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3679.4). Total num frames: 2936832. Throughput: 0: 860.1. Samples: 734022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:24:27,801][00869] Avg episode reward: [(0, '18.369')] | |
| [2023-02-25 14:24:27,820][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000717_2936832.pth... | |
| [2023-02-25 14:24:27,980][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000499_2043904.pth | |
| [2023-02-25 14:24:31,259][10880] Updated weights for policy 0, policy_version 720 (0.0038) | |
| [2023-02-25 14:24:32,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 2953216. Throughput: 0: 873.0. Samples: 739472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:24:32,799][00869] Avg episode reward: [(0, '18.638')] | |
| [2023-02-25 14:24:37,797][00869] Fps is (10 sec: 4096.7, 60 sec: 3549.8, 300 sec: 3735.0). Total num frames: 2977792. Throughput: 0: 872.2. Samples: 742904. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:24:37,804][00869] Avg episode reward: [(0, '21.388')] | |
| [2023-02-25 14:24:37,816][10866] Saving new best policy, reward=21.388! | |
| [2023-02-25 14:24:40,047][10880] Updated weights for policy 0, policy_version 730 (0.0017) | |
| [2023-02-25 14:24:42,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3618.5, 300 sec: 3748.9). Total num frames: 2998272. Throughput: 0: 874.9. Samples: 749340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:24:42,799][00869] Avg episode reward: [(0, '21.222')] | |
| [2023-02-25 14:24:47,800][00869] Fps is (10 sec: 3276.0, 60 sec: 3549.7, 300 sec: 3735.0). Total num frames: 3010560. Throughput: 0: 901.4. Samples: 753818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:24:47,803][00869] Avg episode reward: [(0, '21.830')] | |
| [2023-02-25 14:24:47,815][10866] Saving new best policy, reward=21.830! | |
| [2023-02-25 14:24:52,341][10880] Updated weights for policy 0, policy_version 740 (0.0019) | |
| [2023-02-25 14:24:52,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3721.1). Total num frames: 3031040. Throughput: 0: 917.7. Samples: 756268. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:24:52,804][00869] Avg episode reward: [(0, '23.445')] | |
| [2023-02-25 14:24:52,807][10866] Saving new best policy, reward=23.445! | |
| [2023-02-25 14:24:57,797][00869] Fps is (10 sec: 4097.3, 60 sec: 3549.9, 300 sec: 3721.1). Total num frames: 3051520. Throughput: 0: 972.1. Samples: 763104. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:24:57,799][00869] Avg episode reward: [(0, '22.757')] | |
| [2023-02-25 14:25:01,969][10880] Updated weights for policy 0, policy_version 750 (0.0019) | |
| [2023-02-25 14:25:02,797][00869] Fps is (10 sec: 4095.8, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 3072000. Throughput: 0: 946.8. Samples: 768964. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:25:02,799][00869] Avg episode reward: [(0, '20.553')] | |
| [2023-02-25 14:25:07,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3088384. Throughput: 0: 923.2. Samples: 771208. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:25:07,803][00869] Avg episode reward: [(0, '20.456')] | |
| [2023-02-25 14:25:12,797][00869] Fps is (10 sec: 3277.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3104768. Throughput: 0: 941.7. Samples: 776396. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:25:12,805][00869] Avg episode reward: [(0, '20.647')] | |
| [2023-02-25 14:25:13,797][10880] Updated weights for policy 0, policy_version 760 (0.0015) | |
| [2023-02-25 14:25:17,797][00869] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3129344. Throughput: 0: 977.2. Samples: 783446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:25:17,800][00869] Avg episode reward: [(0, '19.866')] | |
| [2023-02-25 14:25:22,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3149824. Throughput: 0: 973.0. Samples: 786690. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:25:22,801][00869] Avg episode reward: [(0, '19.725')] | |
| [2023-02-25 14:25:23,979][10880] Updated weights for policy 0, policy_version 770 (0.0012) | |
| [2023-02-25 14:25:27,797][00869] Fps is (10 sec: 3276.7, 60 sec: 3754.8, 300 sec: 3721.1). Total num frames: 3162112. Throughput: 0: 927.4. Samples: 791074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:25:27,800][00869] Avg episode reward: [(0, '19.844')] | |
| [2023-02-25 14:25:32,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3182592. Throughput: 0: 954.5. Samples: 796768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:25:32,806][00869] Avg episode reward: [(0, '21.503')] | |
| [2023-02-25 14:25:34,874][10880] Updated weights for policy 0, policy_version 780 (0.0025) | |
| [2023-02-25 14:25:37,797][00869] Fps is (10 sec: 4505.8, 60 sec: 3823.0, 300 sec: 3735.0). Total num frames: 3207168. Throughput: 0: 976.0. Samples: 800188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:25:37,806][00869] Avg episode reward: [(0, '21.780')] | |
| [2023-02-25 14:25:42,798][00869] Fps is (10 sec: 4095.4, 60 sec: 3754.6, 300 sec: 3748.9). Total num frames: 3223552. Throughput: 0: 958.7. Samples: 806246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:25:42,806][00869] Avg episode reward: [(0, '21.694')] | |
| [2023-02-25 14:25:45,846][10880] Updated weights for policy 0, policy_version 790 (0.0013) | |
| [2023-02-25 14:25:47,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3735.0). Total num frames: 3239936. Throughput: 0: 926.7. Samples: 810666. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:25:47,806][00869] Avg episode reward: [(0, '21.670')] | |
| [2023-02-25 14:25:52,797][00869] Fps is (10 sec: 3687.0, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3260416. Throughput: 0: 938.7. Samples: 813450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:25:52,799][00869] Avg episode reward: [(0, '22.763')] | |
| [2023-02-25 14:25:55,984][10880] Updated weights for policy 0, policy_version 800 (0.0013) | |
| [2023-02-25 14:25:57,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3748.9). Total num frames: 3284992. Throughput: 0: 980.7. Samples: 820526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:25:57,799][00869] Avg episode reward: [(0, '20.548')] | |
| [2023-02-25 14:26:02,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 3301376. Throughput: 0: 946.5. Samples: 826040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:26:02,803][00869] Avg episode reward: [(0, '20.069')] | |
| [2023-02-25 14:26:07,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3313664. Throughput: 0: 922.4. Samples: 828198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:26:07,803][00869] Avg episode reward: [(0, '19.562')] | |
| [2023-02-25 14:26:08,164][10880] Updated weights for policy 0, policy_version 810 (0.0018) | |
| [2023-02-25 14:26:12,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3334144. Throughput: 0: 946.9. Samples: 833686. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:26:12,800][00869] Avg episode reward: [(0, '19.652')] | |
| [2023-02-25 14:26:17,151][10880] Updated weights for policy 0, policy_version 820 (0.0015) | |
| [2023-02-25 14:26:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3358720. Throughput: 0: 977.9. Samples: 840774. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:26:17,799][00869] Avg episode reward: [(0, '19.835')] | |
| [2023-02-25 14:26:22,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3375104. Throughput: 0: 965.1. Samples: 843616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:26:22,802][00869] Avg episode reward: [(0, '19.940')] | |
| [2023-02-25 14:26:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3721.1). Total num frames: 3391488. Throughput: 0: 927.9. Samples: 847998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:26:27,800][00869] Avg episode reward: [(0, '19.515')] | |
| [2023-02-25 14:26:27,815][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000828_3391488.pth... | |
| [2023-02-25 14:26:27,955][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000609_2494464.pth | |
| [2023-02-25 14:26:29,703][10880] Updated weights for policy 0, policy_version 830 (0.0039) | |
| [2023-02-25 14:26:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3411968. Throughput: 0: 962.5. Samples: 853980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:26:32,802][00869] Avg episode reward: [(0, '19.501')] | |
| [2023-02-25 14:26:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3436544. Throughput: 0: 978.5. Samples: 857482. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:26:37,799][00869] Avg episode reward: [(0, '20.088')] | |
| [2023-02-25 14:26:38,505][10880] Updated weights for policy 0, policy_version 840 (0.0015) | |
| [2023-02-25 14:26:42,797][00869] Fps is (10 sec: 4095.9, 60 sec: 3823.0, 300 sec: 3748.9). Total num frames: 3452928. Throughput: 0: 950.9. Samples: 863316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:26:42,800][00869] Avg episode reward: [(0, '19.055')] | |
| [2023-02-25 14:26:47,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3469312. Throughput: 0: 927.7. Samples: 867786. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:26:47,800][00869] Avg episode reward: [(0, '18.729')] | |
| [2023-02-25 14:26:50,669][10880] Updated weights for policy 0, policy_version 850 (0.0019) | |
| [2023-02-25 14:26:52,797][00869] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 3489792. Throughput: 0: 948.3. Samples: 870870. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:26:52,800][00869] Avg episode reward: [(0, '18.135')] | |
| [2023-02-25 14:26:57,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3514368. Throughput: 0: 981.6. Samples: 877860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:26:57,804][00869] Avg episode reward: [(0, '17.973')] | |
| [2023-02-25 14:27:00,041][10880] Updated weights for policy 0, policy_version 860 (0.0022) | |
| [2023-02-25 14:27:02,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3526656. Throughput: 0: 938.1. Samples: 882990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:27:02,803][00869] Avg episode reward: [(0, '18.856')] | |
| [2023-02-25 14:27:07,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3543040. Throughput: 0: 924.5. Samples: 885218. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:27:07,806][00869] Avg episode reward: [(0, '19.888')] | |
| [2023-02-25 14:27:12,025][10880] Updated weights for policy 0, policy_version 870 (0.0034) | |
| [2023-02-25 14:27:12,797][00869] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3735.0). Total num frames: 3567616. Throughput: 0: 954.4. Samples: 890948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:27:12,798][00869] Avg episode reward: [(0, '20.569')] | |
| [2023-02-25 14:27:17,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3588096. Throughput: 0: 977.7. Samples: 897978. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:27:17,799][00869] Avg episode reward: [(0, '22.271')] | |
| [2023-02-25 14:27:22,087][10880] Updated weights for policy 0, policy_version 880 (0.0012) | |
| [2023-02-25 14:27:22,797][00869] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3604480. Throughput: 0: 955.7. Samples: 900490. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:27:22,801][00869] Avg episode reward: [(0, '23.034')] | |
| [2023-02-25 14:27:27,797][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 3620864. Throughput: 0: 924.3. Samples: 904908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:27:27,806][00869] Avg episode reward: [(0, '22.238')] | |
| [2023-02-25 14:27:32,797][00869] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3735.1). Total num frames: 3641344. Throughput: 0: 962.7. Samples: 911106. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:27:32,809][00869] Avg episode reward: [(0, '21.516')] | |
| [2023-02-25 14:27:33,301][10880] Updated weights for policy 0, policy_version 890 (0.0012) | |
| [2023-02-25 14:27:37,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3665920. Throughput: 0: 971.2. Samples: 914576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:27:37,799][00869] Avg episode reward: [(0, '20.989')] | |
| [2023-02-25 14:27:42,802][00869] Fps is (10 sec: 3684.6, 60 sec: 3754.4, 300 sec: 3748.8). Total num frames: 3678208. Throughput: 0: 938.7. Samples: 920108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:27:42,808][00869] Avg episode reward: [(0, '20.617')] | |
| [2023-02-25 14:27:44,265][10880] Updated weights for policy 0, policy_version 900 (0.0012) | |
| [2023-02-25 14:27:47,798][00869] Fps is (10 sec: 2866.8, 60 sec: 3754.6, 300 sec: 3735.0). Total num frames: 3694592. Throughput: 0: 925.4. Samples: 924634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:27:47,806][00869] Avg episode reward: [(0, '20.250')] | |
| [2023-02-25 14:27:52,797][00869] Fps is (10 sec: 4098.0, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3719168. Throughput: 0: 946.6. Samples: 927814. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:27:52,802][00869] Avg episode reward: [(0, '18.669')] | |
| [2023-02-25 14:27:54,455][10880] Updated weights for policy 0, policy_version 910 (0.0024) | |
| [2023-02-25 14:27:57,797][00869] Fps is (10 sec: 4506.2, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3739648. Throughput: 0: 976.7. Samples: 934900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:27:57,806][00869] Avg episode reward: [(0, '18.065')] | |
| [2023-02-25 14:28:02,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 3756032. Throughput: 0: 933.3. Samples: 939976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:28:02,801][00869] Avg episode reward: [(0, '18.055')] | |
| [2023-02-25 14:28:06,240][10880] Updated weights for policy 0, policy_version 920 (0.0030) | |
| [2023-02-25 14:28:07,797][00869] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3748.9). Total num frames: 3772416. Throughput: 0: 927.2. Samples: 942216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:28:07,802][00869] Avg episode reward: [(0, '18.557')] | |
| [2023-02-25 14:28:12,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3792896. Throughput: 0: 958.4. Samples: 948034. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:28:12,805][00869] Avg episode reward: [(0, '19.716')] | |
| [2023-02-25 14:28:15,930][10880] Updated weights for policy 0, policy_version 930 (0.0026) | |
| [2023-02-25 14:28:17,797][00869] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 3817472. Throughput: 0: 970.8. Samples: 954792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:28:17,800][00869] Avg episode reward: [(0, '21.107')] | |
| [2023-02-25 14:28:22,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3762.8). Total num frames: 3829760. Throughput: 0: 946.6. Samples: 957172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:28:22,801][00869] Avg episode reward: [(0, '22.183')] | |
| [2023-02-25 14:28:27,797][00869] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3735.0). Total num frames: 3846144. Throughput: 0: 916.8. Samples: 961362. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:28:27,806][00869] Avg episode reward: [(0, '23.707')] | |
| [2023-02-25 14:28:27,823][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000939_3846144.pth... | |
| [2023-02-25 14:28:27,986][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000717_2936832.pth | |
| [2023-02-25 14:28:28,003][10866] Saving new best policy, reward=23.707! | |
| [2023-02-25 14:28:28,738][10880] Updated weights for policy 0, policy_version 940 (0.0020) | |
| [2023-02-25 14:28:32,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3866624. Throughput: 0: 946.4. Samples: 967220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:28:32,803][00869] Avg episode reward: [(0, '23.187')] | |
| [2023-02-25 14:28:37,797][00869] Fps is (10 sec: 4096.3, 60 sec: 3686.4, 300 sec: 3749.0). Total num frames: 3887104. Throughput: 0: 948.9. Samples: 970516. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:28:37,804][00869] Avg episode reward: [(0, '21.678')] | |
| [2023-02-25 14:28:38,308][10880] Updated weights for policy 0, policy_version 950 (0.0018) | |
| [2023-02-25 14:28:42,797][00869] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3748.9). Total num frames: 3903488. Throughput: 0: 907.9. Samples: 975756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:28:42,799][00869] Avg episode reward: [(0, '21.196')] | |
| [2023-02-25 14:28:47,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3707.2). Total num frames: 3915776. Throughput: 0: 888.2. Samples: 979946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:28:47,802][00869] Avg episode reward: [(0, '21.524')] | |
| [2023-02-25 14:28:51,059][10880] Updated weights for policy 0, policy_version 960 (0.0024) | |
| [2023-02-25 14:28:52,801][00869] Fps is (10 sec: 3275.3, 60 sec: 3617.9, 300 sec: 3721.1). Total num frames: 3936256. Throughput: 0: 909.2. Samples: 983134. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:28:52,807][00869] Avg episode reward: [(0, '19.869')] | |
| [2023-02-25 14:28:57,797][00869] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3762.8). Total num frames: 3960832. Throughput: 0: 934.7. Samples: 990094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:28:57,799][00869] Avg episode reward: [(0, '20.040')] | |
| [2023-02-25 14:29:00,851][10880] Updated weights for policy 0, policy_version 970 (0.0028) | |
| [2023-02-25 14:29:02,797][00869] Fps is (10 sec: 4097.8, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 3977216. Throughput: 0: 894.3. Samples: 995036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:29:02,804][00869] Avg episode reward: [(0, '20.145')] | |
| [2023-02-25 14:29:07,797][00869] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3762.8). Total num frames: 3989504. Throughput: 0: 884.8. Samples: 996988. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:29:07,799][00869] Avg episode reward: [(0, '22.530')] | |
| [2023-02-25 14:29:12,797][00869] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3735.0). Total num frames: 4001792. Throughput: 0: 872.2. Samples: 1000610. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:29:12,801][00869] Avg episode reward: [(0, '23.037')] | |
| [2023-02-25 14:29:13,366][10866] Stopping Batcher_0... | |
| [2023-02-25 14:29:13,367][10866] Loop batcher_evt_loop terminating... | |
| [2023-02-25 14:29:13,368][00869] Component Batcher_0 stopped! | |
| [2023-02-25 14:29:13,375][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-25 14:29:13,462][10880] Weights refcount: 2 0 | |
| [2023-02-25 14:29:13,467][10880] Stopping InferenceWorker_p0-w0... | |
| [2023-02-25 14:29:13,470][00869] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-25 14:29:13,472][10880] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-25 14:29:13,505][10886] Stopping RolloutWorker_w5... | |
| [2023-02-25 14:29:13,509][10886] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-25 14:29:13,518][10884] Stopping RolloutWorker_w3... | |
| [2023-02-25 14:29:13,519][10884] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-25 14:29:13,511][00869] Component RolloutWorker_w5 stopped! | |
| [2023-02-25 14:29:13,520][00869] Component RolloutWorker_w3 stopped! | |
| [2023-02-25 14:29:13,524][00869] Component RolloutWorker_w1 stopped! | |
| [2023-02-25 14:29:13,524][10882] Stopping RolloutWorker_w1... | |
| [2023-02-25 14:29:13,529][10882] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-25 14:29:13,538][00869] Component RolloutWorker_w6 stopped! | |
| [2023-02-25 14:29:13,536][10887] Stopping RolloutWorker_w6... | |
| [2023-02-25 14:29:13,557][10887] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-25 14:29:13,554][00869] Component RolloutWorker_w7 stopped! | |
| [2023-02-25 14:29:13,560][10888] Stopping RolloutWorker_w7... | |
| [2023-02-25 14:29:13,567][00869] Component RolloutWorker_w0 stopped! | |
| [2023-02-25 14:29:13,572][10888] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-25 14:29:13,581][10883] Stopping RolloutWorker_w2... | |
| [2023-02-25 14:29:13,568][10881] Stopping RolloutWorker_w0... | |
| [2023-02-25 14:29:13,581][10883] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-25 14:29:13,580][00869] Component RolloutWorker_w2 stopped! | |
| [2023-02-25 14:29:13,590][10881] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-25 14:29:13,620][10866] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000828_3391488.pth | |
| [2023-02-25 14:29:13,628][10885] Stopping RolloutWorker_w4... | |
| [2023-02-25 14:29:13,628][10885] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-25 14:29:13,627][00869] Component RolloutWorker_w4 stopped! | |
| [2023-02-25 14:29:13,641][10866] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-25 14:29:13,976][00869] Component LearnerWorker_p0 stopped! | |
| [2023-02-25 14:29:13,981][00869] Waiting for process learner_proc0 to stop... | |
| [2023-02-25 14:29:13,986][10866] Stopping LearnerWorker_p0... | |
| [2023-02-25 14:29:13,987][10866] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-25 14:29:16,286][00869] Waiting for process inference_proc0-0 to join... | |
| [2023-02-25 14:29:16,637][00869] Waiting for process rollout_proc0 to join... | |
| [2023-02-25 14:29:17,176][00869] Waiting for process rollout_proc1 to join... | |
| [2023-02-25 14:29:17,179][00869] Waiting for process rollout_proc2 to join... | |
| [2023-02-25 14:29:17,181][00869] Waiting for process rollout_proc3 to join... | |
| [2023-02-25 14:29:17,185][00869] Waiting for process rollout_proc4 to join... | |
| [2023-02-25 14:29:17,186][00869] Waiting for process rollout_proc5 to join... | |
| [2023-02-25 14:29:17,187][00869] Waiting for process rollout_proc6 to join... | |
| [2023-02-25 14:29:17,188][00869] Waiting for process rollout_proc7 to join... | |
| [2023-02-25 14:29:17,193][00869] Batcher 0 profile tree view: | |
| batching: 25.8107, releasing_batches: 0.0260 | |
| [2023-02-25 14:29:17,195][00869] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0126 | |
| wait_policy_total: 539.3566 | |
| update_model: 7.7651 | |
| weight_update: 0.0026 | |
| one_step: 0.0023 | |
| handle_policy_step: 505.1338 | |
| deserialize: 14.6392, stack: 2.9281, obs_to_device_normalize: 114.0070, forward: 239.9325, send_messages: 25.9876 | |
| prepare_outputs: 82.4325 | |
| to_cpu: 51.0361 | |
| [2023-02-25 14:29:17,196][00869] Learner 0 profile tree view: | |
| misc: 0.0063, prepare_batch: 15.5831 | |
| train: 75.1513 | |
| epoch_init: 0.0098, minibatch_init: 0.0169, losses_postprocess: 0.5101, kl_divergence: 0.5375, after_optimizer: 33.3234 | |
| calculate_losses: 26.7133 | |
| losses_init: 0.0033, forward_head: 1.6275, bptt_initial: 17.7678, tail: 1.0881, advantages_returns: 0.2904, losses: 3.3937 | |
| bptt: 2.2422 | |
| bptt_forward_core: 2.1779 | |
| update: 13.4551 | |
| clip: 1.3399 | |
| [2023-02-25 14:29:17,199][00869] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.2869, enqueue_policy_requests: 148.5227, env_step: 818.1197, overhead: 20.8435, complete_rollouts: 7.0061 | |
| save_policy_outputs: 20.0368 | |
| split_output_tensors: 9.7787 | |
| [2023-02-25 14:29:17,200][00869] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3380, enqueue_policy_requests: 146.1220, env_step: 820.6365, overhead: 20.3354, complete_rollouts: 7.0897 | |
| save_policy_outputs: 20.3658 | |
| split_output_tensors: 9.9400 | |
| [2023-02-25 14:29:17,202][00869] Loop Runner_EvtLoop terminating... | |
| [2023-02-25 14:29:17,204][00869] Runner profile tree view: | |
| main_loop: 1122.0795 | |
| [2023-02-25 14:29:17,206][00869] Collected {0: 4005888}, FPS: 3570.1 | |
| [2023-02-25 14:29:17,324][00869] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-25 14:29:17,326][00869] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-25 14:29:17,330][00869] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-25 14:29:17,333][00869] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-25 14:29:17,336][00869] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-25 14:29:17,337][00869] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-25 14:29:17,341][00869] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-25 14:29:17,342][00869] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-25 14:29:17,344][00869] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-25 14:29:17,346][00869] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-25 14:29:17,348][00869] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-25 14:29:17,350][00869] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-25 14:29:17,351][00869] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-25 14:29:17,354][00869] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-25 14:29:17,355][00869] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-25 14:29:17,381][00869] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:29:17,383][00869] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:29:17,385][00869] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:29:17,406][00869] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:29:18,077][00869] Conv encoder output size: 512 | |
| [2023-02-25 14:29:18,079][00869] Policy head output size: 512 | |
| [2023-02-25 14:29:21,060][00869] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-25 14:29:22,683][00869] Num frames 100... | |
| [2023-02-25 14:29:22,803][00869] Num frames 200... | |
| [2023-02-25 14:29:22,917][00869] Num frames 300... | |
| [2023-02-25 14:29:23,039][00869] Num frames 400... | |
| [2023-02-25 14:29:23,158][00869] Num frames 500... | |
| [2023-02-25 14:29:23,290][00869] Num frames 600... | |
| [2023-02-25 14:29:23,416][00869] Num frames 700... | |
| [2023-02-25 14:29:23,535][00869] Num frames 800... | |
| [2023-02-25 14:29:23,624][00869] Avg episode rewards: #0: 19.230, true rewards: #0: 8.230 | |
| [2023-02-25 14:29:23,626][00869] Avg episode reward: 19.230, avg true_objective: 8.230 | |
| [2023-02-25 14:29:23,719][00869] Num frames 900... | |
| [2023-02-25 14:29:23,837][00869] Num frames 1000... | |
| [2023-02-25 14:29:23,980][00869] Avg episode rewards: #0: 10.895, true rewards: #0: 5.395 | |
| [2023-02-25 14:29:23,982][00869] Avg episode reward: 10.895, avg true_objective: 5.395 | |
| [2023-02-25 14:29:24,012][00869] Num frames 1100... | |
| [2023-02-25 14:29:24,140][00869] Num frames 1200... | |
| [2023-02-25 14:29:24,256][00869] Num frames 1300... | |
| [2023-02-25 14:29:24,366][00869] Num frames 1400... | |
| [2023-02-25 14:29:24,480][00869] Num frames 1500... | |
| [2023-02-25 14:29:24,597][00869] Num frames 1600... | |
| [2023-02-25 14:29:24,707][00869] Num frames 1700... | |
| [2023-02-25 14:29:24,825][00869] Num frames 1800... | |
| [2023-02-25 14:29:24,937][00869] Num frames 1900... | |
| [2023-02-25 14:29:25,059][00869] Num frames 2000... | |
| [2023-02-25 14:29:25,124][00869] Avg episode rewards: #0: 13.357, true rewards: #0: 6.690 | |
| [2023-02-25 14:29:25,125][00869] Avg episode reward: 13.357, avg true_objective: 6.690 | |
| [2023-02-25 14:29:25,233][00869] Num frames 2100... | |
| [2023-02-25 14:29:25,349][00869] Num frames 2200... | |
| [2023-02-25 14:29:25,467][00869] Num frames 2300... | |
| [2023-02-25 14:29:25,624][00869] Avg episode rewards: #0: 10.978, true rewards: #0: 5.977 | |
| [2023-02-25 14:29:25,627][00869] Avg episode reward: 10.978, avg true_objective: 5.977 | |
| [2023-02-25 14:29:25,640][00869] Num frames 2400... | |
| [2023-02-25 14:29:25,758][00869] Num frames 2500... | |
| [2023-02-25 14:29:25,873][00869] Num frames 2600... | |
| [2023-02-25 14:29:25,995][00869] Num frames 2700... | |
| [2023-02-25 14:29:26,115][00869] Num frames 2800... | |
| [2023-02-25 14:29:26,231][00869] Num frames 2900... | |
| [2023-02-25 14:29:26,355][00869] Num frames 3000... | |
| [2023-02-25 14:29:26,466][00869] Num frames 3100... | |
| [2023-02-25 14:29:26,580][00869] Num frames 3200... | |
| [2023-02-25 14:29:26,697][00869] Num frames 3300... | |
| [2023-02-25 14:29:26,810][00869] Num frames 3400... | |
| [2023-02-25 14:29:26,893][00869] Avg episode rewards: #0: 13.230, true rewards: #0: 6.830 | |
| [2023-02-25 14:29:26,895][00869] Avg episode reward: 13.230, avg true_objective: 6.830 | |
| [2023-02-25 14:29:26,997][00869] Num frames 3500... | |
| [2023-02-25 14:29:27,128][00869] Num frames 3600... | |
| [2023-02-25 14:29:27,243][00869] Num frames 3700... | |
| [2023-02-25 14:29:27,364][00869] Num frames 3800... | |
| [2023-02-25 14:29:27,477][00869] Num frames 3900... | |
| [2023-02-25 14:29:27,604][00869] Num frames 4000... | |
| [2023-02-25 14:29:27,716][00869] Num frames 4100... | |
| [2023-02-25 14:29:27,836][00869] Num frames 4200... | |
| [2023-02-25 14:29:27,950][00869] Num frames 4300... | |
| [2023-02-25 14:29:28,072][00869] Num frames 4400... | |
| [2023-02-25 14:29:28,195][00869] Num frames 4500... | |
| [2023-02-25 14:29:28,315][00869] Num frames 4600... | |
| [2023-02-25 14:29:28,427][00869] Num frames 4700... | |
| [2023-02-25 14:29:28,550][00869] Num frames 4800... | |
| [2023-02-25 14:29:28,668][00869] Num frames 4900... | |
| [2023-02-25 14:29:28,798][00869] Num frames 5000... | |
| [2023-02-25 14:29:28,861][00869] Avg episode rewards: #0: 17.340, true rewards: #0: 8.340 | |
| [2023-02-25 14:29:28,863][00869] Avg episode reward: 17.340, avg true_objective: 8.340 | |
| [2023-02-25 14:29:28,985][00869] Num frames 5100... | |
| [2023-02-25 14:29:29,122][00869] Num frames 5200... | |
| [2023-02-25 14:29:29,252][00869] Num frames 5300... | |
| [2023-02-25 14:29:29,371][00869] Num frames 5400... | |
| [2023-02-25 14:29:29,490][00869] Num frames 5500... | |
| [2023-02-25 14:29:29,611][00869] Num frames 5600... | |
| [2023-02-25 14:29:29,725][00869] Num frames 5700... | |
| [2023-02-25 14:29:29,843][00869] Num frames 5800... | |
| [2023-02-25 14:29:29,954][00869] Num frames 5900... | |
| [2023-02-25 14:29:30,072][00869] Num frames 6000... | |
| [2023-02-25 14:29:30,190][00869] Num frames 6100... | |
| [2023-02-25 14:29:30,309][00869] Num frames 6200... | |
| [2023-02-25 14:29:30,421][00869] Num frames 6300... | |
| [2023-02-25 14:29:30,565][00869] Avg episode rewards: #0: 19.533, true rewards: #0: 9.104 | |
| [2023-02-25 14:29:30,570][00869] Avg episode reward: 19.533, avg true_objective: 9.104 | |
| [2023-02-25 14:29:30,603][00869] Num frames 6400... | |
| [2023-02-25 14:29:30,717][00869] Num frames 6500... | |
| [2023-02-25 14:29:30,835][00869] Num frames 6600... | |
| [2023-02-25 14:29:30,949][00869] Num frames 6700... | |
| [2023-02-25 14:29:31,064][00869] Num frames 6800... | |
| [2023-02-25 14:29:31,190][00869] Num frames 6900... | |
| [2023-02-25 14:29:31,304][00869] Num frames 7000... | |
| [2023-02-25 14:29:31,427][00869] Num frames 7100... | |
| [2023-02-25 14:29:31,545][00869] Num frames 7200... | |
| [2023-02-25 14:29:31,659][00869] Num frames 7300... | |
| [2023-02-25 14:29:31,778][00869] Num frames 7400... | |
| [2023-02-25 14:29:31,895][00869] Num frames 7500... | |
| [2023-02-25 14:29:32,008][00869] Num frames 7600... | |
| [2023-02-25 14:29:32,126][00869] Num frames 7700... | |
| [2023-02-25 14:29:32,246][00869] Num frames 7800... | |
| [2023-02-25 14:29:32,378][00869] Num frames 7900... | |
| [2023-02-25 14:29:32,539][00869] Num frames 8000... | |
| [2023-02-25 14:29:32,703][00869] Num frames 8100... | |
| [2023-02-25 14:29:32,865][00869] Num frames 8200... | |
| [2023-02-25 14:29:33,038][00869] Num frames 8300... | |
| [2023-02-25 14:29:33,201][00869] Num frames 8400... | |
| [2023-02-25 14:29:33,391][00869] Avg episode rewards: #0: 23.716, true rewards: #0: 10.591 | |
| [2023-02-25 14:29:33,394][00869] Avg episode reward: 23.716, avg true_objective: 10.591 | |
| [2023-02-25 14:29:33,446][00869] Num frames 8500... | |
| [2023-02-25 14:29:33,612][00869] Num frames 8600... | |
| [2023-02-25 14:29:33,769][00869] Num frames 8700... | |
| [2023-02-25 14:29:33,933][00869] Num frames 8800... | |
| [2023-02-25 14:29:34,103][00869] Num frames 8900... | |
| [2023-02-25 14:29:34,290][00869] Num frames 9000... | |
| [2023-02-25 14:29:34,452][00869] Num frames 9100... | |
| [2023-02-25 14:29:34,623][00869] Num frames 9200... | |
| [2023-02-25 14:29:34,792][00869] Num frames 9300... | |
| [2023-02-25 14:29:34,952][00869] Num frames 9400... | |
| [2023-02-25 14:29:35,131][00869] Num frames 9500... | |
| [2023-02-25 14:29:35,289][00869] Num frames 9600... | |
| [2023-02-25 14:29:35,373][00869] Avg episode rewards: #0: 23.908, true rewards: #0: 10.686 | |
| [2023-02-25 14:29:35,376][00869] Avg episode reward: 23.908, avg true_objective: 10.686 | |
| [2023-02-25 14:29:35,507][00869] Num frames 9700... | |
| [2023-02-25 14:29:35,674][00869] Num frames 9800... | |
| [2023-02-25 14:29:35,832][00869] Num frames 9900... | |
| [2023-02-25 14:29:35,955][00869] Num frames 10000... | |
| [2023-02-25 14:29:36,069][00869] Num frames 10100... | |
| [2023-02-25 14:29:36,198][00869] Num frames 10200... | |
| [2023-02-25 14:29:36,310][00869] Num frames 10300... | |
| [2023-02-25 14:29:36,435][00869] Num frames 10400... | |
| [2023-02-25 14:29:36,548][00869] Num frames 10500... | |
| [2023-02-25 14:29:36,666][00869] Num frames 10600... | |
| [2023-02-25 14:29:36,784][00869] Num frames 10700... | |
| [2023-02-25 14:29:36,897][00869] Num frames 10800... | |
| [2023-02-25 14:29:37,024][00869] Num frames 10900... | |
| [2023-02-25 14:29:37,143][00869] Avg episode rewards: #0: 24.550, true rewards: #0: 10.950 | |
| [2023-02-25 14:29:37,145][00869] Avg episode reward: 24.550, avg true_objective: 10.950 | |
| [2023-02-25 14:30:40,273][00869] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-25 14:31:07,217][00869] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-25 14:31:07,219][00869] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-25 14:31:07,222][00869] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-25 14:31:07,223][00869] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-25 14:31:07,226][00869] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-25 14:31:07,228][00869] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-25 14:31:07,229][00869] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-25 14:31:07,232][00869] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-25 14:31:07,233][00869] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-25 14:31:07,234][00869] Adding new argument 'hf_repository'='chist/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-25 14:31:07,235][00869] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-25 14:31:07,236][00869] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-25 14:31:07,238][00869] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-25 14:31:07,239][00869] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-25 14:31:07,241][00869] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-25 14:31:07,268][00869] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:31:07,270][00869] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:31:07,283][00869] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:31:07,319][00869] Conv encoder output size: 512 | |
| [2023-02-25 14:31:07,320][00869] Policy head output size: 512 | |
| [2023-02-25 14:31:07,340][00869] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-25 14:31:07,801][00869] Num frames 100... | |
| [2023-02-25 14:31:07,922][00869] Num frames 200... | |
| [2023-02-25 14:31:08,044][00869] Num frames 300... | |
| [2023-02-25 14:31:08,154][00869] Num frames 400... | |
| [2023-02-25 14:31:08,272][00869] Num frames 500... | |
| [2023-02-25 14:31:08,423][00869] Num frames 600... | |
| [2023-02-25 14:31:08,593][00869] Num frames 700... | |
| [2023-02-25 14:31:08,755][00869] Num frames 800... | |
| [2023-02-25 14:31:08,913][00869] Num frames 900... | |
| [2023-02-25 14:31:09,118][00869] Avg episode rewards: #0: 21.980, true rewards: #0: 9.980 | |
| [2023-02-25 14:31:09,122][00869] Avg episode reward: 21.980, avg true_objective: 9.980 | |
| [2023-02-25 14:31:09,129][00869] Num frames 1000... | |
| [2023-02-25 14:31:09,285][00869] Num frames 1100... | |
| [2023-02-25 14:31:09,455][00869] Num frames 1200... | |
| [2023-02-25 14:31:09,619][00869] Num frames 1300... | |
| [2023-02-25 14:31:09,775][00869] Num frames 1400... | |
| [2023-02-25 14:31:09,935][00869] Num frames 1500... | |
| [2023-02-25 14:31:10,097][00869] Num frames 1600... | |
| [2023-02-25 14:31:10,262][00869] Avg episode rewards: #0: 16.850, true rewards: #0: 8.350 | |
| [2023-02-25 14:31:10,265][00869] Avg episode reward: 16.850, avg true_objective: 8.350 | |
| [2023-02-25 14:31:10,321][00869] Num frames 1700... | |
| [2023-02-25 14:31:10,476][00869] Num frames 1800... | |
| [2023-02-25 14:31:10,639][00869] Num frames 1900... | |
| [2023-02-25 14:31:10,807][00869] Num frames 2000... | |
| [2023-02-25 14:31:10,968][00869] Num frames 2100... | |
| [2023-02-25 14:31:11,169][00869] Avg episode rewards: #0: 13.607, true rewards: #0: 7.273 | |
| [2023-02-25 14:31:11,171][00869] Avg episode reward: 13.607, avg true_objective: 7.273 | |
| [2023-02-25 14:31:11,204][00869] Num frames 2200... | |
| [2023-02-25 14:31:11,370][00869] Num frames 2300... | |
| [2023-02-25 14:31:11,534][00869] Num frames 2400... | |
| [2023-02-25 14:31:11,703][00869] Num frames 2500... | |
| [2023-02-25 14:31:11,854][00869] Num frames 2600... | |
| [2023-02-25 14:31:11,967][00869] Num frames 2700... | |
| [2023-02-25 14:31:12,086][00869] Num frames 2800... | |
| [2023-02-25 14:31:12,193][00869] Num frames 2900... | |
| [2023-02-25 14:31:12,310][00869] Avg episode rewards: #0: 14.625, true rewards: #0: 7.375 | |
| [2023-02-25 14:31:12,312][00869] Avg episode reward: 14.625, avg true_objective: 7.375 | |
| [2023-02-25 14:31:12,369][00869] Num frames 3000... | |
| [2023-02-25 14:31:12,483][00869] Num frames 3100... | |
| [2023-02-25 14:31:12,599][00869] Num frames 3200... | |
| [2023-02-25 14:31:12,717][00869] Num frames 3300... | |
| [2023-02-25 14:31:12,876][00869] Avg episode rewards: #0: 12.796, true rewards: #0: 6.796 | |
| [2023-02-25 14:31:12,881][00869] Avg episode reward: 12.796, avg true_objective: 6.796 | |
| [2023-02-25 14:31:12,886][00869] Num frames 3400... | |
| [2023-02-25 14:31:13,000][00869] Num frames 3500... | |
| [2023-02-25 14:31:13,116][00869] Num frames 3600... | |
| [2023-02-25 14:31:13,226][00869] Num frames 3700... | |
| [2023-02-25 14:31:13,342][00869] Num frames 3800... | |
| [2023-02-25 14:31:13,451][00869] Num frames 3900... | |
| [2023-02-25 14:31:13,566][00869] Num frames 4000... | |
| [2023-02-25 14:31:13,685][00869] Num frames 4100... | |
| [2023-02-25 14:31:13,797][00869] Num frames 4200... | |
| [2023-02-25 14:31:13,961][00869] Avg episode rewards: #0: 13.490, true rewards: #0: 7.157 | |
| [2023-02-25 14:31:13,963][00869] Avg episode reward: 13.490, avg true_objective: 7.157 | |
| [2023-02-25 14:31:13,975][00869] Num frames 4300... | |
| [2023-02-25 14:31:14,095][00869] Num frames 4400... | |
| [2023-02-25 14:31:14,208][00869] Num frames 4500... | |
| [2023-02-25 14:31:14,329][00869] Num frames 4600... | |
| [2023-02-25 14:31:14,443][00869] Num frames 4700... | |
| [2023-02-25 14:31:14,562][00869] Num frames 4800... | |
| [2023-02-25 14:31:14,694][00869] Num frames 4900... | |
| [2023-02-25 14:31:14,817][00869] Num frames 5000... | |
| [2023-02-25 14:31:14,937][00869] Num frames 5100... | |
| [2023-02-25 14:31:15,060][00869] Num frames 5200... | |
| [2023-02-25 14:31:15,174][00869] Num frames 5300... | |
| [2023-02-25 14:31:15,296][00869] Num frames 5400... | |
| [2023-02-25 14:31:15,410][00869] Num frames 5500... | |
| [2023-02-25 14:31:15,531][00869] Num frames 5600... | |
| [2023-02-25 14:31:15,657][00869] Num frames 5700... | |
| [2023-02-25 14:31:15,769][00869] Avg episode rewards: #0: 16.777, true rewards: #0: 8.206 | |
| [2023-02-25 14:31:15,770][00869] Avg episode reward: 16.777, avg true_objective: 8.206 | |
| [2023-02-25 14:31:15,837][00869] Num frames 5800... | |
| [2023-02-25 14:31:15,954][00869] Num frames 5900... | |
| [2023-02-25 14:31:16,070][00869] Num frames 6000... | |
| [2023-02-25 14:31:16,187][00869] Num frames 6100... | |
| [2023-02-25 14:31:16,301][00869] Num frames 6200... | |
| [2023-02-25 14:31:16,420][00869] Num frames 6300... | |
| [2023-02-25 14:31:16,532][00869] Num frames 6400... | |
| [2023-02-25 14:31:16,657][00869] Num frames 6500... | |
| [2023-02-25 14:31:16,772][00869] Avg episode rewards: #0: 16.941, true rewards: #0: 8.191 | |
| [2023-02-25 14:31:16,774][00869] Avg episode reward: 16.941, avg true_objective: 8.191 | |
| [2023-02-25 14:31:16,845][00869] Num frames 6600... | |
| [2023-02-25 14:31:16,963][00869] Num frames 6700... | |
| [2023-02-25 14:31:17,077][00869] Num frames 6800... | |
| [2023-02-25 14:31:17,193][00869] Num frames 6900... | |
| [2023-02-25 14:31:17,304][00869] Num frames 7000... | |
| [2023-02-25 14:31:17,419][00869] Num frames 7100... | |
| [2023-02-25 14:31:17,510][00869] Avg episode rewards: #0: 16.143, true rewards: #0: 7.921 | |
| [2023-02-25 14:31:17,513][00869] Avg episode reward: 16.143, avg true_objective: 7.921 | |
| [2023-02-25 14:31:17,591][00869] Num frames 7200... | |
| [2023-02-25 14:31:17,712][00869] Num frames 7300... | |
| [2023-02-25 14:31:17,827][00869] Num frames 7400... | |
| [2023-02-25 14:31:17,943][00869] Num frames 7500... | |
| [2023-02-25 14:31:18,060][00869] Num frames 7600... | |
| [2023-02-25 14:31:18,173][00869] Num frames 7700... | |
| [2023-02-25 14:31:18,287][00869] Num frames 7800... | |
| [2023-02-25 14:31:18,408][00869] Num frames 7900... | |
| [2023-02-25 14:31:18,518][00869] Num frames 8000... | |
| [2023-02-25 14:31:18,644][00869] Num frames 8100... | |
| [2023-02-25 14:31:18,764][00869] Num frames 8200... | |
| [2023-02-25 14:31:18,883][00869] Num frames 8300... | |
| [2023-02-25 14:31:19,004][00869] Num frames 8400... | |
| [2023-02-25 14:31:19,123][00869] Num frames 8500... | |
| [2023-02-25 14:31:19,241][00869] Num frames 8600... | |
| [2023-02-25 14:31:19,358][00869] Num frames 8700... | |
| [2023-02-25 14:31:19,482][00869] Num frames 8800... | |
| [2023-02-25 14:31:19,601][00869] Num frames 8900... | |
| [2023-02-25 14:31:19,731][00869] Num frames 9000... | |
| [2023-02-25 14:31:19,845][00869] Num frames 9100... | |
| [2023-02-25 14:31:19,964][00869] Num frames 9200... | |
| [2023-02-25 14:31:20,054][00869] Avg episode rewards: #0: 20.329, true rewards: #0: 9.229 | |
| [2023-02-25 14:31:20,056][00869] Avg episode reward: 20.329, avg true_objective: 9.229 | |
| [2023-02-25 14:32:13,809][00869] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-25 14:32:17,582][00869] The model has been pushed to https://huggingface.co/chist/rl_course_vizdoom_health_gathering_supreme | |
| [2023-02-25 14:34:35,570][00869] Environment doom_basic already registered, overwriting... | |
| [2023-02-25 14:34:35,573][00869] Environment doom_two_colors_easy already registered, overwriting... | |
| [2023-02-25 14:34:35,575][00869] Environment doom_two_colors_hard already registered, overwriting... | |
| [2023-02-25 14:34:35,577][00869] Environment doom_dm already registered, overwriting... | |
| [2023-02-25 14:34:35,578][00869] Environment doom_dwango5 already registered, overwriting... | |
| [2023-02-25 14:34:35,579][00869] Environment doom_my_way_home_flat_actions already registered, overwriting... | |
| [2023-02-25 14:34:35,581][00869] Environment doom_defend_the_center_flat_actions already registered, overwriting... | |
| [2023-02-25 14:34:35,582][00869] Environment doom_my_way_home already registered, overwriting... | |
| [2023-02-25 14:34:35,584][00869] Environment doom_deadly_corridor already registered, overwriting... | |
| [2023-02-25 14:34:35,586][00869] Environment doom_defend_the_center already registered, overwriting... | |
| [2023-02-25 14:34:35,587][00869] Environment doom_defend_the_line already registered, overwriting... | |
| [2023-02-25 14:34:35,589][00869] Environment doom_health_gathering already registered, overwriting... | |
| [2023-02-25 14:34:35,590][00869] Environment doom_health_gathering_supreme already registered, overwriting... | |
| [2023-02-25 14:34:35,592][00869] Environment doom_battle already registered, overwriting... | |
| [2023-02-25 14:34:35,593][00869] Environment doom_battle2 already registered, overwriting... | |
| [2023-02-25 14:34:35,595][00869] Environment doom_duel_bots already registered, overwriting... | |
| [2023-02-25 14:34:35,597][00869] Environment doom_deathmatch_bots already registered, overwriting... | |
| [2023-02-25 14:34:35,598][00869] Environment doom_duel already registered, overwriting... | |
| [2023-02-25 14:34:35,600][00869] Environment doom_deathmatch_full already registered, overwriting... | |
| [2023-02-25 14:34:35,601][00869] Environment doom_benchmark already registered, overwriting... | |
| [2023-02-25 14:34:35,603][00869] register_encoder_factory: <function make_vizdoom_encoder at 0x7f1109adc5e0> | |
| [2023-02-25 14:34:35,637][00869] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-25 14:34:35,638][00869] Overriding arg 'train_for_env_steps' with value 8000000 passed from command line | |
| [2023-02-25 14:34:35,652][00869] Experiment dir /content/train_dir/default_experiment already exists! | |
| [2023-02-25 14:34:35,653][00869] Resuming existing experiment from /content/train_dir/default_experiment... | |
| [2023-02-25 14:34:35,654][00869] Weights and Biases integration disabled | |
| [2023-02-25 14:34:35,658][00869] Environment var CUDA_VISIBLE_DEVICES is 0 | |
| [2023-02-25 14:34:37,836][00869] Starting experiment with the following configuration: | |
| help=False | |
| algo=APPO | |
| env=doom_health_gathering_supreme | |
| experiment=default_experiment | |
| train_dir=/content/train_dir | |
| restart_behavior=resume | |
| device=gpu | |
| seed=None | |
| num_policies=1 | |
| async_rl=True | |
| serial_mode=False | |
| batched_sampling=False | |
| num_batches_to_accumulate=2 | |
| worker_num_splits=2 | |
| policy_workers_per_policy=1 | |
| max_policy_lag=1000 | |
| num_workers=8 | |
| num_envs_per_worker=4 | |
| batch_size=1024 | |
| num_batches_per_epoch=1 | |
| num_epochs=1 | |
| rollout=32 | |
| recurrence=32 | |
| shuffle_minibatches=False | |
| gamma=0.99 | |
| reward_scale=1.0 | |
| reward_clip=1000.0 | |
| value_bootstrap=False | |
| normalize_returns=True | |
| exploration_loss_coeff=0.001 | |
| value_loss_coeff=0.5 | |
| kl_loss_coeff=0.0 | |
| exploration_loss=symmetric_kl | |
| gae_lambda=0.95 | |
| ppo_clip_ratio=0.1 | |
| ppo_clip_value=0.2 | |
| with_vtrace=False | |
| vtrace_rho=1.0 | |
| vtrace_c=1.0 | |
| optimizer=adam | |
| adam_eps=1e-06 | |
| adam_beta1=0.9 | |
| adam_beta2=0.999 | |
| max_grad_norm=4.0 | |
| learning_rate=0.0001 | |
| lr_schedule=constant | |
| lr_schedule_kl_threshold=0.008 | |
| lr_adaptive_min=1e-06 | |
| lr_adaptive_max=0.01 | |
| obs_subtract_mean=0.0 | |
| obs_scale=255.0 | |
| normalize_input=True | |
| normalize_input_keys=None | |
| decorrelate_experience_max_seconds=0 | |
| decorrelate_envs_on_one_worker=True | |
| actor_worker_gpus=[] | |
| set_workers_cpu_affinity=True | |
| force_envs_single_thread=False | |
| default_niceness=0 | |
| log_to_file=True | |
| experiment_summaries_interval=10 | |
| flush_summaries_interval=30 | |
| stats_avg=100 | |
| summaries_use_frameskip=True | |
| heartbeat_interval=20 | |
| heartbeat_reporting_interval=600 | |
| train_for_env_steps=8000000 | |
| train_for_seconds=10000000000 | |
| save_every_sec=120 | |
| keep_checkpoints=2 | |
| load_checkpoint_kind=latest | |
| save_milestones_sec=-1 | |
| save_best_every_sec=5 | |
| save_best_metric=reward | |
| save_best_after=100000 | |
| benchmark=False | |
| encoder_mlp_layers=[512, 512] | |
| encoder_conv_architecture=convnet_simple | |
| encoder_conv_mlp_layers=[512] | |
| use_rnn=True | |
| rnn_size=512 | |
| rnn_type=gru | |
| rnn_num_layers=1 | |
| decoder_mlp_layers=[] | |
| nonlinearity=elu | |
| policy_initialization=orthogonal | |
| policy_init_gain=1.0 | |
| actor_critic_share_weights=True | |
| adaptive_stddev=True | |
| continuous_tanh_scale=0.0 | |
| initial_stddev=1.0 | |
| use_env_info_cache=False | |
| env_gpu_actions=False | |
| env_gpu_observations=True | |
| env_frameskip=4 | |
| env_framestack=1 | |
| pixel_format=CHW | |
| use_record_episode_statistics=False | |
| with_wandb=False | |
| wandb_user=None | |
| wandb_project=sample_factory | |
| wandb_group=None | |
| wandb_job_type=SF | |
| wandb_tags=[] | |
| with_pbt=False | |
| pbt_mix_policies_in_one_env=True | |
| pbt_period_env_steps=5000000 | |
| pbt_start_mutation=20000000 | |
| pbt_replace_fraction=0.3 | |
| pbt_mutation_rate=0.15 | |
| pbt_replace_reward_gap=0.1 | |
| pbt_replace_reward_gap_absolute=1e-06 | |
| pbt_optimize_gamma=False | |
| pbt_target_objective=true_objective | |
| pbt_perturb_min=1.1 | |
| pbt_perturb_max=1.5 | |
| num_agents=-1 | |
| num_humans=0 | |
| num_bots=-1 | |
| start_bot_difficulty=None | |
| timelimit=None | |
| res_w=128 | |
| res_h=72 | |
| wide_aspect_ratio=False | |
| eval_env_frameskip=1 | |
| fps=35 | |
| command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000 | |
| cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000} | |
| git_hash=unknown | |
| git_repo_name=not a git repository | |
| [2023-02-25 14:34:37,839][00869] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-25 14:34:37,842][00869] Rollout worker 0 uses device cpu | |
| [2023-02-25 14:34:37,844][00869] Rollout worker 1 uses device cpu | |
| [2023-02-25 14:34:37,845][00869] Rollout worker 2 uses device cpu | |
| [2023-02-25 14:34:37,848][00869] Rollout worker 3 uses device cpu | |
| [2023-02-25 14:34:37,850][00869] Rollout worker 4 uses device cpu | |
| [2023-02-25 14:34:37,851][00869] Rollout worker 5 uses device cpu | |
| [2023-02-25 14:34:37,853][00869] Rollout worker 6 uses device cpu | |
| [2023-02-25 14:34:37,854][00869] Rollout worker 7 uses device cpu | |
| [2023-02-25 14:34:38,005][00869] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:34:38,008][00869] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-25 14:34:38,051][00869] Starting all processes... | |
| [2023-02-25 14:34:38,053][00869] Starting process learner_proc0 | |
| [2023-02-25 14:34:38,245][00869] Starting all processes... | |
| [2023-02-25 14:34:38,259][00869] Starting process inference_proc0-0 | |
| [2023-02-25 14:34:38,262][00869] Starting process rollout_proc0 | |
| [2023-02-25 14:34:38,262][00869] Starting process rollout_proc1 | |
| [2023-02-25 14:34:38,262][00869] Starting process rollout_proc2 | |
| [2023-02-25 14:34:38,262][00869] Starting process rollout_proc3 | |
| [2023-02-25 14:34:38,363][00869] Starting process rollout_proc4 | |
| [2023-02-25 14:34:38,373][00869] Starting process rollout_proc5 | |
| [2023-02-25 14:34:38,373][00869] Starting process rollout_proc6 | |
| [2023-02-25 14:34:38,377][00869] Starting process rollout_proc7 | |
| [2023-02-25 14:34:49,144][20465] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:34:49,151][20465] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-25 14:34:49,201][20465] Num visible devices: 1 | |
| [2023-02-25 14:34:49,237][20465] Starting seed is not provided | |
| [2023-02-25 14:34:49,238][20465] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:34:49,238][20465] Initializing actor-critic model on device cuda:0 | |
| [2023-02-25 14:34:49,239][20465] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:34:49,240][20465] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:34:49,325][20465] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:34:50,028][20479] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:34:50,035][20479] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-25 14:34:50,115][20479] Num visible devices: 1 | |
| [2023-02-25 14:34:50,121][20480] Worker 0 uses CPU cores [0] | |
| [2023-02-25 14:34:50,128][20481] Worker 1 uses CPU cores [1] | |
| [2023-02-25 14:34:50,254][20465] Conv encoder output size: 512 | |
| [2023-02-25 14:34:50,254][20465] Policy head output size: 512 | |
| [2023-02-25 14:34:50,348][20465] Created Actor Critic model with architecture: | |
| [2023-02-25 14:34:50,349][20465] 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) | |
| ) | |
| ) | |
| [2023-02-25 14:34:50,638][20490] Worker 3 uses CPU cores [1] | |
| [2023-02-25 14:34:50,898][20489] Worker 2 uses CPU cores [0] | |
| [2023-02-25 14:34:50,933][20492] Worker 5 uses CPU cores [1] | |
| [2023-02-25 14:34:51,075][20506] Worker 7 uses CPU cores [1] | |
| [2023-02-25 14:34:51,151][20498] Worker 6 uses CPU cores [0] | |
| [2023-02-25 14:34:51,190][20500] Worker 4 uses CPU cores [0] | |
| [2023-02-25 14:34:54,317][20465] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-25 14:34:54,318][20465] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-25 14:34:54,362][20465] Loading model from checkpoint | |
| [2023-02-25 14:34:54,370][20465] Loaded experiment state at self.train_step=978, self.env_steps=4005888 | |
| [2023-02-25 14:34:54,371][20465] Initialized policy 0 weights for model version 978 | |
| [2023-02-25 14:34:54,375][20465] LearnerWorker_p0 finished initialization! | |
| [2023-02-25 14:34:54,377][20465] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-25 14:34:54,688][20479] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:34:54,690][20479] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:34:54,708][20479] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:34:54,867][20479] Conv encoder output size: 512 | |
| [2023-02-25 14:34:54,868][20479] Policy head output size: 512 | |
| [2023-02-25 14:34:55,658][00869] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-25 14:34:57,308][00869] Inference worker 0-0 is ready! | |
| [2023-02-25 14:34:57,310][00869] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-25 14:34:57,434][20489] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,458][20500] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,468][20481] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,467][20480] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,475][20492] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,477][20506] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,479][20490] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,481][20498] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-25 14:34:57,995][00869] Heartbeat connected on Batcher_0 | |
| [2023-02-25 14:34:58,001][00869] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-25 14:34:58,034][00869] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-25 14:34:58,981][20481] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:58,985][20506] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:58,988][20492] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:58,993][20490] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:58,991][20489] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:59,028][20480] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:59,037][20500] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:34:59,054][20498] Decorrelating experience for 0 frames... | |
| [2023-02-25 14:35:00,045][20489] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,067][20480] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,085][20500] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,211][20490] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,447][20506] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,462][20492] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,549][20481] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:00,658][00869] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-25 14:35:01,395][20492] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:01,459][20481] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:01,627][20489] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:01,687][20480] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:01,778][20500] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:01,919][20498] Decorrelating experience for 32 frames... | |
| [2023-02-25 14:35:02,308][20481] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:02,501][00869] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-25 14:35:02,883][20490] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:03,200][20500] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:03,250][20492] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:03,402][20480] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:03,568][00869] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-25 14:35:03,581][00869] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-25 14:35:03,685][00869] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-25 14:35:03,729][20498] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:04,477][20490] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:04,542][20489] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:04,792][00869] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-25 14:35:04,894][20506] Decorrelating experience for 64 frames... | |
| [2023-02-25 14:35:04,891][00869] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-25 14:35:05,661][00869] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 2.0. Samples: 20. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-25 14:35:05,667][00869] Avg episode reward: [(0, '1.320')] | |
| [2023-02-25 14:35:05,690][20498] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:06,236][00869] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-25 14:35:08,777][20506] Decorrelating experience for 96 frames... | |
| [2023-02-25 14:35:09,841][20465] Signal inference workers to stop experience collection... | |
| [2023-02-25 14:35:09,865][20479] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-25 14:35:09,984][00869] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-25 14:35:10,659][00869] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 158.8. Samples: 2382. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-25 14:35:10,663][00869] Avg episode reward: [(0, '3.216')] | |
| [2023-02-25 14:35:12,762][20465] Signal inference workers to resume experience collection... | |
| [2023-02-25 14:35:12,763][20479] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-25 14:35:15,658][00869] Fps is (10 sec: 1229.1, 60 sec: 614.4, 300 sec: 614.4). Total num frames: 4018176. Throughput: 0: 185.4. Samples: 3708. Policy #0 lag: (min: 1.0, avg: 1.4, max: 2.0) | |
| [2023-02-25 14:35:15,661][00869] Avg episode reward: [(0, '4.400')] | |
| [2023-02-25 14:35:20,658][00869] Fps is (10 sec: 3686.7, 60 sec: 1474.6, 300 sec: 1474.6). Total num frames: 4042752. Throughput: 0: 286.4. Samples: 7160. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:35:20,661][00869] Avg episode reward: [(0, '11.052')] | |
| [2023-02-25 14:35:21,477][20479] Updated weights for policy 0, policy_version 988 (0.0013) | |
| [2023-02-25 14:35:25,658][00869] Fps is (10 sec: 4505.6, 60 sec: 1911.5, 300 sec: 1911.5). Total num frames: 4063232. Throughput: 0: 475.9. Samples: 14278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:35:25,661][00869] Avg episode reward: [(0, '14.947')] | |
| [2023-02-25 14:35:30,659][00869] Fps is (10 sec: 3686.1, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 4079616. Throughput: 0: 541.2. Samples: 18944. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:35:30,664][00869] Avg episode reward: [(0, '16.247')] | |
| [2023-02-25 14:35:33,461][20479] Updated weights for policy 0, policy_version 998 (0.0033) | |
| [2023-02-25 14:35:35,658][00869] Fps is (10 sec: 2867.2, 60 sec: 2150.4, 300 sec: 2150.4). Total num frames: 4091904. Throughput: 0: 526.4. Samples: 21054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:35:35,660][00869] Avg episode reward: [(0, '17.673')] | |
| [2023-02-25 14:35:40,658][00869] Fps is (10 sec: 3686.7, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 4116480. Throughput: 0: 601.0. Samples: 27046. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:35:40,667][00869] Avg episode reward: [(0, '20.318')] | |
| [2023-02-25 14:35:42,892][20479] Updated weights for policy 0, policy_version 1008 (0.0013) | |
| [2023-02-25 14:35:45,660][00869] Fps is (10 sec: 4504.7, 60 sec: 2621.3, 300 sec: 2621.3). Total num frames: 4136960. Throughput: 0: 755.4. Samples: 33994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:35:45,667][00869] Avg episode reward: [(0, '22.429')] | |
| [2023-02-25 14:35:50,658][00869] Fps is (10 sec: 3686.4, 60 sec: 2681.0, 300 sec: 2681.0). Total num frames: 4153344. Throughput: 0: 802.4. Samples: 36128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:35:50,663][00869] Avg episode reward: [(0, '22.712')] | |
| [2023-02-25 14:35:55,619][20479] Updated weights for policy 0, policy_version 1018 (0.0014) | |
| [2023-02-25 14:35:55,658][00869] Fps is (10 sec: 3277.4, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 4169728. Throughput: 0: 843.7. Samples: 40346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:35:55,661][00869] Avg episode reward: [(0, '22.447')] | |
| [2023-02-25 14:36:00,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 4190208. Throughput: 0: 956.2. Samples: 46738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:36:00,666][00869] Avg episode reward: [(0, '21.958')] | |
| [2023-02-25 14:36:04,884][20479] Updated weights for policy 0, policy_version 1028 (0.0015) | |
| [2023-02-25 14:36:05,659][00869] Fps is (10 sec: 4095.9, 60 sec: 3413.5, 300 sec: 2925.7). Total num frames: 4210688. Throughput: 0: 954.6. Samples: 50118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:36:05,670][00869] Avg episode reward: [(0, '21.638')] | |
| [2023-02-25 14:36:10,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 2949.1). Total num frames: 4227072. Throughput: 0: 904.9. Samples: 54998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:36:10,662][00869] Avg episode reward: [(0, '21.587')] | |
| [2023-02-25 14:36:15,658][00869] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 2969.6). Total num frames: 4243456. Throughput: 0: 903.5. Samples: 59602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:36:15,667][00869] Avg episode reward: [(0, '20.822')] | |
| [2023-02-25 14:36:17,350][20479] Updated weights for policy 0, policy_version 1038 (0.0012) | |
| [2023-02-25 14:36:20,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3035.9). Total num frames: 4263936. Throughput: 0: 935.0. Samples: 63130. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2023-02-25 14:36:20,661][00869] Avg episode reward: [(0, '21.735')] | |
| [2023-02-25 14:36:25,661][00869] Fps is (10 sec: 4504.6, 60 sec: 3754.5, 300 sec: 3140.2). Total num frames: 4288512. Throughput: 0: 958.7. Samples: 70190. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:36:25,669][00869] Avg episode reward: [(0, '21.998')] | |
| [2023-02-25 14:36:26,463][20479] Updated weights for policy 0, policy_version 1048 (0.0020) | |
| [2023-02-25 14:36:30,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3104.3). Total num frames: 4300800. Throughput: 0: 908.6. Samples: 74878. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:36:30,670][00869] Avg episode reward: [(0, '21.704')] | |
| [2023-02-25 14:36:35,658][00869] Fps is (10 sec: 2867.8, 60 sec: 3754.7, 300 sec: 3113.0). Total num frames: 4317184. Throughput: 0: 910.6. Samples: 77106. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:36:35,661][00869] Avg episode reward: [(0, '22.063')] | |
| [2023-02-25 14:36:35,673][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001055_4321280.pth... | |
| [2023-02-25 14:36:35,855][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000939_3846144.pth | |
| [2023-02-25 14:36:38,636][20479] Updated weights for policy 0, policy_version 1058 (0.0030) | |
| [2023-02-25 14:36:40,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3198.8). Total num frames: 4341760. Throughput: 0: 958.5. Samples: 83478. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:36:40,666][00869] Avg episode reward: [(0, '23.105')] | |
| [2023-02-25 14:36:45,659][00869] Fps is (10 sec: 4505.5, 60 sec: 3754.8, 300 sec: 3239.6). Total num frames: 4362240. Throughput: 0: 962.2. Samples: 90038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:36:45,665][00869] Avg episode reward: [(0, '24.815')] | |
| [2023-02-25 14:36:45,677][20465] Saving new best policy, reward=24.815! | |
| [2023-02-25 14:36:48,642][20479] Updated weights for policy 0, policy_version 1068 (0.0038) | |
| [2023-02-25 14:36:50,661][00869] Fps is (10 sec: 3685.4, 60 sec: 3754.5, 300 sec: 3241.1). Total num frames: 4378624. Throughput: 0: 935.9. Samples: 92238. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2023-02-25 14:36:50,671][00869] Avg episode reward: [(0, '23.759')] | |
| [2023-02-25 14:36:55,658][00869] Fps is (10 sec: 3276.9, 60 sec: 3754.7, 300 sec: 3242.7). Total num frames: 4395008. Throughput: 0: 930.5. Samples: 96872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:36:55,662][00869] Avg episode reward: [(0, '25.545')] | |
| [2023-02-25 14:36:55,671][20465] Saving new best policy, reward=25.545! | |
| [2023-02-25 14:36:59,737][20479] Updated weights for policy 0, policy_version 1078 (0.0015) | |
| [2023-02-25 14:37:00,658][00869] Fps is (10 sec: 4097.1, 60 sec: 3822.9, 300 sec: 3309.6). Total num frames: 4419584. Throughput: 0: 983.3. Samples: 103852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:37:00,661][00869] Avg episode reward: [(0, '24.991')] | |
| [2023-02-25 14:37:05,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3339.8). Total num frames: 4440064. Throughput: 0: 980.6. Samples: 107256. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:37:05,664][00869] Avg episode reward: [(0, '23.275')] | |
| [2023-02-25 14:37:10,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3307.1). Total num frames: 4452352. Throughput: 0: 934.8. Samples: 112256. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:37:10,663][00869] Avg episode reward: [(0, '20.026')] | |
| [2023-02-25 14:37:10,829][20479] Updated weights for policy 0, policy_version 1088 (0.0024) | |
| [2023-02-25 14:37:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3335.3). Total num frames: 4472832. Throughput: 0: 941.4. Samples: 117242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:37:15,661][00869] Avg episode reward: [(0, '18.925')] | |
| [2023-02-25 14:37:20,495][20479] Updated weights for policy 0, policy_version 1098 (0.0014) | |
| [2023-02-25 14:37:20,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3389.8). Total num frames: 4497408. Throughput: 0: 968.8. Samples: 120704. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:37:20,665][00869] Avg episode reward: [(0, '18.770')] | |
| [2023-02-25 14:37:25,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3823.1, 300 sec: 3413.3). Total num frames: 4517888. Throughput: 0: 990.0. Samples: 128030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:37:25,662][00869] Avg episode reward: [(0, '18.431')] | |
| [2023-02-25 14:37:30,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3408.9). Total num frames: 4534272. Throughput: 0: 944.1. Samples: 132520. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:37:30,661][00869] Avg episode reward: [(0, '19.272')] | |
| [2023-02-25 14:37:32,019][20479] Updated weights for policy 0, policy_version 1108 (0.0015) | |
| [2023-02-25 14:37:35,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3404.8). Total num frames: 4550656. Throughput: 0: 945.3. Samples: 134774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:37:35,664][00869] Avg episode reward: [(0, '21.006')] | |
| [2023-02-25 14:37:40,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3425.7). Total num frames: 4571136. Throughput: 0: 987.3. Samples: 141300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:37:40,661][00869] Avg episode reward: [(0, '22.728')] | |
| [2023-02-25 14:37:41,674][20479] Updated weights for policy 0, policy_version 1118 (0.0017) | |
| [2023-02-25 14:37:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3445.5). Total num frames: 4591616. Throughput: 0: 972.7. Samples: 147624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:37:45,665][00869] Avg episode reward: [(0, '22.781')] | |
| [2023-02-25 14:37:50,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3823.1, 300 sec: 3440.6). Total num frames: 4608000. Throughput: 0: 943.3. Samples: 149706. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:37:50,661][00869] Avg episode reward: [(0, '23.428')] | |
| [2023-02-25 14:37:53,956][20479] Updated weights for policy 0, policy_version 1128 (0.0026) | |
| [2023-02-25 14:37:55,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3436.1). Total num frames: 4624384. Throughput: 0: 935.4. Samples: 154348. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:37:55,660][00869] Avg episode reward: [(0, '25.012')] | |
| [2023-02-25 14:38:00,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3476.1). Total num frames: 4648960. Throughput: 0: 978.0. Samples: 161254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:38:00,665][00869] Avg episode reward: [(0, '24.371')] | |
| [2023-02-25 14:38:02,828][20479] Updated weights for policy 0, policy_version 1138 (0.0012) | |
| [2023-02-25 14:38:05,661][00869] Fps is (10 sec: 4504.6, 60 sec: 3822.8, 300 sec: 3492.3). Total num frames: 4669440. Throughput: 0: 977.8. Samples: 164708. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:38:05,667][00869] Avg episode reward: [(0, '24.073')] | |
| [2023-02-25 14:38:10,661][00869] Fps is (10 sec: 3276.0, 60 sec: 3822.8, 300 sec: 3465.8). Total num frames: 4681728. Throughput: 0: 913.1. Samples: 169120. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:38:10,664][00869] Avg episode reward: [(0, '23.797')] | |
| [2023-02-25 14:38:15,652][20479] Updated weights for policy 0, policy_version 1148 (0.0025) | |
| [2023-02-25 14:38:15,658][00869] Fps is (10 sec: 3277.5, 60 sec: 3822.9, 300 sec: 3481.6). Total num frames: 4702208. Throughput: 0: 926.0. Samples: 174192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:38:15,661][00869] Avg episode reward: [(0, '23.827')] | |
| [2023-02-25 14:38:20,658][00869] Fps is (10 sec: 4096.9, 60 sec: 3754.7, 300 sec: 3496.6). Total num frames: 4722688. Throughput: 0: 951.9. Samples: 177608. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:38:20,667][00869] Avg episode reward: [(0, '22.376')] | |
| [2023-02-25 14:38:24,776][20479] Updated weights for policy 0, policy_version 1158 (0.0012) | |
| [2023-02-25 14:38:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3510.9). Total num frames: 4743168. Throughput: 0: 955.5. Samples: 184298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:38:25,665][00869] Avg episode reward: [(0, '23.436')] | |
| [2023-02-25 14:38:30,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3486.4). Total num frames: 4755456. Throughput: 0: 904.7. Samples: 188334. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:38:30,660][00869] Avg episode reward: [(0, '22.569')] | |
| [2023-02-25 14:38:35,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 4771840. Throughput: 0: 904.5. Samples: 190408. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:38:35,661][00869] Avg episode reward: [(0, '22.236')] | |
| [2023-02-25 14:38:35,677][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001165_4771840.pth... | |
| [2023-02-25 14:38:35,824][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth | |
| [2023-02-25 14:38:37,846][20479] Updated weights for policy 0, policy_version 1168 (0.0015) | |
| [2023-02-25 14:38:40,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3495.3). Total num frames: 4792320. Throughput: 0: 941.0. Samples: 196694. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:38:40,665][00869] Avg episode reward: [(0, '23.212')] | |
| [2023-02-25 14:38:45,669][00869] Fps is (10 sec: 4091.5, 60 sec: 3685.7, 300 sec: 3508.1). Total num frames: 4812800. Throughput: 0: 925.7. Samples: 202920. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:38:45,680][00869] Avg episode reward: [(0, '22.605')] | |
| [2023-02-25 14:38:48,743][20479] Updated weights for policy 0, policy_version 1178 (0.0017) | |
| [2023-02-25 14:38:50,661][00869] Fps is (10 sec: 3685.3, 60 sec: 3686.2, 300 sec: 3503.3). Total num frames: 4829184. Throughput: 0: 896.8. Samples: 205066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:38:50,665][00869] Avg episode reward: [(0, '23.511')] | |
| [2023-02-25 14:38:55,658][00869] Fps is (10 sec: 3280.4, 60 sec: 3686.4, 300 sec: 3498.7). Total num frames: 4845568. Throughput: 0: 903.5. Samples: 209774. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:38:55,660][00869] Avg episode reward: [(0, '24.918')] | |
| [2023-02-25 14:38:59,437][20479] Updated weights for policy 0, policy_version 1188 (0.0030) | |
| [2023-02-25 14:39:00,658][00869] Fps is (10 sec: 4097.2, 60 sec: 3686.4, 300 sec: 3527.6). Total num frames: 4870144. Throughput: 0: 941.4. Samples: 216556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:39:00,666][00869] Avg episode reward: [(0, '25.199')] | |
| [2023-02-25 14:39:05,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3686.5, 300 sec: 3538.9). Total num frames: 4890624. Throughput: 0: 941.3. Samples: 219966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:39:05,663][00869] Avg episode reward: [(0, '25.806')] | |
| [2023-02-25 14:39:05,680][20465] Saving new best policy, reward=25.806! | |
| [2023-02-25 14:39:10,659][00869] Fps is (10 sec: 3276.5, 60 sec: 3686.5, 300 sec: 3517.7). Total num frames: 4902912. Throughput: 0: 883.7. Samples: 224066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:39:10,669][00869] Avg episode reward: [(0, '24.324')] | |
| [2023-02-25 14:39:11,797][20479] Updated weights for policy 0, policy_version 1198 (0.0018) | |
| [2023-02-25 14:39:15,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3513.1). Total num frames: 4919296. Throughput: 0: 909.3. Samples: 229252. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:39:15,669][00869] Avg episode reward: [(0, '24.408')] | |
| [2023-02-25 14:39:20,660][00869] Fps is (10 sec: 4095.5, 60 sec: 3686.3, 300 sec: 3539.5). Total num frames: 4943872. Throughput: 0: 940.3. Samples: 232724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:39:20,665][00869] Avg episode reward: [(0, '21.130')] | |
| [2023-02-25 14:39:21,249][20479] Updated weights for policy 0, policy_version 1208 (0.0013) | |
| [2023-02-25 14:39:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3534.7). Total num frames: 4960256. Throughput: 0: 945.5. Samples: 239240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:39:25,663][00869] Avg episode reward: [(0, '21.239')] | |
| [2023-02-25 14:39:30,658][00869] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3530.0). Total num frames: 4976640. Throughput: 0: 903.2. Samples: 243556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:39:30,663][00869] Avg episode reward: [(0, '21.370')] | |
| [2023-02-25 14:39:33,889][20479] Updated weights for policy 0, policy_version 1218 (0.0016) | |
| [2023-02-25 14:39:35,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3525.5). Total num frames: 4993024. Throughput: 0: 905.3. Samples: 245802. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:39:35,666][00869] Avg episode reward: [(0, '22.434')] | |
| [2023-02-25 14:39:40,659][00869] Fps is (10 sec: 4095.5, 60 sec: 3754.6, 300 sec: 3549.9). Total num frames: 5017600. Throughput: 0: 947.9. Samples: 252430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:39:40,662][00869] Avg episode reward: [(0, '22.524')] | |
| [2023-02-25 14:39:43,189][20479] Updated weights for policy 0, policy_version 1228 (0.0012) | |
| [2023-02-25 14:39:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3687.1, 300 sec: 3545.2). Total num frames: 5033984. Throughput: 0: 929.6. Samples: 258386. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:39:45,661][00869] Avg episode reward: [(0, '24.239')] | |
| [2023-02-25 14:39:50,660][00869] Fps is (10 sec: 3276.5, 60 sec: 3686.5, 300 sec: 3540.6). Total num frames: 5050368. Throughput: 0: 901.4. Samples: 260532. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-02-25 14:39:50,663][00869] Avg episode reward: [(0, '23.763')] | |
| [2023-02-25 14:39:55,659][00869] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 5066752. Throughput: 0: 912.8. Samples: 265140. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:39:55,661][00869] Avg episode reward: [(0, '23.398')] | |
| [2023-02-25 14:39:55,779][20479] Updated weights for policy 0, policy_version 1238 (0.0015) | |
| [2023-02-25 14:40:00,658][00869] Fps is (10 sec: 4096.8, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 5091328. Throughput: 0: 949.0. Samples: 271958. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:40:00,666][00869] Avg episode reward: [(0, '23.483')] | |
| [2023-02-25 14:40:05,658][00869] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 5107712. Throughput: 0: 945.0. Samples: 275246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:40:05,668][00869] Avg episode reward: [(0, '24.779')] | |
| [2023-02-25 14:40:05,769][20479] Updated weights for policy 0, policy_version 1248 (0.0013) | |
| [2023-02-25 14:40:10,659][00869] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3748.9). Total num frames: 5124096. Throughput: 0: 892.0. Samples: 279382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:40:10,665][00869] Avg episode reward: [(0, '24.985')] | |
| [2023-02-25 14:40:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 5140480. Throughput: 0: 913.1. Samples: 284646. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:40:15,667][00869] Avg episode reward: [(0, '25.356')] | |
| [2023-02-25 14:40:17,704][20479] Updated weights for policy 0, policy_version 1258 (0.0012) | |
| [2023-02-25 14:40:20,658][00869] Fps is (10 sec: 4096.2, 60 sec: 3686.5, 300 sec: 3735.0). Total num frames: 5165056. Throughput: 0: 938.0. Samples: 288014. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:40:20,661][00869] Avg episode reward: [(0, '26.914')] | |
| [2023-02-25 14:40:20,671][20465] Saving new best policy, reward=26.914! | |
| [2023-02-25 14:40:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 5181440. Throughput: 0: 926.5. Samples: 294120. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:40:25,665][00869] Avg episode reward: [(0, '25.818')] | |
| [2023-02-25 14:40:28,913][20479] Updated weights for policy 0, policy_version 1268 (0.0017) | |
| [2023-02-25 14:40:30,660][00869] Fps is (10 sec: 3276.2, 60 sec: 3686.3, 300 sec: 3748.9). Total num frames: 5197824. Throughput: 0: 889.1. Samples: 298398. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:40:30,663][00869] Avg episode reward: [(0, '26.240')] | |
| [2023-02-25 14:40:35,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 5214208. Throughput: 0: 892.8. Samples: 300706. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:40:35,666][00869] Avg episode reward: [(0, '25.482')] | |
| [2023-02-25 14:40:35,681][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001273_5214208.pth... | |
| [2023-02-25 14:40:35,855][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001055_4321280.pth | |
| [2023-02-25 14:40:39,673][20479] Updated weights for policy 0, policy_version 1278 (0.0015) | |
| [2023-02-25 14:40:40,661][00869] Fps is (10 sec: 4095.5, 60 sec: 3686.3, 300 sec: 3735.0). Total num frames: 5238784. Throughput: 0: 938.0. Samples: 307352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:40:40,667][00869] Avg episode reward: [(0, '24.387')] | |
| [2023-02-25 14:40:45,661][00869] Fps is (10 sec: 4094.8, 60 sec: 3686.2, 300 sec: 3735.0). Total num frames: 5255168. Throughput: 0: 910.1. Samples: 312914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:40:45,664][00869] Avg episode reward: [(0, '23.824')] | |
| [2023-02-25 14:40:50,658][00869] Fps is (10 sec: 2868.1, 60 sec: 3618.3, 300 sec: 3721.1). Total num frames: 5267456. Throughput: 0: 884.2. Samples: 315034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:40:50,661][00869] Avg episode reward: [(0, '23.411')] | |
| [2023-02-25 14:40:52,404][20479] Updated weights for policy 0, policy_version 1288 (0.0028) | |
| [2023-02-25 14:40:55,658][00869] Fps is (10 sec: 3277.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 5287936. Throughput: 0: 904.4. Samples: 320080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:40:55,667][00869] Avg episode reward: [(0, '23.788')] | |
| [2023-02-25 14:41:00,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3721.1). Total num frames: 5308416. Throughput: 0: 936.7. Samples: 326798. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:41:00,666][00869] Avg episode reward: [(0, '24.620')] | |
| [2023-02-25 14:41:02,576][20479] Updated weights for policy 0, policy_version 1298 (0.0015) | |
| [2023-02-25 14:41:05,661][00869] Fps is (10 sec: 3275.9, 60 sec: 3549.7, 300 sec: 3707.2). Total num frames: 5320704. Throughput: 0: 905.9. Samples: 328784. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:41:05,666][00869] Avg episode reward: [(0, '25.260')] | |
| [2023-02-25 14:41:10,658][00869] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 5332992. Throughput: 0: 842.4. Samples: 332030. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:41:10,665][00869] Avg episode reward: [(0, '24.088')] | |
| [2023-02-25 14:41:15,662][00869] Fps is (10 sec: 2457.3, 60 sec: 3413.1, 300 sec: 3665.5). Total num frames: 5345280. Throughput: 0: 823.0. Samples: 335434. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:41:15,669][00869] Avg episode reward: [(0, '24.482')] | |
| [2023-02-25 14:41:18,177][20479] Updated weights for policy 0, policy_version 1308 (0.0018) | |
| [2023-02-25 14:41:20,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3651.7). Total num frames: 5365760. Throughput: 0: 842.7. Samples: 338628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:41:20,664][00869] Avg episode reward: [(0, '25.141')] | |
| [2023-02-25 14:41:25,658][00869] Fps is (10 sec: 4507.3, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 5390336. Throughput: 0: 850.5. Samples: 345620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:41:25,666][00869] Avg episode reward: [(0, '25.654')] | |
| [2023-02-25 14:41:27,654][20479] Updated weights for policy 0, policy_version 1318 (0.0019) | |
| [2023-02-25 14:41:30,659][00869] Fps is (10 sec: 4095.9, 60 sec: 3481.7, 300 sec: 3693.3). Total num frames: 5406720. Throughput: 0: 840.5. Samples: 350736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:41:30,666][00869] Avg episode reward: [(0, '25.785')] | |
| [2023-02-25 14:41:35,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 5419008. Throughput: 0: 841.2. Samples: 352886. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:41:35,661][00869] Avg episode reward: [(0, '24.909')] | |
| [2023-02-25 14:41:39,492][20479] Updated weights for policy 0, policy_version 1328 (0.0012) | |
| [2023-02-25 14:41:40,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3413.5, 300 sec: 3665.6). Total num frames: 5443584. Throughput: 0: 860.2. Samples: 358788. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:41:40,661][00869] Avg episode reward: [(0, '23.973')] | |
| [2023-02-25 14:41:45,658][00869] Fps is (10 sec: 4915.2, 60 sec: 3550.0, 300 sec: 3693.4). Total num frames: 5468160. Throughput: 0: 864.0. Samples: 365678. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:41:45,663][00869] Avg episode reward: [(0, '24.099')] | |
| [2023-02-25 14:41:50,036][20479] Updated weights for policy 0, policy_version 1338 (0.0014) | |
| [2023-02-25 14:41:50,659][00869] Fps is (10 sec: 3686.3, 60 sec: 3549.8, 300 sec: 3679.5). Total num frames: 5480448. Throughput: 0: 871.6. Samples: 368006. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:41:50,665][00869] Avg episode reward: [(0, '23.653')] | |
| [2023-02-25 14:41:55,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 5496832. Throughput: 0: 896.0. Samples: 372348. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:41:55,661][00869] Avg episode reward: [(0, '23.471')] | |
| [2023-02-25 14:42:00,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 5517312. Throughput: 0: 966.3. Samples: 378916. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:00,660][00869] Avg episode reward: [(0, '21.867')] | |
| [2023-02-25 14:42:00,748][20479] Updated weights for policy 0, policy_version 1348 (0.0017) | |
| [2023-02-25 14:42:05,666][00869] Fps is (10 sec: 4502.0, 60 sec: 3686.1, 300 sec: 3693.2). Total num frames: 5541888. Throughput: 0: 973.6. Samples: 382448. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:42:05,669][00869] Avg episode reward: [(0, '22.658')] | |
| [2023-02-25 14:42:10,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 5554176. Throughput: 0: 933.8. Samples: 387642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:10,664][00869] Avg episode reward: [(0, '22.421')] | |
| [2023-02-25 14:42:12,330][20479] Updated weights for policy 0, policy_version 1358 (0.0012) | |
| [2023-02-25 14:42:15,658][00869] Fps is (10 sec: 2869.5, 60 sec: 3754.9, 300 sec: 3637.8). Total num frames: 5570560. Throughput: 0: 918.4. Samples: 392062. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:15,661][00869] Avg episode reward: [(0, '22.421')] | |
| [2023-02-25 14:42:20,659][00869] Fps is (10 sec: 4095.8, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 5595136. Throughput: 0: 948.1. Samples: 395552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:20,668][00869] Avg episode reward: [(0, '21.297')] | |
| [2023-02-25 14:42:22,102][20479] Updated weights for policy 0, policy_version 1368 (0.0029) | |
| [2023-02-25 14:42:25,660][00869] Fps is (10 sec: 4504.8, 60 sec: 3754.6, 300 sec: 3665.5). Total num frames: 5615616. Throughput: 0: 972.4. Samples: 402550. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:42:25,666][00869] Avg episode reward: [(0, '22.995')] | |
| [2023-02-25 14:42:30,658][00869] Fps is (10 sec: 3686.6, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 5632000. Throughput: 0: 920.8. Samples: 407112. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:42:30,666][00869] Avg episode reward: [(0, '23.117')] | |
| [2023-02-25 14:42:34,507][20479] Updated weights for policy 0, policy_version 1378 (0.0028) | |
| [2023-02-25 14:42:35,658][00869] Fps is (10 sec: 3277.4, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 5648384. Throughput: 0: 914.8. Samples: 409174. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-25 14:42:35,661][00869] Avg episode reward: [(0, '23.794')] | |
| [2023-02-25 14:42:35,674][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001379_5648384.pth... | |
| [2023-02-25 14:42:35,846][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001165_4771840.pth | |
| [2023-02-25 14:42:40,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 5668864. Throughput: 0: 957.1. Samples: 415416. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:40,661][00869] Avg episode reward: [(0, '22.848')] | |
| [2023-02-25 14:42:43,603][20479] Updated weights for policy 0, policy_version 1388 (0.0014) | |
| [2023-02-25 14:42:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 5689344. Throughput: 0: 961.6. Samples: 422188. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:42:45,667][00869] Avg episode reward: [(0, '23.293')] | |
| [2023-02-25 14:42:50,660][00869] Fps is (10 sec: 3685.9, 60 sec: 3754.6, 300 sec: 3665.6). Total num frames: 5705728. Throughput: 0: 931.7. Samples: 424368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:42:50,667][00869] Avg episode reward: [(0, '21.260')] | |
| [2023-02-25 14:42:55,664][00869] Fps is (10 sec: 3274.9, 60 sec: 3754.3, 300 sec: 3637.7). Total num frames: 5722112. Throughput: 0: 914.3. Samples: 428792. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:42:55,667][00869] Avg episode reward: [(0, '21.354')] | |
| [2023-02-25 14:42:55,965][20479] Updated weights for policy 0, policy_version 1398 (0.0012) | |
| [2023-02-25 14:43:00,658][00869] Fps is (10 sec: 4096.6, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 5746688. Throughput: 0: 973.6. Samples: 435872. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:00,665][00869] Avg episode reward: [(0, '21.756')] | |
| [2023-02-25 14:43:04,957][20479] Updated weights for policy 0, policy_version 1408 (0.0012) | |
| [2023-02-25 14:43:05,658][00869] Fps is (10 sec: 4508.1, 60 sec: 3755.2, 300 sec: 3679.5). Total num frames: 5767168. Throughput: 0: 972.4. Samples: 439310. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:05,661][00869] Avg episode reward: [(0, '23.500')] | |
| [2023-02-25 14:43:10,660][00869] Fps is (10 sec: 3685.7, 60 sec: 3822.8, 300 sec: 3665.5). Total num frames: 5783552. Throughput: 0: 921.5. Samples: 444016. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:10,663][00869] Avg episode reward: [(0, '23.484')] | |
| [2023-02-25 14:43:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3651.7). Total num frames: 5799936. Throughput: 0: 929.4. Samples: 448936. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:43:15,661][00869] Avg episode reward: [(0, '23.687')] | |
| [2023-02-25 14:43:17,124][20479] Updated weights for policy 0, policy_version 1418 (0.0021) | |
| [2023-02-25 14:43:20,658][00869] Fps is (10 sec: 4096.8, 60 sec: 3823.0, 300 sec: 3665.6). Total num frames: 5824512. Throughput: 0: 961.5. Samples: 452440. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:43:20,665][00869] Avg episode reward: [(0, '24.515')] | |
| [2023-02-25 14:43:25,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3823.1, 300 sec: 3693.3). Total num frames: 5844992. Throughput: 0: 976.7. Samples: 459368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:25,662][00869] Avg episode reward: [(0, '24.454')] | |
| [2023-02-25 14:43:27,094][20479] Updated weights for policy 0, policy_version 1428 (0.0014) | |
| [2023-02-25 14:43:30,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 5857280. Throughput: 0: 923.2. Samples: 463734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:43:30,664][00869] Avg episode reward: [(0, '24.289')] | |
| [2023-02-25 14:43:35,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 5877760. Throughput: 0: 924.0. Samples: 465946. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:35,665][00869] Avg episode reward: [(0, '24.416')] | |
| [2023-02-25 14:43:38,465][20479] Updated weights for policy 0, policy_version 1438 (0.0018) | |
| [2023-02-25 14:43:40,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3679.6). Total num frames: 5898240. Throughput: 0: 974.4. Samples: 472636. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:43:40,666][00869] Avg episode reward: [(0, '24.300')] | |
| [2023-02-25 14:43:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3693.4). Total num frames: 5918720. Throughput: 0: 957.1. Samples: 478942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:43:45,671][00869] Avg episode reward: [(0, '24.328')] | |
| [2023-02-25 14:43:49,168][20479] Updated weights for policy 0, policy_version 1448 (0.0014) | |
| [2023-02-25 14:43:50,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3693.3). Total num frames: 5935104. Throughput: 0: 929.7. Samples: 481146. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:43:50,664][00869] Avg episode reward: [(0, '24.408')] | |
| [2023-02-25 14:43:55,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.3, 300 sec: 3665.6). Total num frames: 5951488. Throughput: 0: 931.0. Samples: 485908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:43:55,664][00869] Avg episode reward: [(0, '24.508')] | |
| [2023-02-25 14:43:59,836][20479] Updated weights for policy 0, policy_version 1458 (0.0012) | |
| [2023-02-25 14:44:00,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 5971968. Throughput: 0: 972.0. Samples: 492676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:44:00,665][00869] Avg episode reward: [(0, '23.516')] | |
| [2023-02-25 14:44:05,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.4). Total num frames: 5992448. Throughput: 0: 968.4. Samples: 496018. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:44:05,663][00869] Avg episode reward: [(0, '24.210')] | |
| [2023-02-25 14:44:10,660][00869] Fps is (10 sec: 3276.1, 60 sec: 3686.4, 300 sec: 3679.4). Total num frames: 6004736. Throughput: 0: 908.2. Samples: 500238. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:44:10,663][00869] Avg episode reward: [(0, '25.167')] | |
| [2023-02-25 14:44:12,490][20479] Updated weights for policy 0, policy_version 1468 (0.0024) | |
| [2023-02-25 14:44:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 6025216. Throughput: 0: 921.7. Samples: 505210. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:44:15,660][00869] Avg episode reward: [(0, '24.988')] | |
| [2023-02-25 14:44:20,658][00869] Fps is (10 sec: 4096.8, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 6045696. Throughput: 0: 945.7. Samples: 508504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:44:20,667][00869] Avg episode reward: [(0, '26.008')] | |
| [2023-02-25 14:44:21,828][20479] Updated weights for policy 0, policy_version 1478 (0.0013) | |
| [2023-02-25 14:44:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 6066176. Throughput: 0: 938.1. Samples: 514850. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:44:25,664][00869] Avg episode reward: [(0, '27.008')] | |
| [2023-02-25 14:44:25,685][20465] Saving new best policy, reward=27.008! | |
| [2023-02-25 14:44:30,667][00869] Fps is (10 sec: 3274.0, 60 sec: 3685.9, 300 sec: 3679.4). Total num frames: 6078464. Throughput: 0: 887.8. Samples: 518900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:44:30,673][00869] Avg episode reward: [(0, '25.912')] | |
| [2023-02-25 14:44:34,496][20479] Updated weights for policy 0, policy_version 1488 (0.0011) | |
| [2023-02-25 14:44:35,659][00869] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 6098944. Throughput: 0: 892.8. Samples: 521322. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:44:35,665][00869] Avg episode reward: [(0, '24.472')] | |
| [2023-02-25 14:44:35,677][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001489_6098944.pth... | |
| [2023-02-25 14:44:35,878][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001273_5214208.pth | |
| [2023-02-25 14:44:40,658][00869] Fps is (10 sec: 4099.5, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 6119424. Throughput: 0: 940.7. Samples: 528240. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:44:40,664][00869] Avg episode reward: [(0, '25.728')] | |
| [2023-02-25 14:44:43,555][20479] Updated weights for policy 0, policy_version 1498 (0.0019) | |
| [2023-02-25 14:44:45,658][00869] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 6139904. Throughput: 0: 922.5. Samples: 534190. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:44:45,664][00869] Avg episode reward: [(0, '25.058')] | |
| [2023-02-25 14:44:50,661][00869] Fps is (10 sec: 3685.3, 60 sec: 3686.2, 300 sec: 3693.3). Total num frames: 6156288. Throughput: 0: 896.4. Samples: 536360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:44:50,666][00869] Avg episode reward: [(0, '25.817')] | |
| [2023-02-25 14:44:55,665][20479] Updated weights for policy 0, policy_version 1508 (0.0024) | |
| [2023-02-25 14:44:55,664][00869] Fps is (10 sec: 3684.4, 60 sec: 3754.3, 300 sec: 3679.4). Total num frames: 6176768. Throughput: 0: 920.2. Samples: 541648. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:44:55,674][00869] Avg episode reward: [(0, '24.029')] | |
| [2023-02-25 14:45:00,658][00869] Fps is (10 sec: 4097.2, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 6197248. Throughput: 0: 967.4. Samples: 548742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:45:00,667][00869] Avg episode reward: [(0, '25.732')] | |
| [2023-02-25 14:45:05,458][20479] Updated weights for policy 0, policy_version 1518 (0.0037) | |
| [2023-02-25 14:45:05,662][00869] Fps is (10 sec: 4096.5, 60 sec: 3754.4, 300 sec: 3707.2). Total num frames: 6217728. Throughput: 0: 964.7. Samples: 551918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:45:05,665][00869] Avg episode reward: [(0, '23.135')] | |
| [2023-02-25 14:45:10,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 6230016. Throughput: 0: 921.5. Samples: 556316. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:45:10,667][00869] Avg episode reward: [(0, '22.571')] | |
| [2023-02-25 14:45:15,658][00869] Fps is (10 sec: 3278.1, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 6250496. Throughput: 0: 956.0. Samples: 561914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:45:15,665][00869] Avg episode reward: [(0, '22.832')] | |
| [2023-02-25 14:45:16,948][20479] Updated weights for policy 0, policy_version 1528 (0.0036) | |
| [2023-02-25 14:45:20,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 6275072. Throughput: 0: 979.6. Samples: 565402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:45:20,667][00869] Avg episode reward: [(0, '23.653')] | |
| [2023-02-25 14:45:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 6291456. Throughput: 0: 968.5. Samples: 571824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:45:25,661][00869] Avg episode reward: [(0, '22.273')] | |
| [2023-02-25 14:45:27,265][20479] Updated weights for policy 0, policy_version 1538 (0.0026) | |
| [2023-02-25 14:45:30,659][00869] Fps is (10 sec: 3276.4, 60 sec: 3823.4, 300 sec: 3707.2). Total num frames: 6307840. Throughput: 0: 933.8. Samples: 576210. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:45:30,666][00869] Avg episode reward: [(0, '22.400')] | |
| [2023-02-25 14:45:35,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3693.4). Total num frames: 6328320. Throughput: 0: 946.1. Samples: 578932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:45:35,663][00869] Avg episode reward: [(0, '23.801')] | |
| [2023-02-25 14:45:37,834][20479] Updated weights for policy 0, policy_version 1548 (0.0012) | |
| [2023-02-25 14:45:40,658][00869] Fps is (10 sec: 4506.1, 60 sec: 3891.2, 300 sec: 3721.1). Total num frames: 6352896. Throughput: 0: 986.6. Samples: 586042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:45:40,664][00869] Avg episode reward: [(0, '23.892')] | |
| [2023-02-25 14:45:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3735.0). Total num frames: 6369280. Throughput: 0: 954.4. Samples: 591690. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:45:45,662][00869] Avg episode reward: [(0, '23.680')] | |
| [2023-02-25 14:45:49,108][20479] Updated weights for policy 0, policy_version 1558 (0.0011) | |
| [2023-02-25 14:45:50,659][00869] Fps is (10 sec: 3276.7, 60 sec: 3823.1, 300 sec: 3721.1). Total num frames: 6385664. Throughput: 0: 933.6. Samples: 593926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:45:50,661][00869] Avg episode reward: [(0, '24.873')] | |
| [2023-02-25 14:45:55,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3823.3, 300 sec: 3721.1). Total num frames: 6406144. Throughput: 0: 959.6. Samples: 599500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:45:55,666][00869] Avg episode reward: [(0, '23.881')] | |
| [2023-02-25 14:45:58,732][20479] Updated weights for policy 0, policy_version 1568 (0.0015) | |
| [2023-02-25 14:46:00,659][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 6430720. Throughput: 0: 995.9. Samples: 606728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:46:00,665][00869] Avg episode reward: [(0, '23.566')] | |
| [2023-02-25 14:46:05,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.2, 300 sec: 3776.7). Total num frames: 6447104. Throughput: 0: 983.7. Samples: 609670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:05,662][00869] Avg episode reward: [(0, '22.727')] | |
| [2023-02-25 14:46:10,425][20479] Updated weights for policy 0, policy_version 1578 (0.0026) | |
| [2023-02-25 14:46:10,658][00869] Fps is (10 sec: 3276.9, 60 sec: 3891.2, 300 sec: 3790.6). Total num frames: 6463488. Throughput: 0: 940.4. Samples: 614144. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:46:10,661][00869] Avg episode reward: [(0, '21.956')] | |
| [2023-02-25 14:46:15,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 6483968. Throughput: 0: 976.8. Samples: 620164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:15,667][00869] Avg episode reward: [(0, '21.478')] | |
| [2023-02-25 14:46:19,571][20479] Updated weights for policy 0, policy_version 1588 (0.0012) | |
| [2023-02-25 14:46:20,659][00869] Fps is (10 sec: 4505.4, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 6508544. Throughput: 0: 995.9. Samples: 623748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:20,666][00869] Avg episode reward: [(0, '22.220')] | |
| [2023-02-25 14:46:25,660][00869] Fps is (10 sec: 4095.3, 60 sec: 3891.1, 300 sec: 3790.5). Total num frames: 6524928. Throughput: 0: 972.3. Samples: 629796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:25,667][00869] Avg episode reward: [(0, '21.812')] | |
| [2023-02-25 14:46:30,658][00869] Fps is (10 sec: 3276.9, 60 sec: 3891.3, 300 sec: 3804.4). Total num frames: 6541312. Throughput: 0: 947.4. Samples: 634324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:46:30,665][00869] Avg episode reward: [(0, '23.666')] | |
| [2023-02-25 14:46:31,805][20479] Updated weights for policy 0, policy_version 1598 (0.0011) | |
| [2023-02-25 14:46:35,658][00869] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 6561792. Throughput: 0: 962.6. Samples: 637244. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:35,661][00869] Avg episode reward: [(0, '24.688')] | |
| [2023-02-25 14:46:35,669][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001602_6561792.pth... | |
| [2023-02-25 14:46:35,826][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001379_5648384.pth | |
| [2023-02-25 14:46:40,629][20479] Updated weights for policy 0, policy_version 1608 (0.0012) | |
| [2023-02-25 14:46:40,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 6586368. Throughput: 0: 992.0. Samples: 644142. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:46:40,661][00869] Avg episode reward: [(0, '24.632')] | |
| [2023-02-25 14:46:45,659][00869] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 6602752. Throughput: 0: 956.0. Samples: 649748. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:46:45,665][00869] Avg episode reward: [(0, '24.587')] | |
| [2023-02-25 14:46:50,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 6615040. Throughput: 0: 938.1. Samples: 651884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:46:50,661][00869] Avg episode reward: [(0, '24.480')] | |
| [2023-02-25 14:46:52,984][20479] Updated weights for policy 0, policy_version 1618 (0.0024) | |
| [2023-02-25 14:46:55,659][00869] Fps is (10 sec: 3686.2, 60 sec: 3891.1, 300 sec: 3804.4). Total num frames: 6639616. Throughput: 0: 966.2. Samples: 657626. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:46:55,663][00869] Avg episode reward: [(0, '24.536')] | |
| [2023-02-25 14:47:00,659][00869] Fps is (10 sec: 4915.1, 60 sec: 3891.2, 300 sec: 3804.5). Total num frames: 6664192. Throughput: 0: 993.1. Samples: 664854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:47:00,661][00869] Avg episode reward: [(0, '24.569')] | |
| [2023-02-25 14:47:01,436][20479] Updated weights for policy 0, policy_version 1628 (0.0020) | |
| [2023-02-25 14:47:05,658][00869] Fps is (10 sec: 4096.3, 60 sec: 3891.2, 300 sec: 3818.3). Total num frames: 6680576. Throughput: 0: 974.2. Samples: 667588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:47:05,668][00869] Avg episode reward: [(0, '24.605')] | |
| [2023-02-25 14:47:10,658][00869] Fps is (10 sec: 2867.3, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 6692864. Throughput: 0: 936.2. Samples: 671924. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:47:10,664][00869] Avg episode reward: [(0, '23.945')] | |
| [2023-02-25 14:47:13,847][20479] Updated weights for policy 0, policy_version 1638 (0.0013) | |
| [2023-02-25 14:47:15,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 6717440. Throughput: 0: 976.0. Samples: 678246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:47:15,661][00869] Avg episode reward: [(0, '23.136')] | |
| [2023-02-25 14:47:20,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 6737920. Throughput: 0: 989.4. Samples: 681768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:47:20,663][00869] Avg episode reward: [(0, '25.066')] | |
| [2023-02-25 14:47:23,078][20479] Updated weights for policy 0, policy_version 1648 (0.0020) | |
| [2023-02-25 14:47:25,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 6754304. Throughput: 0: 964.6. Samples: 687548. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:47:25,662][00869] Avg episode reward: [(0, '24.850')] | |
| [2023-02-25 14:47:30,660][00869] Fps is (10 sec: 2866.7, 60 sec: 3754.5, 300 sec: 3790.5). Total num frames: 6766592. Throughput: 0: 917.7. Samples: 691046. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:47:30,663][00869] Avg episode reward: [(0, '23.825')] | |
| [2023-02-25 14:47:35,660][00869] Fps is (10 sec: 2457.1, 60 sec: 3618.0, 300 sec: 3762.7). Total num frames: 6778880. Throughput: 0: 910.1. Samples: 692842. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:47:35,668][00869] Avg episode reward: [(0, '23.766')] | |
| [2023-02-25 14:47:38,562][20479] Updated weights for policy 0, policy_version 1658 (0.0028) | |
| [2023-02-25 14:47:40,658][00869] Fps is (10 sec: 3277.4, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 6799360. Throughput: 0: 894.5. Samples: 697878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:47:40,661][00869] Avg episode reward: [(0, '23.431')] | |
| [2023-02-25 14:47:45,658][00869] Fps is (10 sec: 4096.8, 60 sec: 3618.1, 300 sec: 3776.7). Total num frames: 6819840. Throughput: 0: 883.0. Samples: 704588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:47:45,661][00869] Avg episode reward: [(0, '23.868')] | |
| [2023-02-25 14:47:48,753][20479] Updated weights for policy 0, policy_version 1668 (0.0012) | |
| [2023-02-25 14:47:50,659][00869] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3776.7). Total num frames: 6836224. Throughput: 0: 871.4. Samples: 706800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:47:50,662][00869] Avg episode reward: [(0, '23.854')] | |
| [2023-02-25 14:47:55,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 6852608. Throughput: 0: 874.0. Samples: 711256. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:47:55,660][00869] Avg episode reward: [(0, '22.927')] | |
| [2023-02-25 14:47:59,513][20479] Updated weights for policy 0, policy_version 1678 (0.0015) | |
| [2023-02-25 14:48:00,658][00869] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3762.8). Total num frames: 6877184. Throughput: 0: 887.7. Samples: 718194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:48:00,661][00869] Avg episode reward: [(0, '23.335')] | |
| [2023-02-25 14:48:05,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3776.7). Total num frames: 6897664. Throughput: 0: 886.2. Samples: 721648. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:48:05,661][00869] Avg episode reward: [(0, '25.028')] | |
| [2023-02-25 14:48:10,662][00869] Fps is (10 sec: 3275.6, 60 sec: 3617.9, 300 sec: 3762.7). Total num frames: 6909952. Throughput: 0: 867.1. Samples: 726570. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:48:10,667][00869] Avg episode reward: [(0, '25.668')] | |
| [2023-02-25 14:48:10,680][20479] Updated weights for policy 0, policy_version 1688 (0.0013) | |
| [2023-02-25 14:48:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 6930432. Throughput: 0: 897.8. Samples: 731444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:48:15,661][00869] Avg episode reward: [(0, '25.852')] | |
| [2023-02-25 14:48:20,658][00869] Fps is (10 sec: 4097.5, 60 sec: 3549.9, 300 sec: 3748.9). Total num frames: 6950912. Throughput: 0: 934.7. Samples: 734902. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:48:20,661][00869] Avg episode reward: [(0, '25.444')] | |
| [2023-02-25 14:48:20,701][20479] Updated weights for policy 0, policy_version 1698 (0.0014) | |
| [2023-02-25 14:48:25,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3790.5). Total num frames: 6975488. Throughput: 0: 981.8. Samples: 742058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:48:25,666][00869] Avg episode reward: [(0, '25.473')] | |
| [2023-02-25 14:48:30,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3762.8). Total num frames: 6987776. Throughput: 0: 930.9. Samples: 746478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:48:30,663][00869] Avg episode reward: [(0, '24.946')] | |
| [2023-02-25 14:48:32,463][20479] Updated weights for policy 0, policy_version 1708 (0.0022) | |
| [2023-02-25 14:48:35,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3762.8). Total num frames: 7008256. Throughput: 0: 932.9. Samples: 748782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:48:35,661][00869] Avg episode reward: [(0, '24.671')] | |
| [2023-02-25 14:48:35,673][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001711_7008256.pth... | |
| [2023-02-25 14:48:35,821][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001489_6098944.pth | |
| [2023-02-25 14:48:40,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 7028736. Throughput: 0: 982.1. Samples: 755452. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:48:40,661][00869] Avg episode reward: [(0, '23.288')] | |
| [2023-02-25 14:48:41,802][20479] Updated weights for policy 0, policy_version 1718 (0.0022) | |
| [2023-02-25 14:48:45,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7049216. Throughput: 0: 969.3. Samples: 761812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:48:45,665][00869] Avg episode reward: [(0, '23.377')] | |
| [2023-02-25 14:48:50,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7065600. Throughput: 0: 940.6. Samples: 763974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:48:50,665][00869] Avg episode reward: [(0, '22.863')] | |
| [2023-02-25 14:48:54,260][20479] Updated weights for policy 0, policy_version 1728 (0.0025) | |
| [2023-02-25 14:48:55,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 7081984. Throughput: 0: 935.8. Samples: 768678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:48:55,666][00869] Avg episode reward: [(0, '24.590')] | |
| [2023-02-25 14:49:00,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7106560. Throughput: 0: 983.8. Samples: 775716. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:49:00,665][00869] Avg episode reward: [(0, '24.845')] | |
| [2023-02-25 14:49:02,996][20479] Updated weights for policy 0, policy_version 1738 (0.0015) | |
| [2023-02-25 14:49:05,659][00869] Fps is (10 sec: 4505.2, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 7127040. Throughput: 0: 985.2. Samples: 779236. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:49:05,662][00869] Avg episode reward: [(0, '24.329')] | |
| [2023-02-25 14:49:10,661][00869] Fps is (10 sec: 3276.1, 60 sec: 3823.0, 300 sec: 3776.6). Total num frames: 7139328. Throughput: 0: 928.3. Samples: 783834. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:49:10,670][00869] Avg episode reward: [(0, '24.950')] | |
| [2023-02-25 14:49:15,495][20479] Updated weights for policy 0, policy_version 1748 (0.0044) | |
| [2023-02-25 14:49:15,658][00869] Fps is (10 sec: 3277.1, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 7159808. Throughput: 0: 943.5. Samples: 788934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:49:15,660][00869] Avg episode reward: [(0, '25.941')] | |
| [2023-02-25 14:49:20,658][00869] Fps is (10 sec: 4096.9, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7180288. Throughput: 0: 967.1. Samples: 792300. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:49:20,666][00869] Avg episode reward: [(0, '26.468')] | |
| [2023-02-25 14:49:24,364][20479] Updated weights for policy 0, policy_version 1758 (0.0012) | |
| [2023-02-25 14:49:25,660][00869] Fps is (10 sec: 4095.3, 60 sec: 3754.6, 300 sec: 3804.5). Total num frames: 7200768. Throughput: 0: 971.6. Samples: 799174. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:49:25,664][00869] Avg episode reward: [(0, '25.715')] | |
| [2023-02-25 14:49:30,660][00869] Fps is (10 sec: 3685.8, 60 sec: 3822.8, 300 sec: 3790.5). Total num frames: 7217152. Throughput: 0: 928.5. Samples: 803594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:49:30,664][00869] Avg episode reward: [(0, '25.969')] | |
| [2023-02-25 14:49:35,658][00869] Fps is (10 sec: 3277.4, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 7233536. Throughput: 0: 931.7. Samples: 805902. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-25 14:49:35,664][00869] Avg episode reward: [(0, '24.729')] | |
| [2023-02-25 14:49:36,618][20479] Updated weights for policy 0, policy_version 1768 (0.0014) | |
| [2023-02-25 14:49:40,658][00869] Fps is (10 sec: 4096.7, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 7258112. Throughput: 0: 978.4. Samples: 812706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:49:40,666][00869] Avg episode reward: [(0, '24.458')] | |
| [2023-02-25 14:49:45,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3804.5). Total num frames: 7278592. Throughput: 0: 961.6. Samples: 818986. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:49:45,666][00869] Avg episode reward: [(0, '25.354')] | |
| [2023-02-25 14:49:46,240][20479] Updated weights for policy 0, policy_version 1778 (0.0012) | |
| [2023-02-25 14:49:50,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3790.6). Total num frames: 7294976. Throughput: 0: 931.8. Samples: 821166. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:49:50,663][00869] Avg episode reward: [(0, '25.082')] | |
| [2023-02-25 14:49:55,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7311360. Throughput: 0: 940.4. Samples: 826150. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:49:55,661][00869] Avg episode reward: [(0, '23.002')] | |
| [2023-02-25 14:49:57,712][20479] Updated weights for policy 0, policy_version 1788 (0.0039) | |
| [2023-02-25 14:50:00,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.6). Total num frames: 7335936. Throughput: 0: 982.0. Samples: 833126. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:50:00,665][00869] Avg episode reward: [(0, '23.666')] | |
| [2023-02-25 14:50:05,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3818.3). Total num frames: 7356416. Throughput: 0: 986.7. Samples: 836702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:50:05,665][00869] Avg episode reward: [(0, '24.830')] | |
| [2023-02-25 14:50:08,162][20479] Updated weights for policy 0, policy_version 1798 (0.0020) | |
| [2023-02-25 14:50:10,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3790.5). Total num frames: 7368704. Throughput: 0: 930.9. Samples: 841062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:50:10,662][00869] Avg episode reward: [(0, '25.990')] | |
| [2023-02-25 14:50:15,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7389184. Throughput: 0: 950.7. Samples: 846372. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:50:15,666][00869] Avg episode reward: [(0, '25.484')] | |
| [2023-02-25 14:50:18,839][20479] Updated weights for policy 0, policy_version 1808 (0.0013) | |
| [2023-02-25 14:50:20,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 7413760. Throughput: 0: 977.0. Samples: 849868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:50:20,661][00869] Avg episode reward: [(0, '25.861')] | |
| [2023-02-25 14:50:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3823.0, 300 sec: 3804.4). Total num frames: 7430144. Throughput: 0: 971.6. Samples: 856430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:50:25,662][00869] Avg episode reward: [(0, '28.039')] | |
| [2023-02-25 14:50:25,681][20465] Saving new best policy, reward=28.039! | |
| [2023-02-25 14:50:30,465][20479] Updated weights for policy 0, policy_version 1818 (0.0021) | |
| [2023-02-25 14:50:30,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3790.5). Total num frames: 7446528. Throughput: 0: 927.5. Samples: 860722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:50:30,667][00869] Avg episode reward: [(0, '28.219')] | |
| [2023-02-25 14:50:30,673][20465] Saving new best policy, reward=28.219! | |
| [2023-02-25 14:50:35,659][00869] Fps is (10 sec: 3686.3, 60 sec: 3891.2, 300 sec: 3776.6). Total num frames: 7467008. Throughput: 0: 932.9. Samples: 863146. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:50:35,665][00869] Avg episode reward: [(0, '28.830')] | |
| [2023-02-25 14:50:35,676][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001823_7467008.pth... | |
| [2023-02-25 14:50:35,802][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001602_6561792.pth | |
| [2023-02-25 14:50:35,815][20465] Saving new best policy, reward=28.830! | |
| [2023-02-25 14:50:40,110][20479] Updated weights for policy 0, policy_version 1828 (0.0022) | |
| [2023-02-25 14:50:40,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 7487488. Throughput: 0: 974.6. Samples: 870008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:50:40,661][00869] Avg episode reward: [(0, '27.802')] | |
| [2023-02-25 14:50:45,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3790.5). Total num frames: 7503872. Throughput: 0: 950.2. Samples: 875886. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:50:45,669][00869] Avg episode reward: [(0, '26.841')] | |
| [2023-02-25 14:50:50,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 7520256. Throughput: 0: 921.6. Samples: 878172. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:50:50,661][00869] Avg episode reward: [(0, '26.896')] | |
| [2023-02-25 14:50:52,422][20479] Updated weights for policy 0, policy_version 1838 (0.0021) | |
| [2023-02-25 14:50:55,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 7540736. Throughput: 0: 941.1. Samples: 883410. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-25 14:50:55,664][00869] Avg episode reward: [(0, '26.795')] | |
| [2023-02-25 14:51:00,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 7565312. Throughput: 0: 983.2. Samples: 890616. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:51:00,661][00869] Avg episode reward: [(0, '25.000')] | |
| [2023-02-25 14:51:01,167][20479] Updated weights for policy 0, policy_version 1848 (0.0019) | |
| [2023-02-25 14:51:05,663][00869] Fps is (10 sec: 4093.9, 60 sec: 3754.4, 300 sec: 3790.5). Total num frames: 7581696. Throughput: 0: 972.9. Samples: 893652. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:51:05,666][00869] Avg episode reward: [(0, '24.367')] | |
| [2023-02-25 14:51:10,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3776.6). Total num frames: 7598080. Throughput: 0: 924.4. Samples: 898030. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:51:10,667][00869] Avg episode reward: [(0, '23.892')] | |
| [2023-02-25 14:51:13,676][20479] Updated weights for policy 0, policy_version 1858 (0.0035) | |
| [2023-02-25 14:51:15,658][00869] Fps is (10 sec: 3688.3, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 7618560. Throughput: 0: 955.9. Samples: 903736. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-25 14:51:15,665][00869] Avg episode reward: [(0, '24.266')] | |
| [2023-02-25 14:51:20,658][00869] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3776.7). Total num frames: 7639040. Throughput: 0: 979.2. Samples: 907212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:51:20,661][00869] Avg episode reward: [(0, '24.390')] | |
| [2023-02-25 14:51:22,488][20479] Updated weights for policy 0, policy_version 1868 (0.0015) | |
| [2023-02-25 14:51:25,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3790.5). Total num frames: 7659520. Throughput: 0: 965.5. Samples: 913456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:51:25,661][00869] Avg episode reward: [(0, '24.879')] | |
| [2023-02-25 14:51:30,658][00869] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7675904. Throughput: 0: 934.2. Samples: 917926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:51:30,662][00869] Avg episode reward: [(0, '24.752')] | |
| [2023-02-25 14:51:34,753][20479] Updated weights for policy 0, policy_version 1878 (0.0014) | |
| [2023-02-25 14:51:35,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3823.0, 300 sec: 3762.8). Total num frames: 7696384. Throughput: 0: 942.4. Samples: 920580. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:51:35,661][00869] Avg episode reward: [(0, '26.887')] | |
| [2023-02-25 14:51:40,658][00869] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3776.7). Total num frames: 7716864. Throughput: 0: 986.7. Samples: 927810. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:51:40,666][00869] Avg episode reward: [(0, '25.390')] | |
| [2023-02-25 14:51:43,890][20479] Updated weights for policy 0, policy_version 1888 (0.0022) | |
| [2023-02-25 14:51:45,659][00869] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3804.4). Total num frames: 7737344. Throughput: 0: 953.9. Samples: 933540. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-25 14:51:45,666][00869] Avg episode reward: [(0, '23.188')] | |
| [2023-02-25 14:51:50,658][00869] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3762.8). Total num frames: 7749632. Throughput: 0: 935.6. Samples: 935748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:51:50,664][00869] Avg episode reward: [(0, '22.506')] | |
| [2023-02-25 14:51:55,437][20479] Updated weights for policy 0, policy_version 1898 (0.0015) | |
| [2023-02-25 14:51:55,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3891.2, 300 sec: 3762.8). Total num frames: 7774208. Throughput: 0: 961.9. Samples: 941316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:51:55,661][00869] Avg episode reward: [(0, '22.045')] | |
| [2023-02-25 14:52:00,658][00869] Fps is (10 sec: 4915.2, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 7798784. Throughput: 0: 992.5. Samples: 948400. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:52:00,661][00869] Avg episode reward: [(0, '21.364')] | |
| [2023-02-25 14:52:05,405][20479] Updated weights for policy 0, policy_version 1908 (0.0013) | |
| [2023-02-25 14:52:05,659][00869] Fps is (10 sec: 4095.6, 60 sec: 3891.5, 300 sec: 3804.4). Total num frames: 7815168. Throughput: 0: 978.9. Samples: 951262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:52:05,664][00869] Avg episode reward: [(0, '21.200')] | |
| [2023-02-25 14:52:10,660][00869] Fps is (10 sec: 2866.8, 60 sec: 3822.9, 300 sec: 3762.7). Total num frames: 7827456. Throughput: 0: 938.9. Samples: 955708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:52:10,669][00869] Avg episode reward: [(0, '22.235')] | |
| [2023-02-25 14:52:15,658][00869] Fps is (10 sec: 3686.8, 60 sec: 3891.2, 300 sec: 3776.7). Total num frames: 7852032. Throughput: 0: 973.3. Samples: 961724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:52:15,661][00869] Avg episode reward: [(0, '25.418')] | |
| [2023-02-25 14:52:16,448][20479] Updated weights for policy 0, policy_version 1918 (0.0016) | |
| [2023-02-25 14:52:20,658][00869] Fps is (10 sec: 4506.2, 60 sec: 3891.2, 300 sec: 3790.5). Total num frames: 7872512. Throughput: 0: 994.4. Samples: 965330. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:52:20,665][00869] Avg episode reward: [(0, '25.540')] | |
| [2023-02-25 14:52:25,659][00869] Fps is (10 sec: 3686.3, 60 sec: 3822.9, 300 sec: 3804.4). Total num frames: 7888896. Throughput: 0: 961.2. Samples: 971062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:52:25,667][00869] Avg episode reward: [(0, '25.835')] | |
| [2023-02-25 14:52:27,552][20479] Updated weights for policy 0, policy_version 1928 (0.0016) | |
| [2023-02-25 14:52:30,658][00869] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 7905280. Throughput: 0: 930.3. Samples: 975404. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-25 14:52:30,661][00869] Avg episode reward: [(0, '26.772')] | |
| [2023-02-25 14:52:35,658][00869] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 7925760. Throughput: 0: 950.0. Samples: 978498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:52:35,669][00869] Avg episode reward: [(0, '28.238')] | |
| [2023-02-25 14:52:35,680][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001935_7925760.pth... | |
| [2023-02-25 14:52:35,877][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001711_7008256.pth | |
| [2023-02-25 14:52:37,757][20479] Updated weights for policy 0, policy_version 1938 (0.0014) | |
| [2023-02-25 14:52:40,658][00869] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3832.2). Total num frames: 7950336. Throughput: 0: 983.0. Samples: 985552. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-25 14:52:40,667][00869] Avg episode reward: [(0, '27.272')] | |
| [2023-02-25 14:52:45,659][00869] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3832.2). Total num frames: 7966720. Throughput: 0: 940.5. Samples: 990724. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-25 14:52:45,670][00869] Avg episode reward: [(0, '26.563')] | |
| [2023-02-25 14:52:49,917][20479] Updated weights for policy 0, policy_version 1948 (0.0019) | |
| [2023-02-25 14:52:50,658][00869] Fps is (10 sec: 2867.2, 60 sec: 3822.9, 300 sec: 3818.3). Total num frames: 7979008. Throughput: 0: 921.8. Samples: 992740. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-25 14:52:50,661][00869] Avg episode reward: [(0, '26.513')] | |
| [2023-02-25 14:52:55,660][00869] Fps is (10 sec: 3276.2, 60 sec: 3754.5, 300 sec: 3804.4). Total num frames: 7999488. Throughput: 0: 944.1. Samples: 998194. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-25 14:52:55,666][00869] Avg episode reward: [(0, '27.218')] | |
| [2023-02-25 14:52:56,854][20465] Stopping Batcher_0... | |
| [2023-02-25 14:52:56,854][20465] Loop batcher_evt_loop terminating... | |
| [2023-02-25 14:52:56,856][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth... | |
| [2023-02-25 14:52:56,855][00869] Component Batcher_0 stopped! | |
| [2023-02-25 14:52:56,904][20479] Weights refcount: 2 0 | |
| [2023-02-25 14:52:56,906][00869] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-25 14:52:56,912][20479] Stopping InferenceWorker_p0-w0... | |
| [2023-02-25 14:52:56,913][20479] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-25 14:52:56,989][20465] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001823_7467008.pth | |
| [2023-02-25 14:52:57,010][20465] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth... | |
| [2023-02-25 14:52:57,123][20465] Stopping LearnerWorker_p0... | |
| [2023-02-25 14:52:57,123][20465] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-25 14:52:57,122][00869] Component LearnerWorker_p0 stopped! | |
| [2023-02-25 14:52:57,158][00869] Component RolloutWorker_w5 stopped! | |
| [2023-02-25 14:52:57,164][20480] Stopping RolloutWorker_w0... | |
| [2023-02-25 14:52:57,164][00869] Component RolloutWorker_w0 stopped! | |
| [2023-02-25 14:52:57,169][20492] Stopping RolloutWorker_w5... | |
| [2023-02-25 14:52:57,170][20492] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-25 14:52:57,172][00869] Component RolloutWorker_w4 stopped! | |
| [2023-02-25 14:52:57,171][20500] Stopping RolloutWorker_w4... | |
| [2023-02-25 14:52:57,176][20500] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-25 14:52:57,167][20480] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-25 14:52:57,182][20489] Stopping RolloutWorker_w2... | |
| [2023-02-25 14:52:57,184][00869] Component RolloutWorker_w2 stopped! | |
| [2023-02-25 14:52:57,185][20489] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-25 14:52:57,191][20498] Stopping RolloutWorker_w6... | |
| [2023-02-25 14:52:57,191][20498] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-25 14:52:57,192][00869] Component RolloutWorker_w6 stopped! | |
| [2023-02-25 14:52:57,207][20506] Stopping RolloutWorker_w7... | |
| [2023-02-25 14:52:57,207][20506] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-25 14:52:57,208][00869] Component RolloutWorker_w7 stopped! | |
| [2023-02-25 14:52:57,233][00869] Component RolloutWorker_w3 stopped! | |
| [2023-02-25 14:52:57,242][20490] Stopping RolloutWorker_w3... | |
| [2023-02-25 14:52:57,243][20490] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-25 14:52:57,259][00869] Component RolloutWorker_w1 stopped! | |
| [2023-02-25 14:52:57,265][00869] Waiting for process learner_proc0 to stop... | |
| [2023-02-25 14:52:57,270][20481] Stopping RolloutWorker_w1... | |
| [2023-02-25 14:52:57,271][20481] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-25 14:52:59,908][00869] Waiting for process inference_proc0-0 to join... | |
| [2023-02-25 14:52:59,983][00869] Waiting for process rollout_proc0 to join... | |
| [2023-02-25 14:52:59,985][00869] Waiting for process rollout_proc1 to join... | |
| [2023-02-25 14:52:59,988][00869] Waiting for process rollout_proc2 to join... | |
| [2023-02-25 14:52:59,992][00869] Waiting for process rollout_proc3 to join... | |
| [2023-02-25 14:52:59,995][00869] Waiting for process rollout_proc4 to join... | |
| [2023-02-25 14:52:59,999][00869] Waiting for process rollout_proc5 to join... | |
| [2023-02-25 14:53:00,006][00869] Waiting for process rollout_proc6 to join... | |
| [2023-02-25 14:53:00,008][00869] Waiting for process rollout_proc7 to join... | |
| [2023-02-25 14:53:00,010][00869] Batcher 0 profile tree view: | |
| batching: 25.6095, releasing_batches: 0.0239 | |
| [2023-02-25 14:53:00,013][00869] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 527.6749 | |
| update_model: 7.4080 | |
| weight_update: 0.0019 | |
| one_step: 0.0081 | |
| handle_policy_step: 502.1283 | |
| deserialize: 14.9062, stack: 2.8832, obs_to_device_normalize: 113.1398, forward: 237.8537, send_messages: 25.6391 | |
| prepare_outputs: 82.7057 | |
| to_cpu: 51.8572 | |
| [2023-02-25 14:53:00,014][00869] Learner 0 profile tree view: | |
| misc: 0.0062, prepare_batch: 18.1951 | |
| train: 79.5026 | |
| epoch_init: 0.0080, minibatch_init: 0.0180, losses_postprocess: 0.6632, kl_divergence: 0.6703, after_optimizer: 3.1131 | |
| calculate_losses: 26.0573 | |
| losses_init: 0.0035, forward_head: 1.8272, bptt_initial: 17.0259, tail: 1.1716, advantages_returns: 0.2958, losses: 3.3208 | |
| bptt: 2.1152 | |
| bptt_forward_core: 2.0204 | |
| update: 48.3142 | |
| clip: 1.4455 | |
| [2023-02-25 14:53:00,015][00869] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3206, enqueue_policy_requests: 137.3416, env_step: 816.8512, overhead: 21.0230, complete_rollouts: 7.2355 | |
| save_policy_outputs: 20.4243 | |
| split_output_tensors: 9.8348 | |
| [2023-02-25 14:53:00,017][00869] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3687, enqueue_policy_requests: 144.2824, env_step: 807.5369, overhead: 20.4800, complete_rollouts: 6.4286 | |
| save_policy_outputs: 19.5378 | |
| split_output_tensors: 9.5174 | |
| [2023-02-25 14:53:00,023][00869] Loop Runner_EvtLoop terminating... | |
| [2023-02-25 14:53:00,024][00869] Runner profile tree view: | |
| main_loop: 1101.9735 | |
| [2023-02-25 14:53:00,025][00869] Collected {0: 8007680}, FPS: 3631.5 | |
| [2023-02-25 14:53:00,069][00869] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-25 14:53:00,072][00869] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-25 14:53:00,073][00869] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-25 14:53:00,075][00869] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-25 14:53:00,079][00869] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-25 14:53:00,082][00869] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-25 14:53:00,084][00869] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-25 14:53:00,085][00869] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-25 14:53:00,088][00869] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-25 14:53:00,090][00869] Adding new argument 'hf_repository'='chist/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-25 14:53:00,091][00869] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-25 14:53:00,092][00869] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-25 14:53:00,093][00869] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-25 14:53:00,095][00869] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-25 14:53:00,096][00869] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-25 14:53:00,122][00869] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-25 14:53:00,125][00869] RunningMeanStd input shape: (1,) | |
| [2023-02-25 14:53:00,142][00869] ConvEncoder: input_channels=3 | |
| [2023-02-25 14:53:00,195][00869] Conv encoder output size: 512 | |
| [2023-02-25 14:53:00,197][00869] Policy head output size: 512 | |
| [2023-02-25 14:53:00,225][00869] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001955_8007680.pth... | |
| [2023-02-25 14:53:01,117][00869] Num frames 100... | |
| [2023-02-25 14:53:01,237][00869] Num frames 200... | |
| [2023-02-25 14:53:01,360][00869] Num frames 300... | |
| [2023-02-25 14:53:01,509][00869] Num frames 400... | |
| [2023-02-25 14:53:01,679][00869] Num frames 500... | |
| [2023-02-25 14:53:01,853][00869] Num frames 600... | |
| [2023-02-25 14:53:02,015][00869] Num frames 700... | |
| [2023-02-25 14:53:02,181][00869] Num frames 800... | |
| [2023-02-25 14:53:02,343][00869] Num frames 900... | |
| [2023-02-25 14:53:02,534][00869] Num frames 1000... | |
| [2023-02-25 14:53:02,697][00869] Num frames 1100... | |
| [2023-02-25 14:53:02,857][00869] Num frames 1200... | |
| [2023-02-25 14:53:03,018][00869] Num frames 1300... | |
| [2023-02-25 14:53:03,184][00869] Num frames 1400... | |
| [2023-02-25 14:53:03,382][00869] Avg episode rewards: #0: 35.850, true rewards: #0: 14.850 | |
| [2023-02-25 14:53:03,384][00869] Avg episode reward: 35.850, avg true_objective: 14.850 | |
| [2023-02-25 14:53:03,410][00869] Num frames 1500... | |
| [2023-02-25 14:53:03,568][00869] Num frames 1600... | |
| [2023-02-25 14:53:03,733][00869] Num frames 1700... | |
| [2023-02-25 14:53:03,896][00869] Num frames 1800... | |
| [2023-02-25 14:53:04,067][00869] Num frames 1900... | |
| [2023-02-25 14:53:04,229][00869] Num frames 2000... | |
| [2023-02-25 14:53:04,396][00869] Num frames 2100... | |
| [2023-02-25 14:53:04,560][00869] Num frames 2200... | |
| [2023-02-25 14:53:04,727][00869] Num frames 2300... | |
| [2023-02-25 14:53:04,899][00869] Num frames 2400... | |
| [2023-02-25 14:53:05,033][00869] Avg episode rewards: #0: 27.725, true rewards: #0: 12.225 | |
| [2023-02-25 14:53:05,035][00869] Avg episode reward: 27.725, avg true_objective: 12.225 | |
| [2023-02-25 14:53:05,104][00869] Num frames 2500... | |
| [2023-02-25 14:53:05,215][00869] Num frames 2600... | |
| [2023-02-25 14:53:05,333][00869] Num frames 2700... | |
| [2023-02-25 14:53:05,409][00869] Avg episode rewards: #0: 20.053, true rewards: #0: 9.053 | |
| [2023-02-25 14:53:05,412][00869] Avg episode reward: 20.053, avg true_objective: 9.053 | |
| [2023-02-25 14:53:05,513][00869] Num frames 2800... | |
| [2023-02-25 14:53:05,625][00869] Num frames 2900... | |
| [2023-02-25 14:53:05,735][00869] Num frames 3000... | |
| [2023-02-25 14:53:05,864][00869] Num frames 3100... | |
| [2023-02-25 14:53:05,978][00869] Num frames 3200... | |
| [2023-02-25 14:53:06,103][00869] Num frames 3300... | |
| [2023-02-25 14:53:06,227][00869] Avg episode rewards: #0: 17.650, true rewards: #0: 8.400 | |
| [2023-02-25 14:53:06,229][00869] Avg episode reward: 17.650, avg true_objective: 8.400 | |
| [2023-02-25 14:53:06,276][00869] Num frames 3400... | |
| [2023-02-25 14:53:06,387][00869] Num frames 3500... | |
| [2023-02-25 14:53:06,509][00869] Num frames 3600... | |
| [2023-02-25 14:53:06,622][00869] Num frames 3700... | |
| [2023-02-25 14:53:06,746][00869] Num frames 3800... | |
| [2023-02-25 14:53:06,863][00869] Num frames 3900... | |
| [2023-02-25 14:53:06,982][00869] Num frames 4000... | |
| [2023-02-25 14:53:07,109][00869] Num frames 4100... | |
| [2023-02-25 14:53:07,219][00869] Num frames 4200... | |
| [2023-02-25 14:53:07,344][00869] Num frames 4300... | |
| [2023-02-25 14:53:07,405][00869] Avg episode rewards: #0: 17.808, true rewards: #0: 8.608 | |
| [2023-02-25 14:53:07,408][00869] Avg episode reward: 17.808, avg true_objective: 8.608 | |
| [2023-02-25 14:53:07,526][00869] Num frames 4400... | |
| [2023-02-25 14:53:07,645][00869] Num frames 4500... | |
| [2023-02-25 14:53:07,766][00869] Num frames 4600... | |
| [2023-02-25 14:53:07,890][00869] Num frames 4700... | |
| [2023-02-25 14:53:08,009][00869] Num frames 4800... | |
| [2023-02-25 14:53:08,127][00869] Num frames 4900... | |
| [2023-02-25 14:53:08,244][00869] Num frames 5000... | |
| [2023-02-25 14:53:08,358][00869] Num frames 5100... | |
| [2023-02-25 14:53:08,479][00869] Num frames 5200... | |
| [2023-02-25 14:53:08,601][00869] Num frames 5300... | |
| [2023-02-25 14:53:08,723][00869] Num frames 5400... | |
| [2023-02-25 14:53:08,838][00869] Num frames 5500... | |
| [2023-02-25 14:53:08,962][00869] Num frames 5600... | |
| [2023-02-25 14:53:09,088][00869] Num frames 5700... | |
| [2023-02-25 14:53:09,204][00869] Num frames 5800... | |
| [2023-02-25 14:53:09,319][00869] Num frames 5900... | |
| [2023-02-25 14:53:09,441][00869] Avg episode rewards: #0: 21.098, true rewards: #0: 9.932 | |
| [2023-02-25 14:53:09,443][00869] Avg episode reward: 21.098, avg true_objective: 9.932 | |
| [2023-02-25 14:53:09,493][00869] Num frames 6000... | |
| [2023-02-25 14:53:09,607][00869] Num frames 6100... | |
| [2023-02-25 14:53:09,726][00869] Num frames 6200... | |
| [2023-02-25 14:53:09,843][00869] Num frames 6300... | |
| [2023-02-25 14:53:09,957][00869] Num frames 6400... | |
| [2023-02-25 14:53:10,077][00869] Num frames 6500... | |
| [2023-02-25 14:53:10,195][00869] Num frames 6600... | |
| [2023-02-25 14:53:10,309][00869] Num frames 6700... | |
| [2023-02-25 14:53:10,428][00869] Num frames 6800... | |
| [2023-02-25 14:53:10,542][00869] Num frames 6900... | |
| [2023-02-25 14:53:10,672][00869] Num frames 7000... | |
| [2023-02-25 14:53:10,784][00869] Num frames 7100... | |
| [2023-02-25 14:53:10,897][00869] Avg episode rewards: #0: 22.643, true rewards: #0: 10.214 | |
| [2023-02-25 14:53:10,898][00869] Avg episode reward: 22.643, avg true_objective: 10.214 | |
| [2023-02-25 14:53:10,959][00869] Num frames 7200... | |
| [2023-02-25 14:53:11,075][00869] Num frames 7300... | |
| [2023-02-25 14:53:11,200][00869] Num frames 7400... | |
| [2023-02-25 14:53:11,314][00869] Num frames 7500... | |
| [2023-02-25 14:53:11,433][00869] Num frames 7600... | |
| [2023-02-25 14:53:11,548][00869] Num frames 7700... | |
| [2023-02-25 14:53:11,662][00869] Num frames 7800... | |
| [2023-02-25 14:53:11,785][00869] Num frames 7900... | |
| [2023-02-25 14:53:11,898][00869] Avg episode rewards: #0: 21.688, true rewards: #0: 9.937 | |
| [2023-02-25 14:53:11,900][00869] Avg episode reward: 21.688, avg true_objective: 9.937 | |
| [2023-02-25 14:53:11,964][00869] Num frames 8000... | |
| [2023-02-25 14:53:12,085][00869] Num frames 8100... | |
| [2023-02-25 14:53:12,210][00869] Num frames 8200... | |
| [2023-02-25 14:53:12,329][00869] Avg episode rewards: #0: 19.840, true rewards: #0: 9.173 | |
| [2023-02-25 14:53:12,330][00869] Avg episode reward: 19.840, avg true_objective: 9.173 | |
| [2023-02-25 14:53:12,386][00869] Num frames 8300... | |
| [2023-02-25 14:53:12,507][00869] Num frames 8400... | |
| [2023-02-25 14:53:12,619][00869] Num frames 8500... | |
| [2023-02-25 14:53:12,754][00869] Num frames 8600... | |
| [2023-02-25 14:53:12,877][00869] Num frames 8700... | |
| [2023-02-25 14:53:12,997][00869] Num frames 8800... | |
| [2023-02-25 14:53:13,114][00869] Num frames 8900... | |
| [2023-02-25 14:53:13,243][00869] Num frames 9000... | |
| [2023-02-25 14:53:13,359][00869] Num frames 9100... | |
| [2023-02-25 14:53:13,473][00869] Num frames 9200... | |
| [2023-02-25 14:53:13,595][00869] Num frames 9300... | |
| [2023-02-25 14:53:13,715][00869] Num frames 9400... | |
| [2023-02-25 14:53:13,832][00869] Num frames 9500... | |
| [2023-02-25 14:53:13,891][00869] Avg episode rewards: #0: 21.101, true rewards: #0: 9.501 | |
| [2023-02-25 14:53:13,892][00869] Avg episode reward: 21.101, avg true_objective: 9.501 | |
| [2023-02-25 14:54:12,964][00869] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |