| [2023-02-23 06:30:35,517][10762] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-02-23 06:30:35,520][10762] Rollout worker 0 uses device cpu | |
| [2023-02-23 06:30:35,522][10762] Rollout worker 1 uses device cpu | |
| [2023-02-23 06:30:35,524][10762] Rollout worker 2 uses device cpu | |
| [2023-02-23 06:30:35,528][10762] Rollout worker 3 uses device cpu | |
| [2023-02-23 06:30:35,529][10762] Rollout worker 4 uses device cpu | |
| [2023-02-23 06:30:35,531][10762] Rollout worker 5 uses device cpu | |
| [2023-02-23 06:30:35,532][10762] Rollout worker 6 uses device cpu | |
| [2023-02-23 06:30:35,534][10762] Rollout worker 7 uses device cpu | |
| [2023-02-23 06:30:35,765][10762] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 06:30:35,768][10762] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-02-23 06:30:35,809][10762] Starting all processes... | |
| [2023-02-23 06:30:35,811][10762] Starting process learner_proc0 | |
| [2023-02-23 06:30:35,884][10762] Starting all processes... | |
| [2023-02-23 06:30:35,935][10762] Starting process inference_proc0-0 | |
| [2023-02-23 06:30:35,935][10762] Starting process rollout_proc0 | |
| [2023-02-23 06:30:35,937][10762] Starting process rollout_proc1 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc2 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc3 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc4 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc5 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc6 | |
| [2023-02-23 06:30:35,938][10762] Starting process rollout_proc7 | |
| [2023-02-23 06:30:47,784][11537] Worker 2 uses CPU cores [0] | |
| [2023-02-23 06:30:48,099][11516] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 06:30:48,100][11516] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-02-23 06:30:48,181][11538] Worker 4 uses CPU cores [0] | |
| [2023-02-23 06:30:48,240][11532] Worker 1 uses CPU cores [1] | |
| [2023-02-23 06:30:48,301][11530] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 06:30:48,302][11530] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-02-23 06:30:48,372][11543] Worker 5 uses CPU cores [1] | |
| [2023-02-23 06:30:48,514][11539] Worker 3 uses CPU cores [1] | |
| [2023-02-23 06:30:48,538][11531] Worker 0 uses CPU cores [0] | |
| [2023-02-23 06:30:48,614][11542] Worker 7 uses CPU cores [1] | |
| [2023-02-23 06:30:48,759][11540] Worker 6 uses CPU cores [0] | |
| [2023-02-23 06:30:48,870][11516] Num visible devices: 1 | |
| [2023-02-23 06:30:48,870][11530] Num visible devices: 1 | |
| [2023-02-23 06:30:48,882][11516] Starting seed is not provided | |
| [2023-02-23 06:30:48,882][11516] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 06:30:48,883][11516] Initializing actor-critic model on device cuda:0 | |
| [2023-02-23 06:30:48,883][11516] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 06:30:48,885][11516] RunningMeanStd input shape: (1,) | |
| [2023-02-23 06:30:48,897][11516] ConvEncoder: input_channels=3 | |
| [2023-02-23 06:30:49,174][11516] Conv encoder output size: 512 | |
| [2023-02-23 06:30:49,174][11516] Policy head output size: 512 | |
| [2023-02-23 06:30:49,222][11516] Created Actor Critic model with architecture: | |
| [2023-02-23 06:30:49,223][11516] 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) | |
| ) | |
| ) | |
| [2023-02-23 06:30:55,753][10762] Heartbeat connected on Batcher_0 | |
| [2023-02-23 06:30:55,766][10762] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-02-23 06:30:55,777][10762] Heartbeat connected on RolloutWorker_w0 | |
| [2023-02-23 06:30:55,782][10762] Heartbeat connected on RolloutWorker_w1 | |
| [2023-02-23 06:30:55,786][10762] Heartbeat connected on RolloutWorker_w2 | |
| [2023-02-23 06:30:55,791][10762] Heartbeat connected on RolloutWorker_w3 | |
| [2023-02-23 06:30:55,795][10762] Heartbeat connected on RolloutWorker_w4 | |
| [2023-02-23 06:30:55,799][10762] Heartbeat connected on RolloutWorker_w5 | |
| [2023-02-23 06:30:55,805][10762] Heartbeat connected on RolloutWorker_w6 | |
| [2023-02-23 06:30:55,809][10762] Heartbeat connected on RolloutWorker_w7 | |
| [2023-02-23 06:30:56,671][11516] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-02-23 06:30:56,672][11516] No checkpoints found | |
| [2023-02-23 06:30:56,673][11516] Did not load from checkpoint, starting from scratch! | |
| [2023-02-23 06:30:56,673][11516] Initialized policy 0 weights for model version 0 | |
| [2023-02-23 06:30:56,681][11516] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-02-23 06:30:56,688][11516] LearnerWorker_p0 finished initialization! | |
| [2023-02-23 06:30:56,688][10762] Heartbeat connected on LearnerWorker_p0 | |
| [2023-02-23 06:30:56,929][11530] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 06:30:56,930][11530] RunningMeanStd input shape: (1,) | |
| [2023-02-23 06:30:56,956][11530] ConvEncoder: input_channels=3 | |
| [2023-02-23 06:30:57,113][11530] Conv encoder output size: 512 | |
| [2023-02-23 06:30:57,114][11530] Policy head output size: 512 | |
| [2023-02-23 06:30:59,667][10762] Inference worker 0-0 is ready! | |
| [2023-02-23 06:30:59,669][10762] All inference workers are ready! Signal rollout workers to start! | |
| [2023-02-23 06:30:59,772][11531] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,782][11538] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,812][11537] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,815][11540] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,822][11532] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,832][11542] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,830][11539] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:30:59,852][11543] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:31:00,675][11542] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:00,677][11543] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:00,987][11531] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:00,996][11540] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:01,001][11538] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:01,282][10762] 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) | |
| [2023-02-23 06:31:01,607][11543] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:01,613][11542] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:02,047][11537] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:02,053][11538] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:02,159][11540] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:02,167][11532] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:02,873][11542] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:02,880][11543] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:03,110][11532] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:03,189][11537] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:03,318][11531] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:03,459][11538] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:03,816][11542] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:04,430][11540] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:04,545][11539] Decorrelating experience for 0 frames... | |
| [2023-02-23 06:31:04,702][11532] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:04,708][11537] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:04,868][11531] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:05,609][11543] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:05,712][11539] Decorrelating experience for 32 frames... | |
| [2023-02-23 06:31:05,927][11532] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:06,282][10762] 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) | |
| [2023-02-23 06:31:06,328][11540] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:06,535][11538] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:06,541][11537] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:07,024][11531] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:07,040][11539] Decorrelating experience for 64 frames... | |
| [2023-02-23 06:31:07,427][11539] Decorrelating experience for 96 frames... | |
| [2023-02-23 06:31:11,283][10762] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 40.8. Samples: 408. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-02-23 06:31:11,286][10762] Avg episode reward: [(0, '1.473')] | |
| [2023-02-23 06:31:12,511][11516] Signal inference workers to stop experience collection... | |
| [2023-02-23 06:31:12,535][11530] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-02-23 06:31:14,922][11516] Signal inference workers to resume experience collection... | |
| [2023-02-23 06:31:14,922][11530] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-02-23 06:31:16,282][10762] Fps is (10 sec: 409.6, 60 sec: 273.1, 300 sec: 273.1). Total num frames: 4096. Throughput: 0: 147.5. Samples: 2212. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-02-23 06:31:16,285][10762] Avg episode reward: [(0, '2.133')] | |
| [2023-02-23 06:31:21,282][10762] Fps is (10 sec: 2867.4, 60 sec: 1433.6, 300 sec: 1433.6). Total num frames: 28672. Throughput: 0: 347.7. Samples: 6954. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-23 06:31:21,285][10762] Avg episode reward: [(0, '3.648')] | |
| [2023-02-23 06:31:24,048][11530] Updated weights for policy 0, policy_version 10 (0.0013) | |
| [2023-02-23 06:31:26,283][10762] Fps is (10 sec: 4505.2, 60 sec: 1966.0, 300 sec: 1966.0). Total num frames: 49152. Throughput: 0: 410.1. Samples: 10252. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:31:26,286][10762] Avg episode reward: [(0, '4.354')] | |
| [2023-02-23 06:31:31,282][10762] Fps is (10 sec: 3276.8, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 61440. Throughput: 0: 524.3. Samples: 15730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:31:31,284][10762] Avg episode reward: [(0, '4.326')] | |
| [2023-02-23 06:31:36,282][10762] Fps is (10 sec: 2867.4, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 77824. Throughput: 0: 566.5. Samples: 19828. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:31:36,287][10762] Avg episode reward: [(0, '4.429')] | |
| [2023-02-23 06:31:36,936][11530] Updated weights for policy 0, policy_version 20 (0.0022) | |
| [2023-02-23 06:31:41,282][10762] Fps is (10 sec: 3686.4, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 568.6. Samples: 22746. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-02-23 06:31:41,284][10762] Avg episode reward: [(0, '4.458')] | |
| [2023-02-23 06:31:46,152][11530] Updated weights for policy 0, policy_version 30 (0.0013) | |
| [2023-02-23 06:31:46,282][10762] Fps is (10 sec: 4505.6, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 122880. Throughput: 0: 654.1. Samples: 29434. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:31:46,284][10762] Avg episode reward: [(0, '4.456')] | |
| [2023-02-23 06:31:46,291][11516] Saving new best policy, reward=4.456! | |
| [2023-02-23 06:31:51,282][10762] Fps is (10 sec: 3686.4, 60 sec: 2703.4, 300 sec: 2703.4). Total num frames: 135168. Throughput: 0: 763.2. Samples: 34342. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 06:31:51,286][10762] Avg episode reward: [(0, '4.364')] | |
| [2023-02-23 06:31:56,282][10762] Fps is (10 sec: 2867.2, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 801.2. Samples: 36460. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 06:31:56,288][10762] Avg episode reward: [(0, '4.346')] | |
| [2023-02-23 06:31:59,690][11530] Updated weights for policy 0, policy_version 40 (0.0033) | |
| [2023-02-23 06:32:01,282][10762] Fps is (10 sec: 3276.8, 60 sec: 2798.9, 300 sec: 2798.9). Total num frames: 167936. Throughput: 0: 873.0. Samples: 41496. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:32:01,286][10762] Avg episode reward: [(0, '4.468')] | |
| [2023-02-23 06:32:01,296][11516] Saving new best policy, reward=4.468! | |
| [2023-02-23 06:32:06,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3208.5, 300 sec: 2961.7). Total num frames: 192512. Throughput: 0: 917.9. Samples: 48260. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:32:06,285][10762] Avg episode reward: [(0, '4.576')] | |
| [2023-02-23 06:32:06,295][11516] Saving new best policy, reward=4.576! | |
| [2023-02-23 06:32:10,024][11530] Updated weights for policy 0, policy_version 50 (0.0028) | |
| [2023-02-23 06:32:11,282][10762] Fps is (10 sec: 3686.3, 60 sec: 3413.4, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 901.1. Samples: 50800. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:32:11,290][10762] Avg episode reward: [(0, '4.478')] | |
| [2023-02-23 06:32:16,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 2949.1). Total num frames: 221184. Throughput: 0: 871.1. Samples: 54928. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:32:16,288][10762] Avg episode reward: [(0, '4.421')] | |
| [2023-02-23 06:32:21,282][10762] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3020.8). Total num frames: 241664. Throughput: 0: 905.1. Samples: 60558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:32:21,285][10762] Avg episode reward: [(0, '4.430')] | |
| [2023-02-23 06:32:22,035][11530] Updated weights for policy 0, policy_version 60 (0.0012) | |
| [2023-02-23 06:32:26,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 912.5. Samples: 63808. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:32:26,284][10762] Avg episode reward: [(0, '4.280')] | |
| [2023-02-23 06:32:31,284][10762] Fps is (10 sec: 3685.6, 60 sec: 3618.0, 300 sec: 3094.7). Total num frames: 278528. Throughput: 0: 889.1. Samples: 69446. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:32:31,286][10762] Avg episode reward: [(0, '4.353')] | |
| [2023-02-23 06:32:31,303][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth... | |
| [2023-02-23 06:32:33,766][11530] Updated weights for policy 0, policy_version 70 (0.0017) | |
| [2023-02-23 06:32:36,283][10762] Fps is (10 sec: 2866.9, 60 sec: 3549.8, 300 sec: 3061.2). Total num frames: 290816. Throughput: 0: 870.7. Samples: 73524. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:32:36,292][10762] Avg episode reward: [(0, '4.235')] | |
| [2023-02-23 06:32:41,286][10762] Fps is (10 sec: 3276.1, 60 sec: 3549.6, 300 sec: 3112.8). Total num frames: 311296. Throughput: 0: 880.4. Samples: 76082. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 06:32:41,288][10762] Avg episode reward: [(0, '4.422')] | |
| [2023-02-23 06:32:44,536][11530] Updated weights for policy 0, policy_version 80 (0.0015) | |
| [2023-02-23 06:32:46,283][10762] Fps is (10 sec: 4095.9, 60 sec: 3481.5, 300 sec: 3159.7). Total num frames: 331776. Throughput: 0: 915.2. Samples: 82682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:32:46,287][10762] Avg episode reward: [(0, '4.557')] | |
| [2023-02-23 06:32:51,284][10762] Fps is (10 sec: 3687.1, 60 sec: 3549.7, 300 sec: 3165.0). Total num frames: 348160. Throughput: 0: 884.3. Samples: 88054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:32:51,288][10762] Avg episode reward: [(0, '4.305')] | |
| [2023-02-23 06:32:56,283][10762] Fps is (10 sec: 3276.9, 60 sec: 3549.8, 300 sec: 3169.9). Total num frames: 364544. Throughput: 0: 874.2. Samples: 90138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:32:56,285][10762] Avg episode reward: [(0, '4.188')] | |
| [2023-02-23 06:32:57,321][11530] Updated weights for policy 0, policy_version 90 (0.0025) | |
| [2023-02-23 06:33:01,282][10762] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3208.5). Total num frames: 385024. Throughput: 0: 891.2. Samples: 95032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:33:01,284][10762] Avg episode reward: [(0, '4.298')] | |
| [2023-02-23 06:33:06,282][10762] Fps is (10 sec: 4096.4, 60 sec: 3549.9, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 913.5. Samples: 101666. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:06,285][10762] Avg episode reward: [(0, '4.442')] | |
| [2023-02-23 06:33:06,892][11530] Updated weights for policy 0, policy_version 100 (0.0017) | |
| [2023-02-23 06:33:11,282][10762] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3245.3). Total num frames: 421888. Throughput: 0: 908.5. Samples: 104692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:33:11,288][10762] Avg episode reward: [(0, '4.537')] | |
| [2023-02-23 06:33:16,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3216.1). Total num frames: 434176. Throughput: 0: 877.9. Samples: 108950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:16,287][10762] Avg episode reward: [(0, '4.408')] | |
| [2023-02-23 06:33:19,873][11530] Updated weights for policy 0, policy_version 110 (0.0020) | |
| [2023-02-23 06:33:21,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 905.5. Samples: 114270. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:21,290][10762] Avg episode reward: [(0, '4.247')] | |
| [2023-02-23 06:33:26,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3305.0). Total num frames: 479232. Throughput: 0: 924.0. Samples: 117656. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:26,288][10762] Avg episode reward: [(0, '4.476')] | |
| [2023-02-23 06:33:29,091][11530] Updated weights for policy 0, policy_version 120 (0.0012) | |
| [2023-02-23 06:33:31,282][10762] Fps is (10 sec: 4095.9, 60 sec: 3618.3, 300 sec: 3304.1). Total num frames: 495616. Throughput: 0: 911.1. Samples: 123680. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:31,289][10762] Avg episode reward: [(0, '4.698')] | |
| [2023-02-23 06:33:31,297][11516] Saving new best policy, reward=4.698! | |
| [2023-02-23 06:33:36,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3276.8). Total num frames: 507904. Throughput: 0: 884.3. Samples: 127846. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:33:36,286][10762] Avg episode reward: [(0, '4.560')] | |
| [2023-02-23 06:33:41,282][10762] Fps is (10 sec: 3276.9, 60 sec: 3618.4, 300 sec: 3302.4). Total num frames: 528384. Throughput: 0: 887.4. Samples: 130068. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:33:41,290][10762] Avg episode reward: [(0, '4.773')] | |
| [2023-02-23 06:33:41,301][11516] Saving new best policy, reward=4.773! | |
| [2023-02-23 06:33:41,843][11530] Updated weights for policy 0, policy_version 130 (0.0031) | |
| [2023-02-23 06:33:46,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3326.4). Total num frames: 548864. Throughput: 0: 926.5. Samples: 136724. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:33:46,288][10762] Avg episode reward: [(0, '4.744')] | |
| [2023-02-23 06:33:51,287][10762] Fps is (10 sec: 4093.9, 60 sec: 3686.2, 300 sec: 3349.0). Total num frames: 569344. Throughput: 0: 909.0. Samples: 142578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:33:51,297][10762] Avg episode reward: [(0, '4.402')] | |
| [2023-02-23 06:33:52,561][11530] Updated weights for policy 0, policy_version 140 (0.0026) | |
| [2023-02-23 06:33:56,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 887.7. Samples: 144640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:33:56,288][10762] Avg episode reward: [(0, '4.327')] | |
| [2023-02-23 06:34:01,282][10762] Fps is (10 sec: 3278.5, 60 sec: 3618.1, 300 sec: 3345.1). Total num frames: 602112. Throughput: 0: 893.8. Samples: 149172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:34:01,290][10762] Avg episode reward: [(0, '4.249')] | |
| [2023-02-23 06:34:04,064][11530] Updated weights for policy 0, policy_version 150 (0.0014) | |
| [2023-02-23 06:34:06,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3365.4). Total num frames: 622592. Throughput: 0: 926.3. Samples: 155954. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:34:06,285][10762] Avg episode reward: [(0, '4.408')] | |
| [2023-02-23 06:34:11,292][10762] Fps is (10 sec: 4091.8, 60 sec: 3685.8, 300 sec: 3384.4). Total num frames: 643072. Throughput: 0: 924.7. Samples: 159278. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-02-23 06:34:11,294][10762] Avg episode reward: [(0, '4.637')] | |
| [2023-02-23 06:34:15,504][11530] Updated weights for policy 0, policy_version 160 (0.0023) | |
| [2023-02-23 06:34:16,288][10762] Fps is (10 sec: 3274.8, 60 sec: 3686.0, 300 sec: 3360.7). Total num frames: 655360. Throughput: 0: 889.1. Samples: 163696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:34:16,293][10762] Avg episode reward: [(0, '4.736')] | |
| [2023-02-23 06:34:21,282][10762] Fps is (10 sec: 2870.1, 60 sec: 3618.1, 300 sec: 3358.7). Total num frames: 671744. Throughput: 0: 902.4. Samples: 168452. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:34:21,291][10762] Avg episode reward: [(0, '4.555')] | |
| [2023-02-23 06:34:26,100][11530] Updated weights for policy 0, policy_version 170 (0.0025) | |
| [2023-02-23 06:34:26,282][10762] Fps is (10 sec: 4098.5, 60 sec: 3618.1, 300 sec: 3396.7). Total num frames: 696320. Throughput: 0: 926.5. Samples: 171760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:34:26,284][10762] Avg episode reward: [(0, '4.406')] | |
| [2023-02-23 06:34:31,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3393.8). Total num frames: 712704. Throughput: 0: 924.8. Samples: 178340. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:34:31,292][10762] Avg episode reward: [(0, '4.414')] | |
| [2023-02-23 06:34:31,306][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth... | |
| [2023-02-23 06:34:36,283][10762] Fps is (10 sec: 2866.9, 60 sec: 3618.1, 300 sec: 3372.0). Total num frames: 724992. Throughput: 0: 886.3. Samples: 182460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:34:36,288][10762] Avg episode reward: [(0, '4.472')] | |
| [2023-02-23 06:34:39,117][11530] Updated weights for policy 0, policy_version 180 (0.0012) | |
| [2023-02-23 06:34:41,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3388.5). Total num frames: 745472. Throughput: 0: 887.5. Samples: 184578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:34:41,284][10762] Avg episode reward: [(0, '4.386')] | |
| [2023-02-23 06:34:46,282][10762] Fps is (10 sec: 4096.5, 60 sec: 3618.1, 300 sec: 3404.2). Total num frames: 765952. Throughput: 0: 926.3. Samples: 190854. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:34:46,285][10762] Avg episode reward: [(0, '4.570')] | |
| [2023-02-23 06:34:48,521][11530] Updated weights for policy 0, policy_version 190 (0.0022) | |
| [2023-02-23 06:34:51,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.4, 300 sec: 3419.3). Total num frames: 786432. Throughput: 0: 916.9. Samples: 197216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:34:51,292][10762] Avg episode reward: [(0, '4.609')] | |
| [2023-02-23 06:34:56,284][10762] Fps is (10 sec: 3276.1, 60 sec: 3618.0, 300 sec: 3398.8). Total num frames: 798720. Throughput: 0: 890.0. Samples: 199320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:34:56,291][10762] Avg episode reward: [(0, '4.686')] | |
| [2023-02-23 06:35:01,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3396.3). Total num frames: 815104. Throughput: 0: 885.3. Samples: 203528. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:35:01,288][10762] Avg episode reward: [(0, '4.400')] | |
| [2023-02-23 06:35:01,450][11530] Updated weights for policy 0, policy_version 200 (0.0034) | |
| [2023-02-23 06:35:06,282][10762] Fps is (10 sec: 4096.9, 60 sec: 3618.1, 300 sec: 3427.3). Total num frames: 839680. Throughput: 0: 923.6. Samples: 210016. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:35:06,288][10762] Avg episode reward: [(0, '4.491')] | |
| [2023-02-23 06:35:10,769][11530] Updated weights for policy 0, policy_version 210 (0.0016) | |
| [2023-02-23 06:35:11,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3618.7, 300 sec: 3440.6). Total num frames: 860160. Throughput: 0: 924.4. Samples: 213358. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:35:11,287][10762] Avg episode reward: [(0, '4.704')] | |
| [2023-02-23 06:35:16,282][10762] Fps is (10 sec: 3276.7, 60 sec: 3618.5, 300 sec: 3421.4). Total num frames: 872448. Throughput: 0: 887.3. Samples: 218270. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:35:16,287][10762] Avg episode reward: [(0, '4.855')] | |
| [2023-02-23 06:35:16,290][11516] Saving new best policy, reward=4.855! | |
| [2023-02-23 06:35:21,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3418.6). Total num frames: 888832. Throughput: 0: 890.0. Samples: 222510. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:35:21,284][10762] Avg episode reward: [(0, '4.731')] | |
| [2023-02-23 06:35:23,803][11530] Updated weights for policy 0, policy_version 220 (0.0024) | |
| [2023-02-23 06:35:26,282][10762] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3431.4). Total num frames: 909312. Throughput: 0: 914.1. Samples: 225712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:35:26,289][10762] Avg episode reward: [(0, '4.710')] | |
| [2023-02-23 06:35:31,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3443.7). Total num frames: 929792. Throughput: 0: 923.5. Samples: 232410. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:35:31,287][10762] Avg episode reward: [(0, '4.941')] | |
| [2023-02-23 06:35:31,299][11516] Saving new best policy, reward=4.941! | |
| [2023-02-23 06:35:34,845][11530] Updated weights for policy 0, policy_version 230 (0.0015) | |
| [2023-02-23 06:35:36,284][10762] Fps is (10 sec: 3685.6, 60 sec: 3686.3, 300 sec: 3440.6). Total num frames: 946176. Throughput: 0: 878.2. Samples: 236738. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:35:36,285][10762] Avg episode reward: [(0, '4.667')] | |
| [2023-02-23 06:35:41,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3423.1). Total num frames: 958464. Throughput: 0: 878.7. Samples: 238860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:35:41,288][10762] Avg episode reward: [(0, '4.733')] | |
| [2023-02-23 06:35:46,014][11530] Updated weights for policy 0, policy_version 240 (0.0019) | |
| [2023-02-23 06:35:46,282][10762] Fps is (10 sec: 3687.2, 60 sec: 3618.1, 300 sec: 3449.3). Total num frames: 983040. Throughput: 0: 915.6. Samples: 244728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:35:46,288][10762] Avg episode reward: [(0, '4.821')] | |
| [2023-02-23 06:35:51,288][10762] Fps is (10 sec: 4502.8, 60 sec: 3617.8, 300 sec: 3460.3). Total num frames: 1003520. Throughput: 0: 920.6. Samples: 251448. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:35:51,291][10762] Avg episode reward: [(0, '4.724')] | |
| [2023-02-23 06:35:56,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3457.3). Total num frames: 1019904. Throughput: 0: 897.9. Samples: 253762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:35:56,285][10762] Avg episode reward: [(0, '4.690')] | |
| [2023-02-23 06:35:57,628][11530] Updated weights for policy 0, policy_version 250 (0.0012) | |
| [2023-02-23 06:36:01,282][10762] Fps is (10 sec: 2869.0, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1032192. Throughput: 0: 881.4. Samples: 257932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:36:01,293][10762] Avg episode reward: [(0, '4.660')] | |
| [2023-02-23 06:36:06,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1052672. Throughput: 0: 918.4. Samples: 263836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:36:06,284][10762] Avg episode reward: [(0, '4.938')] | |
| [2023-02-23 06:36:08,235][11530] Updated weights for policy 0, policy_version 260 (0.0032) | |
| [2023-02-23 06:36:11,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1077248. Throughput: 0: 923.6. Samples: 267276. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:36:11,285][10762] Avg episode reward: [(0, '4.919')] | |
| [2023-02-23 06:36:16,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 1089536. Throughput: 0: 897.7. Samples: 272806. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:36:16,284][10762] Avg episode reward: [(0, '4.939')] | |
| [2023-02-23 06:36:20,668][11530] Updated weights for policy 0, policy_version 270 (0.0019) | |
| [2023-02-23 06:36:21,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1105920. Throughput: 0: 895.9. Samples: 277052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:36:21,290][10762] Avg episode reward: [(0, '5.143')] | |
| [2023-02-23 06:36:21,303][11516] Saving new best policy, reward=5.143! | |
| [2023-02-23 06:36:26,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1126400. Throughput: 0: 908.8. Samples: 279756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:36:26,289][10762] Avg episode reward: [(0, '5.313')] | |
| [2023-02-23 06:36:26,296][11516] Saving new best policy, reward=5.313! | |
| [2023-02-23 06:36:30,622][11530] Updated weights for policy 0, policy_version 280 (0.0028) | |
| [2023-02-23 06:36:31,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1146880. Throughput: 0: 924.6. Samples: 286336. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:36:31,289][10762] Avg episode reward: [(0, '5.084')] | |
| [2023-02-23 06:36:31,302][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth... | |
| [2023-02-23 06:36:31,440][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth | |
| [2023-02-23 06:36:36,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3610.0). Total num frames: 1163264. Throughput: 0: 888.2. Samples: 291412. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:36:36,285][10762] Avg episode reward: [(0, '4.654')] | |
| [2023-02-23 06:36:41,283][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 1175552. Throughput: 0: 884.2. Samples: 293552. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:36:41,286][10762] Avg episode reward: [(0, '5.030')] | |
| [2023-02-23 06:36:43,548][11530] Updated weights for policy 0, policy_version 290 (0.0027) | |
| [2023-02-23 06:36:46,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1196032. Throughput: 0: 908.6. Samples: 298818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:36:46,289][10762] Avg episode reward: [(0, '5.373')] | |
| [2023-02-23 06:36:46,291][11516] Saving new best policy, reward=5.373! | |
| [2023-02-23 06:36:51,282][10762] Fps is (10 sec: 4505.7, 60 sec: 3618.5, 300 sec: 3623.9). Total num frames: 1220608. Throughput: 0: 925.1. Samples: 305466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:36:51,285][10762] Avg episode reward: [(0, '5.508')] | |
| [2023-02-23 06:36:51,298][11516] Saving new best policy, reward=5.508! | |
| [2023-02-23 06:36:53,286][11530] Updated weights for policy 0, policy_version 300 (0.0013) | |
| [2023-02-23 06:36:56,282][10762] Fps is (10 sec: 4095.7, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1236992. Throughput: 0: 908.9. Samples: 308178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:36:56,290][10762] Avg episode reward: [(0, '5.600')] | |
| [2023-02-23 06:36:56,292][11516] Saving new best policy, reward=5.600! | |
| [2023-02-23 06:37:01,282][10762] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1249280. Throughput: 0: 878.6. Samples: 312344. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:37:01,297][10762] Avg episode reward: [(0, '5.503')] | |
| [2023-02-23 06:37:05,899][11530] Updated weights for policy 0, policy_version 310 (0.0018) | |
| [2023-02-23 06:37:06,282][10762] Fps is (10 sec: 3277.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1269760. Throughput: 0: 909.2. Samples: 317964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:06,284][10762] Avg episode reward: [(0, '5.368')] | |
| [2023-02-23 06:37:11,282][10762] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 1290240. Throughput: 0: 923.5. Samples: 321314. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:11,289][10762] Avg episode reward: [(0, '5.427')] | |
| [2023-02-23 06:37:16,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1306624. Throughput: 0: 906.8. Samples: 327144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:37:16,284][10762] Avg episode reward: [(0, '5.414')] | |
| [2023-02-23 06:37:16,461][11530] Updated weights for policy 0, policy_version 320 (0.0011) | |
| [2023-02-23 06:37:21,282][10762] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1323008. Throughput: 0: 889.4. Samples: 331436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:37:21,285][10762] Avg episode reward: [(0, '5.736')] | |
| [2023-02-23 06:37:21,300][11516] Saving new best policy, reward=5.736! | |
| [2023-02-23 06:37:26,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 1343488. Throughput: 0: 896.0. Samples: 333872. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:37:26,284][10762] Avg episode reward: [(0, '5.494')] | |
| [2023-02-23 06:37:27,829][11530] Updated weights for policy 0, policy_version 330 (0.0030) | |
| [2023-02-23 06:37:31,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1363968. Throughput: 0: 927.1. Samples: 340538. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:37:31,285][10762] Avg episode reward: [(0, '5.191')] | |
| [2023-02-23 06:37:36,282][10762] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3624.0). Total num frames: 1380352. Throughput: 0: 904.5. Samples: 346168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:36,285][10762] Avg episode reward: [(0, '5.219')] | |
| [2023-02-23 06:37:39,389][11530] Updated weights for policy 0, policy_version 340 (0.0015) | |
| [2023-02-23 06:37:41,283][10762] Fps is (10 sec: 3276.5, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1396736. Throughput: 0: 890.5. Samples: 348250. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:41,287][10762] Avg episode reward: [(0, '5.409')] | |
| [2023-02-23 06:37:46,282][10762] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1417216. Throughput: 0: 904.5. Samples: 353048. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:46,285][10762] Avg episode reward: [(0, '5.387')] | |
| [2023-02-23 06:37:49,860][11530] Updated weights for policy 0, policy_version 350 (0.0015) | |
| [2023-02-23 06:37:51,282][10762] Fps is (10 sec: 4096.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1437696. Throughput: 0: 930.9. Samples: 359856. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:37:51,285][10762] Avg episode reward: [(0, '5.464')] | |
| [2023-02-23 06:37:56,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 1454080. Throughput: 0: 925.2. Samples: 362948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:37:56,286][10762] Avg episode reward: [(0, '5.818')] | |
| [2023-02-23 06:37:56,288][11516] Saving new best policy, reward=5.818! | |
| [2023-02-23 06:38:01,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 1466368. Throughput: 0: 886.8. Samples: 367052. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:01,286][10762] Avg episode reward: [(0, '6.110')] | |
| [2023-02-23 06:38:01,377][11516] Saving new best policy, reward=6.110! | |
| [2023-02-23 06:38:02,954][11530] Updated weights for policy 0, policy_version 360 (0.0016) | |
| [2023-02-23 06:38:06,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1486848. Throughput: 0: 906.0. Samples: 372206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:38:06,290][10762] Avg episode reward: [(0, '5.817')] | |
| [2023-02-23 06:38:11,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1511424. Throughput: 0: 926.0. Samples: 375544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:11,290][10762] Avg episode reward: [(0, '5.980')] | |
| [2023-02-23 06:38:12,105][11530] Updated weights for policy 0, policy_version 370 (0.0017) | |
| [2023-02-23 06:38:16,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1527808. Throughput: 0: 919.1. Samples: 381898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:16,289][10762] Avg episode reward: [(0, '5.834')] | |
| [2023-02-23 06:38:21,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1544192. Throughput: 0: 888.4. Samples: 386146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:21,284][10762] Avg episode reward: [(0, '5.956')] | |
| [2023-02-23 06:38:24,940][11530] Updated weights for policy 0, policy_version 380 (0.0014) | |
| [2023-02-23 06:38:26,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1560576. Throughput: 0: 891.1. Samples: 388350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:38:26,285][10762] Avg episode reward: [(0, '6.210')] | |
| [2023-02-23 06:38:26,292][11516] Saving new best policy, reward=6.210! | |
| [2023-02-23 06:38:31,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1581056. Throughput: 0: 926.8. Samples: 394756. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:31,285][10762] Avg episode reward: [(0, '6.479')] | |
| [2023-02-23 06:38:31,296][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth... | |
| [2023-02-23 06:38:31,450][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000174_712704.pth | |
| [2023-02-23 06:38:31,473][11516] Saving new best policy, reward=6.479! | |
| [2023-02-23 06:38:34,618][11530] Updated weights for policy 0, policy_version 390 (0.0018) | |
| [2023-02-23 06:38:36,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1601536. Throughput: 0: 905.3. Samples: 400594. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:36,285][10762] Avg episode reward: [(0, '6.667')] | |
| [2023-02-23 06:38:36,293][11516] Saving new best policy, reward=6.667! | |
| [2023-02-23 06:38:41,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3610.0). Total num frames: 1613824. Throughput: 0: 882.6. Samples: 402666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:38:41,286][10762] Avg episode reward: [(0, '6.508')] | |
| [2023-02-23 06:38:46,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 1630208. Throughput: 0: 888.6. Samples: 407038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:46,289][10762] Avg episode reward: [(0, '6.905')] | |
| [2023-02-23 06:38:46,293][11516] Saving new best policy, reward=6.905! | |
| [2023-02-23 06:38:47,550][11530] Updated weights for policy 0, policy_version 400 (0.0026) | |
| [2023-02-23 06:38:51,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1654784. Throughput: 0: 922.0. Samples: 413694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:38:51,284][10762] Avg episode reward: [(0, '6.816')] | |
| [2023-02-23 06:38:56,284][10762] Fps is (10 sec: 4095.2, 60 sec: 3618.0, 300 sec: 3623.9). Total num frames: 1671168. Throughput: 0: 921.2. Samples: 417000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:38:56,289][10762] Avg episode reward: [(0, '7.449')] | |
| [2023-02-23 06:38:56,292][11516] Saving new best policy, reward=7.449! | |
| [2023-02-23 06:38:58,343][11530] Updated weights for policy 0, policy_version 410 (0.0013) | |
| [2023-02-23 06:39:01,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1687552. Throughput: 0: 879.1. Samples: 421456. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:39:01,285][10762] Avg episode reward: [(0, '7.346')] | |
| [2023-02-23 06:39:06,282][10762] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3596.3). Total num frames: 1703936. Throughput: 0: 888.0. Samples: 426108. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 06:39:06,292][10762] Avg episode reward: [(0, '7.681')] | |
| [2023-02-23 06:39:06,296][11516] Saving new best policy, reward=7.681! | |
| [2023-02-23 06:39:09,858][11530] Updated weights for policy 0, policy_version 420 (0.0046) | |
| [2023-02-23 06:39:11,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3624.0). Total num frames: 1724416. Throughput: 0: 911.8. Samples: 429380. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:39:11,285][10762] Avg episode reward: [(0, '7.769')] | |
| [2023-02-23 06:39:11,297][11516] Saving new best policy, reward=7.769! | |
| [2023-02-23 06:39:16,282][10762] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1744896. Throughput: 0: 918.5. Samples: 436090. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:39:16,287][10762] Avg episode reward: [(0, '7.970')] | |
| [2023-02-23 06:39:16,291][11516] Saving new best policy, reward=7.970! | |
| [2023-02-23 06:39:21,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1757184. Throughput: 0: 885.8. Samples: 440454. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:39:21,293][10762] Avg episode reward: [(0, '8.322')] | |
| [2023-02-23 06:39:21,349][11516] Saving new best policy, reward=8.322! | |
| [2023-02-23 06:39:21,357][11530] Updated weights for policy 0, policy_version 430 (0.0017) | |
| [2023-02-23 06:39:26,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1773568. Throughput: 0: 885.4. Samples: 442510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:39:26,290][10762] Avg episode reward: [(0, '7.950')] | |
| [2023-02-23 06:39:31,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1798144. Throughput: 0: 924.8. Samples: 448654. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:39:31,285][10762] Avg episode reward: [(0, '9.130')] | |
| [2023-02-23 06:39:31,296][11516] Saving new best policy, reward=9.130! | |
| [2023-02-23 06:39:32,023][11530] Updated weights for policy 0, policy_version 440 (0.0012) | |
| [2023-02-23 06:39:36,283][10762] Fps is (10 sec: 4505.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1818624. Throughput: 0: 921.2. Samples: 455150. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:39:36,289][10762] Avg episode reward: [(0, '9.084')] | |
| [2023-02-23 06:39:41,286][10762] Fps is (10 sec: 3275.4, 60 sec: 3617.9, 300 sec: 3610.0). Total num frames: 1830912. Throughput: 0: 896.0. Samples: 457320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:39:41,289][10762] Avg episode reward: [(0, '9.618')] | |
| [2023-02-23 06:39:41,312][11516] Saving new best policy, reward=9.618! | |
| [2023-02-23 06:39:44,445][11530] Updated weights for policy 0, policy_version 450 (0.0030) | |
| [2023-02-23 06:39:46,282][10762] Fps is (10 sec: 2867.6, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 1847296. Throughput: 0: 890.5. Samples: 461530. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:39:46,284][10762] Avg episode reward: [(0, '9.418')] | |
| [2023-02-23 06:39:51,282][10762] Fps is (10 sec: 4097.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1871872. Throughput: 0: 929.0. Samples: 467914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:39:51,289][10762] Avg episode reward: [(0, '9.476')] | |
| [2023-02-23 06:39:54,010][11530] Updated weights for policy 0, policy_version 460 (0.0024) | |
| [2023-02-23 06:39:56,283][10762] Fps is (10 sec: 4505.1, 60 sec: 3686.5, 300 sec: 3651.7). Total num frames: 1892352. Throughput: 0: 932.0. Samples: 471320. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:39:56,288][10762] Avg episode reward: [(0, '9.299')] | |
| [2023-02-23 06:40:01,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 1904640. Throughput: 0: 897.1. Samples: 476460. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:01,289][10762] Avg episode reward: [(0, '9.382')] | |
| [2023-02-23 06:40:06,282][10762] Fps is (10 sec: 2867.5, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1921024. Throughput: 0: 895.7. Samples: 480760. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 06:40:06,290][10762] Avg episode reward: [(0, '8.864')] | |
| [2023-02-23 06:40:06,936][11530] Updated weights for policy 0, policy_version 470 (0.0020) | |
| [2023-02-23 06:40:11,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1941504. Throughput: 0: 919.9. Samples: 483906. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:11,285][10762] Avg episode reward: [(0, '9.424')] | |
| [2023-02-23 06:40:15,960][11530] Updated weights for policy 0, policy_version 480 (0.0013) | |
| [2023-02-23 06:40:16,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1966080. Throughput: 0: 934.7. Samples: 490714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:16,289][10762] Avg episode reward: [(0, '9.874')] | |
| [2023-02-23 06:40:16,291][11516] Saving new best policy, reward=9.874! | |
| [2023-02-23 06:40:21,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1978368. Throughput: 0: 899.4. Samples: 495624. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:40:21,285][10762] Avg episode reward: [(0, '9.697')] | |
| [2023-02-23 06:40:26,283][10762] Fps is (10 sec: 2867.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1994752. Throughput: 0: 897.7. Samples: 497712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:40:26,289][10762] Avg episode reward: [(0, '10.148')] | |
| [2023-02-23 06:40:26,293][11516] Saving new best policy, reward=10.148! | |
| [2023-02-23 06:40:28,893][11530] Updated weights for policy 0, policy_version 490 (0.0013) | |
| [2023-02-23 06:40:31,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2015232. Throughput: 0: 925.2. Samples: 503164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:40:31,285][10762] Avg episode reward: [(0, '11.065')] | |
| [2023-02-23 06:40:31,303][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth... | |
| [2023-02-23 06:40:31,461][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000280_1146880.pth | |
| [2023-02-23 06:40:31,477][11516] Saving new best policy, reward=11.065! | |
| [2023-02-23 06:40:36,282][10762] Fps is (10 sec: 4096.3, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2035712. Throughput: 0: 922.0. Samples: 509404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:36,284][10762] Avg episode reward: [(0, '11.152')] | |
| [2023-02-23 06:40:36,291][11516] Saving new best policy, reward=11.152! | |
| [2023-02-23 06:40:40,060][11530] Updated weights for policy 0, policy_version 500 (0.0016) | |
| [2023-02-23 06:40:41,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.4, 300 sec: 3610.0). Total num frames: 2048000. Throughput: 0: 899.2. Samples: 511782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:41,287][10762] Avg episode reward: [(0, '12.336')] | |
| [2023-02-23 06:40:41,300][11516] Saving new best policy, reward=12.336! | |
| [2023-02-23 06:40:46,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3596.2). Total num frames: 2064384. Throughput: 0: 878.3. Samples: 515984. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:40:46,288][10762] Avg episode reward: [(0, '11.778')] | |
| [2023-02-23 06:40:51,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 2084864. Throughput: 0: 914.4. Samples: 521906. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:40:51,284][10762] Avg episode reward: [(0, '11.521')] | |
| [2023-02-23 06:40:51,530][11530] Updated weights for policy 0, policy_version 510 (0.0015) | |
| [2023-02-23 06:40:56,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2109440. Throughput: 0: 920.4. Samples: 525322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:40:56,285][10762] Avg episode reward: [(0, '10.287')] | |
| [2023-02-23 06:41:01,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2125824. Throughput: 0: 892.3. Samples: 530866. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:41:01,286][10762] Avg episode reward: [(0, '10.892')] | |
| [2023-02-23 06:41:02,676][11530] Updated weights for policy 0, policy_version 520 (0.0026) | |
| [2023-02-23 06:41:06,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 2138112. Throughput: 0: 876.8. Samples: 535082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:41:06,288][10762] Avg episode reward: [(0, '11.351')] | |
| [2023-02-23 06:41:11,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2158592. Throughput: 0: 895.7. Samples: 538020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:41:11,288][10762] Avg episode reward: [(0, '11.417')] | |
| [2023-02-23 06:41:13,478][11530] Updated weights for policy 0, policy_version 530 (0.0012) | |
| [2023-02-23 06:41:16,282][10762] Fps is (10 sec: 4505.3, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2183168. Throughput: 0: 922.5. Samples: 544678. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:41:16,291][10762] Avg episode reward: [(0, '11.167')] | |
| [2023-02-23 06:41:21,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2195456. Throughput: 0: 899.7. Samples: 549890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:41:21,286][10762] Avg episode reward: [(0, '11.287')] | |
| [2023-02-23 06:41:25,860][11530] Updated weights for policy 0, policy_version 540 (0.0017) | |
| [2023-02-23 06:41:26,283][10762] Fps is (10 sec: 2867.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2211840. Throughput: 0: 894.2. Samples: 552022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:41:26,289][10762] Avg episode reward: [(0, '11.097')] | |
| [2023-02-23 06:41:31,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2232320. Throughput: 0: 916.9. Samples: 557244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:41:31,284][10762] Avg episode reward: [(0, '11.627')] | |
| [2023-02-23 06:41:35,493][11530] Updated weights for policy 0, policy_version 550 (0.0021) | |
| [2023-02-23 06:41:36,282][10762] Fps is (10 sec: 4096.5, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2252800. Throughput: 0: 935.2. Samples: 563992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:41:36,284][10762] Avg episode reward: [(0, '12.217')] | |
| [2023-02-23 06:41:41,283][10762] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3637.8). Total num frames: 2269184. Throughput: 0: 922.2. Samples: 566820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:41:41,290][10762] Avg episode reward: [(0, '11.572')] | |
| [2023-02-23 06:41:46,282][10762] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2285568. Throughput: 0: 892.1. Samples: 571012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:41:46,289][10762] Avg episode reward: [(0, '12.069')] | |
| [2023-02-23 06:41:48,249][11530] Updated weights for policy 0, policy_version 560 (0.0024) | |
| [2023-02-23 06:41:51,282][10762] Fps is (10 sec: 3686.9, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2306048. Throughput: 0: 924.4. Samples: 576682. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:41:51,290][10762] Avg episode reward: [(0, '13.044')] | |
| [2023-02-23 06:41:51,302][11516] Saving new best policy, reward=13.044! | |
| [2023-02-23 06:41:56,282][10762] Fps is (10 sec: 4096.3, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2326528. Throughput: 0: 934.1. Samples: 580056. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:41:56,289][10762] Avg episode reward: [(0, '14.684')] | |
| [2023-02-23 06:41:56,291][11516] Saving new best policy, reward=14.684! | |
| [2023-02-23 06:41:57,455][11530] Updated weights for policy 0, policy_version 570 (0.0015) | |
| [2023-02-23 06:42:01,283][10762] Fps is (10 sec: 3686.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2342912. Throughput: 0: 915.7. Samples: 585884. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:42:01,288][10762] Avg episode reward: [(0, '15.201')] | |
| [2023-02-23 06:42:01,301][11516] Saving new best policy, reward=15.201! | |
| [2023-02-23 06:42:06,282][10762] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2359296. Throughput: 0: 893.5. Samples: 590096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:42:06,287][10762] Avg episode reward: [(0, '15.255')] | |
| [2023-02-23 06:42:06,290][11516] Saving new best policy, reward=15.255! | |
| [2023-02-23 06:42:10,358][11530] Updated weights for policy 0, policy_version 580 (0.0016) | |
| [2023-02-23 06:42:11,282][10762] Fps is (10 sec: 3686.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2379776. Throughput: 0: 900.4. Samples: 592540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:42:11,285][10762] Avg episode reward: [(0, '14.408')] | |
| [2023-02-23 06:42:16,282][10762] Fps is (10 sec: 4096.1, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2400256. Throughput: 0: 938.3. Samples: 599466. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-02-23 06:42:16,284][10762] Avg episode reward: [(0, '14.625')] | |
| [2023-02-23 06:42:20,256][11530] Updated weights for policy 0, policy_version 590 (0.0019) | |
| [2023-02-23 06:42:21,282][10762] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2416640. Throughput: 0: 913.6. Samples: 605106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:42:21,289][10762] Avg episode reward: [(0, '15.207')] | |
| [2023-02-23 06:42:26,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.5, 300 sec: 3623.9). Total num frames: 2433024. Throughput: 0: 898.7. Samples: 607262. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:42:26,290][10762] Avg episode reward: [(0, '16.009')] | |
| [2023-02-23 06:42:26,299][11516] Saving new best policy, reward=16.009! | |
| [2023-02-23 06:42:31,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2449408. Throughput: 0: 913.2. Samples: 612104. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:42:31,287][10762] Avg episode reward: [(0, '16.945')] | |
| [2023-02-23 06:42:31,299][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000598_2449408.pth... | |
| [2023-02-23 06:42:31,416][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000386_1581056.pth | |
| [2023-02-23 06:42:31,426][11516] Saving new best policy, reward=16.945! | |
| [2023-02-23 06:42:32,534][11530] Updated weights for policy 0, policy_version 600 (0.0030) | |
| [2023-02-23 06:42:36,282][10762] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2473984. Throughput: 0: 934.8. Samples: 618748. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:42:36,284][10762] Avg episode reward: [(0, '16.799')] | |
| [2023-02-23 06:42:41,282][10762] Fps is (10 sec: 4096.1, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 2490368. Throughput: 0: 929.1. Samples: 621866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:42:41,289][10762] Avg episode reward: [(0, '17.528')] | |
| [2023-02-23 06:42:41,299][11516] Saving new best policy, reward=17.528! | |
| [2023-02-23 06:42:43,240][11530] Updated weights for policy 0, policy_version 610 (0.0017) | |
| [2023-02-23 06:42:46,282][10762] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2506752. Throughput: 0: 892.6. Samples: 626052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:42:46,285][10762] Avg episode reward: [(0, '16.152')] | |
| [2023-02-23 06:42:51,282][10762] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2523136. Throughput: 0: 916.1. Samples: 631320. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:42:51,283][10762] Avg episode reward: [(0, '16.888')] | |
| [2023-02-23 06:42:54,397][11530] Updated weights for policy 0, policy_version 620 (0.0014) | |
| [2023-02-23 06:42:56,282][10762] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2547712. Throughput: 0: 936.7. Samples: 634692. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:42:56,284][10762] Avg episode reward: [(0, '16.638')] | |
| [2023-02-23 06:43:01,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3651.7). Total num frames: 2564096. Throughput: 0: 921.9. Samples: 640952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:01,285][10762] Avg episode reward: [(0, '17.461')] | |
| [2023-02-23 06:43:06,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2576384. Throughput: 0: 890.3. Samples: 645170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:43:06,287][10762] Avg episode reward: [(0, '17.227')] | |
| [2023-02-23 06:43:06,450][11530] Updated weights for policy 0, policy_version 630 (0.0025) | |
| [2023-02-23 06:43:11,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2596864. Throughput: 0: 890.8. Samples: 647346. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:11,284][10762] Avg episode reward: [(0, '16.589')] | |
| [2023-02-23 06:43:16,267][11530] Updated weights for policy 0, policy_version 640 (0.0014) | |
| [2023-02-23 06:43:16,282][10762] Fps is (10 sec: 4505.5, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2621440. Throughput: 0: 932.7. Samples: 654076. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:43:16,284][10762] Avg episode reward: [(0, '15.261')] | |
| [2023-02-23 06:43:21,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2637824. Throughput: 0: 918.4. Samples: 660078. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:43:21,285][10762] Avg episode reward: [(0, '14.101')] | |
| [2023-02-23 06:43:26,282][10762] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2654208. Throughput: 0: 897.2. Samples: 662238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:26,290][10762] Avg episode reward: [(0, '14.147')] | |
| [2023-02-23 06:43:28,901][11530] Updated weights for policy 0, policy_version 650 (0.0032) | |
| [2023-02-23 06:43:31,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 2670592. Throughput: 0: 910.8. Samples: 667036. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:31,289][10762] Avg episode reward: [(0, '15.283')] | |
| [2023-02-23 06:43:36,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3651.7). Total num frames: 2691072. Throughput: 0: 938.5. Samples: 673554. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:36,285][10762] Avg episode reward: [(0, '16.302')] | |
| [2023-02-23 06:43:38,210][11530] Updated weights for policy 0, policy_version 660 (0.0012) | |
| [2023-02-23 06:43:41,283][10762] Fps is (10 sec: 4095.4, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 2711552. Throughput: 0: 938.4. Samples: 676920. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:43:41,285][10762] Avg episode reward: [(0, '16.790')] | |
| [2023-02-23 06:43:46,284][10762] Fps is (10 sec: 3276.2, 60 sec: 3618.0, 300 sec: 3623.9). Total num frames: 2723840. Throughput: 0: 893.8. Samples: 681174. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:46,288][10762] Avg episode reward: [(0, '17.986')] | |
| [2023-02-23 06:43:46,291][11516] Saving new best policy, reward=17.986! | |
| [2023-02-23 06:43:51,095][11530] Updated weights for policy 0, policy_version 670 (0.0039) | |
| [2023-02-23 06:43:51,282][10762] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2744320. Throughput: 0: 910.6. Samples: 686148. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:43:51,284][10762] Avg episode reward: [(0, '18.854')] | |
| [2023-02-23 06:43:51,304][11516] Saving new best policy, reward=18.854! | |
| [2023-02-23 06:43:56,283][10762] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2764800. Throughput: 0: 936.8. Samples: 689504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:43:56,286][10762] Avg episode reward: [(0, '19.785')] | |
| [2023-02-23 06:43:56,293][11516] Saving new best policy, reward=19.785! | |
| [2023-02-23 06:44:01,015][11530] Updated weights for policy 0, policy_version 680 (0.0019) | |
| [2023-02-23 06:44:01,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2785280. Throughput: 0: 928.7. Samples: 695868. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:44:01,285][10762] Avg episode reward: [(0, '20.792')] | |
| [2023-02-23 06:44:01,303][11516] Saving new best policy, reward=20.792! | |
| [2023-02-23 06:44:06,282][10762] Fps is (10 sec: 3277.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2797568. Throughput: 0: 884.3. Samples: 699870. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:44:06,287][10762] Avg episode reward: [(0, '20.166')] | |
| [2023-02-23 06:44:11,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2813952. Throughput: 0: 883.4. Samples: 701992. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:44:11,284][10762] Avg episode reward: [(0, '20.150')] | |
| [2023-02-23 06:44:13,529][11530] Updated weights for policy 0, policy_version 690 (0.0012) | |
| [2023-02-23 06:44:16,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3665.6). Total num frames: 2838528. Throughput: 0: 921.0. Samples: 708480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:44:16,290][10762] Avg episode reward: [(0, '20.979')] | |
| [2023-02-23 06:44:16,296][11516] Saving new best policy, reward=20.979! | |
| [2023-02-23 06:44:21,283][10762] Fps is (10 sec: 4095.5, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2854912. Throughput: 0: 913.6. Samples: 714668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:44:21,289][10762] Avg episode reward: [(0, '20.811')] | |
| [2023-02-23 06:44:24,637][11530] Updated weights for policy 0, policy_version 700 (0.0038) | |
| [2023-02-23 06:44:26,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2871296. Throughput: 0: 884.5. Samples: 716722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:44:26,284][10762] Avg episode reward: [(0, '21.131')] | |
| [2023-02-23 06:44:26,287][11516] Saving new best policy, reward=21.131! | |
| [2023-02-23 06:44:31,282][10762] Fps is (10 sec: 3277.2, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2887680. Throughput: 0: 882.4. Samples: 720882. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:44:31,284][10762] Avg episode reward: [(0, '20.617')] | |
| [2023-02-23 06:44:31,301][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000705_2887680.pth... | |
| [2023-02-23 06:44:31,420][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000492_2015232.pth | |
| [2023-02-23 06:44:35,834][11530] Updated weights for policy 0, policy_version 710 (0.0013) | |
| [2023-02-23 06:44:36,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2908160. Throughput: 0: 918.0. Samples: 727458. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:44:36,284][10762] Avg episode reward: [(0, '20.725')] | |
| [2023-02-23 06:44:41,284][10762] Fps is (10 sec: 4095.3, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 2928640. Throughput: 0: 919.1. Samples: 730866. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:44:41,288][10762] Avg episode reward: [(0, '19.597')] | |
| [2023-02-23 06:44:46,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 2940928. Throughput: 0: 879.3. Samples: 735436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:44:46,286][10762] Avg episode reward: [(0, '19.927')] | |
| [2023-02-23 06:44:48,174][11530] Updated weights for policy 0, policy_version 720 (0.0018) | |
| [2023-02-23 06:44:51,282][10762] Fps is (10 sec: 2867.7, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 2957312. Throughput: 0: 888.2. Samples: 739838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:44:51,289][10762] Avg episode reward: [(0, '20.041')] | |
| [2023-02-23 06:44:56,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 2977792. Throughput: 0: 912.3. Samples: 743044. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:44:56,288][10762] Avg episode reward: [(0, '19.314')] | |
| [2023-02-23 06:44:58,319][11530] Updated weights for policy 0, policy_version 730 (0.0020) | |
| [2023-02-23 06:45:01,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2998272. Throughput: 0: 915.2. Samples: 749666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:45:01,284][10762] Avg episode reward: [(0, '20.221')] | |
| [2023-02-23 06:45:06,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3014656. Throughput: 0: 870.7. Samples: 753850. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:45:06,292][10762] Avg episode reward: [(0, '20.586')] | |
| [2023-02-23 06:45:11,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 3026944. Throughput: 0: 872.0. Samples: 755960. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:11,285][10762] Avg episode reward: [(0, '21.679')] | |
| [2023-02-23 06:45:11,307][11530] Updated weights for policy 0, policy_version 740 (0.0017) | |
| [2023-02-23 06:45:11,308][11516] Saving new best policy, reward=21.679! | |
| [2023-02-23 06:45:16,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3051520. Throughput: 0: 915.2. Samples: 762064. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:45:16,284][10762] Avg episode reward: [(0, '21.155')] | |
| [2023-02-23 06:45:20,523][11530] Updated weights for policy 0, policy_version 750 (0.0012) | |
| [2023-02-23 06:45:21,283][10762] Fps is (10 sec: 4505.1, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3072000. Throughput: 0: 915.5. Samples: 768656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:21,295][10762] Avg episode reward: [(0, '20.986')] | |
| [2023-02-23 06:45:26,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3088384. Throughput: 0: 886.4. Samples: 770752. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:26,287][10762] Avg episode reward: [(0, '20.445')] | |
| [2023-02-23 06:45:31,282][10762] Fps is (10 sec: 2867.5, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3100672. Throughput: 0: 881.3. Samples: 775096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:31,290][10762] Avg episode reward: [(0, '20.262')] | |
| [2023-02-23 06:45:33,646][11530] Updated weights for policy 0, policy_version 760 (0.0044) | |
| [2023-02-23 06:45:36,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3121152. Throughput: 0: 916.2. Samples: 781068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-02-23 06:45:36,290][10762] Avg episode reward: [(0, '20.569')] | |
| [2023-02-23 06:45:41,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3618.2, 300 sec: 3665.6). Total num frames: 3145728. Throughput: 0: 921.6. Samples: 784516. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:41,287][10762] Avg episode reward: [(0, '19.525')] | |
| [2023-02-23 06:45:43,836][11530] Updated weights for policy 0, policy_version 770 (0.0020) | |
| [2023-02-23 06:45:46,282][10762] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3158016. Throughput: 0: 886.3. Samples: 789548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:45:46,287][10762] Avg episode reward: [(0, '19.687')] | |
| [2023-02-23 06:45:51,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3174400. Throughput: 0: 889.8. Samples: 793890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:45:51,284][10762] Avg episode reward: [(0, '19.861')] | |
| [2023-02-23 06:45:55,499][11530] Updated weights for policy 0, policy_version 780 (0.0016) | |
| [2023-02-23 06:45:56,282][10762] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3194880. Throughput: 0: 918.2. Samples: 797280. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:45:56,290][10762] Avg episode reward: [(0, '18.334')] | |
| [2023-02-23 06:46:01,286][10762] Fps is (10 sec: 4503.6, 60 sec: 3686.1, 300 sec: 3665.5). Total num frames: 3219456. Throughput: 0: 933.2. Samples: 804062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:46:01,300][10762] Avg episode reward: [(0, '18.547')] | |
| [2023-02-23 06:46:06,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3231744. Throughput: 0: 890.6. Samples: 808730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:06,284][10762] Avg episode reward: [(0, '18.129')] | |
| [2023-02-23 06:46:06,727][11530] Updated weights for policy 0, policy_version 790 (0.0022) | |
| [2023-02-23 06:46:11,282][10762] Fps is (10 sec: 2868.5, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3248128. Throughput: 0: 891.1. Samples: 810850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:11,287][10762] Avg episode reward: [(0, '17.990')] | |
| [2023-02-23 06:46:16,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3268608. Throughput: 0: 925.3. Samples: 816736. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:46:16,290][10762] Avg episode reward: [(0, '19.173')] | |
| [2023-02-23 06:46:17,295][11530] Updated weights for policy 0, policy_version 800 (0.0020) | |
| [2023-02-23 06:46:21,282][10762] Fps is (10 sec: 4505.5, 60 sec: 3686.5, 300 sec: 3665.6). Total num frames: 3293184. Throughput: 0: 945.2. Samples: 823602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:21,287][10762] Avg episode reward: [(0, '20.507')] | |
| [2023-02-23 06:46:26,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3305472. Throughput: 0: 916.6. Samples: 825764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:26,290][10762] Avg episode reward: [(0, '21.322')] | |
| [2023-02-23 06:46:29,840][11530] Updated weights for policy 0, policy_version 810 (0.0016) | |
| [2023-02-23 06:46:31,282][10762] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3321856. Throughput: 0: 898.2. Samples: 829968. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:46:31,289][10762] Avg episode reward: [(0, '22.459')] | |
| [2023-02-23 06:46:31,307][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000811_3321856.pth... | |
| [2023-02-23 06:46:31,455][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000598_2449408.pth | |
| [2023-02-23 06:46:31,463][11516] Saving new best policy, reward=22.459! | |
| [2023-02-23 06:46:36,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3342336. Throughput: 0: 934.3. Samples: 835932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:36,284][10762] Avg episode reward: [(0, '23.633')] | |
| [2023-02-23 06:46:36,287][11516] Saving new best policy, reward=23.633! | |
| [2023-02-23 06:46:39,536][11530] Updated weights for policy 0, policy_version 820 (0.0018) | |
| [2023-02-23 06:46:41,282][10762] Fps is (10 sec: 4096.3, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3362816. Throughput: 0: 931.1. Samples: 839180. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:46:41,285][10762] Avg episode reward: [(0, '24.204')] | |
| [2023-02-23 06:46:41,357][11516] Saving new best policy, reward=24.204! | |
| [2023-02-23 06:46:46,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3379200. Throughput: 0: 897.7. Samples: 844456. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:46,285][10762] Avg episode reward: [(0, '24.105')] | |
| [2023-02-23 06:46:51,284][10762] Fps is (10 sec: 2866.5, 60 sec: 3618.0, 300 sec: 3610.0). Total num frames: 3391488. Throughput: 0: 888.6. Samples: 848718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:46:51,292][10762] Avg episode reward: [(0, '22.792')] | |
| [2023-02-23 06:46:52,698][11530] Updated weights for policy 0, policy_version 830 (0.0025) | |
| [2023-02-23 06:46:56,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3411968. Throughput: 0: 907.2. Samples: 851676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:46:56,284][10762] Avg episode reward: [(0, '22.195')] | |
| [2023-02-23 06:47:01,282][10762] Fps is (10 sec: 4506.7, 60 sec: 3618.4, 300 sec: 3651.7). Total num frames: 3436544. Throughput: 0: 927.4. Samples: 858468. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:01,283][10762] Avg episode reward: [(0, '20.610')] | |
| [2023-02-23 06:47:01,765][11530] Updated weights for policy 0, policy_version 840 (0.0023) | |
| [2023-02-23 06:47:06,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3452928. Throughput: 0: 888.2. Samples: 863572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:47:06,286][10762] Avg episode reward: [(0, '20.788')] | |
| [2023-02-23 06:47:11,283][10762] Fps is (10 sec: 2866.9, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3465216. Throughput: 0: 887.4. Samples: 865698. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:47:11,288][10762] Avg episode reward: [(0, '19.960')] | |
| [2023-02-23 06:47:14,534][11530] Updated weights for policy 0, policy_version 850 (0.0029) | |
| [2023-02-23 06:47:16,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3485696. Throughput: 0: 914.0. Samples: 871096. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:16,284][10762] Avg episode reward: [(0, '19.978')] | |
| [2023-02-23 06:47:21,282][10762] Fps is (10 sec: 4506.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3510272. Throughput: 0: 936.4. Samples: 878072. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:47:21,289][10762] Avg episode reward: [(0, '21.476')] | |
| [2023-02-23 06:47:24,420][11530] Updated weights for policy 0, policy_version 860 (0.0021) | |
| [2023-02-23 06:47:26,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3526656. Throughput: 0: 923.3. Samples: 880728. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:26,288][10762] Avg episode reward: [(0, '21.829')] | |
| [2023-02-23 06:47:31,282][10762] Fps is (10 sec: 2867.3, 60 sec: 3618.2, 300 sec: 3610.0). Total num frames: 3538944. Throughput: 0: 899.3. Samples: 884924. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:31,290][10762] Avg episode reward: [(0, '22.262')] | |
| [2023-02-23 06:47:36,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3559424. Throughput: 0: 928.3. Samples: 890490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:47:36,288][10762] Avg episode reward: [(0, '23.351')] | |
| [2023-02-23 06:47:36,510][11530] Updated weights for policy 0, policy_version 870 (0.0015) | |
| [2023-02-23 06:47:41,282][10762] Fps is (10 sec: 4505.5, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3584000. Throughput: 0: 939.9. Samples: 893974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:47:41,284][10762] Avg episode reward: [(0, '22.656')] | |
| [2023-02-23 06:47:46,282][10762] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3600384. Throughput: 0: 918.9. Samples: 899818. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:47:46,286][10762] Avg episode reward: [(0, '20.905')] | |
| [2023-02-23 06:47:47,405][11530] Updated weights for policy 0, policy_version 880 (0.0019) | |
| [2023-02-23 06:47:51,282][10762] Fps is (10 sec: 2867.3, 60 sec: 3686.5, 300 sec: 3610.0). Total num frames: 3612672. Throughput: 0: 899.3. Samples: 904040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:51,287][10762] Avg episode reward: [(0, '20.172')] | |
| [2023-02-23 06:47:56,282][10762] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3633152. Throughput: 0: 910.4. Samples: 906666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:47:56,284][10762] Avg episode reward: [(0, '20.158')] | |
| [2023-02-23 06:47:58,372][11530] Updated weights for policy 0, policy_version 890 (0.0036) | |
| [2023-02-23 06:48:01,282][10762] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3657728. Throughput: 0: 941.0. Samples: 913440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:48:01,283][10762] Avg episode reward: [(0, '18.872')] | |
| [2023-02-23 06:48:06,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 3674112. Throughput: 0: 908.0. Samples: 918930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:48:06,284][10762] Avg episode reward: [(0, '18.789')] | |
| [2023-02-23 06:48:10,322][11530] Updated weights for policy 0, policy_version 900 (0.0029) | |
| [2023-02-23 06:48:11,282][10762] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3610.0). Total num frames: 3686400. Throughput: 0: 895.0. Samples: 921002. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:48:11,284][10762] Avg episode reward: [(0, '18.836')] | |
| [2023-02-23 06:48:16,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3706880. Throughput: 0: 909.7. Samples: 925862. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:48:16,284][10762] Avg episode reward: [(0, '20.328')] | |
| [2023-02-23 06:48:20,764][11530] Updated weights for policy 0, policy_version 910 (0.0012) | |
| [2023-02-23 06:48:21,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 3727360. Throughput: 0: 932.9. Samples: 932472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-02-23 06:48:21,285][10762] Avg episode reward: [(0, '20.523')] | |
| [2023-02-23 06:48:26,286][10762] Fps is (10 sec: 3684.9, 60 sec: 3617.9, 300 sec: 3637.8). Total num frames: 3743744. Throughput: 0: 922.9. Samples: 935506. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:48:26,289][10762] Avg episode reward: [(0, '21.106')] | |
| [2023-02-23 06:48:31,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3760128. Throughput: 0: 883.9. Samples: 939592. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:48:31,287][10762] Avg episode reward: [(0, '20.493')] | |
| [2023-02-23 06:48:31,301][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000918_3760128.pth... | |
| [2023-02-23 06:48:31,468][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000705_2887680.pth | |
| [2023-02-23 06:48:33,974][11530] Updated weights for policy 0, policy_version 920 (0.0029) | |
| [2023-02-23 06:48:36,282][10762] Fps is (10 sec: 3278.1, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 3776512. Throughput: 0: 900.9. Samples: 944582. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:48:36,284][10762] Avg episode reward: [(0, '20.918')] | |
| [2023-02-23 06:48:41,282][10762] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3796992. Throughput: 0: 915.9. Samples: 947880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:48:41,290][10762] Avg episode reward: [(0, '19.798')] | |
| [2023-02-23 06:48:43,256][11530] Updated weights for policy 0, policy_version 930 (0.0022) | |
| [2023-02-23 06:48:46,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3817472. Throughput: 0: 902.6. Samples: 954056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:48:46,289][10762] Avg episode reward: [(0, '20.056')] | |
| [2023-02-23 06:48:51,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3829760. Throughput: 0: 874.7. Samples: 958290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:48:51,284][10762] Avg episode reward: [(0, '20.960')] | |
| [2023-02-23 06:48:56,205][11530] Updated weights for policy 0, policy_version 940 (0.0022) | |
| [2023-02-23 06:48:56,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3850240. Throughput: 0: 876.5. Samples: 960446. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:48:56,288][10762] Avg episode reward: [(0, '19.902')] | |
| [2023-02-23 06:49:01,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3870720. Throughput: 0: 915.6. Samples: 967064. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:49:01,285][10762] Avg episode reward: [(0, '19.813')] | |
| [2023-02-23 06:49:06,077][11530] Updated weights for policy 0, policy_version 950 (0.0018) | |
| [2023-02-23 06:49:06,283][10762] Fps is (10 sec: 4095.5, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3891200. Throughput: 0: 900.7. Samples: 973006. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-02-23 06:49:06,288][10762] Avg episode reward: [(0, '19.409')] | |
| [2023-02-23 06:49:11,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3903488. Throughput: 0: 879.5. Samples: 975082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:49:11,289][10762] Avg episode reward: [(0, '19.009')] | |
| [2023-02-23 06:49:16,282][10762] Fps is (10 sec: 2867.6, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 3919872. Throughput: 0: 886.7. Samples: 979494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:49:16,284][10762] Avg episode reward: [(0, '19.841')] | |
| [2023-02-23 06:49:18,589][11530] Updated weights for policy 0, policy_version 960 (0.0012) | |
| [2023-02-23 06:49:21,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3944448. Throughput: 0: 923.9. Samples: 986158. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-02-23 06:49:21,285][10762] Avg episode reward: [(0, '21.807')] | |
| [2023-02-23 06:49:26,282][10762] Fps is (10 sec: 4096.0, 60 sec: 3618.4, 300 sec: 3637.8). Total num frames: 3960832. Throughput: 0: 923.3. Samples: 989428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-02-23 06:49:26,286][10762] Avg episode reward: [(0, '22.374')] | |
| [2023-02-23 06:49:29,907][11530] Updated weights for policy 0, policy_version 970 (0.0026) | |
| [2023-02-23 06:49:31,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3977216. Throughput: 0: 883.0. Samples: 993792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-02-23 06:49:31,289][10762] Avg episode reward: [(0, '21.918')] | |
| [2023-02-23 06:49:36,282][10762] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 3993600. Throughput: 0: 890.9. Samples: 998380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-02-23 06:49:36,284][10762] Avg episode reward: [(0, '22.495')] | |
| [2023-02-23 06:49:38,966][11516] Stopping Batcher_0... | |
| [2023-02-23 06:49:38,967][11516] Loop batcher_evt_loop terminating... | |
| [2023-02-23 06:49:38,968][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 06:49:38,966][10762] Component Batcher_0 stopped! | |
| [2023-02-23 06:49:39,035][11530] Weights refcount: 2 0 | |
| [2023-02-23 06:49:39,042][10762] Component InferenceWorker_p0-w0 stopped! | |
| [2023-02-23 06:49:39,045][11530] Stopping InferenceWorker_p0-w0... | |
| [2023-02-23 06:49:39,045][11530] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-02-23 06:49:39,063][10762] Component RolloutWorker_w6 stopped! | |
| [2023-02-23 06:49:39,065][11540] Stopping RolloutWorker_w6... | |
| [2023-02-23 06:49:39,071][11539] Stopping RolloutWorker_w3... | |
| [2023-02-23 06:49:39,071][10762] Component RolloutWorker_w3 stopped! | |
| [2023-02-23 06:49:39,071][11540] Loop rollout_proc6_evt_loop terminating... | |
| [2023-02-23 06:49:39,082][11543] Stopping RolloutWorker_w5... | |
| [2023-02-23 06:49:39,082][10762] Component RolloutWorker_w5 stopped! | |
| [2023-02-23 06:49:39,085][10762] Component RolloutWorker_w0 stopped! | |
| [2023-02-23 06:49:39,089][11538] Stopping RolloutWorker_w4... | |
| [2023-02-23 06:49:39,089][10762] Component RolloutWorker_w4 stopped! | |
| [2023-02-23 06:49:39,088][11531] Stopping RolloutWorker_w0... | |
| [2023-02-23 06:49:39,095][11538] Loop rollout_proc4_evt_loop terminating... | |
| [2023-02-23 06:49:39,102][11539] Loop rollout_proc3_evt_loop terminating... | |
| [2023-02-23 06:49:39,100][10762] Component RolloutWorker_w2 stopped! | |
| [2023-02-23 06:49:39,103][11537] Stopping RolloutWorker_w2... | |
| [2023-02-23 06:49:39,098][11531] Loop rollout_proc0_evt_loop terminating... | |
| [2023-02-23 06:49:39,104][11537] Loop rollout_proc2_evt_loop terminating... | |
| [2023-02-23 06:49:39,083][11543] Loop rollout_proc5_evt_loop terminating... | |
| [2023-02-23 06:49:39,135][11532] Stopping RolloutWorker_w1... | |
| [2023-02-23 06:49:39,135][10762] Component RolloutWorker_w1 stopped! | |
| [2023-02-23 06:49:39,144][11542] Stopping RolloutWorker_w7... | |
| [2023-02-23 06:49:39,145][11532] Loop rollout_proc1_evt_loop terminating... | |
| [2023-02-23 06:49:39,145][10762] Component RolloutWorker_w7 stopped! | |
| [2023-02-23 06:49:39,156][11542] Loop rollout_proc7_evt_loop terminating... | |
| [2023-02-23 06:49:39,187][11516] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000811_3321856.pth | |
| [2023-02-23 06:49:39,195][11516] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 06:49:39,330][10762] Component LearnerWorker_p0 stopped! | |
| [2023-02-23 06:49:39,337][10762] Waiting for process learner_proc0 to stop... | |
| [2023-02-23 06:49:39,342][11516] Stopping LearnerWorker_p0... | |
| [2023-02-23 06:49:39,344][11516] Loop learner_proc0_evt_loop terminating... | |
| [2023-02-23 06:49:41,269][10762] Waiting for process inference_proc0-0 to join... | |
| [2023-02-23 06:49:41,692][10762] Waiting for process rollout_proc0 to join... | |
| [2023-02-23 06:49:41,695][10762] Waiting for process rollout_proc1 to join... | |
| [2023-02-23 06:49:42,065][10762] Waiting for process rollout_proc2 to join... | |
| [2023-02-23 06:49:42,068][10762] Waiting for process rollout_proc3 to join... | |
| [2023-02-23 06:49:42,073][10762] Waiting for process rollout_proc4 to join... | |
| [2023-02-23 06:49:42,078][10762] Waiting for process rollout_proc5 to join... | |
| [2023-02-23 06:49:42,080][10762] Waiting for process rollout_proc6 to join... | |
| [2023-02-23 06:49:42,081][10762] Waiting for process rollout_proc7 to join... | |
| [2023-02-23 06:49:42,083][10762] Batcher 0 profile tree view: | |
| batching: 26.8884, releasing_batches: 0.0241 | |
| [2023-02-23 06:49:42,084][10762] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 551.8631 | |
| update_model: 7.5904 | |
| weight_update: 0.0034 | |
| one_step: 0.0043 | |
| handle_policy_step: 517.1613 | |
| deserialize: 15.2241, stack: 2.9196, obs_to_device_normalize: 114.7867, forward: 248.9452, send_messages: 26.3966 | |
| prepare_outputs: 82.9385 | |
| to_cpu: 51.1423 | |
| [2023-02-23 06:49:42,085][10762] Learner 0 profile tree view: | |
| misc: 0.0062, prepare_batch: 17.2146 | |
| train: 76.2094 | |
| epoch_init: 0.0054, minibatch_init: 0.0299, losses_postprocess: 0.6892, kl_divergence: 0.6840, after_optimizer: 33.0248 | |
| calculate_losses: 26.9021 | |
| losses_init: 0.0038, forward_head: 1.9675, bptt_initial: 17.6464, tail: 1.0878, advantages_returns: 0.2835, losses: 3.4164 | |
| bptt: 2.2193 | |
| bptt_forward_core: 2.1147 | |
| update: 14.2036 | |
| clip: 1.4675 | |
| [2023-02-23 06:49:42,089][10762] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.3530, enqueue_policy_requests: 152.9121, env_step: 837.9538, overhead: 21.4276, complete_rollouts: 7.2493 | |
| save_policy_outputs: 21.2662 | |
| split_output_tensors: 10.2282 | |
| [2023-02-23 06:49:42,091][10762] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.3389, enqueue_policy_requests: 151.2741, env_step: 841.1772, overhead: 20.9279, complete_rollouts: 6.9364 | |
| save_policy_outputs: 21.3173 | |
| split_output_tensors: 10.7894 | |
| [2023-02-23 06:49:42,092][10762] Loop Runner_EvtLoop terminating... | |
| [2023-02-23 06:49:42,094][10762] Runner profile tree view: | |
| main_loop: 1146.2850 | |
| [2023-02-23 06:49:42,095][10762] Collected {0: 4005888}, FPS: 3494.7 | |
| [2023-02-23 06:51:42,458][10762] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 06:51:42,460][10762] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 06:51:42,463][10762] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 06:51:42,465][10762] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 06:51:42,467][10762] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 06:51:42,469][10762] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 06:51:42,470][10762] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 06:51:42,472][10762] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 06:51:42,473][10762] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-02-23 06:51:42,474][10762] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-02-23 06:51:42,476][10762] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 06:51:42,477][10762] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 06:51:42,478][10762] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 06:51:42,480][10762] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 06:51:42,481][10762] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 06:51:42,511][10762] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-02-23 06:51:42,515][10762] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 06:51:42,517][10762] RunningMeanStd input shape: (1,) | |
| [2023-02-23 06:51:42,534][10762] ConvEncoder: input_channels=3 | |
| [2023-02-23 06:51:43,249][10762] Conv encoder output size: 512 | |
| [2023-02-23 06:51:43,250][10762] Policy head output size: 512 | |
| [2023-02-23 06:51:45,737][10762] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 06:51:47,047][10762] Num frames 100... | |
| [2023-02-23 06:51:47,163][10762] Num frames 200... | |
| [2023-02-23 06:51:47,278][10762] Num frames 300... | |
| [2023-02-23 06:51:47,403][10762] Num frames 400... | |
| [2023-02-23 06:51:47,534][10762] Num frames 500... | |
| [2023-02-23 06:51:47,652][10762] Num frames 600... | |
| [2023-02-23 06:51:47,774][10762] Num frames 700... | |
| [2023-02-23 06:51:47,889][10762] Num frames 800... | |
| [2023-02-23 06:51:48,022][10762] Avg episode rewards: #0: 17.640, true rewards: #0: 8.640 | |
| [2023-02-23 06:51:48,023][10762] Avg episode reward: 17.640, avg true_objective: 8.640 | |
| [2023-02-23 06:51:48,070][10762] Num frames 900... | |
| [2023-02-23 06:51:48,190][10762] Num frames 1000... | |
| [2023-02-23 06:51:48,304][10762] Num frames 1100... | |
| [2023-02-23 06:51:48,424][10762] Num frames 1200... | |
| [2023-02-23 06:51:48,542][10762] Num frames 1300... | |
| [2023-02-23 06:51:48,658][10762] Num frames 1400... | |
| [2023-02-23 06:51:48,788][10762] Num frames 1500... | |
| [2023-02-23 06:51:48,916][10762] Num frames 1600... | |
| [2023-02-23 06:51:49,037][10762] Num frames 1700... | |
| [2023-02-23 06:51:49,169][10762] Avg episode rewards: #0: 18.320, true rewards: #0: 8.820 | |
| [2023-02-23 06:51:49,171][10762] Avg episode reward: 18.320, avg true_objective: 8.820 | |
| [2023-02-23 06:51:49,217][10762] Num frames 1800... | |
| [2023-02-23 06:51:49,333][10762] Num frames 1900... | |
| [2023-02-23 06:51:49,458][10762] Num frames 2000... | |
| [2023-02-23 06:51:49,580][10762] Num frames 2100... | |
| [2023-02-23 06:51:49,705][10762] Num frames 2200... | |
| [2023-02-23 06:51:49,825][10762] Num frames 2300... | |
| [2023-02-23 06:51:49,945][10762] Num frames 2400... | |
| [2023-02-23 06:51:50,064][10762] Num frames 2500... | |
| [2023-02-23 06:51:50,189][10762] Num frames 2600... | |
| [2023-02-23 06:51:50,317][10762] Num frames 2700... | |
| [2023-02-23 06:51:50,494][10762] Num frames 2800... | |
| [2023-02-23 06:51:50,701][10762] Avg episode rewards: #0: 20.624, true rewards: #0: 9.623 | |
| [2023-02-23 06:51:50,703][10762] Avg episode reward: 20.624, avg true_objective: 9.623 | |
| [2023-02-23 06:51:50,731][10762] Num frames 2900... | |
| [2023-02-23 06:51:50,896][10762] Num frames 3000... | |
| [2023-02-23 06:51:51,063][10762] Num frames 3100... | |
| [2023-02-23 06:51:51,234][10762] Num frames 3200... | |
| [2023-02-23 06:51:51,397][10762] Num frames 3300... | |
| [2023-02-23 06:51:51,566][10762] Num frames 3400... | |
| [2023-02-23 06:51:51,739][10762] Num frames 3500... | |
| [2023-02-23 06:51:51,910][10762] Num frames 3600... | |
| [2023-02-23 06:51:52,079][10762] Num frames 3700... | |
| [2023-02-23 06:51:52,242][10762] Num frames 3800... | |
| [2023-02-23 06:51:52,408][10762] Num frames 3900... | |
| [2023-02-23 06:51:52,578][10762] Num frames 4000... | |
| [2023-02-23 06:51:52,751][10762] Num frames 4100... | |
| [2023-02-23 06:51:52,926][10762] Num frames 4200... | |
| [2023-02-23 06:51:53,094][10762] Num frames 4300... | |
| [2023-02-23 06:51:53,265][10762] Num frames 4400... | |
| [2023-02-23 06:51:53,436][10762] Num frames 4500... | |
| [2023-02-23 06:51:53,606][10762] Num frames 4600... | |
| [2023-02-23 06:51:53,781][10762] Num frames 4700... | |
| [2023-02-23 06:51:53,953][10762] Num frames 4800... | |
| [2023-02-23 06:51:54,109][10762] Num frames 4900... | |
| [2023-02-23 06:51:54,267][10762] Avg episode rewards: #0: 29.717, true rewards: #0: 12.468 | |
| [2023-02-23 06:51:54,269][10762] Avg episode reward: 29.717, avg true_objective: 12.468 | |
| [2023-02-23 06:51:54,296][10762] Num frames 5000... | |
| [2023-02-23 06:51:54,415][10762] Num frames 5100... | |
| [2023-02-23 06:51:54,533][10762] Num frames 5200... | |
| [2023-02-23 06:51:54,656][10762] Num frames 5300... | |
| [2023-02-23 06:51:54,768][10762] Num frames 5400... | |
| [2023-02-23 06:51:54,897][10762] Num frames 5500... | |
| [2023-02-23 06:51:55,016][10762] Num frames 5600... | |
| [2023-02-23 06:51:55,136][10762] Num frames 5700... | |
| [2023-02-23 06:51:55,256][10762] Avg episode rewards: #0: 26.310, true rewards: #0: 11.510 | |
| [2023-02-23 06:51:55,260][10762] Avg episode reward: 26.310, avg true_objective: 11.510 | |
| [2023-02-23 06:51:55,318][10762] Num frames 5800... | |
| [2023-02-23 06:51:55,436][10762] Num frames 5900... | |
| [2023-02-23 06:51:55,558][10762] Num frames 6000... | |
| [2023-02-23 06:51:55,705][10762] Avg episode rewards: #0: 22.625, true rewards: #0: 10.125 | |
| [2023-02-23 06:51:55,707][10762] Avg episode reward: 22.625, avg true_objective: 10.125 | |
| [2023-02-23 06:51:55,741][10762] Num frames 6100... | |
| [2023-02-23 06:51:55,854][10762] Num frames 6200... | |
| [2023-02-23 06:51:55,978][10762] Num frames 6300... | |
| [2023-02-23 06:51:56,097][10762] Num frames 6400... | |
| [2023-02-23 06:51:56,219][10762] Num frames 6500... | |
| [2023-02-23 06:51:56,343][10762] Num frames 6600... | |
| [2023-02-23 06:51:56,474][10762] Num frames 6700... | |
| [2023-02-23 06:51:56,597][10762] Num frames 6800... | |
| [2023-02-23 06:51:56,721][10762] Num frames 6900... | |
| [2023-02-23 06:51:56,847][10762] Num frames 7000... | |
| [2023-02-23 06:51:56,983][10762] Num frames 7100... | |
| [2023-02-23 06:51:57,105][10762] Num frames 7200... | |
| [2023-02-23 06:51:57,271][10762] Avg episode rewards: #0: 23.416, true rewards: #0: 10.416 | |
| [2023-02-23 06:51:57,273][10762] Avg episode reward: 23.416, avg true_objective: 10.416 | |
| [2023-02-23 06:51:57,286][10762] Num frames 7300... | |
| [2023-02-23 06:51:57,405][10762] Num frames 7400... | |
| [2023-02-23 06:51:57,520][10762] Num frames 7500... | |
| [2023-02-23 06:51:57,636][10762] Num frames 7600... | |
| [2023-02-23 06:51:57,753][10762] Num frames 7700... | |
| [2023-02-23 06:51:57,884][10762] Num frames 7800... | |
| [2023-02-23 06:51:58,014][10762] Num frames 7900... | |
| [2023-02-23 06:51:58,145][10762] Num frames 8000... | |
| [2023-02-23 06:51:58,270][10762] Num frames 8100... | |
| [2023-02-23 06:51:58,385][10762] Num frames 8200... | |
| [2023-02-23 06:51:58,511][10762] Num frames 8300... | |
| [2023-02-23 06:51:58,636][10762] Num frames 8400... | |
| [2023-02-23 06:51:58,752][10762] Num frames 8500... | |
| [2023-02-23 06:51:58,876][10762] Num frames 8600... | |
| [2023-02-23 06:51:58,999][10762] Num frames 8700... | |
| [2023-02-23 06:51:59,119][10762] Num frames 8800... | |
| [2023-02-23 06:51:59,244][10762] Num frames 8900... | |
| [2023-02-23 06:51:59,363][10762] Num frames 9000... | |
| [2023-02-23 06:51:59,482][10762] Avg episode rewards: #0: 25.814, true rewards: #0: 11.314 | |
| [2023-02-23 06:51:59,484][10762] Avg episode reward: 25.814, avg true_objective: 11.314 | |
| [2023-02-23 06:51:59,544][10762] Num frames 9100... | |
| [2023-02-23 06:51:59,667][10762] Num frames 9200... | |
| [2023-02-23 06:51:59,781][10762] Num frames 9300... | |
| [2023-02-23 06:51:59,895][10762] Num frames 9400... | |
| [2023-02-23 06:52:00,025][10762] Num frames 9500... | |
| [2023-02-23 06:52:00,153][10762] Avg episode rewards: #0: 24.070, true rewards: #0: 10.626 | |
| [2023-02-23 06:52:00,156][10762] Avg episode reward: 24.070, avg true_objective: 10.626 | |
| [2023-02-23 06:52:00,201][10762] Num frames 9600... | |
| [2023-02-23 06:52:00,330][10762] Num frames 9700... | |
| [2023-02-23 06:52:00,451][10762] Num frames 9800... | |
| [2023-02-23 06:52:00,570][10762] Num frames 9900... | |
| [2023-02-23 06:52:00,693][10762] Num frames 10000... | |
| [2023-02-23 06:52:00,815][10762] Num frames 10100... | |
| [2023-02-23 06:52:00,944][10762] Num frames 10200... | |
| [2023-02-23 06:52:01,080][10762] Num frames 10300... | |
| [2023-02-23 06:52:01,202][10762] Num frames 10400... | |
| [2023-02-23 06:52:01,323][10762] Num frames 10500... | |
| [2023-02-23 06:52:01,410][10762] Avg episode rewards: #0: 23.823, true rewards: #0: 10.523 | |
| [2023-02-23 06:52:01,412][10762] Avg episode reward: 23.823, avg true_objective: 10.523 | |
| [2023-02-23 06:53:09,237][10762] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-02-23 06:56:49,330][10762] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-02-23 06:56:49,332][10762] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-02-23 06:56:49,336][10762] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-02-23 06:56:49,338][10762] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-02-23 06:56:49,340][10762] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-02-23 06:56:49,341][10762] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-02-23 06:56:49,343][10762] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-02-23 06:56:49,344][10762] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-02-23 06:56:49,345][10762] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-02-23 06:56:49,347][10762] Adding new argument 'hf_repository'='RajMoodley/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-02-23 06:56:49,348][10762] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-02-23 06:56:49,349][10762] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-02-23 06:56:49,351][10762] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-02-23 06:56:49,352][10762] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-02-23 06:56:49,353][10762] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-02-23 06:56:49,390][10762] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-02-23 06:56:49,394][10762] RunningMeanStd input shape: (1,) | |
| [2023-02-23 06:56:49,414][10762] ConvEncoder: input_channels=3 | |
| [2023-02-23 06:56:49,474][10762] Conv encoder output size: 512 | |
| [2023-02-23 06:56:49,476][10762] Policy head output size: 512 | |
| [2023-02-23 06:56:49,505][10762] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-02-23 06:56:50,215][10762] Num frames 100... | |
| [2023-02-23 06:56:50,399][10762] Num frames 200... | |
| [2023-02-23 06:56:50,560][10762] Num frames 300... | |
| [2023-02-23 06:56:50,735][10762] Num frames 400... | |
| [2023-02-23 06:56:50,906][10762] Num frames 500... | |
| [2023-02-23 06:56:51,080][10762] Num frames 600... | |
| [2023-02-23 06:56:51,259][10762] Num frames 700... | |
| [2023-02-23 06:56:51,425][10762] Num frames 800... | |
| [2023-02-23 06:56:51,623][10762] Num frames 900... | |
| [2023-02-23 06:56:51,797][10762] Num frames 1000... | |
| [2023-02-23 06:56:51,963][10762] Num frames 1100... | |
| [2023-02-23 06:56:52,132][10762] Num frames 1200... | |
| [2023-02-23 06:56:52,271][10762] Num frames 1300... | |
| [2023-02-23 06:56:52,403][10762] Avg episode rewards: #0: 31.650, true rewards: #0: 13.650 | |
| [2023-02-23 06:56:52,405][10762] Avg episode reward: 31.650, avg true_objective: 13.650 | |
| [2023-02-23 06:56:52,452][10762] Num frames 1400... | |
| [2023-02-23 06:56:52,566][10762] Num frames 1500... | |
| [2023-02-23 06:56:52,685][10762] Num frames 1600... | |
| [2023-02-23 06:56:52,811][10762] Num frames 1700... | |
| [2023-02-23 06:56:52,923][10762] Num frames 1800... | |
| [2023-02-23 06:56:53,065][10762] Num frames 1900... | |
| [2023-02-23 06:56:53,186][10762] Num frames 2000... | |
| [2023-02-23 06:56:53,303][10762] Num frames 2100... | |
| [2023-02-23 06:56:53,420][10762] Num frames 2200... | |
| [2023-02-23 06:56:53,536][10762] Num frames 2300... | |
| [2023-02-23 06:56:53,669][10762] Num frames 2400... | |
| [2023-02-23 06:56:53,794][10762] Num frames 2500... | |
| [2023-02-23 06:56:53,914][10762] Num frames 2600... | |
| [2023-02-23 06:56:54,033][10762] Num frames 2700... | |
| [2023-02-23 06:56:54,105][10762] Avg episode rewards: #0: 29.545, true rewards: #0: 13.545 | |
| [2023-02-23 06:56:54,107][10762] Avg episode reward: 29.545, avg true_objective: 13.545 | |
| [2023-02-23 06:56:54,213][10762] Num frames 2800... | |
| [2023-02-23 06:56:54,346][10762] Num frames 2900... | |
| [2023-02-23 06:56:54,470][10762] Num frames 3000... | |
| [2023-02-23 06:56:54,586][10762] Num frames 3100... | |
| [2023-02-23 06:56:54,705][10762] Num frames 3200... | |
| [2023-02-23 06:56:54,822][10762] Num frames 3300... | |
| [2023-02-23 06:56:54,883][10762] Avg episode rewards: #0: 23.010, true rewards: #0: 11.010 | |
| [2023-02-23 06:56:54,885][10762] Avg episode reward: 23.010, avg true_objective: 11.010 | |
| [2023-02-23 06:56:55,008][10762] Num frames 3400... | |
| [2023-02-23 06:56:55,131][10762] Num frames 3500... | |
| [2023-02-23 06:56:55,255][10762] Num frames 3600... | |
| [2023-02-23 06:56:55,369][10762] Num frames 3700... | |
| [2023-02-23 06:56:55,489][10762] Num frames 3800... | |
| [2023-02-23 06:56:55,607][10762] Num frames 3900... | |
| [2023-02-23 06:56:55,726][10762] Num frames 4000... | |
| [2023-02-23 06:56:55,841][10762] Num frames 4100... | |
| [2023-02-23 06:56:55,958][10762] Num frames 4200... | |
| [2023-02-23 06:56:56,075][10762] Num frames 4300... | |
| [2023-02-23 06:56:56,198][10762] Num frames 4400... | |
| [2023-02-23 06:56:56,337][10762] Num frames 4500... | |
| [2023-02-23 06:56:56,458][10762] Num frames 4600... | |
| [2023-02-23 06:56:56,576][10762] Num frames 4700... | |
| [2023-02-23 06:56:56,705][10762] Avg episode rewards: #0: 26.395, true rewards: #0: 11.895 | |
| [2023-02-23 06:56:56,707][10762] Avg episode reward: 26.395, avg true_objective: 11.895 | |
| [2023-02-23 06:56:56,762][10762] Num frames 4800... | |
| [2023-02-23 06:56:56,885][10762] Num frames 4900... | |
| [2023-02-23 06:56:57,008][10762] Num frames 5000... | |
| [2023-02-23 06:56:57,132][10762] Num frames 5100... | |
| [2023-02-23 06:56:57,251][10762] Num frames 5200... | |
| [2023-02-23 06:56:57,369][10762] Num frames 5300... | |
| [2023-02-23 06:56:57,490][10762] Num frames 5400... | |
| [2023-02-23 06:56:57,607][10762] Num frames 5500... | |
| [2023-02-23 06:56:57,734][10762] Num frames 5600... | |
| [2023-02-23 06:56:57,864][10762] Num frames 5700... | |
| [2023-02-23 06:56:57,984][10762] Num frames 5800... | |
| [2023-02-23 06:56:58,098][10762] Avg episode rewards: #0: 25.692, true rewards: #0: 11.692 | |
| [2023-02-23 06:56:58,099][10762] Avg episode reward: 25.692, avg true_objective: 11.692 | |
| [2023-02-23 06:56:58,170][10762] Num frames 5900... | |
| [2023-02-23 06:56:58,285][10762] Num frames 6000... | |
| [2023-02-23 06:56:58,417][10762] Num frames 6100... | |
| [2023-02-23 06:56:58,537][10762] Num frames 6200... | |
| [2023-02-23 06:56:58,656][10762] Num frames 6300... | |
| [2023-02-23 06:56:58,774][10762] Num frames 6400... | |
| [2023-02-23 06:56:58,888][10762] Num frames 6500... | |
| [2023-02-23 06:56:59,004][10762] Num frames 6600... | |
| [2023-02-23 06:56:59,139][10762] Num frames 6700... | |
| [2023-02-23 06:56:59,257][10762] Num frames 6800... | |
| [2023-02-23 06:56:59,378][10762] Num frames 6900... | |
| [2023-02-23 06:56:59,499][10762] Num frames 7000... | |
| [2023-02-23 06:56:59,616][10762] Num frames 7100... | |
| [2023-02-23 06:56:59,739][10762] Avg episode rewards: #0: 26.093, true rewards: #0: 11.927 | |
| [2023-02-23 06:56:59,742][10762] Avg episode reward: 26.093, avg true_objective: 11.927 | |
| [2023-02-23 06:56:59,796][10762] Num frames 7200... | |
| [2023-02-23 06:56:59,912][10762] Num frames 7300... | |
| [2023-02-23 06:57:00,028][10762] Num frames 7400... | |
| [2023-02-23 06:57:00,145][10762] Num frames 7500... | |
| [2023-02-23 06:57:00,267][10762] Num frames 7600... | |
| [2023-02-23 06:57:00,399][10762] Avg episode rewards: #0: 23.526, true rewards: #0: 10.954 | |
| [2023-02-23 06:57:00,401][10762] Avg episode reward: 23.526, avg true_objective: 10.954 | |
| [2023-02-23 06:57:00,444][10762] Num frames 7700... | |
| [2023-02-23 06:57:00,564][10762] Num frames 7800... | |
| [2023-02-23 06:57:00,701][10762] Num frames 7900... | |
| [2023-02-23 06:57:00,822][10762] Num frames 8000... | |
| [2023-02-23 06:57:00,942][10762] Num frames 8100... | |
| [2023-02-23 06:57:01,064][10762] Num frames 8200... | |
| [2023-02-23 06:57:01,200][10762] Num frames 8300... | |
| [2023-02-23 06:57:01,311][10762] Avg episode rewards: #0: 22.806, true rewards: #0: 10.431 | |
| [2023-02-23 06:57:01,313][10762] Avg episode reward: 22.806, avg true_objective: 10.431 | |
| [2023-02-23 06:57:01,380][10762] Num frames 8400... | |
| [2023-02-23 06:57:01,512][10762] Num frames 8500... | |
| [2023-02-23 06:57:01,631][10762] Num frames 8600... | |
| [2023-02-23 06:57:01,751][10762] Num frames 8700... | |
| [2023-02-23 06:57:01,869][10762] Num frames 8800... | |
| [2023-02-23 06:57:01,987][10762] Num frames 8900... | |
| [2023-02-23 06:57:02,110][10762] Num frames 9000... | |
| [2023-02-23 06:57:02,243][10762] Num frames 9100... | |
| [2023-02-23 06:57:02,417][10762] Num frames 9200... | |
| [2023-02-23 06:57:02,588][10762] Num frames 9300... | |
| [2023-02-23 06:57:02,761][10762] Num frames 9400... | |
| [2023-02-23 06:57:02,927][10762] Num frames 9500... | |
| [2023-02-23 06:57:03,102][10762] Num frames 9600... | |
| [2023-02-23 06:57:03,285][10762] Num frames 9700... | |
| [2023-02-23 06:57:03,433][10762] Avg episode rewards: #0: 24.170, true rewards: #0: 10.837 | |
| [2023-02-23 06:57:03,435][10762] Avg episode reward: 24.170, avg true_objective: 10.837 | |
| [2023-02-23 06:57:03,515][10762] Num frames 9800... | |
| [2023-02-23 06:57:03,682][10762] Num frames 9900... | |
| [2023-02-23 06:57:03,849][10762] Num frames 10000... | |
| [2023-02-23 06:57:04,021][10762] Num frames 10100... | |
| [2023-02-23 06:57:04,195][10762] Num frames 10200... | |
| [2023-02-23 06:57:04,377][10762] Num frames 10300... | |
| [2023-02-23 06:57:04,547][10762] Num frames 10400... | |
| [2023-02-23 06:57:04,721][10762] Num frames 10500... | |
| [2023-02-23 06:57:04,896][10762] Num frames 10600... | |
| [2023-02-23 06:57:05,069][10762] Num frames 10700... | |
| [2023-02-23 06:57:05,240][10762] Num frames 10800... | |
| [2023-02-23 06:57:05,425][10762] Num frames 10900... | |
| [2023-02-23 06:57:05,596][10762] Avg episode rewards: #0: 24.969, true rewards: #0: 10.969 | |
| [2023-02-23 06:57:05,599][10762] Avg episode reward: 24.969, avg true_objective: 10.969 | |
| [2023-02-23 06:58:14,966][10762] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |