diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1211 @@ +[2023-02-22 19:21:17,455][00804] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-02-22 19:21:17,462][00804] Rollout worker 0 uses device cpu +[2023-02-22 19:21:17,463][00804] Rollout worker 1 uses device cpu +[2023-02-22 19:21:17,465][00804] Rollout worker 2 uses device cpu +[2023-02-22 19:21:17,469][00804] Rollout worker 3 uses device cpu +[2023-02-22 19:21:17,472][00804] Rollout worker 4 uses device cpu +[2023-02-22 19:21:17,476][00804] Rollout worker 5 uses device cpu +[2023-02-22 19:21:17,477][00804] Rollout worker 6 uses device cpu +[2023-02-22 19:21:17,480][00804] Rollout worker 7 uses device cpu +[2023-02-22 19:21:17,947][00804] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-22 19:21:17,958][00804] InferenceWorker_p0-w0: min num requests: 2 +[2023-02-22 19:21:18,081][00804] Starting all processes... +[2023-02-22 19:21:18,096][00804] Starting process learner_proc0 +[2023-02-22 19:21:18,266][00804] Starting all processes... +[2023-02-22 19:21:18,307][00804] Starting process inference_proc0-0 +[2023-02-22 19:21:18,310][00804] Starting process rollout_proc0 +[2023-02-22 19:21:18,310][00804] Starting process rollout_proc1 +[2023-02-22 19:21:18,310][00804] Starting process rollout_proc2 +[2023-02-22 19:21:18,310][00804] Starting process rollout_proc3 +[2023-02-22 19:21:18,310][00804] Starting process rollout_proc4 +[2023-02-22 19:21:18,348][00804] Starting process rollout_proc5 +[2023-02-22 19:21:18,348][00804] Starting process rollout_proc6 +[2023-02-22 19:21:18,348][00804] Starting process rollout_proc7 +[2023-02-22 19:21:30,535][11058] Worker 3 uses CPU cores [1] +[2023-02-22 19:21:30,604][11041] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-22 19:21:30,605][11041] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-02-22 19:21:30,829][11059] Worker 2 uses CPU cores [0] +[2023-02-22 19:21:30,848][11063] Worker 7 uses CPU cores [1] +[2023-02-22 19:21:31,203][11061] Worker 5 uses CPU cores [1] +[2023-02-22 19:21:31,278][11056] Worker 0 uses CPU cores [0] +[2023-02-22 19:21:31,296][11057] Worker 1 uses CPU cores [1] +[2023-02-22 19:21:31,390][11055] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-22 19:21:31,392][11055] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-02-22 19:21:31,532][11062] Worker 6 uses CPU cores [0] +[2023-02-22 19:21:31,533][11060] Worker 4 uses CPU cores [0] +[2023-02-22 19:21:31,682][11055] Num visible devices: 1 +[2023-02-22 19:21:31,686][11041] Num visible devices: 1 +[2023-02-22 19:21:31,698][11041] Starting seed is not provided +[2023-02-22 19:21:31,698][11041] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-22 19:21:31,699][11041] Initializing actor-critic model on device cuda:0 +[2023-02-22 19:21:31,700][11041] RunningMeanStd input shape: (3, 72, 128) +[2023-02-22 19:21:31,702][11041] RunningMeanStd input shape: (1,) +[2023-02-22 19:21:31,721][11041] ConvEncoder: input_channels=3 +[2023-02-22 19:21:32,133][11041] Conv encoder output size: 512 +[2023-02-22 19:21:32,135][11041] Policy head output size: 512 +[2023-02-22 19:21:32,255][11041] Created Actor Critic model with architecture: +[2023-02-22 19:21:32,257][11041] 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) + ) +) +[2023-02-22 19:21:37,919][00804] Heartbeat connected on Batcher_0 +[2023-02-22 19:21:37,948][00804] Heartbeat connected on InferenceWorker_p0-w0 +[2023-02-22 19:21:37,965][00804] Heartbeat connected on RolloutWorker_w0 +[2023-02-22 19:21:37,991][00804] Heartbeat connected on RolloutWorker_w1 +[2023-02-22 19:21:37,999][00804] Heartbeat connected on RolloutWorker_w2 +[2023-02-22 19:21:38,019][00804] Heartbeat connected on RolloutWorker_w3 +[2023-02-22 19:21:38,023][00804] Heartbeat connected on RolloutWorker_w4 +[2023-02-22 19:21:38,052][00804] Heartbeat connected on RolloutWorker_w5 +[2023-02-22 19:21:38,058][00804] Heartbeat connected on RolloutWorker_w6 +[2023-02-22 19:21:38,079][00804] Heartbeat connected on RolloutWorker_w7 +[2023-02-22 19:21:40,651][11041] Using optimizer +[2023-02-22 19:21:40,652][11041] No checkpoints found +[2023-02-22 19:21:40,652][11041] Did not load from checkpoint, starting from scratch! +[2023-02-22 19:21:40,652][11041] Initialized policy 0 weights for model version 0 +[2023-02-22 19:21:40,656][11041] LearnerWorker_p0 finished initialization! +[2023-02-22 19:21:40,660][11041] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-22 19:21:40,658][00804] Heartbeat connected on LearnerWorker_p0 +[2023-02-22 19:21:40,876][11055] RunningMeanStd input shape: (3, 72, 128) +[2023-02-22 19:21:40,878][11055] RunningMeanStd input shape: (1,) +[2023-02-22 19:21:40,890][11055] ConvEncoder: input_channels=3 +[2023-02-22 19:21:40,990][11055] Conv encoder output size: 512 +[2023-02-22 19:21:40,990][11055] Policy head output size: 512 +[2023-02-22 19:21:42,718][00804] 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) +[2023-02-22 19:21:43,270][00804] Inference worker 0-0 is ready! +[2023-02-22 19:21:43,273][00804] All inference workers are ready! Signal rollout workers to start! +[2023-02-22 19:21:43,413][11063] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,425][11060] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,439][11056] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,447][11061] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,442][11062] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,452][11057] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,445][11059] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,465][11058] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:21:43,672][11056] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... +[2023-02-22 19:21:43,675][11056] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() +Traceback (most recent call last): + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init + self.game.init() +vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly. + +During handling of the above exception, another exception occurred: + +Traceback (most recent call last): + File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal + slot_callable(*args) + File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init + env_runner.init(self.timing) + File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init + self._reset() + File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset + observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 + File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 323, in reset + return self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset + return self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 379, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 323, in reset + return self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset + return self.env.reset(**kwargs) + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset + self._ensure_initialized() + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized + self.initialize() + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize + self._game_init() + File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init + raise EnvCriticalError() +sample_factory.envs.env_utils.EnvCriticalError +[2023-02-22 19:21:43,681][11056] Unhandled exception in evt loop rollout_proc0_evt_loop +[2023-02-22 19:21:44,662][11060] Decorrelating experience for 0 frames... +[2023-02-22 19:21:44,662][11059] Decorrelating experience for 0 frames... +[2023-02-22 19:21:44,834][11063] Decorrelating experience for 0 frames... +[2023-02-22 19:21:44,836][11057] Decorrelating experience for 0 frames... +[2023-02-22 19:21:44,847][11058] Decorrelating experience for 0 frames... +[2023-02-22 19:21:44,851][11061] Decorrelating experience for 0 frames... +[2023-02-22 19:21:45,531][11063] Decorrelating experience for 32 frames... +[2023-02-22 19:21:45,540][11058] Decorrelating experience for 32 frames... +[2023-02-22 19:21:45,912][11059] Decorrelating experience for 32 frames... +[2023-02-22 19:21:45,918][11060] Decorrelating experience for 32 frames... +[2023-02-22 19:21:45,981][11062] Decorrelating experience for 0 frames... +[2023-02-22 19:21:46,466][11061] Decorrelating experience for 32 frames... +[2023-02-22 19:21:46,588][11063] Decorrelating experience for 64 frames... +[2023-02-22 19:21:46,830][11057] Decorrelating experience for 32 frames... +[2023-02-22 19:21:47,106][11062] Decorrelating experience for 32 frames... +[2023-02-22 19:21:47,255][11059] Decorrelating experience for 64 frames... +[2023-02-22 19:21:47,270][11060] Decorrelating experience for 64 frames... +[2023-02-22 19:21:47,718][00804] 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) +[2023-02-22 19:21:48,453][11058] Decorrelating experience for 64 frames... +[2023-02-22 19:21:48,631][11063] Decorrelating experience for 96 frames... +[2023-02-22 19:21:48,747][11057] Decorrelating experience for 64 frames... +[2023-02-22 19:21:49,318][11062] Decorrelating experience for 64 frames... +[2023-02-22 19:21:49,324][11059] Decorrelating experience for 96 frames... +[2023-02-22 19:21:49,344][11060] Decorrelating experience for 96 frames... +[2023-02-22 19:21:50,331][11061] Decorrelating experience for 64 frames... +[2023-02-22 19:21:50,437][11058] Decorrelating experience for 96 frames... +[2023-02-22 19:21:50,754][11057] Decorrelating experience for 96 frames... +[2023-02-22 19:21:51,160][11061] Decorrelating experience for 96 frames... +[2023-02-22 19:21:51,497][11062] Decorrelating experience for 96 frames... +[2023-02-22 19:21:52,718][00804] 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) +[2023-02-22 19:21:56,435][11041] Signal inference workers to stop experience collection... +[2023-02-22 19:21:56,448][11055] InferenceWorker_p0-w0: stopping experience collection +[2023-02-22 19:21:57,718][00804] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 122.9. Samples: 1844. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-22 19:21:57,720][00804] Avg episode reward: [(0, '2.625')] +[2023-02-22 19:21:58,911][11041] Signal inference workers to resume experience collection... +[2023-02-22 19:21:58,913][11055] InferenceWorker_p0-w0: resuming experience collection +[2023-02-22 19:22:02,718][00804] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 227.8. Samples: 4556. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) +[2023-02-22 19:22:02,723][00804] Avg episode reward: [(0, '3.596')] +[2023-02-22 19:22:07,568][11055] Updated weights for policy 0, policy_version 10 (0.0014) +[2023-02-22 19:22:07,718][00804] Fps is (10 sec: 4096.0, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 40960. Throughput: 0: 408.6. Samples: 10214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:22:07,724][00804] Avg episode reward: [(0, '3.896')] +[2023-02-22 19:22:12,718][00804] Fps is (10 sec: 3276.8, 60 sec: 1774.9, 300 sec: 1774.9). Total num frames: 53248. Throughput: 0: 412.6. Samples: 12378. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:22:12,720][00804] Avg episode reward: [(0, '4.335')] +[2023-02-22 19:22:17,718][00804] Fps is (10 sec: 3276.8, 60 sec: 2106.5, 300 sec: 2106.5). Total num frames: 73728. Throughput: 0: 511.7. Samples: 17908. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:22:17,721][00804] Avg episode reward: [(0, '4.368')] +[2023-02-22 19:22:18,961][11055] Updated weights for policy 0, policy_version 20 (0.0027) +[2023-02-22 19:22:22,718][00804] Fps is (10 sec: 4505.8, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 98304. Throughput: 0: 623.8. Samples: 24952. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:22:22,721][00804] Avg episode reward: [(0, '4.363')] +[2023-02-22 19:22:27,721][00804] Fps is (10 sec: 4094.7, 60 sec: 2548.4, 300 sec: 2548.4). Total num frames: 114688. Throughput: 0: 618.8. Samples: 27850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:22:27,727][00804] Avg episode reward: [(0, '4.449')] +[2023-02-22 19:22:27,732][11041] Saving new best policy, reward=4.449! +[2023-02-22 19:22:29,789][11055] Updated weights for policy 0, policy_version 30 (0.0022) +[2023-02-22 19:22:32,718][00804] Fps is (10 sec: 3276.8, 60 sec: 2621.4, 300 sec: 2621.4). Total num frames: 131072. Throughput: 0: 716.4. Samples: 32240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:22:32,720][00804] Avg episode reward: [(0, '4.389')] +[2023-02-22 19:22:37,718][00804] Fps is (10 sec: 3687.6, 60 sec: 2755.5, 300 sec: 2755.5). Total num frames: 151552. Throughput: 0: 860.3. Samples: 38712. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:22:37,724][00804] Avg episode reward: [(0, '4.423')] +[2023-02-22 19:22:39,566][11055] Updated weights for policy 0, policy_version 40 (0.0016) +[2023-02-22 19:22:42,718][00804] Fps is (10 sec: 4505.6, 60 sec: 2935.5, 300 sec: 2935.5). Total num frames: 176128. Throughput: 0: 897.0. Samples: 42210. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:22:42,720][00804] Avg episode reward: [(0, '4.594')] +[2023-02-22 19:22:42,731][11041] Saving new best policy, reward=4.594! +[2023-02-22 19:22:47,747][00804] Fps is (10 sec: 4084.0, 60 sec: 3207.0, 300 sec: 2960.4). Total num frames: 192512. Throughput: 0: 956.1. Samples: 47608. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:22:47,758][00804] Avg episode reward: [(0, '4.427')] +[2023-02-22 19:22:52,400][11055] Updated weights for policy 0, policy_version 50 (0.0018) +[2023-02-22 19:22:52,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 918.0. Samples: 51522. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:22:52,720][00804] Avg episode reward: [(0, '4.574')] +[2023-02-22 19:22:57,720][00804] Fps is (10 sec: 3285.6, 60 sec: 3754.5, 300 sec: 3003.6). Total num frames: 225280. Throughput: 0: 943.6. Samples: 54840. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:22:57,723][00804] Avg episode reward: [(0, '4.457')] +[2023-02-22 19:23:01,744][11055] Updated weights for policy 0, policy_version 60 (0.0017) +[2023-02-22 19:23:02,726][00804] Fps is (10 sec: 4092.8, 60 sec: 3754.2, 300 sec: 3071.7). Total num frames: 245760. Throughput: 0: 968.8. Samples: 61510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:23:02,733][00804] Avg episode reward: [(0, '4.308')] +[2023-02-22 19:23:07,718][00804] Fps is (10 sec: 3687.2, 60 sec: 3686.4, 300 sec: 3084.1). Total num frames: 262144. Throughput: 0: 916.0. Samples: 66172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:23:07,726][00804] Avg episode reward: [(0, '4.389')] +[2023-02-22 19:23:12,718][00804] Fps is (10 sec: 3279.3, 60 sec: 3754.7, 300 sec: 3094.8). Total num frames: 278528. Throughput: 0: 898.5. Samples: 68278. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:23:12,724][00804] Avg episode reward: [(0, '4.723')] +[2023-02-22 19:23:12,735][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth... +[2023-02-22 19:23:12,841][11041] Saving new best policy, reward=4.723! +[2023-02-22 19:23:14,532][11055] Updated weights for policy 0, policy_version 70 (0.0018) +[2023-02-22 19:23:17,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3147.5). Total num frames: 299008. Throughput: 0: 932.9. Samples: 74220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:23:17,726][00804] Avg episode reward: [(0, '4.610')] +[2023-02-22 19:23:22,723][00804] Fps is (10 sec: 4093.9, 60 sec: 3686.1, 300 sec: 3194.7). Total num frames: 319488. Throughput: 0: 930.9. Samples: 80606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:23:22,726][00804] Avg episode reward: [(0, '4.292')] +[2023-02-22 19:23:25,091][11055] Updated weights for policy 0, policy_version 80 (0.0011) +[2023-02-22 19:23:27,722][00804] Fps is (10 sec: 3275.4, 60 sec: 3618.1, 300 sec: 3159.6). Total num frames: 331776. Throughput: 0: 897.8. Samples: 82616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:23:27,725][00804] Avg episode reward: [(0, '4.220')] +[2023-02-22 19:23:32,718][00804] Fps is (10 sec: 2868.7, 60 sec: 3618.1, 300 sec: 3165.1). Total num frames: 348160. Throughput: 0: 875.4. Samples: 86976. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:23:32,726][00804] Avg episode reward: [(0, '4.378')] +[2023-02-22 19:23:36,298][11055] Updated weights for policy 0, policy_version 90 (0.0023) +[2023-02-22 19:23:37,718][00804] Fps is (10 sec: 4097.8, 60 sec: 3686.4, 300 sec: 3241.2). Total num frames: 372736. Throughput: 0: 937.4. Samples: 93704. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:23:37,721][00804] Avg episode reward: [(0, '4.501')] +[2023-02-22 19:23:42,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3276.8). Total num frames: 393216. Throughput: 0: 936.1. Samples: 96962. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:23:42,720][00804] Avg episode reward: [(0, '4.553')] +[2023-02-22 19:23:47,721][00804] Fps is (10 sec: 3275.7, 60 sec: 3551.4, 300 sec: 3243.9). Total num frames: 405504. Throughput: 0: 890.5. Samples: 101578. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:23:47,726][00804] Avg episode reward: [(0, '4.411')] +[2023-02-22 19:23:48,114][11055] Updated weights for policy 0, policy_version 100 (0.0026) +[2023-02-22 19:23:52,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3276.8). Total num frames: 425984. Throughput: 0: 901.2. Samples: 106724. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:23:52,722][00804] Avg episode reward: [(0, '4.603')] +[2023-02-22 19:23:57,718][00804] Fps is (10 sec: 4097.3, 60 sec: 3686.5, 300 sec: 3307.1). Total num frames: 446464. Throughput: 0: 926.2. Samples: 109956. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:23:57,726][00804] Avg episode reward: [(0, '4.636')] +[2023-02-22 19:23:58,184][11055] Updated weights for policy 0, policy_version 110 (0.0014) +[2023-02-22 19:24:02,718][00804] Fps is (10 sec: 3686.3, 60 sec: 3618.6, 300 sec: 3306.1). Total num frames: 462848. Throughput: 0: 927.3. Samples: 115948. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:24:02,724][00804] Avg episode reward: [(0, '4.512')] +[2023-02-22 19:24:07,719][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3305.1). Total num frames: 479232. Throughput: 0: 878.3. Samples: 120124. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:24:07,727][00804] Avg episode reward: [(0, '4.464')] +[2023-02-22 19:24:10,757][11055] Updated weights for policy 0, policy_version 120 (0.0027) +[2023-02-22 19:24:12,718][00804] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3331.4). Total num frames: 499712. Throughput: 0: 890.8. Samples: 122698. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-22 19:24:12,720][00804] Avg episode reward: [(0, '4.510')] +[2023-02-22 19:24:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3356.1). Total num frames: 520192. Throughput: 0: 943.5. Samples: 129432. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:24:17,720][00804] Avg episode reward: [(0, '4.453')] +[2023-02-22 19:24:20,621][11055] Updated weights for policy 0, policy_version 130 (0.0015) +[2023-02-22 19:24:22,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3618.5, 300 sec: 3353.6). Total num frames: 536576. Throughput: 0: 915.1. Samples: 134884. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:24:22,725][00804] Avg episode reward: [(0, '4.259')] +[2023-02-22 19:24:27,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.4, 300 sec: 3326.5). Total num frames: 548864. Throughput: 0: 889.9. Samples: 137006. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:24:27,726][00804] Avg episode reward: [(0, '4.429')] +[2023-02-22 19:24:32,722][00804] Fps is (10 sec: 2866.0, 60 sec: 3617.9, 300 sec: 3324.9). Total num frames: 565248. Throughput: 0: 884.3. Samples: 141370. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:24:32,727][00804] Avg episode reward: [(0, '4.521')] +[2023-02-22 19:24:35,012][11055] Updated weights for policy 0, policy_version 140 (0.0013) +[2023-02-22 19:24:37,718][00804] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3323.6). Total num frames: 581632. Throughput: 0: 862.5. Samples: 145536. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:24:37,726][00804] Avg episode reward: [(0, '4.442')] +[2023-02-22 19:24:42,718][00804] Fps is (10 sec: 2868.4, 60 sec: 3345.1, 300 sec: 3299.6). Total num frames: 593920. Throughput: 0: 844.1. Samples: 147942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:24:42,722][00804] Avg episode reward: [(0, '4.454')] +[2023-02-22 19:24:47,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3413.5, 300 sec: 3298.9). Total num frames: 610304. Throughput: 0: 803.2. Samples: 152094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:24:47,721][00804] Avg episode reward: [(0, '4.490')] +[2023-02-22 19:24:48,521][11055] Updated weights for policy 0, policy_version 150 (0.0038) +[2023-02-22 19:24:52,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3319.9). Total num frames: 630784. Throughput: 0: 849.4. Samples: 158348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:24:52,724][00804] Avg episode reward: [(0, '4.440')] +[2023-02-22 19:24:57,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3339.8). Total num frames: 651264. Throughput: 0: 863.8. Samples: 161568. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:24:57,720][00804] Avg episode reward: [(0, '4.530')] +[2023-02-22 19:24:57,914][11055] Updated weights for policy 0, policy_version 160 (0.0018) +[2023-02-22 19:25:02,720][00804] Fps is (10 sec: 3685.5, 60 sec: 3413.2, 300 sec: 3338.2). Total num frames: 667648. Throughput: 0: 828.5. Samples: 166716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:02,723][00804] Avg episode reward: [(0, '4.591')] +[2023-02-22 19:25:07,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3336.7). Total num frames: 684032. Throughput: 0: 805.0. Samples: 171110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:25:07,720][00804] Avg episode reward: [(0, '4.819')] +[2023-02-22 19:25:07,724][11041] Saving new best policy, reward=4.819! +[2023-02-22 19:25:10,595][11055] Updated weights for policy 0, policy_version 170 (0.0021) +[2023-02-22 19:25:12,718][00804] Fps is (10 sec: 3687.3, 60 sec: 3413.3, 300 sec: 3354.8). Total num frames: 704512. Throughput: 0: 829.2. Samples: 174320. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:12,722][00804] Avg episode reward: [(0, '4.941')] +[2023-02-22 19:25:12,738][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth... +[2023-02-22 19:25:12,860][11041] Saving new best policy, reward=4.941! +[2023-02-22 19:25:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3372.1). Total num frames: 724992. Throughput: 0: 876.7. Samples: 180818. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:25:17,727][00804] Avg episode reward: [(0, '4.797')] +[2023-02-22 19:25:21,559][11055] Updated weights for policy 0, policy_version 180 (0.0013) +[2023-02-22 19:25:22,721][00804] Fps is (10 sec: 3275.7, 60 sec: 3344.9, 300 sec: 3351.2). Total num frames: 737280. Throughput: 0: 884.1. Samples: 185322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:22,724][00804] Avg episode reward: [(0, '4.698')] +[2023-02-22 19:25:27,718][00804] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3367.8). Total num frames: 757760. Throughput: 0: 879.2. Samples: 187506. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:27,720][00804] Avg episode reward: [(0, '4.809')] +[2023-02-22 19:25:32,359][11055] Updated weights for policy 0, policy_version 190 (0.0019) +[2023-02-22 19:25:32,718][00804] Fps is (10 sec: 4097.2, 60 sec: 3550.1, 300 sec: 3383.6). Total num frames: 778240. Throughput: 0: 928.2. Samples: 193862. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-22 19:25:32,721][00804] Avg episode reward: [(0, '4.925')] +[2023-02-22 19:25:37,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3618.2, 300 sec: 3398.8). Total num frames: 798720. Throughput: 0: 927.5. Samples: 200084. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:25:37,720][00804] Avg episode reward: [(0, '4.883')] +[2023-02-22 19:25:42,718][00804] Fps is (10 sec: 3276.9, 60 sec: 3618.1, 300 sec: 3379.2). Total num frames: 811008. Throughput: 0: 902.1. Samples: 202164. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:25:42,727][00804] Avg episode reward: [(0, '4.864')] +[2023-02-22 19:25:44,668][11055] Updated weights for policy 0, policy_version 200 (0.0015) +[2023-02-22 19:25:47,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3393.8). Total num frames: 831488. Throughput: 0: 890.7. Samples: 206794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:47,725][00804] Avg episode reward: [(0, '4.769')] +[2023-02-22 19:25:52,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3407.9). Total num frames: 851968. Throughput: 0: 942.1. Samples: 213504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:25:52,726][00804] Avg episode reward: [(0, '4.907')] +[2023-02-22 19:25:54,293][11055] Updated weights for policy 0, policy_version 210 (0.0011) +[2023-02-22 19:25:57,724][00804] Fps is (10 sec: 4093.4, 60 sec: 3686.0, 300 sec: 3421.3). Total num frames: 872448. Throughput: 0: 944.4. Samples: 216824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:25:57,727][00804] Avg episode reward: [(0, '4.921')] +[2023-02-22 19:26:02,718][00804] Fps is (10 sec: 3276.7, 60 sec: 3618.3, 300 sec: 3402.8). Total num frames: 884736. Throughput: 0: 894.1. Samples: 221052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:26:02,726][00804] Avg episode reward: [(0, '5.000')] +[2023-02-22 19:26:02,736][11041] Saving new best policy, reward=5.000! +[2023-02-22 19:26:06,777][11055] Updated weights for policy 0, policy_version 220 (0.0020) +[2023-02-22 19:26:07,718][00804] Fps is (10 sec: 2869.0, 60 sec: 3618.1, 300 sec: 3400.5). Total num frames: 901120. Throughput: 0: 912.2. Samples: 226366. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:26:07,726][00804] Avg episode reward: [(0, '5.132')] +[2023-02-22 19:26:07,783][11041] Saving new best policy, reward=5.132! +[2023-02-22 19:26:12,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3428.5). Total num frames: 925696. Throughput: 0: 937.1. Samples: 229676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-22 19:26:12,721][00804] Avg episode reward: [(0, '5.179')] +[2023-02-22 19:26:12,734][11041] Saving new best policy, reward=5.179! +[2023-02-22 19:26:16,392][11055] Updated weights for policy 0, policy_version 230 (0.0017) +[2023-02-22 19:26:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3425.7). Total num frames: 942080. Throughput: 0: 928.6. Samples: 235650. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:26:17,722][00804] Avg episode reward: [(0, '5.020')] +[2023-02-22 19:26:22,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.3, 300 sec: 3408.5). Total num frames: 954368. Throughput: 0: 881.5. Samples: 239750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:26:22,721][00804] Avg episode reward: [(0, '4.932')] +[2023-02-22 19:26:27,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3420.5). Total num frames: 974848. Throughput: 0: 897.6. Samples: 242558. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:26:27,719][00804] Avg episode reward: [(0, '5.076')] +[2023-02-22 19:26:28,582][11055] Updated weights for policy 0, policy_version 240 (0.0015) +[2023-02-22 19:26:32,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3446.3). Total num frames: 999424. Throughput: 0: 944.8. Samples: 249310. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:26:32,725][00804] Avg episode reward: [(0, '5.075')] +[2023-02-22 19:26:37,722][00804] Fps is (10 sec: 4094.5, 60 sec: 3617.9, 300 sec: 3443.4). Total num frames: 1015808. Throughput: 0: 909.8. Samples: 254448. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:26:37,724][00804] Avg episode reward: [(0, '5.073')] +[2023-02-22 19:26:40,482][11055] Updated weights for policy 0, policy_version 250 (0.0023) +[2023-02-22 19:26:42,718][00804] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3485.1). Total num frames: 1028096. Throughput: 0: 883.0. Samples: 256554. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-02-22 19:26:42,725][00804] Avg episode reward: [(0, '5.208')] +[2023-02-22 19:26:42,736][11041] Saving new best policy, reward=5.208! +[2023-02-22 19:26:47,718][00804] Fps is (10 sec: 3278.0, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 911.5. Samples: 262070. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-22 19:26:47,724][00804] Avg episode reward: [(0, '5.105')] +[2023-02-22 19:26:50,695][11055] Updated weights for policy 0, policy_version 260 (0.0034) +[2023-02-22 19:26:52,718][00804] Fps is (10 sec: 4505.7, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1073152. Throughput: 0: 942.3. Samples: 268768. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:26:52,724][00804] Avg episode reward: [(0, '5.245')] +[2023-02-22 19:26:52,736][11041] Saving new best policy, reward=5.245! +[2023-02-22 19:26:57,719][00804] Fps is (10 sec: 3685.9, 60 sec: 3550.2, 300 sec: 3610.0). Total num frames: 1085440. Throughput: 0: 916.5. Samples: 270918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:26:57,724][00804] Avg episode reward: [(0, '5.450')] +[2023-02-22 19:26:57,728][11041] Saving new best policy, reward=5.450! +[2023-02-22 19:27:02,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.2, 300 sec: 3596.1). Total num frames: 1101824. Throughput: 0: 874.4. Samples: 274996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:27:02,720][00804] Avg episode reward: [(0, '5.733')] +[2023-02-22 19:27:02,731][11041] Saving new best policy, reward=5.733! +[2023-02-22 19:27:03,477][11055] Updated weights for policy 0, policy_version 270 (0.0015) +[2023-02-22 19:27:07,718][00804] Fps is (10 sec: 3686.9, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1122304. Throughput: 0: 920.3. Samples: 281164. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-22 19:27:07,720][00804] Avg episode reward: [(0, '5.729')] +[2023-02-22 19:27:12,723][00804] Fps is (10 sec: 4093.8, 60 sec: 3617.8, 300 sec: 3623.9). Total num frames: 1142784. Throughput: 0: 931.7. Samples: 284490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:27:12,726][00804] Avg episode reward: [(0, '5.989')] +[2023-02-22 19:27:12,743][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000279_1142784.pth... +[2023-02-22 19:27:12,878][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000068_278528.pth +[2023-02-22 19:27:12,900][11041] Saving new best policy, reward=5.989! +[2023-02-22 19:27:13,246][11055] Updated weights for policy 0, policy_version 280 (0.0013) +[2023-02-22 19:27:17,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1159168. Throughput: 0: 889.5. Samples: 289336. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:27:17,724][00804] Avg episode reward: [(0, '6.205')] +[2023-02-22 19:27:17,728][11041] Saving new best policy, reward=6.205! +[2023-02-22 19:27:22,718][00804] Fps is (10 sec: 2868.7, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1171456. Throughput: 0: 876.0. Samples: 293864. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-22 19:27:22,726][00804] Avg episode reward: [(0, '6.092')] +[2023-02-22 19:27:25,426][11055] Updated weights for policy 0, policy_version 290 (0.0012) +[2023-02-22 19:27:27,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1196032. Throughput: 0: 902.9. Samples: 297186. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:27:27,725][00804] Avg episode reward: [(0, '6.117')] +[2023-02-22 19:27:32,722][00804] Fps is (10 sec: 4503.7, 60 sec: 3617.9, 300 sec: 3610.0). Total num frames: 1216512. Throughput: 0: 925.5. Samples: 303720. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:27:32,730][00804] Avg episode reward: [(0, '5.917')] +[2023-02-22 19:27:36,642][11055] Updated weights for policy 0, policy_version 300 (0.0015) +[2023-02-22 19:27:37,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3568.4). Total num frames: 1228800. Throughput: 0: 871.3. Samples: 307976. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:27:37,724][00804] Avg episode reward: [(0, '5.900')] +[2023-02-22 19:27:42,718][00804] Fps is (10 sec: 2868.4, 60 sec: 3618.1, 300 sec: 3568.7). Total num frames: 1245184. Throughput: 0: 871.1. Samples: 310118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:27:42,720][00804] Avg episode reward: [(0, '5.726')] +[2023-02-22 19:27:47,469][11055] Updated weights for policy 0, policy_version 310 (0.0015) +[2023-02-22 19:27:47,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1269760. Throughput: 0: 924.7. Samples: 316608. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:27:47,720][00804] Avg episode reward: [(0, '6.345')] +[2023-02-22 19:27:47,728][11041] Saving new best policy, reward=6.345! +[2023-02-22 19:27:52,718][00804] Fps is (10 sec: 4505.7, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 1290240. Throughput: 0: 922.1. Samples: 322658. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:27:52,720][00804] Avg episode reward: [(0, '6.413')] +[2023-02-22 19:27:52,732][11041] Saving new best policy, reward=6.413! +[2023-02-22 19:27:57,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3582.4). Total num frames: 1302528. Throughput: 0: 894.2. Samples: 324724. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:27:57,721][00804] Avg episode reward: [(0, '6.560')] +[2023-02-22 19:27:57,723][11041] Saving new best policy, reward=6.560! +[2023-02-22 19:28:00,060][11055] Updated weights for policy 0, policy_version 320 (0.0014) +[2023-02-22 19:28:02,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3582.3). Total num frames: 1318912. Throughput: 0: 890.7. Samples: 329418. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:28:02,720][00804] Avg episode reward: [(0, '6.468')] +[2023-02-22 19:28:07,718][00804] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1343488. Throughput: 0: 940.5. Samples: 336186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:07,721][00804] Avg episode reward: [(0, '7.199')] +[2023-02-22 19:28:07,724][11041] Saving new best policy, reward=7.199! +[2023-02-22 19:28:09,184][11055] Updated weights for policy 0, policy_version 330 (0.0021) +[2023-02-22 19:28:12,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.5, 300 sec: 3596.1). Total num frames: 1359872. Throughput: 0: 938.7. Samples: 339428. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:28:12,720][00804] Avg episode reward: [(0, '7.439')] +[2023-02-22 19:28:12,729][11041] Saving new best policy, reward=7.439! +[2023-02-22 19:28:17,720][00804] Fps is (10 sec: 3276.1, 60 sec: 3618.0, 300 sec: 3582.3). Total num frames: 1376256. Throughput: 0: 889.9. Samples: 343762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:17,723][00804] Avg episode reward: [(0, '7.509')] +[2023-02-22 19:28:17,728][11041] Saving new best policy, reward=7.509! +[2023-02-22 19:28:21,730][11055] Updated weights for policy 0, policy_version 340 (0.0022) +[2023-02-22 19:28:22,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3610.1). Total num frames: 1396736. Throughput: 0: 921.2. Samples: 349430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:28:22,725][00804] Avg episode reward: [(0, '7.434')] +[2023-02-22 19:28:27,718][00804] Fps is (10 sec: 4097.0, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 1417216. Throughput: 0: 950.5. Samples: 352892. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:27,721][00804] Avg episode reward: [(0, '7.914')] +[2023-02-22 19:28:27,760][11041] Saving new best policy, reward=7.914! +[2023-02-22 19:28:31,204][11055] Updated weights for policy 0, policy_version 350 (0.0014) +[2023-02-22 19:28:32,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3610.0). Total num frames: 1437696. Throughput: 0: 943.1. Samples: 359046. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:28:32,725][00804] Avg episode reward: [(0, '7.964')] +[2023-02-22 19:28:32,739][11041] Saving new best policy, reward=7.964! +[2023-02-22 19:28:37,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 1449984. Throughput: 0: 906.8. Samples: 363464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:28:37,725][00804] Avg episode reward: [(0, '8.360')] +[2023-02-22 19:28:37,727][11041] Saving new best policy, reward=8.360! +[2023-02-22 19:28:42,483][11055] Updated weights for policy 0, policy_version 360 (0.0019) +[2023-02-22 19:28:42,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3624.0). Total num frames: 1474560. Throughput: 0: 927.0. Samples: 366438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:42,720][00804] Avg episode reward: [(0, '8.779')] +[2023-02-22 19:28:42,733][11041] Saving new best policy, reward=8.779! +[2023-02-22 19:28:47,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3623.9). Total num frames: 1495040. Throughput: 0: 975.6. Samples: 373318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:47,721][00804] Avg episode reward: [(0, '10.356')] +[2023-02-22 19:28:47,724][11041] Saving new best policy, reward=10.356! +[2023-02-22 19:28:52,718][00804] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1511424. Throughput: 0: 943.0. Samples: 378620. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:28:52,725][00804] Avg episode reward: [(0, '10.666')] +[2023-02-22 19:28:52,736][11041] Saving new best policy, reward=10.666! +[2023-02-22 19:28:53,829][11055] Updated weights for policy 0, policy_version 370 (0.0011) +[2023-02-22 19:28:57,720][00804] Fps is (10 sec: 2866.7, 60 sec: 3686.3, 300 sec: 3596.1). Total num frames: 1523712. Throughput: 0: 909.4. Samples: 380352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:28:57,726][00804] Avg episode reward: [(0, '11.593')] +[2023-02-22 19:28:57,729][11041] Saving new best policy, reward=11.593! +[2023-02-22 19:29:02,720][00804] Fps is (10 sec: 2457.1, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 1536000. Throughput: 0: 887.9. Samples: 383718. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:29:02,725][00804] Avg episode reward: [(0, '11.584')] +[2023-02-22 19:29:07,592][11055] Updated weights for policy 0, policy_version 380 (0.0012) +[2023-02-22 19:29:07,718][00804] Fps is (10 sec: 3277.4, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 1556480. Throughput: 0: 887.8. Samples: 389380. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:29:07,721][00804] Avg episode reward: [(0, '11.088')] +[2023-02-22 19:29:12,720][00804] Fps is (10 sec: 4095.9, 60 sec: 3618.0, 300 sec: 3582.2). Total num frames: 1576960. Throughput: 0: 886.3. Samples: 392778. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:29:12,727][00804] Avg episode reward: [(0, '10.786')] +[2023-02-22 19:29:12,742][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000385_1576960.pth... +[2023-02-22 19:29:12,883][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth +[2023-02-22 19:29:17,719][00804] Fps is (10 sec: 3276.4, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 1589248. Throughput: 0: 853.9. Samples: 397474. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:29:17,726][00804] Avg episode reward: [(0, '10.547')] +[2023-02-22 19:29:19,603][11055] Updated weights for policy 0, policy_version 390 (0.0021) +[2023-02-22 19:29:22,718][00804] Fps is (10 sec: 3277.6, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 1609728. Throughput: 0: 866.7. Samples: 402466. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:29:22,721][00804] Avg episode reward: [(0, '10.128')] +[2023-02-22 19:29:27,718][00804] Fps is (10 sec: 4096.5, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 1630208. Throughput: 0: 877.3. Samples: 405918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:29:27,726][00804] Avg episode reward: [(0, '10.701')] +[2023-02-22 19:29:29,034][11055] Updated weights for policy 0, policy_version 400 (0.0019) +[2023-02-22 19:29:32,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 1650688. Throughput: 0: 868.4. Samples: 412394. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:29:32,720][00804] Avg episode reward: [(0, '10.413')] +[2023-02-22 19:29:37,725][00804] Fps is (10 sec: 3274.4, 60 sec: 3549.4, 300 sec: 3623.8). Total num frames: 1662976. Throughput: 0: 847.0. Samples: 416742. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:29:37,729][00804] Avg episode reward: [(0, '10.769')] +[2023-02-22 19:29:41,544][11055] Updated weights for policy 0, policy_version 410 (0.0025) +[2023-02-22 19:29:42,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1683456. Throughput: 0: 859.3. Samples: 419020. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:29:42,726][00804] Avg episode reward: [(0, '12.010')] +[2023-02-22 19:29:42,735][11041] Saving new best policy, reward=12.010! +[2023-02-22 19:29:47,718][00804] Fps is (10 sec: 4099.0, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1703936. Throughput: 0: 932.4. Samples: 425676. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:29:47,720][00804] Avg episode reward: [(0, '13.293')] +[2023-02-22 19:29:47,727][11041] Saving new best policy, reward=13.293! +[2023-02-22 19:29:51,050][11055] Updated weights for policy 0, policy_version 420 (0.0012) +[2023-02-22 19:29:52,718][00804] Fps is (10 sec: 4095.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1724416. Throughput: 0: 933.5. Samples: 431388. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:29:52,721][00804] Avg episode reward: [(0, '13.583')] +[2023-02-22 19:29:52,733][11041] Saving new best policy, reward=13.583! +[2023-02-22 19:29:57,718][00804] Fps is (10 sec: 3276.6, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 1736704. Throughput: 0: 903.0. Samples: 433410. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:29:57,721][00804] Avg episode reward: [(0, '13.816')] +[2023-02-22 19:29:57,726][11041] Saving new best policy, reward=13.816! +[2023-02-22 19:30:02,718][00804] Fps is (10 sec: 3276.9, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 1757184. Throughput: 0: 907.0. Samples: 438288. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:30:02,725][00804] Avg episode reward: [(0, '13.814')] +[2023-02-22 19:30:03,693][11055] Updated weights for policy 0, policy_version 430 (0.0038) +[2023-02-22 19:30:07,718][00804] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1777664. Throughput: 0: 942.3. Samples: 444868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:30:07,720][00804] Avg episode reward: [(0, '14.664')] +[2023-02-22 19:30:07,725][11041] Saving new best policy, reward=14.664! +[2023-02-22 19:30:12,718][00804] Fps is (10 sec: 3686.5, 60 sec: 3618.3, 300 sec: 3623.9). Total num frames: 1794048. Throughput: 0: 930.6. Samples: 447794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:30:12,721][00804] Avg episode reward: [(0, '15.159')] +[2023-02-22 19:30:12,735][11041] Saving new best policy, reward=15.159! +[2023-02-22 19:30:15,161][11055] Updated weights for policy 0, policy_version 440 (0.0015) +[2023-02-22 19:30:17,721][00804] Fps is (10 sec: 2866.3, 60 sec: 3618.0, 300 sec: 3623.9). Total num frames: 1806336. Throughput: 0: 876.5. Samples: 451840. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:30:17,724][00804] Avg episode reward: [(0, '15.761')] +[2023-02-22 19:30:17,728][11041] Saving new best policy, reward=15.761! +[2023-02-22 19:30:22,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1826816. Throughput: 0: 904.3. Samples: 457428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:30:22,720][00804] Avg episode reward: [(0, '16.319')] +[2023-02-22 19:30:22,733][11041] Saving new best policy, reward=16.319! +[2023-02-22 19:30:25,746][11055] Updated weights for policy 0, policy_version 450 (0.0025) +[2023-02-22 19:30:27,718][00804] Fps is (10 sec: 4507.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 1851392. Throughput: 0: 926.0. Samples: 460690. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:30:27,721][00804] Avg episode reward: [(0, '16.021')] +[2023-02-22 19:30:32,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 1863680. Throughput: 0: 902.9. Samples: 466308. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:30:32,725][00804] Avg episode reward: [(0, '15.107')] +[2023-02-22 19:30:37,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.6, 300 sec: 3623.9). Total num frames: 1880064. Throughput: 0: 865.9. Samples: 470354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:30:37,723][00804] Avg episode reward: [(0, '14.583')] +[2023-02-22 19:30:38,424][11055] Updated weights for policy 0, policy_version 460 (0.0040) +[2023-02-22 19:30:42,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1900544. Throughput: 0: 890.3. Samples: 473474. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:30:42,720][00804] Avg episode reward: [(0, '14.217')] +[2023-02-22 19:30:47,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1921024. Throughput: 0: 929.0. Samples: 480094. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:30:47,723][00804] Avg episode reward: [(0, '15.128')] +[2023-02-22 19:30:47,913][11055] Updated weights for policy 0, policy_version 470 (0.0023) +[2023-02-22 19:30:52,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 1937408. Throughput: 0: 888.2. Samples: 484836. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:30:52,724][00804] Avg episode reward: [(0, '15.161')] +[2023-02-22 19:30:57,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 1953792. Throughput: 0: 868.2. Samples: 486862. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:30:57,721][00804] Avg episode reward: [(0, '15.737')] +[2023-02-22 19:31:00,566][11055] Updated weights for policy 0, policy_version 480 (0.0027) +[2023-02-22 19:31:02,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1974272. Throughput: 0: 912.1. Samples: 492880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-02-22 19:31:02,725][00804] Avg episode reward: [(0, '16.568')] +[2023-02-22 19:31:02,735][11041] Saving new best policy, reward=16.568! +[2023-02-22 19:31:07,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 1994752. Throughput: 0: 927.5. Samples: 499164. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:31:07,722][00804] Avg episode reward: [(0, '17.030')] +[2023-02-22 19:31:07,727][11041] Saving new best policy, reward=17.030! +[2023-02-22 19:31:11,858][11055] Updated weights for policy 0, policy_version 490 (0.0014) +[2023-02-22 19:31:12,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 2007040. Throughput: 0: 899.9. Samples: 501186. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:31:12,724][00804] Avg episode reward: [(0, '17.010')] +[2023-02-22 19:31:12,736][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth... +[2023-02-22 19:31:12,870][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000279_1142784.pth +[2023-02-22 19:31:17,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.3, 300 sec: 3623.9). Total num frames: 2023424. Throughput: 0: 869.9. Samples: 505452. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:31:17,721][00804] Avg episode reward: [(0, '16.790')] +[2023-02-22 19:31:22,548][11055] Updated weights for policy 0, policy_version 500 (0.0024) +[2023-02-22 19:31:22,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2048000. Throughput: 0: 929.5. Samples: 512182. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:31:22,720][00804] Avg episode reward: [(0, '16.067')] +[2023-02-22 19:31:27,718][00804] Fps is (10 sec: 4505.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2068480. Throughput: 0: 933.5. Samples: 515480. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:31:27,726][00804] Avg episode reward: [(0, '15.065')] +[2023-02-22 19:31:32,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3610.1). Total num frames: 2080768. Throughput: 0: 887.5. Samples: 520032. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:31:32,726][00804] Avg episode reward: [(0, '13.873')] +[2023-02-22 19:31:35,158][11055] Updated weights for policy 0, policy_version 510 (0.0013) +[2023-02-22 19:31:37,718][00804] Fps is (10 sec: 2867.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2097152. Throughput: 0: 892.4. Samples: 524994. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:31:37,726][00804] Avg episode reward: [(0, '13.726')] +[2023-02-22 19:31:42,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2121728. Throughput: 0: 923.2. Samples: 528406. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:31:42,720][00804] Avg episode reward: [(0, '14.147')] +[2023-02-22 19:31:44,628][11055] Updated weights for policy 0, policy_version 520 (0.0015) +[2023-02-22 19:31:47,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2138112. Throughput: 0: 925.8. Samples: 534540. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:31:47,719][00804] Avg episode reward: [(0, '15.159')] +[2023-02-22 19:31:52,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 2150400. Throughput: 0: 879.4. Samples: 538736. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:31:52,721][00804] Avg episode reward: [(0, '16.804')] +[2023-02-22 19:31:57,172][11055] Updated weights for policy 0, policy_version 530 (0.0031) +[2023-02-22 19:31:57,719][00804] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2170880. Throughput: 0: 886.4. Samples: 541074. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:31:57,722][00804] Avg episode reward: [(0, '17.633')] +[2023-02-22 19:31:57,728][11041] Saving new best policy, reward=17.633! +[2023-02-22 19:32:02,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2191360. Throughput: 0: 934.7. Samples: 547514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:32:02,724][00804] Avg episode reward: [(0, '18.108')] +[2023-02-22 19:32:02,736][11041] Saving new best policy, reward=18.108! +[2023-02-22 19:32:07,718][00804] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3610.1). Total num frames: 2207744. Throughput: 0: 904.8. Samples: 552900. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:32:07,722][00804] Avg episode reward: [(0, '18.383')] +[2023-02-22 19:32:07,728][11041] Saving new best policy, reward=18.383! +[2023-02-22 19:32:08,185][11055] Updated weights for policy 0, policy_version 540 (0.0021) +[2023-02-22 19:32:12,719][00804] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2224128. Throughput: 0: 877.0. Samples: 554944. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:32:12,727][00804] Avg episode reward: [(0, '17.231')] +[2023-02-22 19:32:17,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2240512. Throughput: 0: 889.4. Samples: 560054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:32:17,721][00804] Avg episode reward: [(0, '15.837')] +[2023-02-22 19:32:19,671][11055] Updated weights for policy 0, policy_version 550 (0.0017) +[2023-02-22 19:32:22,718][00804] Fps is (10 sec: 4096.4, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2265088. Throughput: 0: 925.5. Samples: 566642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:32:22,720][00804] Avg episode reward: [(0, '15.372')] +[2023-02-22 19:32:27,720][00804] Fps is (10 sec: 4095.0, 60 sec: 3549.8, 300 sec: 3610.1). Total num frames: 2281472. Throughput: 0: 910.7. Samples: 569390. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:32:27,723][00804] Avg episode reward: [(0, '14.448')] +[2023-02-22 19:32:32,117][11055] Updated weights for policy 0, policy_version 560 (0.0027) +[2023-02-22 19:32:32,718][00804] Fps is (10 sec: 2867.1, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 2293760. Throughput: 0: 864.0. Samples: 573422. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:32:32,728][00804] Avg episode reward: [(0, '14.982')] +[2023-02-22 19:32:37,718][00804] Fps is (10 sec: 3277.6, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2314240. Throughput: 0: 897.7. Samples: 579134. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:32:37,726][00804] Avg episode reward: [(0, '14.537')] +[2023-02-22 19:32:41,798][11055] Updated weights for policy 0, policy_version 570 (0.0015) +[2023-02-22 19:32:42,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 2334720. Throughput: 0: 919.0. Samples: 582430. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:32:42,720][00804] Avg episode reward: [(0, '13.628')] +[2023-02-22 19:32:47,718][00804] Fps is (10 sec: 3686.2, 60 sec: 3549.8, 300 sec: 3596.1). Total num frames: 2351104. Throughput: 0: 893.8. Samples: 587736. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:32:47,723][00804] Avg episode reward: [(0, '13.846')] +[2023-02-22 19:32:52,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2363392. Throughput: 0: 869.7. Samples: 592036. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:32:52,724][00804] Avg episode reward: [(0, '13.971')] +[2023-02-22 19:32:54,566][11055] Updated weights for policy 0, policy_version 580 (0.0012) +[2023-02-22 19:32:57,718][00804] Fps is (10 sec: 3686.6, 60 sec: 3618.2, 300 sec: 3623.9). Total num frames: 2387968. Throughput: 0: 893.8. Samples: 595166. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:32:57,721][00804] Avg episode reward: [(0, '14.018')] +[2023-02-22 19:33:02,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 2408448. Throughput: 0: 923.6. Samples: 601618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:33:02,720][00804] Avg episode reward: [(0, '14.242')] +[2023-02-22 19:33:04,876][11055] Updated weights for policy 0, policy_version 590 (0.0014) +[2023-02-22 19:33:07,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2420736. Throughput: 0: 878.4. Samples: 606170. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:33:07,721][00804] Avg episode reward: [(0, '14.564')] +[2023-02-22 19:33:12,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 2437120. Throughput: 0: 863.3. Samples: 608238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:33:12,725][00804] Avg episode reward: [(0, '14.844')] +[2023-02-22 19:33:12,739][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth... +[2023-02-22 19:33:12,843][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000385_1576960.pth +[2023-02-22 19:33:17,719][00804] Fps is (10 sec: 3276.4, 60 sec: 3549.8, 300 sec: 3582.2). Total num frames: 2453504. Throughput: 0: 889.4. Samples: 613448. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:33:17,724][00804] Avg episode reward: [(0, '15.366')] +[2023-02-22 19:33:18,316][11055] Updated weights for policy 0, policy_version 600 (0.0024) +[2023-02-22 19:33:22,719][00804] Fps is (10 sec: 2866.9, 60 sec: 3345.0, 300 sec: 3554.5). Total num frames: 2465792. Throughput: 0: 850.7. Samples: 617416. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:33:22,723][00804] Avg episode reward: [(0, '16.173')] +[2023-02-22 19:33:27,718][00804] Fps is (10 sec: 2457.9, 60 sec: 3276.9, 300 sec: 3526.7). Total num frames: 2478080. Throughput: 0: 814.8. Samples: 619094. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:33:27,720][00804] Avg episode reward: [(0, '16.870')] +[2023-02-22 19:33:32,718][00804] Fps is (10 sec: 2867.5, 60 sec: 3345.1, 300 sec: 3540.6). Total num frames: 2494464. Throughput: 0: 786.1. Samples: 623110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:33:32,724][00804] Avg episode reward: [(0, '18.095')] +[2023-02-22 19:33:33,424][11055] Updated weights for policy 0, policy_version 610 (0.0022) +[2023-02-22 19:33:37,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3526.7). Total num frames: 2514944. Throughput: 0: 829.5. Samples: 629364. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:33:37,725][00804] Avg episode reward: [(0, '19.023')] +[2023-02-22 19:33:37,732][11041] Saving new best policy, reward=19.023! +[2023-02-22 19:33:42,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3526.7). Total num frames: 2535424. Throughput: 0: 832.0. Samples: 632604. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:33:42,721][00804] Avg episode reward: [(0, '19.522')] +[2023-02-22 19:33:42,736][11041] Saving new best policy, reward=19.522! +[2023-02-22 19:33:43,404][11055] Updated weights for policy 0, policy_version 620 (0.0011) +[2023-02-22 19:33:47,720][00804] Fps is (10 sec: 3276.1, 60 sec: 3276.7, 300 sec: 3512.8). Total num frames: 2547712. Throughput: 0: 793.1. Samples: 637310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:33:47,727][00804] Avg episode reward: [(0, '19.712')] +[2023-02-22 19:33:47,732][11041] Saving new best policy, reward=19.712! +[2023-02-22 19:33:52,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3526.7). Total num frames: 2564096. Throughput: 0: 791.2. Samples: 641772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:33:52,724][00804] Avg episode reward: [(0, '19.523')] +[2023-02-22 19:33:55,866][11055] Updated weights for policy 0, policy_version 630 (0.0014) +[2023-02-22 19:33:57,718][00804] Fps is (10 sec: 3687.2, 60 sec: 3276.8, 300 sec: 3554.5). Total num frames: 2584576. Throughput: 0: 815.1. Samples: 644918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:33:57,722][00804] Avg episode reward: [(0, '19.646')] +[2023-02-22 19:34:02,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3276.8, 300 sec: 3554.5). Total num frames: 2605056. Throughput: 0: 841.0. Samples: 651294. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:34:02,720][00804] Avg episode reward: [(0, '19.420')] +[2023-02-22 19:34:07,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3526.8). Total num frames: 2617344. Throughput: 0: 840.9. Samples: 655254. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:34:07,724][00804] Avg episode reward: [(0, '20.185')] +[2023-02-22 19:34:07,726][11041] Saving new best policy, reward=20.185! +[2023-02-22 19:34:08,300][11055] Updated weights for policy 0, policy_version 640 (0.0025) +[2023-02-22 19:34:12,719][00804] Fps is (10 sec: 2867.0, 60 sec: 3276.8, 300 sec: 3540.6). Total num frames: 2633728. Throughput: 0: 846.1. Samples: 657170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:34:12,731][00804] Avg episode reward: [(0, '20.738')] +[2023-02-22 19:34:12,771][11041] Saving new best policy, reward=20.738! +[2023-02-22 19:34:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3413.4, 300 sec: 3554.5). Total num frames: 2658304. Throughput: 0: 900.1. Samples: 663616. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:34:17,726][00804] Avg episode reward: [(0, '20.954')] +[2023-02-22 19:34:17,729][11041] Saving new best policy, reward=20.954! +[2023-02-22 19:34:18,744][11055] Updated weights for policy 0, policy_version 650 (0.0031) +[2023-02-22 19:34:22,718][00804] Fps is (10 sec: 4096.3, 60 sec: 3481.7, 300 sec: 3540.6). Total num frames: 2674688. Throughput: 0: 890.2. Samples: 669424. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:34:22,724][00804] Avg episode reward: [(0, '19.897')] +[2023-02-22 19:34:27,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 2686976. Throughput: 0: 864.9. Samples: 671526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:34:27,720][00804] Avg episode reward: [(0, '18.935')] +[2023-02-22 19:34:31,238][11055] Updated weights for policy 0, policy_version 660 (0.0013) +[2023-02-22 19:34:32,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3540.7). Total num frames: 2707456. Throughput: 0: 867.8. Samples: 676360. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:34:32,726][00804] Avg episode reward: [(0, '19.296')] +[2023-02-22 19:34:37,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 2732032. Throughput: 0: 918.0. Samples: 683084. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:34:37,726][00804] Avg episode reward: [(0, '19.664')] +[2023-02-22 19:34:40,678][11055] Updated weights for policy 0, policy_version 670 (0.0012) +[2023-02-22 19:34:42,722][00804] Fps is (10 sec: 4094.4, 60 sec: 3549.6, 300 sec: 3540.6). Total num frames: 2748416. Throughput: 0: 917.5. Samples: 686210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:34:42,729][00804] Avg episode reward: [(0, '19.804')] +[2023-02-22 19:34:47,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3512.8). Total num frames: 2760704. Throughput: 0: 866.6. Samples: 690290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:34:47,720][00804] Avg episode reward: [(0, '20.264')] +[2023-02-22 19:34:52,718][00804] Fps is (10 sec: 3278.1, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 2781184. Throughput: 0: 900.4. Samples: 695774. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:34:52,726][00804] Avg episode reward: [(0, '20.557')] +[2023-02-22 19:34:53,235][11055] Updated weights for policy 0, policy_version 680 (0.0031) +[2023-02-22 19:34:57,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 2801664. Throughput: 0: 930.7. Samples: 699050. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:34:57,720][00804] Avg episode reward: [(0, '20.915')] +[2023-02-22 19:35:02,719][00804] Fps is (10 sec: 3686.1, 60 sec: 3549.8, 300 sec: 3526.7). Total num frames: 2818048. Throughput: 0: 913.7. Samples: 704732. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:35:02,732][00804] Avg episode reward: [(0, '19.946')] +[2023-02-22 19:35:04,778][11055] Updated weights for policy 0, policy_version 690 (0.0014) +[2023-02-22 19:35:07,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2834432. Throughput: 0: 875.1. Samples: 708802. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:35:07,731][00804] Avg episode reward: [(0, '19.905')] +[2023-02-22 19:35:12,718][00804] Fps is (10 sec: 3686.7, 60 sec: 3686.4, 300 sec: 3554.5). Total num frames: 2854912. Throughput: 0: 891.6. Samples: 711648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:35:12,721][00804] Avg episode reward: [(0, '20.442')] +[2023-02-22 19:35:12,739][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000697_2854912.pth... +[2023-02-22 19:35:12,864][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000490_2007040.pth +[2023-02-22 19:35:15,486][11055] Updated weights for policy 0, policy_version 700 (0.0026) +[2023-02-22 19:35:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 2875392. Throughput: 0: 930.2. Samples: 718220. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:35:17,721][00804] Avg episode reward: [(0, '21.393')] +[2023-02-22 19:35:17,729][11041] Saving new best policy, reward=21.393! +[2023-02-22 19:35:22,718][00804] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2891776. Throughput: 0: 887.5. Samples: 723024. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:35:22,731][00804] Avg episode reward: [(0, '20.745')] +[2023-02-22 19:35:27,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2904064. Throughput: 0: 863.4. Samples: 725060. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:35:27,724][00804] Avg episode reward: [(0, '20.015')] +[2023-02-22 19:35:28,478][11055] Updated weights for policy 0, policy_version 710 (0.0016) +[2023-02-22 19:35:32,718][00804] Fps is (10 sec: 3277.0, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 2924544. Throughput: 0: 897.9. Samples: 730694. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:35:32,723][00804] Avg episode reward: [(0, '20.294')] +[2023-02-22 19:35:37,719][00804] Fps is (10 sec: 4095.4, 60 sec: 3549.8, 300 sec: 3540.6). Total num frames: 2945024. Throughput: 0: 924.3. Samples: 737370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:35:37,724][00804] Avg episode reward: [(0, '20.140')] +[2023-02-22 19:35:37,760][11055] Updated weights for policy 0, policy_version 720 (0.0015) +[2023-02-22 19:35:42,721][00804] Fps is (10 sec: 3685.2, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2961408. Throughput: 0: 899.4. Samples: 739526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:35:42,723][00804] Avg episode reward: [(0, '21.348')] +[2023-02-22 19:35:47,718][00804] Fps is (10 sec: 3277.3, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2977792. Throughput: 0: 866.8. Samples: 743736. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:35:47,730][00804] Avg episode reward: [(0, '20.515')] +[2023-02-22 19:35:50,412][11055] Updated weights for policy 0, policy_version 730 (0.0024) +[2023-02-22 19:35:52,718][00804] Fps is (10 sec: 3687.5, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 2998272. Throughput: 0: 917.7. Samples: 750098. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:35:52,726][00804] Avg episode reward: [(0, '21.592')] +[2023-02-22 19:35:52,743][11041] Saving new best policy, reward=21.592! +[2023-02-22 19:35:57,724][00804] Fps is (10 sec: 4093.6, 60 sec: 3617.8, 300 sec: 3540.5). Total num frames: 3018752. Throughput: 0: 922.0. Samples: 753142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:35:57,729][00804] Avg episode reward: [(0, '22.688')] +[2023-02-22 19:35:57,735][11041] Saving new best policy, reward=22.688! +[2023-02-22 19:36:02,148][11055] Updated weights for policy 0, policy_version 740 (0.0012) +[2023-02-22 19:36:02,718][00804] Fps is (10 sec: 3276.9, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3031040. Throughput: 0: 875.7. Samples: 757628. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:36:02,722][00804] Avg episode reward: [(0, '21.838')] +[2023-02-22 19:36:07,718][00804] Fps is (10 sec: 2868.9, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3047424. Throughput: 0: 870.8. Samples: 762208. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:36:07,721][00804] Avg episode reward: [(0, '20.676')] +[2023-02-22 19:36:12,718][00804] Fps is (10 sec: 3686.3, 60 sec: 3549.8, 300 sec: 3540.6). Total num frames: 3067904. Throughput: 0: 899.0. Samples: 765516. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:36:12,721][00804] Avg episode reward: [(0, '19.683')] +[2023-02-22 19:36:12,982][11055] Updated weights for policy 0, policy_version 750 (0.0045) +[2023-02-22 19:36:17,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3088384. Throughput: 0: 919.1. Samples: 772054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:36:17,721][00804] Avg episode reward: [(0, '19.689')] +[2023-02-22 19:36:22,719][00804] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3498.9). Total num frames: 3100672. Throughput: 0: 861.7. Samples: 776146. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:36:22,736][00804] Avg episode reward: [(0, '18.274')] +[2023-02-22 19:36:25,774][11055] Updated weights for policy 0, policy_version 760 (0.0012) +[2023-02-22 19:36:27,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3121152. Throughput: 0: 862.6. Samples: 778342. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:36:27,725][00804] Avg episode reward: [(0, '18.567')] +[2023-02-22 19:36:32,718][00804] Fps is (10 sec: 4096.4, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3141632. Throughput: 0: 912.9. Samples: 784816. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:36:32,721][00804] Avg episode reward: [(0, '18.209')] +[2023-02-22 19:36:35,540][11055] Updated weights for policy 0, policy_version 770 (0.0013) +[2023-02-22 19:36:37,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3158016. Throughput: 0: 892.8. Samples: 790272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:36:37,723][00804] Avg episode reward: [(0, '20.174')] +[2023-02-22 19:36:42,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3550.1, 300 sec: 3512.8). Total num frames: 3174400. Throughput: 0: 871.8. Samples: 792368. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:36:42,721][00804] Avg episode reward: [(0, '21.874')] +[2023-02-22 19:36:47,718][00804] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3526.7). Total num frames: 3190784. Throughput: 0: 882.5. Samples: 797342. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:36:47,728][00804] Avg episode reward: [(0, '21.858')] +[2023-02-22 19:36:47,977][11055] Updated weights for policy 0, policy_version 780 (0.0022) +[2023-02-22 19:36:52,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3540.6). Total num frames: 3215360. Throughput: 0: 931.3. Samples: 804116. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:36:52,728][00804] Avg episode reward: [(0, '24.463')] +[2023-02-22 19:36:52,740][11041] Saving new best policy, reward=24.463! +[2023-02-22 19:36:57,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3550.2, 300 sec: 3526.7). Total num frames: 3231744. Throughput: 0: 922.5. Samples: 807028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:36:57,727][00804] Avg episode reward: [(0, '25.598')] +[2023-02-22 19:36:57,733][11041] Saving new best policy, reward=25.598! +[2023-02-22 19:36:58,838][11055] Updated weights for policy 0, policy_version 790 (0.0012) +[2023-02-22 19:37:02,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3244032. Throughput: 0: 868.6. Samples: 811142. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:37:02,725][00804] Avg episode reward: [(0, '26.121')] +[2023-02-22 19:37:02,736][11041] Saving new best policy, reward=26.121! +[2023-02-22 19:37:07,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3264512. Throughput: 0: 900.0. Samples: 816644. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:37:07,726][00804] Avg episode reward: [(0, '26.207')] +[2023-02-22 19:37:07,730][11041] Saving new best policy, reward=26.207! +[2023-02-22 19:37:10,167][11055] Updated weights for policy 0, policy_version 800 (0.0016) +[2023-02-22 19:37:12,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3618.2, 300 sec: 3540.6). Total num frames: 3284992. Throughput: 0: 920.5. Samples: 819764. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:37:12,721][00804] Avg episode reward: [(0, '24.942')] +[2023-02-22 19:37:12,728][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000802_3284992.pth... +[2023-02-22 19:37:12,839][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000595_2437120.pth +[2023-02-22 19:37:17,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3301376. Throughput: 0: 898.3. Samples: 825240. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:37:17,720][00804] Avg episode reward: [(0, '25.108')] +[2023-02-22 19:37:22,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3499.0). Total num frames: 3313664. Throughput: 0: 871.2. Samples: 829478. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:37:22,723][00804] Avg episode reward: [(0, '25.359')] +[2023-02-22 19:37:22,941][11055] Updated weights for policy 0, policy_version 810 (0.0018) +[2023-02-22 19:37:27,720][00804] Fps is (10 sec: 3685.5, 60 sec: 3618.0, 300 sec: 3540.6). Total num frames: 3338240. Throughput: 0: 891.6. Samples: 832490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:37:27,726][00804] Avg episode reward: [(0, '25.081')] +[2023-02-22 19:37:32,233][11055] Updated weights for policy 0, policy_version 820 (0.0011) +[2023-02-22 19:37:32,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3540.6). Total num frames: 3358720. Throughput: 0: 928.5. Samples: 839124. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:37:32,723][00804] Avg episode reward: [(0, '24.504')] +[2023-02-22 19:37:37,718][00804] Fps is (10 sec: 3277.5, 60 sec: 3549.8, 300 sec: 3512.8). Total num frames: 3371008. Throughput: 0: 881.2. Samples: 843772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:37:37,723][00804] Avg episode reward: [(0, '24.388')] +[2023-02-22 19:37:42,718][00804] Fps is (10 sec: 2457.5, 60 sec: 3481.6, 300 sec: 3499.0). Total num frames: 3383296. Throughput: 0: 852.0. Samples: 845368. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:37:42,725][00804] Avg episode reward: [(0, '24.836')] +[2023-02-22 19:37:47,718][00804] Fps is (10 sec: 2457.7, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 3395584. Throughput: 0: 833.2. Samples: 848638. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:37:47,724][00804] Avg episode reward: [(0, '25.277')] +[2023-02-22 19:37:48,421][11055] Updated weights for policy 0, policy_version 830 (0.0042) +[2023-02-22 19:37:52,718][00804] Fps is (10 sec: 3276.9, 60 sec: 3345.1, 300 sec: 3485.1). Total num frames: 3416064. Throughput: 0: 846.2. Samples: 854722. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:37:52,721][00804] Avg episode reward: [(0, '23.068')] +[2023-02-22 19:37:57,721][00804] Fps is (10 sec: 4095.2, 60 sec: 3413.2, 300 sec: 3485.0). Total num frames: 3436544. Throughput: 0: 849.3. Samples: 857982. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:37:57,723][00804] Avg episode reward: [(0, '23.583')] +[2023-02-22 19:37:59,044][11055] Updated weights for policy 0, policy_version 840 (0.0025) +[2023-02-22 19:38:02,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 3448832. Throughput: 0: 823.4. Samples: 862294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:38:02,722][00804] Avg episode reward: [(0, '23.858')] +[2023-02-22 19:38:07,718][00804] Fps is (10 sec: 3277.5, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 3469312. Throughput: 0: 841.3. Samples: 867336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:38:07,725][00804] Avg episode reward: [(0, '24.572')] +[2023-02-22 19:38:10,666][11055] Updated weights for policy 0, policy_version 850 (0.0015) +[2023-02-22 19:38:12,718][00804] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3512.9). Total num frames: 3489792. Throughput: 0: 847.6. Samples: 870630. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:38:12,721][00804] Avg episode reward: [(0, '24.184')] +[2023-02-22 19:38:17,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3506176. Throughput: 0: 835.7. Samples: 876732. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:38:17,725][00804] Avg episode reward: [(0, '23.544')] +[2023-02-22 19:38:22,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3518464. Throughput: 0: 822.0. Samples: 880762. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:38:22,728][00804] Avg episode reward: [(0, '23.787')] +[2023-02-22 19:38:22,968][11055] Updated weights for policy 0, policy_version 860 (0.0012) +[2023-02-22 19:38:27,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3345.2, 300 sec: 3540.6). Total num frames: 3538944. Throughput: 0: 844.8. Samples: 883384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:38:27,727][00804] Avg episode reward: [(0, '23.567')] +[2023-02-22 19:38:32,479][11055] Updated weights for policy 0, policy_version 870 (0.0020) +[2023-02-22 19:38:32,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3413.3, 300 sec: 3554.5). Total num frames: 3563520. Throughput: 0: 919.7. Samples: 890024. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-22 19:38:32,723][00804] Avg episode reward: [(0, '23.328')] +[2023-02-22 19:38:37,718][00804] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3579904. Throughput: 0: 902.4. Samples: 895332. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:38:37,722][00804] Avg episode reward: [(0, '22.489')] +[2023-02-22 19:38:42,718][00804] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 3592192. Throughput: 0: 877.2. Samples: 897454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:38:42,727][00804] Avg episode reward: [(0, '21.861')] +[2023-02-22 19:38:45,228][11055] Updated weights for policy 0, policy_version 880 (0.0023) +[2023-02-22 19:38:47,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 3612672. Throughput: 0: 901.9. Samples: 902880. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:38:47,726][00804] Avg episode reward: [(0, '22.385')] +[2023-02-22 19:38:52,718][00804] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3637248. Throughput: 0: 939.7. Samples: 909622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:38:52,726][00804] Avg episode reward: [(0, '23.322')] +[2023-02-22 19:38:54,915][11055] Updated weights for policy 0, policy_version 890 (0.0019) +[2023-02-22 19:38:57,718][00804] Fps is (10 sec: 4095.9, 60 sec: 3618.2, 300 sec: 3554.5). Total num frames: 3653632. Throughput: 0: 923.8. Samples: 912202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:38:57,722][00804] Avg episode reward: [(0, '23.527')] +[2023-02-22 19:39:02,720][00804] Fps is (10 sec: 2866.6, 60 sec: 3618.0, 300 sec: 3554.5). Total num frames: 3665920. Throughput: 0: 885.4. Samples: 916576. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:39:02,723][00804] Avg episode reward: [(0, '22.808')] +[2023-02-22 19:39:06,753][11055] Updated weights for policy 0, policy_version 900 (0.0025) +[2023-02-22 19:39:07,718][00804] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3582.3). Total num frames: 3690496. Throughput: 0: 929.5. Samples: 922588. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:39:07,720][00804] Avg episode reward: [(0, '23.872')] +[2023-02-22 19:39:12,718][00804] Fps is (10 sec: 4506.6, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3710976. Throughput: 0: 946.4. Samples: 925974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:39:12,726][00804] Avg episode reward: [(0, '24.689')] +[2023-02-22 19:39:12,739][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000906_3710976.pth... +[2023-02-22 19:39:12,852][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000697_2854912.pth +[2023-02-22 19:39:17,718][00804] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 3723264. Throughput: 0: 917.6. Samples: 931316. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:39:17,725][00804] Avg episode reward: [(0, '24.809')] +[2023-02-22 19:39:17,743][11055] Updated weights for policy 0, policy_version 910 (0.0013) +[2023-02-22 19:39:22,718][00804] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3739648. Throughput: 0: 892.9. Samples: 935514. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:39:22,720][00804] Avg episode reward: [(0, '24.071')] +[2023-02-22 19:39:27,720][00804] Fps is (10 sec: 4094.9, 60 sec: 3754.5, 300 sec: 3582.2). Total num frames: 3764224. Throughput: 0: 919.8. Samples: 938848. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:39:27,729][00804] Avg episode reward: [(0, '24.038')] +[2023-02-22 19:39:28,619][11055] Updated weights for policy 0, policy_version 920 (0.0015) +[2023-02-22 19:39:32,721][00804] Fps is (10 sec: 4504.1, 60 sec: 3686.2, 300 sec: 3568.3). Total num frames: 3784704. Throughput: 0: 944.1. Samples: 945368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:39:32,723][00804] Avg episode reward: [(0, '25.252')] +[2023-02-22 19:39:37,720][00804] Fps is (10 sec: 3276.9, 60 sec: 3618.0, 300 sec: 3554.5). Total num frames: 3796992. Throughput: 0: 896.8. Samples: 949978. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:39:37,726][00804] Avg episode reward: [(0, '24.801')] +[2023-02-22 19:39:41,551][11055] Updated weights for policy 0, policy_version 930 (0.0018) +[2023-02-22 19:39:42,718][00804] Fps is (10 sec: 2868.2, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3813376. Throughput: 0: 885.7. Samples: 952058. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:39:42,728][00804] Avg episode reward: [(0, '25.037')] +[2023-02-22 19:39:47,718][00804] Fps is (10 sec: 3687.3, 60 sec: 3686.4, 300 sec: 3568.4). Total num frames: 3833856. Throughput: 0: 922.3. Samples: 958076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:39:47,720][00804] Avg episode reward: [(0, '25.544')] +[2023-02-22 19:39:50,742][11055] Updated weights for policy 0, policy_version 940 (0.0017) +[2023-02-22 19:39:52,722][00804] Fps is (10 sec: 4094.5, 60 sec: 3617.9, 300 sec: 3568.3). Total num frames: 3854336. Throughput: 0: 930.7. Samples: 964472. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:39:52,724][00804] Avg episode reward: [(0, '25.286')] +[2023-02-22 19:39:57,718][00804] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3870720. Throughput: 0: 902.1. Samples: 966570. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-02-22 19:39:57,726][00804] Avg episode reward: [(0, '26.110')] +[2023-02-22 19:40:02,718][00804] Fps is (10 sec: 3277.9, 60 sec: 3686.5, 300 sec: 3568.4). Total num frames: 3887104. Throughput: 0: 878.7. Samples: 970856. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:40:02,721][00804] Avg episode reward: [(0, '25.651')] +[2023-02-22 19:40:03,696][11055] Updated weights for policy 0, policy_version 950 (0.0018) +[2023-02-22 19:40:07,718][00804] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3907584. Throughput: 0: 928.9. Samples: 977316. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-22 19:40:07,723][00804] Avg episode reward: [(0, '24.852')] +[2023-02-22 19:40:12,719][00804] Fps is (10 sec: 4095.8, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3928064. Throughput: 0: 928.9. Samples: 980648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-22 19:40:12,723][00804] Avg episode reward: [(0, '22.974')] +[2023-02-22 19:40:13,775][11055] Updated weights for policy 0, policy_version 960 (0.0011) +[2023-02-22 19:40:17,723][00804] Fps is (10 sec: 3275.0, 60 sec: 3617.8, 300 sec: 3554.4). Total num frames: 3940352. Throughput: 0: 884.1. Samples: 985154. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-22 19:40:17,730][00804] Avg episode reward: [(0, '21.882')] +[2023-02-22 19:40:22,718][00804] Fps is (10 sec: 2867.5, 60 sec: 3618.1, 300 sec: 3568.4). Total num frames: 3956736. Throughput: 0: 889.9. Samples: 990020. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-22 19:40:22,721][00804] Avg episode reward: [(0, '21.508')] +[2023-02-22 19:40:25,834][11055] Updated weights for policy 0, policy_version 970 (0.0034) +[2023-02-22 19:40:27,718][00804] Fps is (10 sec: 4098.2, 60 sec: 3618.3, 300 sec: 3582.3). Total num frames: 3981312. Throughput: 0: 915.2. Samples: 993244. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-22 19:40:27,721][00804] Avg episode reward: [(0, '20.654')] +[2023-02-22 19:40:32,720][00804] Fps is (10 sec: 4095.1, 60 sec: 3549.9, 300 sec: 3568.4). Total num frames: 3997696. Throughput: 0: 917.9. Samples: 999384. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-22 19:40:32,723][00804] Avg episode reward: [(0, '21.686')] +[2023-02-22 19:40:34,982][11041] Stopping Batcher_0... +[2023-02-22 19:40:34,983][11041] Loop batcher_evt_loop terminating... +[2023-02-22 19:40:34,984][00804] Component Batcher_0 stopped! +[2023-02-22 19:40:34,986][00804] Component RolloutWorker_w0 process died already! Don't wait for it. +[2023-02-22 19:40:34,995][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-22 19:40:35,062][11055] Weights refcount: 2 0 +[2023-02-22 19:40:35,065][11055] Stopping InferenceWorker_p0-w0... +[2023-02-22 19:40:35,066][00804] Component InferenceWorker_p0-w0 stopped! +[2023-02-22 19:40:35,078][00804] Component RolloutWorker_w1 stopped! +[2023-02-22 19:40:35,082][11057] Stopping RolloutWorker_w1... +[2023-02-22 19:40:35,082][11057] Loop rollout_proc1_evt_loop terminating... +[2023-02-22 19:40:35,093][00804] Component RolloutWorker_w5 stopped! +[2023-02-22 19:40:35,095][11061] Stopping RolloutWorker_w5... +[2023-02-22 19:40:35,065][11055] Loop inference_proc0-0_evt_loop terminating... +[2023-02-22 19:40:35,102][11061] Loop rollout_proc5_evt_loop terminating... +[2023-02-22 19:40:35,124][00804] Component RolloutWorker_w3 stopped! +[2023-02-22 19:40:35,127][11058] Stopping RolloutWorker_w3... +[2023-02-22 19:40:35,140][11060] Stopping RolloutWorker_w4... +[2023-02-22 19:40:35,140][00804] Component RolloutWorker_w4 stopped! +[2023-02-22 19:40:35,146][00804] Component RolloutWorker_w7 stopped! +[2023-02-22 19:40:35,150][11063] Stopping RolloutWorker_w7... +[2023-02-22 19:40:35,151][11063] Loop rollout_proc7_evt_loop terminating... +[2023-02-22 19:40:35,136][11058] Loop rollout_proc3_evt_loop terminating... +[2023-02-22 19:40:35,162][11060] Loop rollout_proc4_evt_loop terminating... +[2023-02-22 19:40:35,192][11041] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000802_3284992.pth +[2023-02-22 19:40:35,201][11041] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-22 19:40:35,227][00804] Component RolloutWorker_w2 stopped! +[2023-02-22 19:40:35,233][11059] Stopping RolloutWorker_w2... +[2023-02-22 19:40:35,233][11059] Loop rollout_proc2_evt_loop terminating... +[2023-02-22 19:40:35,239][00804] Component RolloutWorker_w6 stopped! +[2023-02-22 19:40:35,241][11062] Stopping RolloutWorker_w6... +[2023-02-22 19:40:35,249][11062] Loop rollout_proc6_evt_loop terminating... +[2023-02-22 19:40:35,435][00804] Component LearnerWorker_p0 stopped! +[2023-02-22 19:40:35,439][00804] Waiting for process learner_proc0 to stop... +[2023-02-22 19:40:35,445][11041] Stopping LearnerWorker_p0... +[2023-02-22 19:40:35,446][11041] Loop learner_proc0_evt_loop terminating... +[2023-02-22 19:40:37,695][00804] Waiting for process inference_proc0-0 to join... +[2023-02-22 19:40:38,526][00804] Waiting for process rollout_proc0 to join... +[2023-02-22 19:40:38,533][00804] Waiting for process rollout_proc1 to join... +[2023-02-22 19:40:38,783][00804] Waiting for process rollout_proc2 to join... +[2023-02-22 19:40:38,911][00804] Waiting for process rollout_proc3 to join... +[2023-02-22 19:40:38,913][00804] Waiting for process rollout_proc4 to join... +[2023-02-22 19:40:38,915][00804] Waiting for process rollout_proc5 to join... +[2023-02-22 19:40:38,916][00804] Waiting for process rollout_proc6 to join... +[2023-02-22 19:40:38,917][00804] Waiting for process rollout_proc7 to join... +[2023-02-22 19:40:38,920][00804] Batcher 0 profile tree view: +batching: 26.2346, releasing_batches: 0.0318 +[2023-02-22 19:40:38,922][00804] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0000 + wait_policy_total: 544.7672 +update_model: 8.1558 + weight_update: 0.0017 +one_step: 0.0169 + handle_policy_step: 535.7754 + deserialize: 15.6744, stack: 3.1573, obs_to_device_normalize: 119.9518, forward: 260.5496, send_messages: 25.1291 + prepare_outputs: 84.2802 + to_cpu: 52.2570 +[2023-02-22 19:40:38,923][00804] Learner 0 profile tree view: +misc: 0.0062, prepare_batch: 15.1086 +train: 74.6749 + epoch_init: 0.0159, minibatch_init: 0.0163, losses_postprocess: 0.5405, kl_divergence: 0.5935, after_optimizer: 32.6658 + calculate_losses: 26.1922 + losses_init: 0.0076, forward_head: 1.7194, bptt_initial: 17.2524, tail: 0.9984, advantages_returns: 0.3143, losses: 3.4254 + bptt: 2.1589 + bptt_forward_core: 2.0823 + update: 13.9871 + clip: 1.4154 +[2023-02-22 19:40:38,927][00804] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3476, enqueue_policy_requests: 146.1553, env_step: 855.0100, overhead: 23.1727, complete_rollouts: 8.0434 +save_policy_outputs: 21.3814 + split_output_tensors: 10.2768 +[2023-02-22 19:40:38,928][00804] Loop Runner_EvtLoop terminating... +[2023-02-22 19:40:38,930][00804] Runner profile tree view: +main_loop: 1160.8495 +[2023-02-22 19:40:38,933][00804] Collected {0: 4005888}, FPS: 3450.8 +[2023-02-22 19:40:39,101][00804] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-22 19:40:39,103][00804] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-22 19:40:39,106][00804] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-22 19:40:39,108][00804] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-22 19:40:39,110][00804] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-22 19:40:39,112][00804] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-22 19:40:39,114][00804] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-02-22 19:40:39,115][00804] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-22 19:40:39,117][00804] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-02-22 19:40:39,118][00804] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-02-22 19:40:39,119][00804] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-22 19:40:39,121][00804] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-22 19:40:39,122][00804] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-22 19:40:39,123][00804] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-22 19:40:39,125][00804] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-22 19:40:39,153][00804] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-22 19:40:39,156][00804] RunningMeanStd input shape: (3, 72, 128) +[2023-02-22 19:40:39,157][00804] RunningMeanStd input shape: (1,) +[2023-02-22 19:40:39,174][00804] ConvEncoder: input_channels=3 +[2023-02-22 19:40:39,889][00804] Conv encoder output size: 512 +[2023-02-22 19:40:39,892][00804] Policy head output size: 512 +[2023-02-22 19:40:42,361][00804] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-22 19:40:43,689][00804] Num frames 100... +[2023-02-22 19:40:43,809][00804] Num frames 200... +[2023-02-22 19:40:43,930][00804] Num frames 300... +[2023-02-22 19:40:44,045][00804] Num frames 400... +[2023-02-22 19:40:44,160][00804] Num frames 500... +[2023-02-22 19:40:44,272][00804] Avg episode rewards: #0: 9.440, true rewards: #0: 5.440 +[2023-02-22 19:40:44,274][00804] Avg episode reward: 9.440, avg true_objective: 5.440 +[2023-02-22 19:40:44,341][00804] Num frames 600... +[2023-02-22 19:40:44,460][00804] Num frames 700... +[2023-02-22 19:40:44,574][00804] Num frames 800... +[2023-02-22 19:40:44,698][00804] Num frames 900... +[2023-02-22 19:40:44,821][00804] Num frames 1000... +[2023-02-22 19:40:44,948][00804] Num frames 1100... +[2023-02-22 19:40:45,068][00804] Num frames 1200... +[2023-02-22 19:40:45,184][00804] Num frames 1300... +[2023-02-22 19:40:45,296][00804] Num frames 1400... +[2023-02-22 19:40:45,423][00804] Num frames 1500... +[2023-02-22 19:40:45,537][00804] Num frames 1600... +[2023-02-22 19:40:45,656][00804] Num frames 1700... +[2023-02-22 19:40:45,784][00804] Num frames 1800... +[2023-02-22 19:40:45,902][00804] Avg episode rewards: #0: 21.280, true rewards: #0: 9.280 +[2023-02-22 19:40:45,904][00804] Avg episode reward: 21.280, avg true_objective: 9.280 +[2023-02-22 19:40:45,957][00804] Num frames 1900... +[2023-02-22 19:40:46,082][00804] Num frames 2000... +[2023-02-22 19:40:46,202][00804] Num frames 2100... +[2023-02-22 19:40:46,324][00804] Num frames 2200... +[2023-02-22 19:40:46,438][00804] Num frames 2300... +[2023-02-22 19:40:46,559][00804] Num frames 2400... +[2023-02-22 19:40:46,673][00804] Num frames 2500... +[2023-02-22 19:40:46,800][00804] Num frames 2600... +[2023-02-22 19:40:46,922][00804] Num frames 2700... +[2023-02-22 19:40:47,037][00804] Num frames 2800... +[2023-02-22 19:40:47,154][00804] Num frames 2900... +[2023-02-22 19:40:47,258][00804] Avg episode rewards: #0: 22.480, true rewards: #0: 9.813 +[2023-02-22 19:40:47,260][00804] Avg episode reward: 22.480, avg true_objective: 9.813 +[2023-02-22 19:40:47,333][00804] Num frames 3000... +[2023-02-22 19:40:47,447][00804] Num frames 3100... +[2023-02-22 19:40:47,569][00804] Num frames 3200... +[2023-02-22 19:40:47,679][00804] Num frames 3300... +[2023-02-22 19:40:47,799][00804] Num frames 3400... +[2023-02-22 19:40:47,915][00804] Num frames 3500... +[2023-02-22 19:40:48,036][00804] Avg episode rewards: #0: 19.880, true rewards: #0: 8.880 +[2023-02-22 19:40:48,038][00804] Avg episode reward: 19.880, avg true_objective: 8.880 +[2023-02-22 19:40:48,097][00804] Num frames 3600... +[2023-02-22 19:40:48,219][00804] Num frames 3700... +[2023-02-22 19:40:48,332][00804] Num frames 3800... +[2023-02-22 19:40:48,447][00804] Num frames 3900... +[2023-02-22 19:40:48,569][00804] Num frames 4000... +[2023-02-22 19:40:48,686][00804] Num frames 4100... +[2023-02-22 19:40:48,815][00804] Num frames 4200... +[2023-02-22 19:40:48,929][00804] Num frames 4300... +[2023-02-22 19:40:49,048][00804] Num frames 4400... +[2023-02-22 19:40:49,197][00804] Num frames 4500... +[2023-02-22 19:40:49,281][00804] Avg episode rewards: #0: 20.624, true rewards: #0: 9.024 +[2023-02-22 19:40:49,283][00804] Avg episode reward: 20.624, avg true_objective: 9.024 +[2023-02-22 19:40:49,428][00804] Num frames 4600... +[2023-02-22 19:40:49,590][00804] Num frames 4700... +[2023-02-22 19:40:49,766][00804] Num frames 4800... +[2023-02-22 19:40:49,951][00804] Num frames 4900... +[2023-02-22 19:40:50,134][00804] Num frames 5000... +[2023-02-22 19:40:50,300][00804] Num frames 5100... +[2023-02-22 19:40:50,464][00804] Num frames 5200... +[2023-02-22 19:40:50,619][00804] Num frames 5300... +[2023-02-22 19:40:50,791][00804] Num frames 5400... +[2023-02-22 19:40:50,960][00804] Num frames 5500... +[2023-02-22 19:40:51,133][00804] Num frames 5600... +[2023-02-22 19:40:51,296][00804] Num frames 5700... +[2023-02-22 19:40:51,471][00804] Num frames 5800... +[2023-02-22 19:40:51,636][00804] Num frames 5900... +[2023-02-22 19:40:51,728][00804] Avg episode rewards: #0: 22.700, true rewards: #0: 9.867 +[2023-02-22 19:40:51,730][00804] Avg episode reward: 22.700, avg true_objective: 9.867 +[2023-02-22 19:40:51,862][00804] Num frames 6000... +[2023-02-22 19:40:52,040][00804] Num frames 6100... +[2023-02-22 19:40:52,197][00804] Num frames 6200... +[2023-02-22 19:40:52,363][00804] Num frames 6300... +[2023-02-22 19:40:52,524][00804] Num frames 6400... +[2023-02-22 19:40:52,677][00804] Num frames 6500... +[2023-02-22 19:40:52,798][00804] Num frames 6600... +[2023-02-22 19:40:52,915][00804] Num frames 6700... +[2023-02-22 19:40:53,050][00804] Num frames 6800... +[2023-02-22 19:40:53,172][00804] Num frames 6900... +[2023-02-22 19:40:53,293][00804] Num frames 7000... +[2023-02-22 19:40:53,405][00804] Num frames 7100... +[2023-02-22 19:40:53,525][00804] Num frames 7200... +[2023-02-22 19:40:53,637][00804] Num frames 7300... +[2023-02-22 19:40:53,751][00804] Num frames 7400... +[2023-02-22 19:40:53,875][00804] Num frames 7500... +[2023-02-22 19:40:54,009][00804] Num frames 7600... +[2023-02-22 19:40:54,126][00804] Num frames 7700... +[2023-02-22 19:40:54,241][00804] Num frames 7800... +[2023-02-22 19:40:54,357][00804] Num frames 7900... +[2023-02-22 19:40:54,479][00804] Num frames 8000... +[2023-02-22 19:40:54,558][00804] Avg episode rewards: #0: 27.600, true rewards: #0: 11.457 +[2023-02-22 19:40:54,560][00804] Avg episode reward: 27.600, avg true_objective: 11.457 +[2023-02-22 19:40:54,654][00804] Num frames 8100... +[2023-02-22 19:40:54,771][00804] Num frames 8200... +[2023-02-22 19:40:54,884][00804] Num frames 8300... +[2023-02-22 19:40:55,007][00804] Num frames 8400... +[2023-02-22 19:40:55,122][00804] Num frames 8500... +[2023-02-22 19:40:55,245][00804] Num frames 8600... +[2023-02-22 19:40:55,362][00804] Num frames 8700... +[2023-02-22 19:40:55,482][00804] Num frames 8800... +[2023-02-22 19:40:55,594][00804] Num frames 8900... +[2023-02-22 19:40:55,711][00804] Num frames 9000... +[2023-02-22 19:40:55,825][00804] Num frames 9100... +[2023-02-22 19:40:55,950][00804] Num frames 9200... +[2023-02-22 19:40:56,089][00804] Avg episode rewards: #0: 27.710, true rewards: #0: 11.585 +[2023-02-22 19:40:56,090][00804] Avg episode reward: 27.710, avg true_objective: 11.585 +[2023-02-22 19:40:56,134][00804] Num frames 9300... +[2023-02-22 19:40:56,252][00804] Num frames 9400... +[2023-02-22 19:40:56,368][00804] Num frames 9500... +[2023-02-22 19:40:56,490][00804] Num frames 9600... +[2023-02-22 19:40:56,606][00804] Num frames 9700... +[2023-02-22 19:40:56,725][00804] Num frames 9800... +[2023-02-22 19:40:56,838][00804] Num frames 9900... +[2023-02-22 19:40:56,951][00804] Num frames 10000... +[2023-02-22 19:40:57,078][00804] Num frames 10100... +[2023-02-22 19:40:57,205][00804] Num frames 10200... +[2023-02-22 19:40:57,317][00804] Num frames 10300... +[2023-02-22 19:40:57,436][00804] Num frames 10400... +[2023-02-22 19:40:57,552][00804] Num frames 10500... +[2023-02-22 19:40:57,674][00804] Num frames 10600... +[2023-02-22 19:40:57,797][00804] Num frames 10700... +[2023-02-22 19:40:57,918][00804] Num frames 10800... +[2023-02-22 19:40:58,031][00804] Num frames 10900... +[2023-02-22 19:40:58,166][00804] Num frames 11000... +[2023-02-22 19:40:58,285][00804] Num frames 11100... +[2023-02-22 19:40:58,404][00804] Num frames 11200... +[2023-02-22 19:40:58,523][00804] Num frames 11300... +[2023-02-22 19:40:58,660][00804] Avg episode rewards: #0: 31.187, true rewards: #0: 12.631 +[2023-02-22 19:40:58,661][00804] Avg episode reward: 31.187, avg true_objective: 12.631 +[2023-02-22 19:40:58,701][00804] Num frames 11400... +[2023-02-22 19:40:58,822][00804] Num frames 11500... +[2023-02-22 19:40:58,933][00804] Num frames 11600... +[2023-02-22 19:40:59,049][00804] Num frames 11700... +[2023-02-22 19:40:59,178][00804] Num frames 11800... +[2023-02-22 19:40:59,271][00804] Avg episode rewards: #0: 28.931, true rewards: #0: 11.831 +[2023-02-22 19:40:59,272][00804] Avg episode reward: 28.931, avg true_objective: 11.831 +[2023-02-22 19:42:12,432][00804] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-02-22 20:15:31,100][00804] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-22 20:15:31,102][00804] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-22 20:15:31,105][00804] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-22 20:15:31,106][00804] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-22 20:15:31,108][00804] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-22 20:15:31,111][00804] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-22 20:15:31,112][00804] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-02-22 20:15:31,113][00804] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-22 20:15:31,115][00804] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-02-22 20:15:31,116][00804] Adding new argument 'hf_repository'='albertqueralto/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-02-22 20:15:31,122][00804] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-22 20:15:31,124][00804] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-22 20:15:31,125][00804] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-22 20:15:31,126][00804] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-22 20:15:31,128][00804] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-22 20:15:31,154][00804] RunningMeanStd input shape: (3, 72, 128) +[2023-02-22 20:15:31,159][00804] RunningMeanStd input shape: (1,) +[2023-02-22 20:15:31,173][00804] ConvEncoder: input_channels=3 +[2023-02-22 20:15:31,211][00804] Conv encoder output size: 512 +[2023-02-22 20:15:31,213][00804] Policy head output size: 512 +[2023-02-22 20:15:31,233][00804] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-22 20:15:31,678][00804] Num frames 100... +[2023-02-22 20:15:31,789][00804] Num frames 200... +[2023-02-22 20:15:31,916][00804] Num frames 300... +[2023-02-22 20:15:32,027][00804] Num frames 400... +[2023-02-22 20:15:32,163][00804] Num frames 500... +[2023-02-22 20:15:32,279][00804] Num frames 600... +[2023-02-22 20:15:32,401][00804] Num frames 700... +[2023-02-22 20:15:32,524][00804] Num frames 800... +[2023-02-22 20:15:32,612][00804] Avg episode rewards: #0: 16.280, true rewards: #0: 8.280 +[2023-02-22 20:15:32,617][00804] Avg episode reward: 16.280, avg true_objective: 8.280 +[2023-02-22 20:15:32,701][00804] Num frames 900... +[2023-02-22 20:15:32,813][00804] Num frames 1000... +[2023-02-22 20:15:32,934][00804] Num frames 1100... +[2023-02-22 20:15:33,050][00804] Num frames 1200... +[2023-02-22 20:15:33,183][00804] Num frames 1300... +[2023-02-22 20:15:33,296][00804] Num frames 1400... +[2023-02-22 20:15:33,411][00804] Num frames 1500... +[2023-02-22 20:15:33,530][00804] Num frames 1600... +[2023-02-22 20:15:33,644][00804] Num frames 1700... +[2023-02-22 20:15:33,759][00804] Num frames 1800... +[2023-02-22 20:15:33,877][00804] Num frames 1900... +[2023-02-22 20:15:33,987][00804] Num frames 2000... +[2023-02-22 20:15:34,101][00804] Num frames 2100... +[2023-02-22 20:15:34,217][00804] Num frames 2200... +[2023-02-22 20:15:34,310][00804] Avg episode rewards: #0: 26.160, true rewards: #0: 11.160 +[2023-02-22 20:15:34,312][00804] Avg episode reward: 26.160, avg true_objective: 11.160 +[2023-02-22 20:15:34,397][00804] Num frames 2300... +[2023-02-22 20:15:34,508][00804] Num frames 2400... +[2023-02-22 20:15:34,643][00804] Num frames 2500... +[2023-02-22 20:15:34,756][00804] Num frames 2600... +[2023-02-22 20:15:34,874][00804] Num frames 2700... +[2023-02-22 20:15:34,992][00804] Num frames 2800... +[2023-02-22 20:15:35,107][00804] Num frames 2900... +[2023-02-22 20:15:35,226][00804] Num frames 3000... +[2023-02-22 20:15:35,290][00804] Avg episode rewards: #0: 23.010, true rewards: #0: 10.010 +[2023-02-22 20:15:35,292][00804] Avg episode reward: 23.010, avg true_objective: 10.010 +[2023-02-22 20:15:35,452][00804] Num frames 3100... +[2023-02-22 20:15:35,646][00804] Num frames 3200... +[2023-02-22 20:15:35,797][00804] Num frames 3300... +[2023-02-22 20:15:35,952][00804] Num frames 3400... +[2023-02-22 20:15:36,105][00804] Num frames 3500... +[2023-02-22 20:15:36,266][00804] Num frames 3600... +[2023-02-22 20:15:36,430][00804] Num frames 3700... +[2023-02-22 20:15:36,587][00804] Num frames 3800... +[2023-02-22 20:15:36,763][00804] Num frames 3900... +[2023-02-22 20:15:36,927][00804] Num frames 4000... +[2023-02-22 20:15:37,084][00804] Num frames 4100... +[2023-02-22 20:15:37,254][00804] Num frames 4200... +[2023-02-22 20:15:37,418][00804] Num frames 4300... +[2023-02-22 20:15:37,586][00804] Num frames 4400... +[2023-02-22 20:15:37,754][00804] Num frames 4500... +[2023-02-22 20:15:37,919][00804] Num frames 4600... +[2023-02-22 20:15:38,090][00804] Num frames 4700... +[2023-02-22 20:15:38,256][00804] Num frames 4800... +[2023-02-22 20:15:38,423][00804] Num frames 4900... +[2023-02-22 20:15:38,594][00804] Num frames 5000... +[2023-02-22 20:15:38,762][00804] Num frames 5100... +[2023-02-22 20:15:38,829][00804] Avg episode rewards: #0: 31.257, true rewards: #0: 12.757 +[2023-02-22 20:15:38,831][00804] Avg episode reward: 31.257, avg true_objective: 12.757 +[2023-02-22 20:15:38,969][00804] Num frames 5200... +[2023-02-22 20:15:39,090][00804] Num frames 5300... +[2023-02-22 20:15:39,208][00804] Num frames 5400... +[2023-02-22 20:15:39,327][00804] Num frames 5500... +[2023-02-22 20:15:39,451][00804] Num frames 5600... +[2023-02-22 20:15:39,573][00804] Num frames 5700... +[2023-02-22 20:15:39,684][00804] Num frames 5800... +[2023-02-22 20:15:39,813][00804] Num frames 5900... +[2023-02-22 20:15:39,874][00804] Avg episode rewards: #0: 28.006, true rewards: #0: 11.806 +[2023-02-22 20:15:39,876][00804] Avg episode reward: 28.006, avg true_objective: 11.806 +[2023-02-22 20:15:39,989][00804] Num frames 6000... +[2023-02-22 20:15:40,112][00804] Num frames 6100... +[2023-02-22 20:15:40,228][00804] Num frames 6200... +[2023-02-22 20:15:40,339][00804] Num frames 6300... +[2023-02-22 20:15:40,462][00804] Num frames 6400... +[2023-02-22 20:15:40,583][00804] Num frames 6500... +[2023-02-22 20:15:40,729][00804] Avg episode rewards: #0: 25.800, true rewards: #0: 10.967 +[2023-02-22 20:15:40,730][00804] Avg episode reward: 25.800, avg true_objective: 10.967 +[2023-02-22 20:15:40,760][00804] Num frames 6600... +[2023-02-22 20:15:40,881][00804] Num frames 6700... +[2023-02-22 20:15:40,992][00804] Num frames 6800... +[2023-02-22 20:15:41,109][00804] Num frames 6900... +[2023-02-22 20:15:41,219][00804] Num frames 7000... +[2023-02-22 20:15:41,343][00804] Num frames 7100... +[2023-02-22 20:15:41,467][00804] Num frames 7200... +[2023-02-22 20:15:41,581][00804] Num frames 7300... +[2023-02-22 20:15:41,700][00804] Num frames 7400... +[2023-02-22 20:15:41,822][00804] Num frames 7500... +[2023-02-22 20:15:41,937][00804] Num frames 7600... +[2023-02-22 20:15:42,063][00804] Num frames 7700... +[2023-02-22 20:15:42,185][00804] Num frames 7800... +[2023-02-22 20:15:42,300][00804] Num frames 7900... +[2023-02-22 20:15:42,417][00804] Num frames 8000... +[2023-02-22 20:15:42,538][00804] Num frames 8100... +[2023-02-22 20:15:42,668][00804] Num frames 8200... +[2023-02-22 20:15:42,740][00804] Avg episode rewards: #0: 28.017, true rewards: #0: 11.731 +[2023-02-22 20:15:42,743][00804] Avg episode reward: 28.017, avg true_objective: 11.731 +[2023-02-22 20:15:42,849][00804] Num frames 8300... +[2023-02-22 20:15:42,971][00804] Num frames 8400... +[2023-02-22 20:15:43,089][00804] Num frames 8500... +[2023-02-22 20:15:43,211][00804] Num frames 8600... +[2023-02-22 20:15:43,325][00804] Num frames 8700... +[2023-02-22 20:15:43,442][00804] Num frames 8800... +[2023-02-22 20:15:43,554][00804] Num frames 8900... +[2023-02-22 20:15:43,676][00804] Num frames 9000... +[2023-02-22 20:15:43,747][00804] Avg episode rewards: #0: 26.390, true rewards: #0: 11.265 +[2023-02-22 20:15:43,752][00804] Avg episode reward: 26.390, avg true_objective: 11.265 +[2023-02-22 20:15:43,863][00804] Num frames 9100... +[2023-02-22 20:15:43,982][00804] Num frames 9200... +[2023-02-22 20:15:44,104][00804] Num frames 9300... +[2023-02-22 20:15:44,216][00804] Num frames 9400... +[2023-02-22 20:15:44,332][00804] Num frames 9500... +[2023-02-22 20:15:44,460][00804] Num frames 9600... +[2023-02-22 20:15:44,572][00804] Num frames 9700... +[2023-02-22 20:15:44,687][00804] Num frames 9800... +[2023-02-22 20:15:44,796][00804] Num frames 9900... +[2023-02-22 20:15:44,918][00804] Num frames 10000... +[2023-02-22 20:15:45,028][00804] Num frames 10100... +[2023-02-22 20:15:45,145][00804] Num frames 10200... +[2023-02-22 20:15:45,266][00804] Num frames 10300... +[2023-02-22 20:15:45,382][00804] Num frames 10400... +[2023-02-22 20:15:45,501][00804] Num frames 10500... +[2023-02-22 20:15:45,624][00804] Num frames 10600... +[2023-02-22 20:15:45,738][00804] Num frames 10700... +[2023-02-22 20:15:45,857][00804] Num frames 10800... +[2023-02-22 20:15:45,976][00804] Num frames 10900... +[2023-02-22 20:15:46,094][00804] Num frames 11000... +[2023-02-22 20:15:46,211][00804] Num frames 11100... +[2023-02-22 20:15:46,281][00804] Avg episode rewards: #0: 30.013, true rewards: #0: 12.347 +[2023-02-22 20:15:46,282][00804] Avg episode reward: 30.013, avg true_objective: 12.347 +[2023-02-22 20:15:46,401][00804] Num frames 11200... +[2023-02-22 20:15:46,521][00804] Num frames 11300... +[2023-02-22 20:15:46,641][00804] Num frames 11400... +[2023-02-22 20:15:46,757][00804] Num frames 11500... +[2023-02-22 20:15:46,881][00804] Num frames 11600... +[2023-02-22 20:15:47,001][00804] Num frames 11700... +[2023-02-22 20:15:47,130][00804] Num frames 11800... +[2023-02-22 20:15:47,244][00804] Num frames 11900... +[2023-02-22 20:15:47,358][00804] Num frames 12000... +[2023-02-22 20:15:47,483][00804] Num frames 12100... +[2023-02-22 20:15:47,621][00804] Avg episode rewards: #0: 29.268, true rewards: #0: 12.168 +[2023-02-22 20:15:47,623][00804] Avg episode reward: 29.268, avg true_objective: 12.168 +[2023-02-22 20:17:03,872][00804] Replay video saved to /content/train_dir/default_experiment/replay.mp4!