diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1244 @@ +[2023-02-23 23:11:11,509][00448] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-02-23 23:11:11,515][00448] Rollout worker 0 uses device cpu +[2023-02-23 23:11:11,517][00448] Rollout worker 1 uses device cpu +[2023-02-23 23:11:11,519][00448] Rollout worker 2 uses device cpu +[2023-02-23 23:11:11,521][00448] Rollout worker 3 uses device cpu +[2023-02-23 23:11:11,523][00448] Rollout worker 4 uses device cpu +[2023-02-23 23:11:11,525][00448] Rollout worker 5 uses device cpu +[2023-02-23 23:11:11,527][00448] Rollout worker 6 uses device cpu +[2023-02-23 23:11:11,529][00448] Rollout worker 7 uses device cpu +[2023-02-23 23:11:11,704][00448] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-23 23:11:11,705][00448] InferenceWorker_p0-w0: min num requests: 2 +[2023-02-23 23:11:11,739][00448] Starting all processes... +[2023-02-23 23:11:11,740][00448] Starting process learner_proc0 +[2023-02-23 23:11:11,792][00448] Starting all processes... +[2023-02-23 23:11:11,805][00448] Starting process inference_proc0-0 +[2023-02-23 23:11:11,805][00448] Starting process rollout_proc0 +[2023-02-23 23:11:11,810][00448] Starting process rollout_proc1 +[2023-02-23 23:11:11,810][00448] Starting process rollout_proc2 +[2023-02-23 23:11:11,811][00448] Starting process rollout_proc3 +[2023-02-23 23:11:11,811][00448] Starting process rollout_proc4 +[2023-02-23 23:11:11,811][00448] Starting process rollout_proc5 +[2023-02-23 23:11:11,811][00448] Starting process rollout_proc6 +[2023-02-23 23:11:11,811][00448] Starting process rollout_proc7 +[2023-02-23 23:11:22,978][11085] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-23 23:11:22,989][11085] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-02-23 23:11:22,991][11099] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-23 23:11:22,994][11099] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-02-23 23:11:23,399][11105] Worker 5 uses CPU cores [1] +[2023-02-23 23:11:23,493][11102] Worker 2 uses CPU cores [0] +[2023-02-23 23:11:23,568][11100] Worker 0 uses CPU cores [0] +[2023-02-23 23:11:23,571][11107] Worker 7 uses CPU cores [1] +[2023-02-23 23:11:23,615][11103] Worker 3 uses CPU cores [1] +[2023-02-23 23:11:23,627][11106] Worker 6 uses CPU cores [0] +[2023-02-23 23:11:23,655][11101] Worker 1 uses CPU cores [1] +[2023-02-23 23:11:23,676][11104] Worker 4 uses CPU cores [0] +[2023-02-23 23:11:24,129][11099] Num visible devices: 1 +[2023-02-23 23:11:24,129][11085] Num visible devices: 1 +[2023-02-23 23:11:24,139][11085] Starting seed is not provided +[2023-02-23 23:11:24,140][11085] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-23 23:11:24,141][11085] Initializing actor-critic model on device cuda:0 +[2023-02-23 23:11:24,142][11085] RunningMeanStd input shape: (3, 72, 128) +[2023-02-23 23:11:24,143][11085] RunningMeanStd input shape: (1,) +[2023-02-23 23:11:24,155][11085] ConvEncoder: input_channels=3 +[2023-02-23 23:11:24,406][11085] Conv encoder output size: 512 +[2023-02-23 23:11:24,406][11085] Policy head output size: 512 +[2023-02-23 23:11:24,451][11085] Created Actor Critic model with architecture: +[2023-02-23 23:11:24,451][11085] ActorCriticSharedWeights( + (obs_normalizer): ObservationNormalizer( + (running_mean_std): RunningMeanStdDictInPlace( + (running_mean_std): ModuleDict( + (obs): RunningMeanStdInPlace() + ) + ) + ) + (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) + (encoder): VizdoomEncoder( + (basic_encoder): ConvEncoder( + (enc): RecursiveScriptModule( + original_name=ConvEncoderImpl + (conv_head): RecursiveScriptModule( + original_name=Sequential + (0): RecursiveScriptModule(original_name=Conv2d) + (1): RecursiveScriptModule(original_name=ELU) + (2): RecursiveScriptModule(original_name=Conv2d) + (3): RecursiveScriptModule(original_name=ELU) + (4): RecursiveScriptModule(original_name=Conv2d) + (5): RecursiveScriptModule(original_name=ELU) + ) + (mlp_layers): RecursiveScriptModule( + original_name=Sequential + (0): RecursiveScriptModule(original_name=Linear) + (1): RecursiveScriptModule(original_name=ELU) + ) + ) + ) + ) + (core): ModelCoreRNN( + (core): GRU(512, 512) + ) + (decoder): MlpDecoder( + (mlp): Identity() + ) + (critic_linear): Linear(in_features=512, out_features=1, bias=True) + (action_parameterization): ActionParameterizationDefault( + (distribution_linear): Linear(in_features=512, out_features=5, bias=True) + ) +) +[2023-02-23 23:11:30,548][11085] Using optimizer +[2023-02-23 23:11:30,550][11085] No checkpoints found +[2023-02-23 23:11:30,551][11085] Did not load from checkpoint, starting from scratch! +[2023-02-23 23:11:30,551][11085] Initialized policy 0 weights for model version 0 +[2023-02-23 23:11:30,554][11085] LearnerWorker_p0 finished initialization! +[2023-02-23 23:11:30,557][11085] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-02-23 23:11:30,863][11099] RunningMeanStd input shape: (3, 72, 128) +[2023-02-23 23:11:30,865][11099] RunningMeanStd input shape: (1,) +[2023-02-23 23:11:30,883][11099] ConvEncoder: input_channels=3 +[2023-02-23 23:11:31,037][11099] Conv encoder output size: 512 +[2023-02-23 23:11:31,038][11099] Policy head output size: 512 +[2023-02-23 23:11:31,697][00448] Heartbeat connected on Batcher_0 +[2023-02-23 23:11:31,702][00448] Heartbeat connected on LearnerWorker_p0 +[2023-02-23 23:11:31,718][00448] Heartbeat connected on RolloutWorker_w0 +[2023-02-23 23:11:31,719][00448] Heartbeat connected on RolloutWorker_w1 +[2023-02-23 23:11:31,721][00448] Heartbeat connected on RolloutWorker_w2 +[2023-02-23 23:11:31,731][00448] Heartbeat connected on RolloutWorker_w3 +[2023-02-23 23:11:31,734][00448] Heartbeat connected on RolloutWorker_w4 +[2023-02-23 23:11:31,737][00448] Heartbeat connected on RolloutWorker_w5 +[2023-02-23 23:11:31,741][00448] Heartbeat connected on RolloutWorker_w6 +[2023-02-23 23:11:31,748][00448] Heartbeat connected on RolloutWorker_w7 +[2023-02-23 23:11:32,677][00448] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-23 23:11:33,845][00448] Inference worker 0-0 is ready! +[2023-02-23 23:11:33,847][00448] All inference workers are ready! Signal rollout workers to start! +[2023-02-23 23:11:33,853][00448] Heartbeat connected on InferenceWorker_p0-w0 +[2023-02-23 23:11:33,965][11103] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:33,976][11101] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:33,977][11105] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:33,978][11107] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:34,004][11106] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:34,014][11104] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:34,023][11100] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:34,038][11102] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:11:34,189][11101] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... +[2023-02-23 23:11:34,191][11103] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... +[2023-02-23 23:11:34,194][11101] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] 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 +[2023-02-23 23:11:34,196][11101] Unhandled exception in evt loop rollout_proc1_evt_loop +[2023-02-23 23:11:34,196][11103] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] 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 +[2023-02-23 23:11:34,200][11103] Unhandled exception in evt loop rollout_proc3_evt_loop +[2023-02-23 23:11:35,448][11107] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,500][11100] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,507][11106] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,513][11104] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,516][11102] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,576][11105] Decorrelating experience for 0 frames... +[2023-02-23 23:11:35,867][11107] Decorrelating experience for 32 frames... +[2023-02-23 23:11:36,588][11105] Decorrelating experience for 32 frames... +[2023-02-23 23:11:36,673][11107] Decorrelating experience for 64 frames... +[2023-02-23 23:11:36,824][11102] Decorrelating experience for 32 frames... +[2023-02-23 23:11:36,834][11104] Decorrelating experience for 32 frames... +[2023-02-23 23:11:36,837][11106] Decorrelating experience for 32 frames... +[2023-02-23 23:11:37,011][11100] Decorrelating experience for 32 frames... +[2023-02-23 23:11:37,309][11105] Decorrelating experience for 64 frames... +[2023-02-23 23:11:37,560][11107] Decorrelating experience for 96 frames... +[2023-02-23 23:11:37,677][00448] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-23 23:11:38,045][11105] Decorrelating experience for 96 frames... +[2023-02-23 23:11:38,384][11104] Decorrelating experience for 64 frames... +[2023-02-23 23:11:38,386][11102] Decorrelating experience for 64 frames... +[2023-02-23 23:11:38,401][11106] Decorrelating experience for 64 frames... +[2023-02-23 23:11:38,687][11100] Decorrelating experience for 64 frames... +[2023-02-23 23:11:39,428][11102] Decorrelating experience for 96 frames... +[2023-02-23 23:11:39,439][11104] Decorrelating experience for 96 frames... +[2023-02-23 23:11:39,457][11106] Decorrelating experience for 96 frames... +[2023-02-23 23:11:39,943][11100] Decorrelating experience for 96 frames... +[2023-02-23 23:11:42,677][00448] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 2.8. Samples: 28. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-02-23 23:11:42,683][00448] Avg episode reward: [(0, '1.925')] +[2023-02-23 23:11:43,758][11085] Signal inference workers to stop experience collection... +[2023-02-23 23:11:43,784][11099] InferenceWorker_p0-w0: stopping experience collection +[2023-02-23 23:11:46,367][11085] Signal inference workers to resume experience collection... +[2023-02-23 23:11:46,367][11099] InferenceWorker_p0-w0: resuming experience collection +[2023-02-23 23:11:47,678][00448] Fps is (10 sec: 409.5, 60 sec: 273.0, 300 sec: 273.0). Total num frames: 4096. Throughput: 0: 156.4. Samples: 2346. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-02-23 23:11:47,692][00448] Avg episode reward: [(0, '3.084')] +[2023-02-23 23:11:52,677][00448] Fps is (10 sec: 2457.6, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 24576. Throughput: 0: 320.7. Samples: 6414. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:11:52,683][00448] Avg episode reward: [(0, '3.815')] +[2023-02-23 23:11:55,644][11099] Updated weights for policy 0, policy_version 10 (0.0021) +[2023-02-23 23:11:57,677][00448] Fps is (10 sec: 4506.3, 60 sec: 1966.1, 300 sec: 1966.1). Total num frames: 49152. Throughput: 0: 393.1. Samples: 9828. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:11:57,679][00448] Avg episode reward: [(0, '4.233')] +[2023-02-23 23:12:02,679][00448] Fps is (10 sec: 4095.3, 60 sec: 2184.4, 300 sec: 2184.4). Total num frames: 65536. Throughput: 0: 538.4. Samples: 16154. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:12:02,686][00448] Avg episode reward: [(0, '4.249')] +[2023-02-23 23:12:07,306][11099] Updated weights for policy 0, policy_version 20 (0.0011) +[2023-02-23 23:12:07,677][00448] Fps is (10 sec: 3276.8, 60 sec: 2340.6, 300 sec: 2340.6). Total num frames: 81920. Throughput: 0: 590.9. Samples: 20682. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:12:07,684][00448] Avg episode reward: [(0, '4.251')] +[2023-02-23 23:12:12,677][00448] Fps is (10 sec: 3687.1, 60 sec: 2560.0, 300 sec: 2560.0). Total num frames: 102400. Throughput: 0: 592.2. Samples: 23686. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:12:12,682][00448] Avg episode reward: [(0, '4.259')] +[2023-02-23 23:12:12,685][11085] Saving new best policy, reward=4.259! +[2023-02-23 23:12:16,394][11099] Updated weights for policy 0, policy_version 30 (0.0013) +[2023-02-23 23:12:17,677][00448] Fps is (10 sec: 4505.6, 60 sec: 2821.7, 300 sec: 2821.7). Total num frames: 126976. Throughput: 0: 673.1. Samples: 30288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:12:17,679][00448] Avg episode reward: [(0, '4.291')] +[2023-02-23 23:12:17,693][11085] Saving new best policy, reward=4.291! +[2023-02-23 23:12:22,677][00448] Fps is (10 sec: 3686.4, 60 sec: 2785.3, 300 sec: 2785.3). Total num frames: 139264. Throughput: 0: 788.3. Samples: 35474. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:12:22,679][00448] Avg episode reward: [(0, '4.267')] +[2023-02-23 23:12:27,677][00448] Fps is (10 sec: 3276.7, 60 sec: 2904.4, 300 sec: 2904.4). Total num frames: 159744. Throughput: 0: 839.7. Samples: 37816. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:12:27,680][00448] Avg episode reward: [(0, '4.349')] +[2023-02-23 23:12:27,691][11085] Saving new best policy, reward=4.349! +[2023-02-23 23:12:28,412][11099] Updated weights for policy 0, policy_version 40 (0.0018) +[2023-02-23 23:12:32,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 180224. Throughput: 0: 925.8. Samples: 44004. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-23 23:12:32,679][00448] Avg episode reward: [(0, '4.344')] +[2023-02-23 23:12:37,681][00448] Fps is (10 sec: 4094.3, 60 sec: 3344.8, 300 sec: 3087.5). Total num frames: 200704. Throughput: 0: 981.0. Samples: 50562. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:12:37,686][00448] Avg episode reward: [(0, '4.451')] +[2023-02-23 23:12:37,695][11085] Saving new best policy, reward=4.451! +[2023-02-23 23:12:38,129][11099] Updated weights for policy 0, policy_version 50 (0.0011) +[2023-02-23 23:12:42,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3101.3). Total num frames: 217088. Throughput: 0: 953.6. Samples: 52742. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:12:42,683][00448] Avg episode reward: [(0, '4.515')] +[2023-02-23 23:12:42,687][11085] Saving new best policy, reward=4.515! +[2023-02-23 23:12:47,677][00448] Fps is (10 sec: 3278.3, 60 sec: 3823.0, 300 sec: 3113.0). Total num frames: 233472. Throughput: 0: 924.0. Samples: 57732. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:12:47,679][00448] Avg episode reward: [(0, '4.455')] +[2023-02-23 23:12:49,438][11099] Updated weights for policy 0, policy_version 60 (0.0020) +[2023-02-23 23:12:52,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3891.2, 300 sec: 3225.6). Total num frames: 258048. Throughput: 0: 968.5. Samples: 64264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:12:52,679][00448] Avg episode reward: [(0, '4.463')] +[2023-02-23 23:12:57,680][00448] Fps is (10 sec: 4094.6, 60 sec: 3754.5, 300 sec: 3228.5). Total num frames: 274432. Throughput: 0: 971.1. Samples: 67390. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:12:57,684][00448] Avg episode reward: [(0, '4.680')] +[2023-02-23 23:12:57,697][11085] Saving new best policy, reward=4.680! +[2023-02-23 23:13:01,770][11099] Updated weights for policy 0, policy_version 70 (0.0025) +[2023-02-23 23:13:02,677][00448] Fps is (10 sec: 2867.2, 60 sec: 3686.5, 300 sec: 3185.8). Total num frames: 286720. Throughput: 0: 915.7. Samples: 71494. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:02,683][00448] Avg episode reward: [(0, '4.493')] +[2023-02-23 23:13:07,677][00448] Fps is (10 sec: 3277.9, 60 sec: 3754.7, 300 sec: 3233.7). Total num frames: 307200. Throughput: 0: 929.4. Samples: 77298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:07,679][00448] Avg episode reward: [(0, '4.532')] +[2023-02-23 23:13:07,689][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000075_307200.pth... +[2023-02-23 23:13:11,453][11099] Updated weights for policy 0, policy_version 80 (0.0022) +[2023-02-23 23:13:12,677][00448] Fps is (10 sec: 4505.7, 60 sec: 3822.9, 300 sec: 3317.8). Total num frames: 331776. Throughput: 0: 950.5. Samples: 80588. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:13:12,681][00448] Avg episode reward: [(0, '4.363')] +[2023-02-23 23:13:17,678][00448] Fps is (10 sec: 4095.4, 60 sec: 3686.3, 300 sec: 3315.8). Total num frames: 348160. Throughput: 0: 938.1. Samples: 86220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:13:17,682][00448] Avg episode reward: [(0, '4.448')] +[2023-02-23 23:13:22,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3314.0). Total num frames: 364544. Throughput: 0: 896.0. Samples: 90878. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:13:22,679][00448] Avg episode reward: [(0, '4.506')] +[2023-02-23 23:13:23,288][11099] Updated weights for policy 0, policy_version 90 (0.0011) +[2023-02-23 23:13:27,677][00448] Fps is (10 sec: 3686.9, 60 sec: 3754.7, 300 sec: 3348.0). Total num frames: 385024. Throughput: 0: 923.5. Samples: 94298. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:27,679][00448] Avg episode reward: [(0, '4.544')] +[2023-02-23 23:13:32,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3379.2). Total num frames: 405504. Throughput: 0: 960.1. Samples: 100936. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:32,682][00448] Avg episode reward: [(0, '4.714')] +[2023-02-23 23:13:32,686][11085] Saving new best policy, reward=4.714! +[2023-02-23 23:13:33,141][11099] Updated weights for policy 0, policy_version 100 (0.0012) +[2023-02-23 23:13:37,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.7, 300 sec: 3375.1). Total num frames: 421888. Throughput: 0: 916.7. Samples: 105516. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:37,680][00448] Avg episode reward: [(0, '4.559')] +[2023-02-23 23:13:42,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3402.8). Total num frames: 442368. Throughput: 0: 900.1. Samples: 107890. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:42,680][00448] Avg episode reward: [(0, '4.236')] +[2023-02-23 23:13:44,529][11099] Updated weights for policy 0, policy_version 110 (0.0029) +[2023-02-23 23:13:47,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3428.5). Total num frames: 462848. Throughput: 0: 958.1. Samples: 114610. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:13:47,681][00448] Avg episode reward: [(0, '4.286')] +[2023-02-23 23:13:52,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3452.3). Total num frames: 483328. Throughput: 0: 961.5. Samples: 120566. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:52,681][00448] Avg episode reward: [(0, '4.508')] +[2023-02-23 23:13:55,564][11099] Updated weights for policy 0, policy_version 120 (0.0011) +[2023-02-23 23:13:57,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.6, 300 sec: 3418.0). Total num frames: 495616. Throughput: 0: 937.8. Samples: 122790. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:13:57,682][00448] Avg episode reward: [(0, '4.560')] +[2023-02-23 23:14:02,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3823.0, 300 sec: 3440.6). Total num frames: 516096. Throughput: 0: 936.4. Samples: 128356. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-23 23:14:02,685][00448] Avg episode reward: [(0, '4.470')] +[2023-02-23 23:14:05,493][11099] Updated weights for policy 0, policy_version 130 (0.0018) +[2023-02-23 23:14:07,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3891.2, 300 sec: 3488.2). Total num frames: 540672. Throughput: 0: 982.8. Samples: 135102. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:14:07,681][00448] Avg episode reward: [(0, '4.538')] +[2023-02-23 23:14:12,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3754.7, 300 sec: 3481.6). Total num frames: 557056. Throughput: 0: 964.1. Samples: 137682. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:12,683][00448] Avg episode reward: [(0, '4.715')] +[2023-02-23 23:14:17,497][11099] Updated weights for policy 0, policy_version 140 (0.0018) +[2023-02-23 23:14:17,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3475.4). Total num frames: 573440. Throughput: 0: 916.6. Samples: 142184. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:14:17,680][00448] Avg episode reward: [(0, '4.632')] +[2023-02-23 23:14:22,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3493.6). Total num frames: 593920. Throughput: 0: 957.3. Samples: 148596. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:14:22,679][00448] Avg episode reward: [(0, '4.468')] +[2023-02-23 23:14:26,805][11099] Updated weights for policy 0, policy_version 150 (0.0017) +[2023-02-23 23:14:27,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3510.9). Total num frames: 614400. Throughput: 0: 977.6. Samples: 151882. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-02-23 23:14:27,679][00448] Avg episode reward: [(0, '4.415')] +[2023-02-23 23:14:32,682][00448] Fps is (10 sec: 3684.4, 60 sec: 3754.3, 300 sec: 3504.2). Total num frames: 630784. Throughput: 0: 943.5. Samples: 157074. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:32,686][00448] Avg episode reward: [(0, '4.442')] +[2023-02-23 23:14:37,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3498.2). Total num frames: 647168. Throughput: 0: 926.2. Samples: 162246. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:37,679][00448] Avg episode reward: [(0, '4.585')] +[2023-02-23 23:14:38,617][11099] Updated weights for policy 0, policy_version 160 (0.0013) +[2023-02-23 23:14:42,677][00448] Fps is (10 sec: 4098.2, 60 sec: 3822.9, 300 sec: 3535.5). Total num frames: 671744. Throughput: 0: 952.7. Samples: 165660. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:42,679][00448] Avg episode reward: [(0, '4.399')] +[2023-02-23 23:14:47,679][00448] Fps is (10 sec: 4095.0, 60 sec: 3754.5, 300 sec: 3528.8). Total num frames: 688128. Throughput: 0: 970.7. Samples: 172040. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:47,682][00448] Avg episode reward: [(0, '4.405')] +[2023-02-23 23:14:49,048][11099] Updated weights for policy 0, policy_version 170 (0.0011) +[2023-02-23 23:14:52,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3522.6). Total num frames: 704512. Throughput: 0: 921.4. Samples: 176564. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:14:52,680][00448] Avg episode reward: [(0, '4.456')] +[2023-02-23 23:14:57,677][00448] Fps is (10 sec: 3277.6, 60 sec: 3754.7, 300 sec: 3516.6). Total num frames: 720896. Throughput: 0: 908.4. Samples: 178560. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:14:57,679][00448] Avg episode reward: [(0, '4.428')] +[2023-02-23 23:15:02,373][11099] Updated weights for policy 0, policy_version 180 (0.0016) +[2023-02-23 23:15:02,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3510.9). Total num frames: 737280. Throughput: 0: 910.2. Samples: 183142. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:02,680][00448] Avg episode reward: [(0, '4.797')] +[2023-02-23 23:15:02,685][11085] Saving new best policy, reward=4.797! +[2023-02-23 23:15:07,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3505.4). Total num frames: 753664. Throughput: 0: 891.8. Samples: 188726. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:15:07,684][00448] Avg episode reward: [(0, '4.619')] +[2023-02-23 23:15:07,703][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000184_753664.pth... +[2023-02-23 23:15:12,677][00448] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3481.6). Total num frames: 765952. Throughput: 0: 861.2. Samples: 190634. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:15:12,680][00448] Avg episode reward: [(0, '4.517')] +[2023-02-23 23:15:14,699][11099] Updated weights for policy 0, policy_version 190 (0.0014) +[2023-02-23 23:15:17,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3513.5). Total num frames: 790528. Throughput: 0: 868.7. Samples: 196160. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:17,679][00448] Avg episode reward: [(0, '4.528')] +[2023-02-23 23:15:22,677][00448] Fps is (10 sec: 4505.5, 60 sec: 3618.1, 300 sec: 3526.1). Total num frames: 811008. Throughput: 0: 904.0. Samples: 202928. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:22,679][00448] Avg episode reward: [(0, '4.620')] +[2023-02-23 23:15:24,432][11099] Updated weights for policy 0, policy_version 200 (0.0015) +[2023-02-23 23:15:27,682][00448] Fps is (10 sec: 3684.6, 60 sec: 3549.6, 300 sec: 3520.7). Total num frames: 827392. Throughput: 0: 886.4. Samples: 205554. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:27,684][00448] Avg episode reward: [(0, '4.591')] +[2023-02-23 23:15:32,677][00448] Fps is (10 sec: 3276.9, 60 sec: 3550.2, 300 sec: 3515.7). Total num frames: 843776. Throughput: 0: 845.3. Samples: 210076. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:32,680][00448] Avg episode reward: [(0, '4.785')] +[2023-02-23 23:15:36,007][11099] Updated weights for policy 0, policy_version 210 (0.0020) +[2023-02-23 23:15:37,677][00448] Fps is (10 sec: 3688.1, 60 sec: 3618.1, 300 sec: 3527.6). Total num frames: 864256. Throughput: 0: 884.9. Samples: 216384. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:37,687][00448] Avg episode reward: [(0, '4.794')] +[2023-02-23 23:15:42,677][00448] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3538.9). Total num frames: 884736. Throughput: 0: 914.3. Samples: 219704. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:15:42,681][00448] Avg episode reward: [(0, '4.697')] +[2023-02-23 23:15:47,177][11099] Updated weights for policy 0, policy_version 220 (0.0011) +[2023-02-23 23:15:47,679][00448] Fps is (10 sec: 3685.7, 60 sec: 3549.9, 300 sec: 3533.8). Total num frames: 901120. Throughput: 0: 923.9. Samples: 224718. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:15:47,684][00448] Avg episode reward: [(0, '4.593')] +[2023-02-23 23:15:52,678][00448] Fps is (10 sec: 3276.3, 60 sec: 3549.8, 300 sec: 3528.8). Total num frames: 917504. Throughput: 0: 911.2. Samples: 229730. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:15:52,681][00448] Avg episode reward: [(0, '4.477')] +[2023-02-23 23:15:57,677][00448] Fps is (10 sec: 3687.1, 60 sec: 3618.1, 300 sec: 3539.6). Total num frames: 937984. Throughput: 0: 936.2. Samples: 232762. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:15:57,683][00448] Avg episode reward: [(0, '4.801')] +[2023-02-23 23:15:57,694][11085] Saving new best policy, reward=4.801! +[2023-02-23 23:15:57,947][11099] Updated weights for policy 0, policy_version 230 (0.0015) +[2023-02-23 23:16:02,677][00448] Fps is (10 sec: 4096.6, 60 sec: 3686.4, 300 sec: 3549.9). Total num frames: 958464. Throughput: 0: 951.2. Samples: 238964. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:16:02,685][00448] Avg episode reward: [(0, '4.937')] +[2023-02-23 23:16:02,687][11085] Saving new best policy, reward=4.937! +[2023-02-23 23:16:07,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3530.0). Total num frames: 970752. Throughput: 0: 893.6. Samples: 243138. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:16:07,683][00448] Avg episode reward: [(0, '4.733')] +[2023-02-23 23:16:10,366][11099] Updated weights for policy 0, policy_version 240 (0.0022) +[2023-02-23 23:16:12,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3540.1). Total num frames: 991232. Throughput: 0: 890.2. Samples: 245610. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:16:12,679][00448] Avg episode reward: [(0, '4.692')] +[2023-02-23 23:16:17,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3549.9). Total num frames: 1011712. Throughput: 0: 926.7. Samples: 251778. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:16:17,684][00448] Avg episode reward: [(0, '4.772')] +[2023-02-23 23:16:20,867][11099] Updated weights for policy 0, policy_version 250 (0.0017) +[2023-02-23 23:16:22,677][00448] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3545.2). Total num frames: 1028096. Throughput: 0: 904.7. Samples: 257096. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:16:22,680][00448] Avg episode reward: [(0, '4.731')] +[2023-02-23 23:16:27,677][00448] Fps is (10 sec: 2867.2, 60 sec: 3550.1, 300 sec: 3526.7). Total num frames: 1040384. Throughput: 0: 877.6. Samples: 259196. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:16:27,684][00448] Avg episode reward: [(0, '4.655')] +[2023-02-23 23:16:32,500][11099] Updated weights for policy 0, policy_version 260 (0.0018) +[2023-02-23 23:16:32,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 1064960. Throughput: 0: 890.1. Samples: 264772. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:16:32,680][00448] Avg episode reward: [(0, '4.785')] +[2023-02-23 23:16:37,679][00448] Fps is (10 sec: 4504.8, 60 sec: 3686.3, 300 sec: 3679.4). Total num frames: 1085440. Throughput: 0: 929.1. Samples: 271540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:16:37,682][00448] Avg episode reward: [(0, '4.703')] +[2023-02-23 23:16:42,679][00448] Fps is (10 sec: 3685.8, 60 sec: 3618.0, 300 sec: 3721.1). Total num frames: 1101824. Throughput: 0: 913.9. Samples: 273890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:16:42,681][00448] Avg episode reward: [(0, '4.616')] +[2023-02-23 23:16:43,798][11099] Updated weights for policy 0, policy_version 270 (0.0011) +[2023-02-23 23:16:47,677][00448] Fps is (10 sec: 3277.4, 60 sec: 3618.3, 300 sec: 3707.2). Total num frames: 1118208. Throughput: 0: 878.9. Samples: 278516. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:16:47,679][00448] Avg episode reward: [(0, '4.475')] +[2023-02-23 23:16:52,677][00448] Fps is (10 sec: 3687.1, 60 sec: 3686.5, 300 sec: 3693.3). Total num frames: 1138688. Throughput: 0: 931.6. Samples: 285062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:16:52,679][00448] Avg episode reward: [(0, '4.409')] +[2023-02-23 23:16:53,693][11099] Updated weights for policy 0, policy_version 280 (0.0015) +[2023-02-23 23:16:57,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1159168. Throughput: 0: 951.3. Samples: 288420. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:16:57,681][00448] Avg episode reward: [(0, '4.623')] +[2023-02-23 23:17:02,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 1175552. Throughput: 0: 921.0. Samples: 293224. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:17:02,680][00448] Avg episode reward: [(0, '4.586')] +[2023-02-23 23:17:05,658][11099] Updated weights for policy 0, policy_version 290 (0.0030) +[2023-02-23 23:17:07,680][00448] Fps is (10 sec: 3685.4, 60 sec: 3754.5, 300 sec: 3707.2). Total num frames: 1196032. Throughput: 0: 922.8. Samples: 298626. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-23 23:17:07,683][00448] Avg episode reward: [(0, '4.463')] +[2023-02-23 23:17:07,696][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000292_1196032.pth... +[2023-02-23 23:17:07,824][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000075_307200.pth +[2023-02-23 23:17:12,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1216512. Throughput: 0: 948.1. Samples: 301860. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:17:12,680][00448] Avg episode reward: [(0, '4.702')] +[2023-02-23 23:17:15,499][11099] Updated weights for policy 0, policy_version 300 (0.0012) +[2023-02-23 23:17:17,677][00448] Fps is (10 sec: 3687.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 1232896. Throughput: 0: 960.8. Samples: 308008. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:17:17,679][00448] Avg episode reward: [(0, '4.788')] +[2023-02-23 23:17:22,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1249280. Throughput: 0: 911.3. Samples: 312546. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:17:22,680][00448] Avg episode reward: [(0, '4.931')] +[2023-02-23 23:17:27,016][11099] Updated weights for policy 0, policy_version 310 (0.0018) +[2023-02-23 23:17:27,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1269760. Throughput: 0: 924.2. Samples: 315478. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:17:27,681][00448] Avg episode reward: [(0, '4.755')] +[2023-02-23 23:17:32,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3707.3). Total num frames: 1294336. Throughput: 0: 971.4. Samples: 322228. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:17:32,686][00448] Avg episode reward: [(0, '4.561')] +[2023-02-23 23:17:37,642][11099] Updated weights for policy 0, policy_version 320 (0.0011) +[2023-02-23 23:17:37,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3707.2). Total num frames: 1310720. Throughput: 0: 943.6. Samples: 327526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:17:37,684][00448] Avg episode reward: [(0, '4.697')] +[2023-02-23 23:17:42,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.8, 300 sec: 3707.2). Total num frames: 1327104. Throughput: 0: 919.5. Samples: 329798. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:17:42,680][00448] Avg episode reward: [(0, '4.905')] +[2023-02-23 23:17:47,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3693.3). Total num frames: 1347584. Throughput: 0: 951.3. Samples: 336034. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:17:47,680][00448] Avg episode reward: [(0, '4.890')] +[2023-02-23 23:17:48,028][11099] Updated weights for policy 0, policy_version 330 (0.0017) +[2023-02-23 23:17:52,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3822.9, 300 sec: 3707.3). Total num frames: 1368064. Throughput: 0: 979.7. Samples: 342710. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:17:52,682][00448] Avg episode reward: [(0, '4.798')] +[2023-02-23 23:17:57,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 1384448. Throughput: 0: 956.2. Samples: 344888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:17:57,681][00448] Avg episode reward: [(0, '4.902')] +[2023-02-23 23:17:59,577][11099] Updated weights for policy 0, policy_version 340 (0.0012) +[2023-02-23 23:18:02,677][00448] Fps is (10 sec: 3686.5, 60 sec: 3822.9, 300 sec: 3721.1). Total num frames: 1404928. Throughput: 0: 926.5. Samples: 349702. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:02,679][00448] Avg episode reward: [(0, '4.859')] +[2023-02-23 23:18:07,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3823.1, 300 sec: 3707.2). Total num frames: 1425408. Throughput: 0: 967.7. Samples: 356094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:07,680][00448] Avg episode reward: [(0, '4.810')] +[2023-02-23 23:18:09,572][11099] Updated weights for policy 0, policy_version 350 (0.0012) +[2023-02-23 23:18:12,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 1441792. Throughput: 0: 970.5. Samples: 359150. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:12,683][00448] Avg episode reward: [(0, '5.002')] +[2023-02-23 23:18:12,691][11085] Saving new best policy, reward=5.002! +[2023-02-23 23:18:17,679][00448] Fps is (10 sec: 2866.7, 60 sec: 3686.3, 300 sec: 3693.3). Total num frames: 1454080. Throughput: 0: 913.6. Samples: 363340. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:18:17,683][00448] Avg episode reward: [(0, '5.010')] +[2023-02-23 23:18:17,696][11085] Saving new best policy, reward=5.010! +[2023-02-23 23:18:22,001][11099] Updated weights for policy 0, policy_version 360 (0.0018) +[2023-02-23 23:18:22,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1474560. Throughput: 0: 920.4. Samples: 368946. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:22,683][00448] Avg episode reward: [(0, '5.002')] +[2023-02-23 23:18:27,677][00448] Fps is (10 sec: 4506.4, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 1499136. Throughput: 0: 941.0. Samples: 372144. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:27,680][00448] Avg episode reward: [(0, '5.324')] +[2023-02-23 23:18:27,693][11085] Saving new best policy, reward=5.324! +[2023-02-23 23:18:32,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 1511424. Throughput: 0: 929.0. Samples: 377838. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:18:32,682][00448] Avg episode reward: [(0, '5.429')] +[2023-02-23 23:18:32,692][11085] Saving new best policy, reward=5.429! +[2023-02-23 23:18:32,954][11099] Updated weights for policy 0, policy_version 370 (0.0015) +[2023-02-23 23:18:37,679][00448] Fps is (10 sec: 2866.6, 60 sec: 3618.0, 300 sec: 3679.4). Total num frames: 1527808. Throughput: 0: 877.7. Samples: 382208. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:18:37,681][00448] Avg episode reward: [(0, '5.533')] +[2023-02-23 23:18:37,697][11085] Saving new best policy, reward=5.533! +[2023-02-23 23:18:42,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1552384. Throughput: 0: 901.2. Samples: 385444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:18:42,682][00448] Avg episode reward: [(0, '5.251')] +[2023-02-23 23:18:43,872][11099] Updated weights for policy 0, policy_version 380 (0.0017) +[2023-02-23 23:18:47,678][00448] Fps is (10 sec: 3686.7, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1564672. Throughput: 0: 917.5. Samples: 390990. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:18:47,681][00448] Avg episode reward: [(0, '5.199')] +[2023-02-23 23:18:52,677][00448] Fps is (10 sec: 2457.6, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 1576960. Throughput: 0: 858.8. Samples: 394742. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:18:52,681][00448] Avg episode reward: [(0, '5.209')] +[2023-02-23 23:18:57,677][00448] Fps is (10 sec: 2867.5, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 1593344. Throughput: 0: 834.1. Samples: 396686. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:18:57,682][00448] Avg episode reward: [(0, '5.233')] +[2023-02-23 23:18:58,378][11099] Updated weights for policy 0, policy_version 390 (0.0019) +[2023-02-23 23:19:02,677][00448] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1613824. Throughput: 0: 870.5. Samples: 402510. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:19:02,682][00448] Avg episode reward: [(0, '5.237')] +[2023-02-23 23:19:07,569][11099] Updated weights for policy 0, policy_version 400 (0.0011) +[2023-02-23 23:19:07,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 1638400. Throughput: 0: 893.6. Samples: 409158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:19:07,683][00448] Avg episode reward: [(0, '5.583')] +[2023-02-23 23:19:07,695][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000400_1638400.pth... +[2023-02-23 23:19:07,831][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000184_753664.pth +[2023-02-23 23:19:07,843][11085] Saving new best policy, reward=5.583! +[2023-02-23 23:19:12,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 1650688. Throughput: 0: 874.1. Samples: 411478. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:19:12,682][00448] Avg episode reward: [(0, '5.710')] +[2023-02-23 23:19:12,687][11085] Saving new best policy, reward=5.710! +[2023-02-23 23:19:17,677][00448] Fps is (10 sec: 2867.2, 60 sec: 3550.0, 300 sec: 3637.8). Total num frames: 1667072. Throughput: 0: 841.7. Samples: 415714. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:19:17,680][00448] Avg episode reward: [(0, '5.759')] +[2023-02-23 23:19:17,695][11085] Saving new best policy, reward=5.759! +[2023-02-23 23:19:20,109][11099] Updated weights for policy 0, policy_version 410 (0.0014) +[2023-02-23 23:19:22,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1687552. Throughput: 0: 890.0. Samples: 422258. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:19:22,680][00448] Avg episode reward: [(0, '6.286')] +[2023-02-23 23:19:22,683][11085] Saving new best policy, reward=6.286! +[2023-02-23 23:19:27,680][00448] Fps is (10 sec: 4094.6, 60 sec: 3481.4, 300 sec: 3651.7). Total num frames: 1708032. Throughput: 0: 890.4. Samples: 425514. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:19:27,682][00448] Avg episode reward: [(0, '6.477')] +[2023-02-23 23:19:27,699][11085] Saving new best policy, reward=6.477! +[2023-02-23 23:19:31,390][11099] Updated weights for policy 0, policy_version 420 (0.0011) +[2023-02-23 23:19:32,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1720320. Throughput: 0: 868.4. Samples: 430066. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:19:32,683][00448] Avg episode reward: [(0, '6.540')] +[2023-02-23 23:19:32,712][11085] Saving new best policy, reward=6.540! +[2023-02-23 23:19:37,677][00448] Fps is (10 sec: 3278.0, 60 sec: 3550.0, 300 sec: 3623.9). Total num frames: 1740800. Throughput: 0: 900.5. Samples: 435266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:19:37,680][00448] Avg episode reward: [(0, '6.306')] +[2023-02-23 23:19:42,083][11099] Updated weights for policy 0, policy_version 430 (0.0015) +[2023-02-23 23:19:42,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 1761280. Throughput: 0: 927.8. Samples: 438436. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:19:42,682][00448] Avg episode reward: [(0, '6.460')] +[2023-02-23 23:19:47,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 1777664. Throughput: 0: 930.8. Samples: 444398. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:19:47,681][00448] Avg episode reward: [(0, '6.551')] +[2023-02-23 23:19:47,695][11085] Saving new best policy, reward=6.551! +[2023-02-23 23:19:52,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1794048. Throughput: 0: 876.4. Samples: 448594. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:19:52,682][00448] Avg episode reward: [(0, '6.445')] +[2023-02-23 23:19:54,441][11099] Updated weights for policy 0, policy_version 440 (0.0014) +[2023-02-23 23:19:57,678][00448] Fps is (10 sec: 3686.0, 60 sec: 3686.3, 300 sec: 3651.7). Total num frames: 1814528. Throughput: 0: 887.0. Samples: 451392. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:19:57,683][00448] Avg episode reward: [(0, '7.097')] +[2023-02-23 23:19:57,694][11085] Saving new best policy, reward=7.097! +[2023-02-23 23:20:02,679][00448] Fps is (10 sec: 4095.1, 60 sec: 3686.3, 300 sec: 3665.5). Total num frames: 1835008. Throughput: 0: 938.8. Samples: 457962. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:20:02,685][00448] Avg episode reward: [(0, '7.742')] +[2023-02-23 23:20:02,689][11085] Saving new best policy, reward=7.742! +[2023-02-23 23:20:04,323][11099] Updated weights for policy 0, policy_version 450 (0.0011) +[2023-02-23 23:20:07,677][00448] Fps is (10 sec: 3686.8, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 1851392. Throughput: 0: 908.0. Samples: 463118. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:20:07,682][00448] Avg episode reward: [(0, '8.163')] +[2023-02-23 23:20:07,696][11085] Saving new best policy, reward=8.163! +[2023-02-23 23:20:12,677][00448] Fps is (10 sec: 3277.5, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1867776. Throughput: 0: 881.3. Samples: 465168. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:12,680][00448] Avg episode reward: [(0, '7.221')] +[2023-02-23 23:20:16,116][11099] Updated weights for policy 0, policy_version 460 (0.0027) +[2023-02-23 23:20:17,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1888256. Throughput: 0: 912.8. Samples: 471142. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:20:17,684][00448] Avg episode reward: [(0, '6.704')] +[2023-02-23 23:20:22,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1908736. Throughput: 0: 940.7. Samples: 477598. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:22,684][00448] Avg episode reward: [(0, '7.189')] +[2023-02-23 23:20:27,472][11099] Updated weights for policy 0, policy_version 470 (0.0014) +[2023-02-23 23:20:27,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3665.6). Total num frames: 1925120. Throughput: 0: 918.9. Samples: 479786. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:27,681][00448] Avg episode reward: [(0, '7.623')] +[2023-02-23 23:20:32,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1941504. Throughput: 0: 887.2. Samples: 484322. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:32,679][00448] Avg episode reward: [(0, '8.474')] +[2023-02-23 23:20:32,687][11085] Saving new best policy, reward=8.474! +[2023-02-23 23:20:37,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1961984. Throughput: 0: 936.8. Samples: 490750. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:37,683][00448] Avg episode reward: [(0, '8.259')] +[2023-02-23 23:20:38,037][11099] Updated weights for policy 0, policy_version 480 (0.0013) +[2023-02-23 23:20:42,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1982464. Throughput: 0: 947.1. Samples: 494012. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:20:42,679][00448] Avg episode reward: [(0, '8.366')] +[2023-02-23 23:20:47,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 1994752. Throughput: 0: 899.7. Samples: 498446. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:20:47,680][00448] Avg episode reward: [(0, '8.088')] +[2023-02-23 23:20:50,144][11099] Updated weights for policy 0, policy_version 490 (0.0011) +[2023-02-23 23:20:52,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2015232. Throughput: 0: 909.6. Samples: 504048. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:20:52,682][00448] Avg episode reward: [(0, '8.475')] +[2023-02-23 23:20:57,677][00448] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2039808. Throughput: 0: 933.9. Samples: 507192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:20:57,689][00448] Avg episode reward: [(0, '8.439')] +[2023-02-23 23:21:00,236][11099] Updated weights for policy 0, policy_version 500 (0.0018) +[2023-02-23 23:21:02,677][00448] Fps is (10 sec: 3686.3, 60 sec: 3618.2, 300 sec: 3665.6). Total num frames: 2052096. Throughput: 0: 929.9. Samples: 512990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:21:02,683][00448] Avg episode reward: [(0, '8.589')] +[2023-02-23 23:21:02,685][11085] Saving new best policy, reward=8.589! +[2023-02-23 23:21:07,677][00448] Fps is (10 sec: 2867.3, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2068480. Throughput: 0: 881.0. Samples: 517242. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:21:07,679][00448] Avg episode reward: [(0, '8.642')] +[2023-02-23 23:21:07,692][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth... +[2023-02-23 23:21:07,810][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000292_1196032.pth +[2023-02-23 23:21:07,828][11085] Saving new best policy, reward=8.642! +[2023-02-23 23:21:12,094][11099] Updated weights for policy 0, policy_version 510 (0.0016) +[2023-02-23 23:21:12,677][00448] Fps is (10 sec: 3686.6, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2088960. Throughput: 0: 901.4. Samples: 520350. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:21:12,679][00448] Avg episode reward: [(0, '9.510')] +[2023-02-23 23:21:12,689][11085] Saving new best policy, reward=9.510! +[2023-02-23 23:21:17,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2109440. Throughput: 0: 946.7. Samples: 526922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:21:17,683][00448] Avg episode reward: [(0, '9.439')] +[2023-02-23 23:21:22,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2125824. Throughput: 0: 911.9. Samples: 531784. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:21:22,683][00448] Avg episode reward: [(0, '8.940')] +[2023-02-23 23:21:23,563][11099] Updated weights for policy 0, policy_version 520 (0.0011) +[2023-02-23 23:21:27,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 2142208. Throughput: 0: 888.4. Samples: 533988. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:21:27,683][00448] Avg episode reward: [(0, '8.812')] +[2023-02-23 23:21:32,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2166784. Throughput: 0: 933.4. Samples: 540450. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:21:32,680][00448] Avg episode reward: [(0, '9.224')] +[2023-02-23 23:21:33,481][11099] Updated weights for policy 0, policy_version 530 (0.0020) +[2023-02-23 23:21:37,678][00448] Fps is (10 sec: 4095.4, 60 sec: 3686.3, 300 sec: 3665.6). Total num frames: 2183168. Throughput: 0: 936.5. Samples: 546194. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:21:37,691][00448] Avg episode reward: [(0, '10.552')] +[2023-02-23 23:21:37,703][11085] Saving new best policy, reward=10.552! +[2023-02-23 23:21:42,677][00448] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3651.7). Total num frames: 2195456. Throughput: 0: 912.8. Samples: 548268. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:21:42,684][00448] Avg episode reward: [(0, '10.440')] +[2023-02-23 23:21:45,840][11099] Updated weights for policy 0, policy_version 540 (0.0021) +[2023-02-23 23:21:47,677][00448] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2215936. Throughput: 0: 898.5. Samples: 553422. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:21:47,679][00448] Avg episode reward: [(0, '10.709')] +[2023-02-23 23:21:47,690][11085] Saving new best policy, reward=10.709! +[2023-02-23 23:21:52,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2240512. Throughput: 0: 948.6. Samples: 559930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:21:52,680][00448] Avg episode reward: [(0, '11.159')] +[2023-02-23 23:21:52,684][11085] Saving new best policy, reward=11.159! +[2023-02-23 23:21:55,596][11099] Updated weights for policy 0, policy_version 550 (0.0012) +[2023-02-23 23:21:57,680][00448] Fps is (10 sec: 4094.9, 60 sec: 3618.0, 300 sec: 3665.5). Total num frames: 2256896. Throughput: 0: 946.7. Samples: 562956. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:21:57,682][00448] Avg episode reward: [(0, '11.256')] +[2023-02-23 23:21:57,701][11085] Saving new best policy, reward=11.256! +[2023-02-23 23:22:02,677][00448] Fps is (10 sec: 2867.1, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 2269184. Throughput: 0: 894.5. Samples: 567176. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:22:02,680][00448] Avg episode reward: [(0, '12.031')] +[2023-02-23 23:22:02,683][11085] Saving new best policy, reward=12.031! +[2023-02-23 23:22:07,510][11099] Updated weights for policy 0, policy_version 560 (0.0011) +[2023-02-23 23:22:07,677][00448] Fps is (10 sec: 3687.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 2293760. Throughput: 0: 919.6. Samples: 573168. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:22:07,679][00448] Avg episode reward: [(0, '14.228')] +[2023-02-23 23:22:07,688][11085] Saving new best policy, reward=14.228! +[2023-02-23 23:22:12,679][00448] Fps is (10 sec: 4505.0, 60 sec: 3754.6, 300 sec: 3665.6). Total num frames: 2314240. Throughput: 0: 941.4. Samples: 576352. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:22:12,684][00448] Avg episode reward: [(0, '14.440')] +[2023-02-23 23:22:12,690][11085] Saving new best policy, reward=14.440! +[2023-02-23 23:22:17,679][00448] Fps is (10 sec: 3276.0, 60 sec: 3618.0, 300 sec: 3651.7). Total num frames: 2326528. Throughput: 0: 916.3. Samples: 581684. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:22:17,685][00448] Avg episode reward: [(0, '14.446')] +[2023-02-23 23:22:17,713][11085] Saving new best policy, reward=14.446! +[2023-02-23 23:22:19,108][11099] Updated weights for policy 0, policy_version 570 (0.0022) +[2023-02-23 23:22:22,677][00448] Fps is (10 sec: 3277.3, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 2347008. Throughput: 0: 893.6. Samples: 586404. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:22:22,682][00448] Avg episode reward: [(0, '14.675')] +[2023-02-23 23:22:22,685][11085] Saving new best policy, reward=14.675! +[2023-02-23 23:22:27,677][00448] Fps is (10 sec: 4097.0, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2367488. Throughput: 0: 921.5. Samples: 589734. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:22:27,679][00448] Avg episode reward: [(0, '14.480')] +[2023-02-23 23:22:29,450][11099] Updated weights for policy 0, policy_version 580 (0.0014) +[2023-02-23 23:22:32,680][00448] Fps is (10 sec: 3685.1, 60 sec: 3617.9, 300 sec: 3637.8). Total num frames: 2383872. Throughput: 0: 945.9. Samples: 595992. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:22:32,683][00448] Avg episode reward: [(0, '15.685')] +[2023-02-23 23:22:32,685][11085] Saving new best policy, reward=15.685! +[2023-02-23 23:22:37,677][00448] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 2396160. Throughput: 0: 878.9. Samples: 599480. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-23 23:22:37,680][00448] Avg episode reward: [(0, '15.326')] +[2023-02-23 23:22:42,677][00448] Fps is (10 sec: 2458.5, 60 sec: 3549.9, 300 sec: 3596.1). Total num frames: 2408448. Throughput: 0: 851.4. Samples: 601266. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-23 23:22:42,684][00448] Avg episode reward: [(0, '15.809')] +[2023-02-23 23:22:42,687][11085] Saving new best policy, reward=15.809! +[2023-02-23 23:22:44,777][11099] Updated weights for policy 0, policy_version 590 (0.0015) +[2023-02-23 23:22:47,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3596.2). Total num frames: 2428928. Throughput: 0: 858.8. Samples: 605824. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:22:47,683][00448] Avg episode reward: [(0, '17.286')] +[2023-02-23 23:22:47,693][11085] Saving new best policy, reward=17.286! +[2023-02-23 23:22:52,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 2449408. Throughput: 0: 874.5. Samples: 612522. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:22:52,683][00448] Avg episode reward: [(0, '16.911')] +[2023-02-23 23:22:54,184][11099] Updated weights for policy 0, policy_version 600 (0.0012) +[2023-02-23 23:22:57,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3596.1). Total num frames: 2465792. Throughput: 0: 871.2. Samples: 615556. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-23 23:22:57,685][00448] Avg episode reward: [(0, '16.729')] +[2023-02-23 23:23:02,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2482176. Throughput: 0: 851.3. Samples: 619990. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:23:02,679][00448] Avg episode reward: [(0, '16.567')] +[2023-02-23 23:23:05,901][11099] Updated weights for policy 0, policy_version 610 (0.0017) +[2023-02-23 23:23:07,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3596.1). Total num frames: 2502656. Throughput: 0: 882.0. Samples: 626096. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:07,679][00448] Avg episode reward: [(0, '17.245')] +[2023-02-23 23:23:07,742][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000612_2506752.pth... +[2023-02-23 23:23:07,842][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000400_1638400.pth +[2023-02-23 23:23:12,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3481.7, 300 sec: 3623.9). Total num frames: 2523136. Throughput: 0: 875.8. Samples: 629146. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:12,679][00448] Avg episode reward: [(0, '16.824')] +[2023-02-23 23:23:17,606][11099] Updated weights for policy 0, policy_version 620 (0.0025) +[2023-02-23 23:23:17,683][00448] Fps is (10 sec: 3684.3, 60 sec: 3549.7, 300 sec: 3610.0). Total num frames: 2539520. Throughput: 0: 848.6. Samples: 634182. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:17,685][00448] Avg episode reward: [(0, '15.652')] +[2023-02-23 23:23:22,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3582.3). Total num frames: 2555904. Throughput: 0: 868.6. Samples: 638568. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:22,686][00448] Avg episode reward: [(0, '16.224')] +[2023-02-23 23:23:27,677][00448] Fps is (10 sec: 3688.5, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 2576384. Throughput: 0: 897.3. Samples: 641644. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:27,682][00448] Avg episode reward: [(0, '16.194')] +[2023-02-23 23:23:28,759][11099] Updated weights for policy 0, policy_version 630 (0.0013) +[2023-02-23 23:23:32,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3610.1). Total num frames: 2592768. Throughput: 0: 937.0. Samples: 647990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-23 23:23:32,679][00448] Avg episode reward: [(0, '16.252')] +[2023-02-23 23:23:37,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3582.3). Total num frames: 2609152. Throughput: 0: 889.0. Samples: 652526. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:23:37,679][00448] Avg episode reward: [(0, '17.013')] +[2023-02-23 23:23:40,691][11099] Updated weights for policy 0, policy_version 640 (0.0013) +[2023-02-23 23:23:42,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2629632. Throughput: 0: 871.5. Samples: 654772. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:23:42,682][00448] Avg episode reward: [(0, '17.431')] +[2023-02-23 23:23:42,685][11085] Saving new best policy, reward=17.431! +[2023-02-23 23:23:47,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 2650112. Throughput: 0: 920.8. Samples: 661426. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:23:47,684][00448] Avg episode reward: [(0, '18.032')] +[2023-02-23 23:23:47,693][11085] Saving new best policy, reward=18.032! +[2023-02-23 23:23:50,177][11099] Updated weights for policy 0, policy_version 650 (0.0017) +[2023-02-23 23:23:52,681][00448] Fps is (10 sec: 3684.7, 60 sec: 3617.9, 300 sec: 3637.7). Total num frames: 2666496. Throughput: 0: 914.3. Samples: 667244. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:23:52,684][00448] Avg episode reward: [(0, '17.729')] +[2023-02-23 23:23:57,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 2682880. Throughput: 0: 896.7. Samples: 669500. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:23:57,680][00448] Avg episode reward: [(0, '17.311')] +[2023-02-23 23:24:02,063][11099] Updated weights for policy 0, policy_version 660 (0.0012) +[2023-02-23 23:24:02,677][00448] Fps is (10 sec: 3688.1, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 2703360. Throughput: 0: 907.9. Samples: 675034. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:24:02,679][00448] Avg episode reward: [(0, '17.448')] +[2023-02-23 23:24:07,677][00448] Fps is (10 sec: 4505.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 2727936. Throughput: 0: 960.4. Samples: 681784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:24:07,682][00448] Avg episode reward: [(0, '18.755')] +[2023-02-23 23:24:07,693][11085] Saving new best policy, reward=18.755! +[2023-02-23 23:24:12,542][11099] Updated weights for policy 0, policy_version 670 (0.0011) +[2023-02-23 23:24:12,679][00448] Fps is (10 sec: 4094.9, 60 sec: 3686.2, 300 sec: 3651.7). Total num frames: 2744320. Throughput: 0: 951.6. Samples: 684468. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:24:12,684][00448] Avg episode reward: [(0, '19.476')] +[2023-02-23 23:24:12,686][11085] Saving new best policy, reward=19.476! +[2023-02-23 23:24:17,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.7, 300 sec: 3637.8). Total num frames: 2760704. Throughput: 0: 909.0. Samples: 688894. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:24:17,683][00448] Avg episode reward: [(0, '20.182')] +[2023-02-23 23:24:17,693][11085] Saving new best policy, reward=20.182! +[2023-02-23 23:24:22,677][00448] Fps is (10 sec: 3687.4, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2781184. Throughput: 0: 952.3. Samples: 695378. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:24:22,679][00448] Avg episode reward: [(0, '19.606')] +[2023-02-23 23:24:23,047][11099] Updated weights for policy 0, policy_version 680 (0.0015) +[2023-02-23 23:24:27,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2801664. Throughput: 0: 976.2. Samples: 698702. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-02-23 23:24:27,680][00448] Avg episode reward: [(0, '18.898')] +[2023-02-23 23:24:32,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 2818048. Throughput: 0: 940.6. Samples: 703752. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:24:32,681][00448] Avg episode reward: [(0, '18.364')] +[2023-02-23 23:24:35,106][11099] Updated weights for policy 0, policy_version 690 (0.0015) +[2023-02-23 23:24:37,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3637.8). Total num frames: 2834432. Throughput: 0: 926.9. Samples: 708950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:24:37,685][00448] Avg episode reward: [(0, '17.754')] +[2023-02-23 23:24:42,677][00448] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2859008. Throughput: 0: 952.1. Samples: 712342. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:24:42,679][00448] Avg episode reward: [(0, '18.640')] +[2023-02-23 23:24:44,029][11099] Updated weights for policy 0, policy_version 700 (0.0020) +[2023-02-23 23:24:47,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 2875392. Throughput: 0: 971.7. Samples: 718760. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:24:47,683][00448] Avg episode reward: [(0, '18.454')] +[2023-02-23 23:24:52,678][00448] Fps is (10 sec: 3276.5, 60 sec: 3754.9, 300 sec: 3651.7). Total num frames: 2891776. Throughput: 0: 921.1. Samples: 723234. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:24:52,684][00448] Avg episode reward: [(0, '18.099')] +[2023-02-23 23:24:56,053][11099] Updated weights for policy 0, policy_version 710 (0.0013) +[2023-02-23 23:24:57,677][00448] Fps is (10 sec: 3686.5, 60 sec: 3823.0, 300 sec: 3651.7). Total num frames: 2912256. Throughput: 0: 924.9. Samples: 726088. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:24:57,680][00448] Avg episode reward: [(0, '17.981')] +[2023-02-23 23:25:02,677][00448] Fps is (10 sec: 4096.3, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2932736. Throughput: 0: 969.2. Samples: 732506. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:25:02,680][00448] Avg episode reward: [(0, '16.032')] +[2023-02-23 23:25:07,083][11099] Updated weights for policy 0, policy_version 720 (0.0014) +[2023-02-23 23:25:07,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2949120. Throughput: 0: 938.9. Samples: 737628. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:25:07,679][00448] Avg episode reward: [(0, '16.424')] +[2023-02-23 23:25:07,690][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000720_2949120.pth... +[2023-02-23 23:25:07,806][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth +[2023-02-23 23:25:12,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.6, 300 sec: 3651.7). Total num frames: 2965504. Throughput: 0: 911.2. Samples: 739708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:25:12,681][00448] Avg episode reward: [(0, '17.320')] +[2023-02-23 23:25:17,664][11099] Updated weights for policy 0, policy_version 730 (0.0017) +[2023-02-23 23:25:17,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3822.9, 300 sec: 3665.6). Total num frames: 2990080. Throughput: 0: 935.5. Samples: 745848. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:25:17,679][00448] Avg episode reward: [(0, '18.150')] +[2023-02-23 23:25:22,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3010560. Throughput: 0: 969.8. Samples: 752592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:25:22,679][00448] Avg episode reward: [(0, '19.034')] +[2023-02-23 23:25:27,679][00448] Fps is (10 sec: 3276.0, 60 sec: 3686.3, 300 sec: 3665.5). Total num frames: 3022848. Throughput: 0: 941.5. Samples: 754710. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:25:27,681][00448] Avg episode reward: [(0, '18.429')] +[2023-02-23 23:25:29,791][11099] Updated weights for policy 0, policy_version 740 (0.0020) +[2023-02-23 23:25:32,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 3043328. Throughput: 0: 899.2. Samples: 759226. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:25:32,682][00448] Avg episode reward: [(0, '17.762')] +[2023-02-23 23:25:37,677][00448] Fps is (10 sec: 4097.0, 60 sec: 3823.0, 300 sec: 3665.6). Total num frames: 3063808. Throughput: 0: 947.6. Samples: 765874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:25:37,679][00448] Avg episode reward: [(0, '17.780')] +[2023-02-23 23:25:39,159][11099] Updated weights for policy 0, policy_version 750 (0.0012) +[2023-02-23 23:25:42,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3084288. Throughput: 0: 958.5. Samples: 769222. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:25:42,684][00448] Avg episode reward: [(0, '17.623')] +[2023-02-23 23:25:47,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3096576. Throughput: 0: 916.9. Samples: 773766. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:25:47,680][00448] Avg episode reward: [(0, '17.530')] +[2023-02-23 23:25:51,047][11099] Updated weights for policy 0, policy_version 760 (0.0020) +[2023-02-23 23:25:52,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 3117056. Throughput: 0: 930.4. Samples: 779496. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:25:52,679][00448] Avg episode reward: [(0, '18.780')] +[2023-02-23 23:25:57,677][00448] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 3137536. Throughput: 0: 955.6. Samples: 782708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:25:57,680][00448] Avg episode reward: [(0, '19.732')] +[2023-02-23 23:26:01,626][11099] Updated weights for policy 0, policy_version 770 (0.0019) +[2023-02-23 23:26:02,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3153920. Throughput: 0: 945.7. Samples: 788406. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:26:02,683][00448] Avg episode reward: [(0, '19.363')] +[2023-02-23 23:26:07,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3170304. Throughput: 0: 895.4. Samples: 792886. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:26:07,679][00448] Avg episode reward: [(0, '20.404')] +[2023-02-23 23:26:07,694][11085] Saving new best policy, reward=20.404! +[2023-02-23 23:26:12,628][11099] Updated weights for policy 0, policy_version 780 (0.0015) +[2023-02-23 23:26:12,677][00448] Fps is (10 sec: 4096.1, 60 sec: 3822.9, 300 sec: 3679.5). Total num frames: 3194880. Throughput: 0: 920.6. Samples: 796136. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:12,679][00448] Avg episode reward: [(0, '20.820')] +[2023-02-23 23:26:12,682][11085] Saving new best policy, reward=20.820! +[2023-02-23 23:26:17,680][00448] Fps is (10 sec: 4504.0, 60 sec: 3754.4, 300 sec: 3693.3). Total num frames: 3215360. Throughput: 0: 967.7. Samples: 802778. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:17,685][00448] Avg episode reward: [(0, '21.613')] +[2023-02-23 23:26:17,699][11085] Saving new best policy, reward=21.613! +[2023-02-23 23:26:22,681][00448] Fps is (10 sec: 3275.3, 60 sec: 3617.9, 300 sec: 3679.4). Total num frames: 3227648. Throughput: 0: 920.2. Samples: 807288. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:26:22,685][00448] Avg episode reward: [(0, '21.879')] +[2023-02-23 23:26:22,692][11085] Saving new best policy, reward=21.879! +[2023-02-23 23:26:25,203][11099] Updated weights for policy 0, policy_version 790 (0.0011) +[2023-02-23 23:26:27,678][00448] Fps is (10 sec: 2458.1, 60 sec: 3618.2, 300 sec: 3637.8). Total num frames: 3239936. Throughput: 0: 886.3. Samples: 809106. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:26:27,683][00448] Avg episode reward: [(0, '21.070')] +[2023-02-23 23:26:32,677][00448] Fps is (10 sec: 2868.5, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3256320. Throughput: 0: 873.0. Samples: 813052. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:32,684][00448] Avg episode reward: [(0, '21.017')] +[2023-02-23 23:26:36,890][11099] Updated weights for policy 0, policy_version 800 (0.0019) +[2023-02-23 23:26:37,677][00448] Fps is (10 sec: 3687.0, 60 sec: 3549.9, 300 sec: 3665.6). Total num frames: 3276800. Throughput: 0: 893.0. Samples: 819682. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:37,679][00448] Avg episode reward: [(0, '19.728')] +[2023-02-23 23:26:42,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3293184. Throughput: 0: 882.4. Samples: 822416. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:42,683][00448] Avg episode reward: [(0, '18.310')] +[2023-02-23 23:26:47,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3623.9). Total num frames: 3309568. Throughput: 0: 850.4. Samples: 826672. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:47,680][00448] Avg episode reward: [(0, '18.071')] +[2023-02-23 23:26:49,141][11099] Updated weights for policy 0, policy_version 810 (0.0038) +[2023-02-23 23:26:52,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3334144. Throughput: 0: 891.7. Samples: 833012. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:26:52,679][00448] Avg episode reward: [(0, '18.272')] +[2023-02-23 23:26:57,677][00448] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 3354624. Throughput: 0: 895.6. Samples: 836438. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:26:57,684][00448] Avg episode reward: [(0, '18.611')] +[2023-02-23 23:26:58,650][11099] Updated weights for policy 0, policy_version 820 (0.0022) +[2023-02-23 23:27:02,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3637.8). Total num frames: 3366912. Throughput: 0: 863.9. Samples: 841650. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:02,681][00448] Avg episode reward: [(0, '18.252')] +[2023-02-23 23:27:07,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 3387392. Throughput: 0: 879.7. Samples: 846872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:27:07,680][00448] Avg episode reward: [(0, '18.671')] +[2023-02-23 23:27:07,690][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000827_3387392.pth... +[2023-02-23 23:27:07,806][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000612_2506752.pth +[2023-02-23 23:27:09,950][11099] Updated weights for policy 0, policy_version 830 (0.0012) +[2023-02-23 23:27:12,677][00448] Fps is (10 sec: 4095.9, 60 sec: 3549.8, 300 sec: 3665.6). Total num frames: 3407872. Throughput: 0: 913.0. Samples: 850192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:27:12,685][00448] Avg episode reward: [(0, '21.207')] +[2023-02-23 23:27:17,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3550.1, 300 sec: 3665.6). Total num frames: 3428352. Throughput: 0: 969.6. Samples: 856684. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:27:17,684][00448] Avg episode reward: [(0, '21.281')] +[2023-02-23 23:27:21,266][11099] Updated weights for policy 0, policy_version 840 (0.0011) +[2023-02-23 23:27:22,677][00448] Fps is (10 sec: 3686.3, 60 sec: 3618.4, 300 sec: 3651.7). Total num frames: 3444736. Throughput: 0: 920.3. Samples: 861098. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:22,689][00448] Avg episode reward: [(0, '21.938')] +[2023-02-23 23:27:22,693][11085] Saving new best policy, reward=21.938! +[2023-02-23 23:27:27,677][00448] Fps is (10 sec: 3276.7, 60 sec: 3686.5, 300 sec: 3651.7). Total num frames: 3461120. Throughput: 0: 915.1. Samples: 863596. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:27,685][00448] Avg episode reward: [(0, '21.966')] +[2023-02-23 23:27:27,703][11085] Saving new best policy, reward=21.966! +[2023-02-23 23:27:31,787][11099] Updated weights for policy 0, policy_version 850 (0.0011) +[2023-02-23 23:27:32,677][00448] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 3481600. Throughput: 0: 958.5. Samples: 869804. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:27:32,684][00448] Avg episode reward: [(0, '20.330')] +[2023-02-23 23:27:37,677][00448] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3497984. Throughput: 0: 932.9. Samples: 874994. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:37,681][00448] Avg episode reward: [(0, '19.176')] +[2023-02-23 23:27:42,680][00448] Fps is (10 sec: 3275.9, 60 sec: 3686.2, 300 sec: 3679.4). Total num frames: 3514368. Throughput: 0: 906.4. Samples: 877228. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:42,682][00448] Avg episode reward: [(0, '17.990')] +[2023-02-23 23:27:44,014][11099] Updated weights for policy 0, policy_version 860 (0.0018) +[2023-02-23 23:27:47,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 3534848. Throughput: 0: 923.2. Samples: 883196. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:47,686][00448] Avg episode reward: [(0, '16.382')] +[2023-02-23 23:27:52,683][00448] Fps is (10 sec: 4503.9, 60 sec: 3754.3, 300 sec: 3707.1). Total num frames: 3559424. Throughput: 0: 953.4. Samples: 889780. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:52,691][00448] Avg episode reward: [(0, '17.212')] +[2023-02-23 23:27:53,724][11099] Updated weights for policy 0, policy_version 870 (0.0011) +[2023-02-23 23:27:57,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3571712. Throughput: 0: 929.5. Samples: 892020. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:27:57,680][00448] Avg episode reward: [(0, '18.457')] +[2023-02-23 23:28:02,677][00448] Fps is (10 sec: 3278.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3592192. Throughput: 0: 885.1. Samples: 896514. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:28:02,680][00448] Avg episode reward: [(0, '19.120')] +[2023-02-23 23:28:05,407][11099] Updated weights for policy 0, policy_version 880 (0.0011) +[2023-02-23 23:28:07,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 3612672. Throughput: 0: 935.4. Samples: 903192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:28:07,682][00448] Avg episode reward: [(0, '19.948')] +[2023-02-23 23:28:12,677][00448] Fps is (10 sec: 4096.1, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 3633152. Throughput: 0: 952.9. Samples: 906474. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:28:12,682][00448] Avg episode reward: [(0, '21.699')] +[2023-02-23 23:28:16,475][11099] Updated weights for policy 0, policy_version 890 (0.0013) +[2023-02-23 23:28:17,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3645440. Throughput: 0: 919.0. Samples: 911160. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:28:17,683][00448] Avg episode reward: [(0, '22.236')] +[2023-02-23 23:28:17,694][11085] Saving new best policy, reward=22.236! +[2023-02-23 23:28:22,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3665920. Throughput: 0: 926.3. Samples: 916676. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-02-23 23:28:22,682][00448] Avg episode reward: [(0, '22.584')] +[2023-02-23 23:28:22,685][11085] Saving new best policy, reward=22.584! +[2023-02-23 23:28:26,702][11099] Updated weights for policy 0, policy_version 900 (0.0015) +[2023-02-23 23:28:27,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3686400. Throughput: 0: 948.4. Samples: 919904. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:28:27,683][00448] Avg episode reward: [(0, '22.822')] +[2023-02-23 23:28:27,698][11085] Saving new best policy, reward=22.822! +[2023-02-23 23:28:32,677][00448] Fps is (10 sec: 3686.2, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 3702784. Throughput: 0: 940.7. Samples: 925530. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:28:32,682][00448] Avg episode reward: [(0, '23.394')] +[2023-02-23 23:28:32,685][11085] Saving new best policy, reward=23.394! +[2023-02-23 23:28:37,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3719168. Throughput: 0: 887.2. Samples: 929698. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:28:37,680][00448] Avg episode reward: [(0, '22.679')] +[2023-02-23 23:28:39,423][11099] Updated weights for policy 0, policy_version 910 (0.0012) +[2023-02-23 23:28:42,677][00448] Fps is (10 sec: 3686.6, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 3739648. Throughput: 0: 904.2. Samples: 932708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:28:42,680][00448] Avg episode reward: [(0, '22.645')] +[2023-02-23 23:28:47,681][00448] Fps is (10 sec: 4094.6, 60 sec: 3754.4, 300 sec: 3707.2). Total num frames: 3760128. Throughput: 0: 947.3. Samples: 939146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:28:47,683][00448] Avg episode reward: [(0, '21.734')] +[2023-02-23 23:28:49,670][11099] Updated weights for policy 0, policy_version 920 (0.0014) +[2023-02-23 23:28:52,682][00448] Fps is (10 sec: 3275.0, 60 sec: 3549.9, 300 sec: 3693.3). Total num frames: 3772416. Throughput: 0: 903.9. Samples: 943874. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-02-23 23:28:52,685][00448] Avg episode reward: [(0, '21.531')] +[2023-02-23 23:28:57,677][00448] Fps is (10 sec: 3278.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3792896. Throughput: 0: 881.7. Samples: 946150. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) +[2023-02-23 23:28:57,685][00448] Avg episode reward: [(0, '21.153')] +[2023-02-23 23:29:00,985][11099] Updated weights for policy 0, policy_version 930 (0.0013) +[2023-02-23 23:29:02,677][00448] Fps is (10 sec: 4098.3, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3813376. Throughput: 0: 919.5. Samples: 952536. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:29:02,680][00448] Avg episode reward: [(0, '19.943')] +[2023-02-23 23:29:07,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.4). Total num frames: 3833856. Throughput: 0: 935.6. Samples: 958776. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:07,680][00448] Avg episode reward: [(0, '19.738')] +[2023-02-23 23:29:07,694][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000936_3833856.pth... +[2023-02-23 23:29:07,819][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000720_2949120.pth +[2023-02-23 23:29:12,680][00448] Fps is (10 sec: 3275.9, 60 sec: 3549.7, 300 sec: 3679.4). Total num frames: 3846144. Throughput: 0: 911.5. Samples: 960922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:29:12,687][00448] Avg episode reward: [(0, '20.773')] +[2023-02-23 23:29:12,881][11099] Updated weights for policy 0, policy_version 940 (0.0021) +[2023-02-23 23:29:17,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3866624. Throughput: 0: 895.7. Samples: 965836. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:29:17,685][00448] Avg episode reward: [(0, '19.710')] +[2023-02-23 23:29:22,587][11099] Updated weights for policy 0, policy_version 950 (0.0015) +[2023-02-23 23:29:22,678][00448] Fps is (10 sec: 4506.1, 60 sec: 3754.6, 300 sec: 3693.3). Total num frames: 3891200. Throughput: 0: 948.5. Samples: 972384. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:22,685][00448] Avg episode reward: [(0, '19.276')] +[2023-02-23 23:29:27,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 3907584. Throughput: 0: 948.9. Samples: 975410. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:27,682][00448] Avg episode reward: [(0, '19.610')] +[2023-02-23 23:29:32,677][00448] Fps is (10 sec: 2867.6, 60 sec: 3618.2, 300 sec: 3679.5). Total num frames: 3919872. Throughput: 0: 897.9. Samples: 979550. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:32,687][00448] Avg episode reward: [(0, '19.652')] +[2023-02-23 23:29:35,166][11099] Updated weights for policy 0, policy_version 960 (0.0017) +[2023-02-23 23:29:37,677][00448] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 3940352. Throughput: 0: 922.0. Samples: 985360. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:37,679][00448] Avg episode reward: [(0, '18.707')] +[2023-02-23 23:29:42,677][00448] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 3960832. Throughput: 0: 942.9. Samples: 988580. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:29:42,685][00448] Avg episode reward: [(0, '20.170')] +[2023-02-23 23:29:45,161][11099] Updated weights for policy 0, policy_version 970 (0.0012) +[2023-02-23 23:29:47,677][00448] Fps is (10 sec: 3686.4, 60 sec: 3618.3, 300 sec: 3679.5). Total num frames: 3977216. Throughput: 0: 923.9. Samples: 994112. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-02-23 23:29:47,680][00448] Avg episode reward: [(0, '20.482')] +[2023-02-23 23:29:52,693][00448] Fps is (10 sec: 3680.5, 60 sec: 3754.0, 300 sec: 3679.3). Total num frames: 3997696. Throughput: 0: 889.9. Samples: 998834. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-02-23 23:29:52,695][00448] Avg episode reward: [(0, '20.685')] +[2023-02-23 23:29:54,557][11085] Stopping Batcher_0... +[2023-02-23 23:29:54,558][11085] Loop batcher_evt_loop terminating... +[2023-02-23 23:29:54,560][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-23 23:29:54,558][00448] Component Batcher_0 stopped! +[2023-02-23 23:29:54,562][00448] Component RolloutWorker_w1 process died already! Don't wait for it. +[2023-02-23 23:29:54,570][00448] Component RolloutWorker_w3 process died already! Don't wait for it. +[2023-02-23 23:29:54,608][11099] Weights refcount: 2 0 +[2023-02-23 23:29:54,612][00448] Component InferenceWorker_p0-w0 stopped! +[2023-02-23 23:29:54,616][11099] Stopping InferenceWorker_p0-w0... +[2023-02-23 23:29:54,619][11099] Loop inference_proc0-0_evt_loop terminating... +[2023-02-23 23:29:54,638][00448] Component RolloutWorker_w5 stopped! +[2023-02-23 23:29:54,640][11105] Stopping RolloutWorker_w5... +[2023-02-23 23:29:54,647][00448] Component RolloutWorker_w0 stopped! +[2023-02-23 23:29:54,654][00448] Component RolloutWorker_w7 stopped! +[2023-02-23 23:29:54,657][00448] Component RolloutWorker_w4 stopped! +[2023-02-23 23:29:54,659][11107] Stopping RolloutWorker_w7... +[2023-02-23 23:29:54,643][11105] Loop rollout_proc5_evt_loop terminating... +[2023-02-23 23:29:54,665][11106] Stopping RolloutWorker_w6... +[2023-02-23 23:29:54,665][11106] Loop rollout_proc6_evt_loop terminating... +[2023-02-23 23:29:54,664][00448] Component RolloutWorker_w6 stopped! +[2023-02-23 23:29:54,656][11104] Stopping RolloutWorker_w4... +[2023-02-23 23:29:54,670][11107] Loop rollout_proc7_evt_loop terminating... +[2023-02-23 23:29:54,647][11100] Stopping RolloutWorker_w0... +[2023-02-23 23:29:54,677][11102] Stopping RolloutWorker_w2... +[2023-02-23 23:29:54,678][00448] Component RolloutWorker_w2 stopped! +[2023-02-23 23:29:54,674][11104] Loop rollout_proc4_evt_loop terminating... +[2023-02-23 23:29:54,671][11100] Loop rollout_proc0_evt_loop terminating... +[2023-02-23 23:29:54,679][11102] Loop rollout_proc2_evt_loop terminating... +[2023-02-23 23:29:54,725][11085] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000827_3387392.pth +[2023-02-23 23:29:54,733][11085] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-23 23:29:54,877][11085] Stopping LearnerWorker_p0... +[2023-02-23 23:29:54,876][00448] Component LearnerWorker_p0 stopped! +[2023-02-23 23:29:54,879][11085] Loop learner_proc0_evt_loop terminating... +[2023-02-23 23:29:54,879][00448] Waiting for process learner_proc0 to stop... +[2023-02-23 23:29:56,358][00448] Waiting for process inference_proc0-0 to join... +[2023-02-23 23:29:56,646][00448] Waiting for process rollout_proc0 to join... +[2023-02-23 23:29:57,068][00448] Waiting for process rollout_proc1 to join... +[2023-02-23 23:29:57,069][00448] Waiting for process rollout_proc2 to join... +[2023-02-23 23:29:57,071][00448] Waiting for process rollout_proc3 to join... +[2023-02-23 23:29:57,072][00448] Waiting for process rollout_proc4 to join... +[2023-02-23 23:29:57,073][00448] Waiting for process rollout_proc5 to join... +[2023-02-23 23:29:57,074][00448] Waiting for process rollout_proc6 to join... +[2023-02-23 23:29:57,078][00448] Waiting for process rollout_proc7 to join... +[2023-02-23 23:29:57,079][00448] Batcher 0 profile tree view: +batching: 24.0729, releasing_batches: 0.0315 +[2023-02-23 23:29:57,085][00448] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0000 + wait_policy_total: 504.4362 +update_model: 7.9966 + weight_update: 0.0012 +one_step: 0.0021 + handle_policy_step: 543.1392 + deserialize: 15.4918, stack: 3.3463, obs_to_device_normalize: 124.4127, forward: 263.5132, send_messages: 24.1263 + prepare_outputs: 83.8684 + to_cpu: 52.2079 +[2023-02-23 23:29:57,086][00448] Learner 0 profile tree view: +misc: 0.0060, prepare_batch: 16.1872 +train: 71.7079 + epoch_init: 0.0103, minibatch_init: 0.0067, losses_postprocess: 0.5687, kl_divergence: 0.5242, after_optimizer: 32.0091 + calculate_losses: 25.0010 + losses_init: 0.0035, forward_head: 1.6516, bptt_initial: 16.8612, tail: 0.9269, advantages_returns: 0.2884, losses: 3.1125 + bptt: 1.8923 + bptt_forward_core: 1.8242 + update: 13.0143 + clip: 1.3374 +[2023-02-23 23:29:57,088][00448] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3771, enqueue_policy_requests: 121.3785, env_step: 858.6005, overhead: 22.2514, complete_rollouts: 8.3380 +save_policy_outputs: 22.2601 + split_output_tensors: 10.9670 +[2023-02-23 23:29:57,089][00448] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.3809, enqueue_policy_requests: 246.0122, env_step: 723.8699, overhead: 27.1911, complete_rollouts: 5.0990 +save_policy_outputs: 24.1922 + split_output_tensors: 11.7255 +[2023-02-23 23:29:57,091][00448] Loop Runner_EvtLoop terminating... +[2023-02-23 23:29:57,093][00448] Runner profile tree view: +main_loop: 1125.3538 +[2023-02-23 23:29:57,094][00448] Collected {0: 4005888}, FPS: 3559.7 +[2023-02-23 23:29:57,160][00448] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-23 23:29:57,161][00448] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-23 23:29:57,164][00448] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-23 23:29:57,166][00448] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-23 23:29:57,167][00448] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-23 23:29:57,169][00448] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-23 23:29:57,170][00448] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-02-23 23:29:57,172][00448] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-23 23:29:57,173][00448] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-02-23 23:29:57,175][00448] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-02-23 23:29:57,177][00448] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-23 23:29:57,179][00448] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-23 23:29:57,180][00448] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-23 23:29:57,182][00448] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-23 23:29:57,183][00448] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-23 23:29:57,210][00448] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-02-23 23:29:57,213][00448] RunningMeanStd input shape: (3, 72, 128) +[2023-02-23 23:29:57,216][00448] RunningMeanStd input shape: (1,) +[2023-02-23 23:29:57,231][00448] ConvEncoder: input_channels=3 +[2023-02-23 23:29:57,909][00448] Conv encoder output size: 512 +[2023-02-23 23:29:57,911][00448] Policy head output size: 512 +[2023-02-23 23:30:00,247][00448] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-23 23:30:01,498][00448] Num frames 100... +[2023-02-23 23:30:01,652][00448] Num frames 200... +[2023-02-23 23:30:01,813][00448] Num frames 300... +[2023-02-23 23:30:01,968][00448] Num frames 400... +[2023-02-23 23:30:02,126][00448] Num frames 500... +[2023-02-23 23:30:02,276][00448] Num frames 600... +[2023-02-23 23:30:02,429][00448] Num frames 700... +[2023-02-23 23:30:02,586][00448] Num frames 800... +[2023-02-23 23:30:02,743][00448] Num frames 900... +[2023-02-23 23:30:02,910][00448] Num frames 1000... +[2023-02-23 23:30:03,066][00448] Num frames 1100... +[2023-02-23 23:30:03,221][00448] Num frames 1200... +[2023-02-23 23:30:03,376][00448] Num frames 1300... +[2023-02-23 23:30:03,535][00448] Num frames 1400... +[2023-02-23 23:30:03,608][00448] Avg episode rewards: #0: 31.080, true rewards: #0: 14.080 +[2023-02-23 23:30:03,610][00448] Avg episode reward: 31.080, avg true_objective: 14.080 +[2023-02-23 23:30:03,755][00448] Num frames 1500... +[2023-02-23 23:30:03,913][00448] Num frames 1600... +[2023-02-23 23:30:04,072][00448] Num frames 1700... +[2023-02-23 23:30:04,240][00448] Num frames 1800... +[2023-02-23 23:30:04,406][00448] Num frames 1900... +[2023-02-23 23:30:04,569][00448] Num frames 2000... +[2023-02-23 23:30:04,730][00448] Num frames 2100... +[2023-02-23 23:30:04,893][00448] Num frames 2200... +[2023-02-23 23:30:05,017][00448] Num frames 2300... +[2023-02-23 23:30:05,126][00448] Num frames 2400... +[2023-02-23 23:30:05,246][00448] Num frames 2500... +[2023-02-23 23:30:05,355][00448] Num frames 2600... +[2023-02-23 23:30:05,475][00448] Num frames 2700... +[2023-02-23 23:30:05,584][00448] Num frames 2800... +[2023-02-23 23:30:05,697][00448] Num frames 2900... +[2023-02-23 23:30:05,808][00448] Num frames 3000... +[2023-02-23 23:30:05,924][00448] Num frames 3100... +[2023-02-23 23:30:06,040][00448] Num frames 3200... +[2023-02-23 23:30:06,149][00448] Num frames 3300... +[2023-02-23 23:30:06,268][00448] Num frames 3400... +[2023-02-23 23:30:06,384][00448] Num frames 3500... +[2023-02-23 23:30:06,450][00448] Avg episode rewards: #0: 42.540, true rewards: #0: 17.540 +[2023-02-23 23:30:06,451][00448] Avg episode reward: 42.540, avg true_objective: 17.540 +[2023-02-23 23:30:06,553][00448] Num frames 3600... +[2023-02-23 23:30:06,665][00448] Num frames 3700... +[2023-02-23 23:30:06,785][00448] Num frames 3800... +[2023-02-23 23:30:06,896][00448] Num frames 3900... +[2023-02-23 23:30:07,005][00448] Num frames 4000... +[2023-02-23 23:30:07,114][00448] Num frames 4100... +[2023-02-23 23:30:07,232][00448] Num frames 4200... +[2023-02-23 23:30:07,346][00448] Num frames 4300... +[2023-02-23 23:30:07,493][00448] Num frames 4400... +[2023-02-23 23:30:07,648][00448] Num frames 4500... +[2023-02-23 23:30:07,807][00448] Num frames 4600... +[2023-02-23 23:30:07,964][00448] Num frames 4700... +[2023-02-23 23:30:08,121][00448] Num frames 4800... +[2023-02-23 23:30:08,278][00448] Num frames 4900... +[2023-02-23 23:30:08,447][00448] Num frames 5000... +[2023-02-23 23:30:08,605][00448] Num frames 5100... +[2023-02-23 23:30:08,766][00448] Num frames 5200... +[2023-02-23 23:30:08,937][00448] Num frames 5300... +[2023-02-23 23:30:09,104][00448] Num frames 5400... +[2023-02-23 23:30:09,276][00448] Num frames 5500... +[2023-02-23 23:30:09,440][00448] Num frames 5600... +[2023-02-23 23:30:09,513][00448] Avg episode rewards: #0: 45.359, true rewards: #0: 18.693 +[2023-02-23 23:30:09,516][00448] Avg episode reward: 45.359, avg true_objective: 18.693 +[2023-02-23 23:30:09,673][00448] Num frames 5700... +[2023-02-23 23:30:09,835][00448] Num frames 5800... +[2023-02-23 23:30:09,992][00448] Num frames 5900... +[2023-02-23 23:30:10,170][00448] Num frames 6000... +[2023-02-23 23:30:10,324][00448] Num frames 6100... +[2023-02-23 23:30:10,484][00448] Num frames 6200... +[2023-02-23 23:30:10,641][00448] Num frames 6300... +[2023-02-23 23:30:10,785][00448] Num frames 6400... +[2023-02-23 23:30:10,899][00448] Num frames 6500... +[2023-02-23 23:30:11,015][00448] Num frames 6600... +[2023-02-23 23:30:11,136][00448] Num frames 6700... +[2023-02-23 23:30:11,246][00448] Num frames 6800... +[2023-02-23 23:30:11,355][00448] Num frames 6900... +[2023-02-23 23:30:11,477][00448] Num frames 7000... +[2023-02-23 23:30:11,590][00448] Num frames 7100... +[2023-02-23 23:30:11,701][00448] Num frames 7200... +[2023-02-23 23:30:11,811][00448] Num frames 7300... +[2023-02-23 23:30:11,926][00448] Num frames 7400... +[2023-02-23 23:30:12,020][00448] Avg episode rewards: #0: 45.834, true rewards: #0: 18.585 +[2023-02-23 23:30:12,022][00448] Avg episode reward: 45.834, avg true_objective: 18.585 +[2023-02-23 23:30:12,099][00448] Num frames 7500... +[2023-02-23 23:30:12,211][00448] Num frames 7600... +[2023-02-23 23:30:12,320][00448] Num frames 7700... +[2023-02-23 23:30:12,434][00448] Num frames 7800... +[2023-02-23 23:30:12,544][00448] Num frames 7900... +[2023-02-23 23:30:12,660][00448] Num frames 8000... +[2023-02-23 23:30:12,770][00448] Num frames 8100... +[2023-02-23 23:30:12,882][00448] Num frames 8200... +[2023-02-23 23:30:12,992][00448] Num frames 8300... +[2023-02-23 23:30:13,159][00448] Avg episode rewards: #0: 40.988, true rewards: #0: 16.788 +[2023-02-23 23:30:13,160][00448] Avg episode reward: 40.988, avg true_objective: 16.788 +[2023-02-23 23:30:13,173][00448] Num frames 8400... +[2023-02-23 23:30:13,285][00448] Num frames 8500... +[2023-02-23 23:30:13,394][00448] Num frames 8600... +[2023-02-23 23:30:13,512][00448] Num frames 8700... +[2023-02-23 23:30:13,624][00448] Num frames 8800... +[2023-02-23 23:30:13,734][00448] Num frames 8900... +[2023-02-23 23:30:13,848][00448] Num frames 9000... +[2023-02-23 23:30:13,907][00448] Avg episode rewards: #0: 36.170, true rewards: #0: 15.003 +[2023-02-23 23:30:13,910][00448] Avg episode reward: 36.170, avg true_objective: 15.003 +[2023-02-23 23:30:14,017][00448] Num frames 9100... +[2023-02-23 23:30:14,134][00448] Num frames 9200... +[2023-02-23 23:30:14,244][00448] Num frames 9300... +[2023-02-23 23:30:14,352][00448] Num frames 9400... +[2023-02-23 23:30:14,469][00448] Num frames 9500... +[2023-02-23 23:30:14,582][00448] Num frames 9600... +[2023-02-23 23:30:14,688][00448] Num frames 9700... +[2023-02-23 23:30:14,797][00448] Num frames 9800... +[2023-02-23 23:30:14,905][00448] Num frames 9900... +[2023-02-23 23:30:15,061][00448] Num frames 10000... +[2023-02-23 23:30:15,213][00448] Num frames 10100... +[2023-02-23 23:30:15,402][00448] Avg episode rewards: #0: 34.551, true rewards: #0: 14.551 +[2023-02-23 23:30:15,404][00448] Avg episode reward: 34.551, avg true_objective: 14.551 +[2023-02-23 23:30:15,432][00448] Num frames 10200... +[2023-02-23 23:30:15,598][00448] Num frames 10300... +[2023-02-23 23:30:15,760][00448] Num frames 10400... +[2023-02-23 23:30:15,836][00448] Avg episode rewards: #0: 30.637, true rewards: #0: 13.013 +[2023-02-23 23:30:15,838][00448] Avg episode reward: 30.637, avg true_objective: 13.013 +[2023-02-23 23:30:15,978][00448] Num frames 10500... +[2023-02-23 23:30:16,144][00448] Num frames 10600... +[2023-02-23 23:30:16,298][00448] Num frames 10700... +[2023-02-23 23:30:16,455][00448] Num frames 10800... +[2023-02-23 23:30:16,619][00448] Num frames 10900... +[2023-02-23 23:30:16,775][00448] Num frames 11000... +[2023-02-23 23:30:16,948][00448] Num frames 11100... +[2023-02-23 23:30:17,107][00448] Num frames 11200... +[2023-02-23 23:30:17,262][00448] Num frames 11300... +[2023-02-23 23:30:17,433][00448] Avg episode rewards: #0: 29.633, true rewards: #0: 12.633 +[2023-02-23 23:30:17,436][00448] Avg episode reward: 29.633, avg true_objective: 12.633 +[2023-02-23 23:30:17,483][00448] Num frames 11400... +[2023-02-23 23:30:17,646][00448] Num frames 11500... +[2023-02-23 23:30:17,802][00448] Num frames 11600... +[2023-02-23 23:30:17,956][00448] Num frames 11700... +[2023-02-23 23:30:18,112][00448] Num frames 11800... +[2023-02-23 23:30:18,267][00448] Num frames 11900... +[2023-02-23 23:30:18,395][00448] Num frames 12000... +[2023-02-23 23:30:18,505][00448] Num frames 12100... +[2023-02-23 23:30:18,621][00448] Num frames 12200... +[2023-02-23 23:30:18,735][00448] Num frames 12300... +[2023-02-23 23:30:18,852][00448] Num frames 12400... +[2023-02-23 23:30:18,963][00448] Num frames 12500... +[2023-02-23 23:30:19,073][00448] Num frames 12600... +[2023-02-23 23:30:19,184][00448] Num frames 12700... +[2023-02-23 23:30:19,324][00448] Avg episode rewards: #0: 29.878, true rewards: #0: 12.778 +[2023-02-23 23:30:19,326][00448] Avg episode reward: 29.878, avg true_objective: 12.778 +[2023-02-23 23:31:32,468][00448] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-02-23 23:31:32,895][00448] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-02-23 23:31:32,897][00448] Overriding arg 'num_workers' with value 1 passed from command line +[2023-02-23 23:31:32,900][00448] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-02-23 23:31:32,902][00448] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-02-23 23:31:32,904][00448] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-02-23 23:31:32,906][00448] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-02-23 23:31:32,909][00448] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-02-23 23:31:32,910][00448] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-02-23 23:31:32,911][00448] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-02-23 23:31:32,912][00448] Adding new argument 'hf_repository'='eldraco/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-02-23 23:31:32,913][00448] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-02-23 23:31:32,914][00448] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-02-23 23:31:32,916][00448] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-02-23 23:31:32,917][00448] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-02-23 23:31:32,918][00448] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-02-23 23:31:32,942][00448] RunningMeanStd input shape: (3, 72, 128) +[2023-02-23 23:31:32,945][00448] RunningMeanStd input shape: (1,) +[2023-02-23 23:31:32,963][00448] ConvEncoder: input_channels=3 +[2023-02-23 23:31:33,017][00448] Conv encoder output size: 512 +[2023-02-23 23:31:33,019][00448] Policy head output size: 512 +[2023-02-23 23:31:33,045][00448] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-02-23 23:31:33,763][00448] Num frames 100... +[2023-02-23 23:31:33,913][00448] Num frames 200... +[2023-02-23 23:31:34,066][00448] Num frames 300... +[2023-02-23 23:31:34,229][00448] Num frames 400... +[2023-02-23 23:31:34,378][00448] Num frames 500... +[2023-02-23 23:31:34,533][00448] Num frames 600... +[2023-02-23 23:31:34,684][00448] Num frames 700... +[2023-02-23 23:31:34,836][00448] Num frames 800... +[2023-02-23 23:31:35,014][00448] Num frames 900... +[2023-02-23 23:31:35,165][00448] Num frames 1000... +[2023-02-23 23:31:35,318][00448] Num frames 1100... +[2023-02-23 23:31:35,471][00448] Num frames 1200... +[2023-02-23 23:31:35,632][00448] Num frames 1300... +[2023-02-23 23:31:35,780][00448] Num frames 1400... +[2023-02-23 23:31:35,933][00448] Num frames 1500... +[2023-02-23 23:31:36,089][00448] Num frames 1600... +[2023-02-23 23:31:36,266][00448] Num frames 1700... +[2023-02-23 23:31:36,439][00448] Num frames 1800... +[2023-02-23 23:31:36,613][00448] Num frames 1900... +[2023-02-23 23:31:36,783][00448] Num frames 2000... +[2023-02-23 23:31:36,961][00448] Num frames 2100... +[2023-02-23 23:31:37,016][00448] Avg episode rewards: #0: 54.999, true rewards: #0: 21.000 +[2023-02-23 23:31:37,019][00448] Avg episode reward: 54.999, avg true_objective: 21.000 +[2023-02-23 23:31:37,197][00448] Num frames 2200... +[2023-02-23 23:31:37,397][00448] Num frames 2300... +[2023-02-23 23:31:37,514][00448] Avg episode rewards: #0: 29.120, true rewards: #0: 11.620 +[2023-02-23 23:31:37,516][00448] Avg episode reward: 29.120, avg true_objective: 11.620 +[2023-02-23 23:31:37,680][00448] Num frames 2400... +[2023-02-23 23:31:37,863][00448] Num frames 2500... +[2023-02-23 23:31:38,036][00448] Num frames 2600... +[2023-02-23 23:31:38,188][00448] Num frames 2700... +[2023-02-23 23:31:38,340][00448] Num frames 2800... +[2023-02-23 23:31:38,492][00448] Num frames 2900... +[2023-02-23 23:31:38,646][00448] Num frames 3000... +[2023-02-23 23:31:38,805][00448] Num frames 3100... +[2023-02-23 23:31:38,994][00448] Num frames 3200... +[2023-02-23 23:31:39,180][00448] Avg episode rewards: #0: 27.240, true rewards: #0: 10.907 +[2023-02-23 23:31:39,183][00448] Avg episode reward: 27.240, avg true_objective: 10.907 +[2023-02-23 23:31:39,239][00448] Num frames 3300... +[2023-02-23 23:31:39,422][00448] Num frames 3400... +[2023-02-23 23:31:39,601][00448] Num frames 3500... +[2023-02-23 23:31:39,777][00448] Num frames 3600... +[2023-02-23 23:31:39,951][00448] Num frames 3700... +[2023-02-23 23:31:40,131][00448] Num frames 3800... +[2023-02-23 23:31:40,303][00448] Num frames 3900... +[2023-02-23 23:31:40,475][00448] Num frames 4000... +[2023-02-23 23:31:40,638][00448] Num frames 4100... +[2023-02-23 23:31:40,809][00448] Num frames 4200... +[2023-02-23 23:31:40,980][00448] Num frames 4300... +[2023-02-23 23:31:41,142][00448] Num frames 4400... +[2023-02-23 23:31:41,300][00448] Num frames 4500... +[2023-02-23 23:31:41,457][00448] Num frames 4600... +[2023-02-23 23:31:41,618][00448] Num frames 4700... +[2023-02-23 23:31:41,777][00448] Num frames 4800... +[2023-02-23 23:31:41,941][00448] Num frames 4900... +[2023-02-23 23:31:42,006][00448] Avg episode rewards: #0: 31.260, true rewards: #0: 12.260 +[2023-02-23 23:31:42,008][00448] Avg episode reward: 31.260, avg true_objective: 12.260 +[2023-02-23 23:31:42,169][00448] Num frames 5000... +[2023-02-23 23:31:42,320][00448] Num frames 5100... +[2023-02-23 23:31:42,472][00448] Num frames 5200... +[2023-02-23 23:31:42,636][00448] Num frames 5300... +[2023-02-23 23:31:42,793][00448] Num frames 5400... +[2023-02-23 23:31:42,957][00448] Num frames 5500... +[2023-02-23 23:31:43,079][00448] Num frames 5600... +[2023-02-23 23:31:43,188][00448] Num frames 5700... +[2023-02-23 23:31:43,296][00448] Num frames 5800... +[2023-02-23 23:31:43,407][00448] Num frames 5900... +[2023-02-23 23:31:43,562][00448] Avg episode rewards: #0: 30.578, true rewards: #0: 11.978 +[2023-02-23 23:31:43,563][00448] Avg episode reward: 30.578, avg true_objective: 11.978 +[2023-02-23 23:31:43,578][00448] Num frames 6000... +[2023-02-23 23:31:43,689][00448] Num frames 6100... +[2023-02-23 23:31:43,798][00448] Num frames 6200... +[2023-02-23 23:31:43,914][00448] Num frames 6300... +[2023-02-23 23:31:44,023][00448] Num frames 6400... +[2023-02-23 23:31:44,131][00448] Num frames 6500... +[2023-02-23 23:31:44,238][00448] Num frames 6600... +[2023-02-23 23:31:44,395][00448] Avg episode rewards: #0: 27.322, true rewards: #0: 11.155 +[2023-02-23 23:31:44,397][00448] Avg episode reward: 27.322, avg true_objective: 11.155 +[2023-02-23 23:31:44,409][00448] Num frames 6700... +[2023-02-23 23:31:44,517][00448] Num frames 6800... +[2023-02-23 23:31:44,626][00448] Num frames 6900... +[2023-02-23 23:31:44,737][00448] Num frames 7000... +[2023-02-23 23:31:44,849][00448] Num frames 7100... +[2023-02-23 23:31:44,964][00448] Num frames 7200... +[2023-02-23 23:31:45,073][00448] Num frames 7300... +[2023-02-23 23:31:45,133][00448] Avg episode rewards: #0: 25.290, true rewards: #0: 10.433 +[2023-02-23 23:31:45,136][00448] Avg episode reward: 25.290, avg true_objective: 10.433 +[2023-02-23 23:31:45,240][00448] Num frames 7400... +[2023-02-23 23:31:45,348][00448] Num frames 7500... +[2023-02-23 23:31:45,455][00448] Num frames 7600... +[2023-02-23 23:31:45,566][00448] Num frames 7700... +[2023-02-23 23:31:45,675][00448] Num frames 7800... +[2023-02-23 23:31:45,755][00448] Avg episode rewards: #0: 23.026, true rewards: #0: 9.776 +[2023-02-23 23:31:45,757][00448] Avg episode reward: 23.026, avg true_objective: 9.776 +[2023-02-23 23:31:45,844][00448] Num frames 7900... +[2023-02-23 23:31:45,955][00448] Num frames 8000... +[2023-02-23 23:31:46,062][00448] Num frames 8100... +[2023-02-23 23:31:46,169][00448] Num frames 8200... +[2023-02-23 23:31:46,286][00448] Num frames 8300... +[2023-02-23 23:31:46,393][00448] Num frames 8400... +[2023-02-23 23:31:46,502][00448] Num frames 8500... +[2023-02-23 23:31:46,608][00448] Num frames 8600... +[2023-02-23 23:31:46,721][00448] Num frames 8700... +[2023-02-23 23:31:46,833][00448] Num frames 8800... +[2023-02-23 23:31:46,949][00448] Num frames 8900... +[2023-02-23 23:31:47,057][00448] Num frames 9000... +[2023-02-23 23:31:47,211][00448] Avg episode rewards: #0: 24.101, true rewards: #0: 10.101 +[2023-02-23 23:31:47,213][00448] Avg episode reward: 24.101, avg true_objective: 10.101 +[2023-02-23 23:31:47,227][00448] Num frames 9100... +[2023-02-23 23:31:47,336][00448] Num frames 9200... +[2023-02-23 23:31:47,448][00448] Num frames 9300... +[2023-02-23 23:31:47,556][00448] Num frames 9400... +[2023-02-23 23:31:47,668][00448] Num frames 9500... +[2023-02-23 23:31:47,777][00448] Num frames 9600... +[2023-02-23 23:31:47,886][00448] Num frames 9700... +[2023-02-23 23:31:48,005][00448] Num frames 9800... +[2023-02-23 23:31:48,114][00448] Num frames 9900... +[2023-02-23 23:31:48,223][00448] Num frames 10000... +[2023-02-23 23:31:48,333][00448] Num frames 10100... +[2023-02-23 23:31:48,444][00448] Num frames 10200... +[2023-02-23 23:31:48,556][00448] Num frames 10300... +[2023-02-23 23:31:48,671][00448] Num frames 10400... +[2023-02-23 23:31:48,783][00448] Num frames 10500... +[2023-02-23 23:31:48,907][00448] Num frames 10600... +[2023-02-23 23:31:49,024][00448] Num frames 10700... +[2023-02-23 23:31:49,134][00448] Num frames 10800... +[2023-02-23 23:31:49,246][00448] Num frames 10900... +[2023-02-23 23:31:49,365][00448] Num frames 11000... +[2023-02-23 23:31:49,504][00448] Num frames 11100... +[2023-02-23 23:31:49,660][00448] Avg episode rewards: #0: 26.991, true rewards: #0: 11.191 +[2023-02-23 23:31:49,663][00448] Avg episode reward: 26.991, avg true_objective: 11.191 +[2023-02-23 23:32:55,407][00448] Replay video saved to /content/train_dir/default_experiment/replay.mp4!