| [2023-05-12 14:50:13,520][00161] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-05-12 14:50:13,523][00161] Rollout worker 0 uses device cpu | |
| [2023-05-12 14:50:13,525][00161] Rollout worker 1 uses device cpu | |
| [2023-05-12 14:50:13,530][00161] Rollout worker 2 uses device cpu | |
| [2023-05-12 14:50:13,532][00161] Rollout worker 3 uses device cpu | |
| [2023-05-12 14:50:13,534][00161] Rollout worker 4 uses device cpu | |
| [2023-05-12 14:50:13,535][00161] Rollout worker 5 uses device cpu | |
| [2023-05-12 14:50:13,537][00161] Rollout worker 6 uses device cpu | |
| [2023-05-12 14:50:13,540][00161] Rollout worker 7 uses device cpu | |
| [2023-05-12 14:50:13,679][00161] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 14:50:13,680][00161] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-05-12 14:50:13,711][00161] Starting all processes... | |
| [2023-05-12 14:50:13,712][00161] Starting process learner_proc0 | |
| [2023-05-12 14:50:13,761][00161] Starting all processes... | |
| [2023-05-12 14:50:13,772][00161] Starting process inference_proc0-0 | |
| [2023-05-12 14:50:13,773][00161] Starting process rollout_proc0 | |
| [2023-05-12 14:50:13,774][00161] Starting process rollout_proc1 | |
| [2023-05-12 14:50:13,775][00161] Starting process rollout_proc2 | |
| [2023-05-12 14:50:13,776][00161] Starting process rollout_proc3 | |
| [2023-05-12 14:50:13,776][00161] Starting process rollout_proc4 | |
| [2023-05-12 14:50:13,776][00161] Starting process rollout_proc5 | |
| [2023-05-12 14:50:13,776][00161] Starting process rollout_proc6 | |
| [2023-05-12 14:50:13,776][00161] Starting process rollout_proc7 | |
| [2023-05-12 14:50:25,296][14794] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 14:50:25,299][14794] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-05-12 14:50:25,360][14794] Num visible devices: 1 | |
| [2023-05-12 14:50:25,389][14794] Starting seed is not provided | |
| [2023-05-12 14:50:25,390][14794] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 14:50:25,390][14794] Initializing actor-critic model on device cuda:0 | |
| [2023-05-12 14:50:25,391][14794] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 14:50:25,392][14794] RunningMeanStd input shape: (1,) | |
| [2023-05-12 14:50:25,543][14794] ConvEncoder: input_channels=3 | |
| [2023-05-12 14:50:25,771][14812] Worker 6 uses CPU cores [0] | |
| [2023-05-12 14:50:26,028][14807] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 14:50:26,037][14807] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-05-12 14:50:26,095][14813] Worker 4 uses CPU cores [0] | |
| [2023-05-12 14:50:26,148][14808] Worker 0 uses CPU cores [0] | |
| [2023-05-12 14:50:26,151][14807] Num visible devices: 1 | |
| [2023-05-12 14:50:26,168][14810] Worker 2 uses CPU cores [0] | |
| [2023-05-12 14:50:26,286][14814] Worker 5 uses CPU cores [1] | |
| [2023-05-12 14:50:26,301][14815] Worker 7 uses CPU cores [1] | |
| [2023-05-12 14:50:26,316][14809] Worker 1 uses CPU cores [1] | |
| [2023-05-12 14:50:26,340][14811] Worker 3 uses CPU cores [1] | |
| [2023-05-12 14:50:26,380][14794] Conv encoder output size: 512 | |
| [2023-05-12 14:50:26,380][14794] Policy head output size: 512 | |
| [2023-05-12 14:50:26,395][14794] Created Actor Critic model with architecture: | |
| [2023-05-12 14:50:26,395][14794] 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) | |
| ) | |
| ) | |
| [2023-05-12 14:50:31,481][14794] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-05-12 14:50:31,482][14794] No checkpoints found | |
| [2023-05-12 14:50:31,483][14794] Did not load from checkpoint, starting from scratch! | |
| [2023-05-12 14:50:31,483][14794] Initialized policy 0 weights for model version 0 | |
| [2023-05-12 14:50:31,487][14794] LearnerWorker_p0 finished initialization! | |
| [2023-05-12 14:50:31,489][14794] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 14:50:31,720][14807] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 14:50:31,721][14807] RunningMeanStd input shape: (1,) | |
| [2023-05-12 14:50:31,733][14807] ConvEncoder: input_channels=3 | |
| [2023-05-12 14:50:31,845][14807] Conv encoder output size: 512 | |
| [2023-05-12 14:50:31,845][14807] Policy head output size: 512 | |
| [2023-05-12 14:50:33,107][00161] Inference worker 0-0 is ready! | |
| [2023-05-12 14:50:33,108][00161] All inference workers are ready! Signal rollout workers to start! | |
| [2023-05-12 14:50:33,247][14815] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,259][14814] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,268][14808] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,267][14813] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,274][14812] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,276][14810] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,300][14811] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,496][14809] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 14:50:33,566][14812] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... | |
| [2023-05-12 14:50:33,568][14815] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... | |
| [2023-05-12 14:50:33,569][14808] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... | |
| [2023-05-12 14:50:33,568][14810] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... | |
| [2023-05-12 14:50:33,573][14808] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() | |
| Traceback (most recent call last): | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init | |
| env_runner.init(self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init | |
| self._reset() | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 379, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset | |
| self._ensure_initialized() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized | |
| self.initialize() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize | |
| self._game_init() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init | |
| raise EnvCriticalError() | |
| sample_factory.envs.env_utils.EnvCriticalError | |
| [2023-05-12 14:50:33,570][14812] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] 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/python3.10/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/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init | |
| env_runner.init(self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init | |
| self._reset() | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 379, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset | |
| self._ensure_initialized() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized | |
| self.initialize() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize | |
| self._game_init() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init | |
| raise EnvCriticalError() | |
| sample_factory.envs.env_utils.EnvCriticalError | |
| [2023-05-12 14:50:33,571][14810] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] 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/python3.10/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/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init | |
| env_runner.init(self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init | |
| self._reset() | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 379, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset | |
| self._ensure_initialized() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized | |
| self.initialize() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize | |
| self._game_init() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init | |
| raise EnvCriticalError() | |
| sample_factory.envs.env_utils.EnvCriticalError | |
| [2023-05-12 14:50:33,577][14808] Unhandled exception in evt loop rollout_proc0_evt_loop | |
| [2023-05-12 14:50:33,576][14812] Unhandled exception in evt loop rollout_proc6_evt_loop | |
| [2023-05-12 14:50:33,577][14810] Unhandled exception in evt loop rollout_proc2_evt_loop | |
| [2023-05-12 14:50:33,570][14815] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] 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/python3.10/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/python3.10/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init | |
| env_runner.init(self.timing) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init | |
| self._reset() | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/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/python3.10/dist-packages/gym/core.py", line 379, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/gym/core.py", line 323, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset | |
| return self.env.reset(**kwargs) | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset | |
| self._ensure_initialized() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized | |
| self.initialize() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize | |
| self._game_init() | |
| File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init | |
| raise EnvCriticalError() | |
| sample_factory.envs.env_utils.EnvCriticalError | |
| [2023-05-12 14:50:33,580][14815] Unhandled exception in evt loop rollout_proc7_evt_loop | |
| [2023-05-12 14:50:33,672][00161] Heartbeat connected on Batcher_0 | |
| [2023-05-12 14:50:33,677][00161] Heartbeat connected on LearnerWorker_p0 | |
| [2023-05-12 14:50:33,714][00161] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-05-12 14:50:34,447][14814] Decorrelating experience for 0 frames... | |
| [2023-05-12 14:50:34,600][14811] Decorrelating experience for 0 frames... | |
| [2023-05-12 14:50:34,999][00161] 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) | |
| [2023-05-12 14:50:35,012][14814] Decorrelating experience for 32 frames... | |
| [2023-05-12 14:50:35,226][14813] Decorrelating experience for 0 frames... | |
| [2023-05-12 14:50:35,566][14813] Decorrelating experience for 32 frames... | |
| [2023-05-12 14:50:35,588][14814] Decorrelating experience for 64 frames... | |
| [2023-05-12 14:50:35,835][14809] Decorrelating experience for 0 frames... | |
| [2023-05-12 14:50:36,202][14814] Decorrelating experience for 96 frames... | |
| [2023-05-12 14:50:36,222][14813] Decorrelating experience for 64 frames... | |
| [2023-05-12 14:50:36,347][00161] Heartbeat connected on RolloutWorker_w5 | |
| [2023-05-12 14:50:36,680][14813] Decorrelating experience for 96 frames... | |
| [2023-05-12 14:50:36,803][14809] Decorrelating experience for 32 frames... | |
| [2023-05-12 14:50:36,873][00161] Heartbeat connected on RolloutWorker_w4 | |
| [2023-05-12 14:50:37,256][14811] Decorrelating experience for 32 frames... | |
| [2023-05-12 14:50:37,680][14809] Decorrelating experience for 64 frames... | |
| [2023-05-12 14:50:38,165][14811] Decorrelating experience for 64 frames... | |
| [2023-05-12 14:50:38,502][14809] Decorrelating experience for 96 frames... | |
| [2023-05-12 14:50:38,674][00161] Heartbeat connected on RolloutWorker_w1 | |
| [2023-05-12 14:50:39,046][14811] Decorrelating experience for 96 frames... | |
| [2023-05-12 14:50:39,131][00161] Heartbeat connected on RolloutWorker_w3 | |
| [2023-05-12 14:50:39,999][00161] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 4.0. Samples: 20. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-05-12 14:50:40,006][00161] Avg episode reward: [(0, '0.960')] | |
| [2023-05-12 14:50:43,618][14794] Signal inference workers to stop experience collection... | |
| [2023-05-12 14:50:43,637][14807] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-05-12 14:50:44,999][00161] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 150.8. Samples: 1508. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-05-12 14:50:45,005][00161] Avg episode reward: [(0, '3.102')] | |
| [2023-05-12 14:50:45,520][14794] Signal inference workers to resume experience collection... | |
| [2023-05-12 14:50:45,520][14807] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-05-12 14:50:50,000][00161] Fps is (10 sec: 2047.7, 60 sec: 1365.2, 300 sec: 1365.2). Total num frames: 20480. Throughput: 0: 276.8. Samples: 4152. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 14:50:50,004][00161] Avg episode reward: [(0, '3.751')] | |
| [2023-05-12 14:50:54,437][14807] Updated weights for policy 0, policy_version 10 (0.0021) | |
| [2023-05-12 14:50:55,001][00161] Fps is (10 sec: 4095.2, 60 sec: 2047.8, 300 sec: 2047.8). Total num frames: 40960. Throughput: 0: 506.6. Samples: 10132. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:50:55,007][00161] Avg episode reward: [(0, '4.196')] | |
| [2023-05-12 14:50:59,999][00161] Fps is (10 sec: 3277.3, 60 sec: 2129.9, 300 sec: 2129.9). Total num frames: 53248. Throughput: 0: 496.8. Samples: 12420. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:00,001][00161] Avg episode reward: [(0, '4.387')] | |
| [2023-05-12 14:51:04,999][00161] Fps is (10 sec: 2867.7, 60 sec: 2321.1, 300 sec: 2321.1). Total num frames: 69632. Throughput: 0: 553.7. Samples: 16610. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:05,001][00161] Avg episode reward: [(0, '4.560')] | |
| [2023-05-12 14:51:07,073][14807] Updated weights for policy 0, policy_version 20 (0.0013) | |
| [2023-05-12 14:51:09,999][00161] Fps is (10 sec: 3686.4, 60 sec: 2574.6, 300 sec: 2574.6). Total num frames: 90112. Throughput: 0: 655.8. Samples: 22952. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:10,002][00161] Avg episode reward: [(0, '4.685')] | |
| [2023-05-12 14:51:14,999][00161] Fps is (10 sec: 4096.0, 60 sec: 2764.8, 300 sec: 2764.8). Total num frames: 110592. Throughput: 0: 651.9. Samples: 26074. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:15,001][00161] Avg episode reward: [(0, '4.512')] | |
| [2023-05-12 14:51:15,004][14794] Saving new best policy, reward=4.512! | |
| [2023-05-12 14:51:18,557][14807] Updated weights for policy 0, policy_version 30 (0.0012) | |
| [2023-05-12 14:51:19,999][00161] Fps is (10 sec: 3276.7, 60 sec: 2730.6, 300 sec: 2730.6). Total num frames: 122880. Throughput: 0: 681.3. Samples: 30660. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:20,005][00161] Avg episode reward: [(0, '4.403')] | |
| [2023-05-12 14:51:24,999][00161] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2867.2). Total num frames: 143360. Throughput: 0: 784.6. Samples: 35326. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:25,007][00161] Avg episode reward: [(0, '4.332')] | |
| [2023-05-12 14:51:29,663][14807] Updated weights for policy 0, policy_version 40 (0.0022) | |
| [2023-05-12 14:51:29,999][00161] Fps is (10 sec: 4096.2, 60 sec: 2978.9, 300 sec: 2978.9). Total num frames: 163840. Throughput: 0: 823.4. Samples: 38562. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:30,003][00161] Avg episode reward: [(0, '4.497')] | |
| [2023-05-12 14:51:34,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 180224. Throughput: 0: 898.8. Samples: 44596. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:35,004][00161] Avg episode reward: [(0, '4.550')] | |
| [2023-05-12 14:51:35,007][14794] Saving new best policy, reward=4.550! | |
| [2023-05-12 14:51:40,001][00161] Fps is (10 sec: 2866.6, 60 sec: 3208.4, 300 sec: 2961.6). Total num frames: 192512. Throughput: 0: 852.8. Samples: 48506. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:40,006][00161] Avg episode reward: [(0, '4.487')] | |
| [2023-05-12 14:51:42,549][14807] Updated weights for policy 0, policy_version 50 (0.0017) | |
| [2023-05-12 14:51:44,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3042.7). Total num frames: 212992. Throughput: 0: 856.3. Samples: 50952. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:45,001][00161] Avg episode reward: [(0, '4.467')] | |
| [2023-05-12 14:51:49,999][00161] Fps is (10 sec: 4096.8, 60 sec: 3550.0, 300 sec: 3113.0). Total num frames: 233472. Throughput: 0: 902.1. Samples: 57206. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:51:50,001][00161] Avg episode reward: [(0, '4.502')] | |
| [2023-05-12 14:51:53,175][14807] Updated weights for policy 0, policy_version 60 (0.0012) | |
| [2023-05-12 14:51:55,006][00161] Fps is (10 sec: 3683.8, 60 sec: 3481.3, 300 sec: 3122.9). Total num frames: 249856. Throughput: 0: 873.7. Samples: 62276. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:51:55,016][00161] Avg episode reward: [(0, '4.510')] | |
| [2023-05-12 14:51:59,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3084.0). Total num frames: 262144. Throughput: 0: 848.8. Samples: 64272. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:00,002][00161] Avg episode reward: [(0, '4.550')] | |
| [2023-05-12 14:52:04,999][00161] Fps is (10 sec: 3279.1, 60 sec: 3549.9, 300 sec: 3140.3). Total num frames: 282624. Throughput: 0: 867.3. Samples: 69688. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:05,001][00161] Avg episode reward: [(0, '4.624')] | |
| [2023-05-12 14:52:05,004][14794] Saving new best policy, reward=4.624! | |
| [2023-05-12 14:52:05,225][14807] Updated weights for policy 0, policy_version 70 (0.0024) | |
| [2023-05-12 14:52:09,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3190.6). Total num frames: 303104. Throughput: 0: 903.4. Samples: 75978. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:10,003][00161] Avg episode reward: [(0, '4.683')] | |
| [2023-05-12 14:52:10,014][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000074_303104.pth... | |
| [2023-05-12 14:52:10,203][14794] Saving new best policy, reward=4.683! | |
| [2023-05-12 14:52:14,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3153.9). Total num frames: 315392. Throughput: 0: 876.8. Samples: 78020. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:15,002][00161] Avg episode reward: [(0, '4.707')] | |
| [2023-05-12 14:52:15,006][14794] Saving new best policy, reward=4.707! | |
| [2023-05-12 14:52:18,271][14807] Updated weights for policy 0, policy_version 80 (0.0016) | |
| [2023-05-12 14:52:19,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 832.6. Samples: 82064. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:20,002][00161] Avg episode reward: [(0, '4.560')] | |
| [2023-05-12 14:52:24,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3202.3). Total num frames: 352256. Throughput: 0: 880.9. Samples: 88144. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:25,002][00161] Avg episode reward: [(0, '4.363')] | |
| [2023-05-12 14:52:28,313][14807] Updated weights for policy 0, policy_version 90 (0.0013) | |
| [2023-05-12 14:52:29,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3241.2). Total num frames: 372736. Throughput: 0: 897.4. Samples: 91336. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:30,005][00161] Avg episode reward: [(0, '4.349')] | |
| [2023-05-12 14:52:34,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3208.5). Total num frames: 385024. Throughput: 0: 856.1. Samples: 95732. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:35,002][00161] Avg episode reward: [(0, '4.483')] | |
| [2023-05-12 14:52:40,001][00161] Fps is (10 sec: 3276.0, 60 sec: 3549.8, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 856.0. Samples: 100790. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:40,004][00161] Avg episode reward: [(0, '4.687')] | |
| [2023-05-12 14:52:40,924][14807] Updated weights for policy 0, policy_version 100 (0.0014) | |
| [2023-05-12 14:52:44,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 425984. Throughput: 0: 881.9. Samples: 103956. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:45,005][00161] Avg episode reward: [(0, '4.733')] | |
| [2023-05-12 14:52:45,009][14794] Saving new best policy, reward=4.733! | |
| [2023-05-12 14:52:49,999][00161] Fps is (10 sec: 3687.3, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 442368. Throughput: 0: 888.1. Samples: 109652. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:52:50,009][00161] Avg episode reward: [(0, '4.669')] | |
| [2023-05-12 14:52:53,000][14807] Updated weights for policy 0, policy_version 110 (0.0019) | |
| [2023-05-12 14:52:54,999][00161] Fps is (10 sec: 2867.1, 60 sec: 3413.7, 300 sec: 3247.5). Total num frames: 454656. Throughput: 0: 838.4. Samples: 113706. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:52:55,003][00161] Avg episode reward: [(0, '4.480')] | |
| [2023-05-12 14:52:59,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3276.8). Total num frames: 475136. Throughput: 0: 851.7. Samples: 116346. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:53:00,004][00161] Avg episode reward: [(0, '4.661')] | |
| [2023-05-12 14:53:03,441][14807] Updated weights for policy 0, policy_version 120 (0.0012) | |
| [2023-05-12 14:53:04,999][00161] Fps is (10 sec: 4096.2, 60 sec: 3549.9, 300 sec: 3304.1). Total num frames: 495616. Throughput: 0: 905.3. Samples: 122804. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:53:05,005][00161] Avg episode reward: [(0, '4.776')] | |
| [2023-05-12 14:53:05,010][14794] Saving new best policy, reward=4.776! | |
| [2023-05-12 14:53:09,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3303.2). Total num frames: 512000. Throughput: 0: 878.4. Samples: 127670. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:10,003][00161] Avg episode reward: [(0, '4.650')] | |
| [2023-05-12 14:53:14,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 524288. Throughput: 0: 852.4. Samples: 129694. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:53:15,001][00161] Avg episode reward: [(0, '4.710')] | |
| [2023-05-12 14:53:16,315][14807] Updated weights for policy 0, policy_version 130 (0.0014) | |
| [2023-05-12 14:53:19,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3301.6). Total num frames: 544768. Throughput: 0: 880.0. Samples: 135330. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:20,011][00161] Avg episode reward: [(0, '5.203')] | |
| [2023-05-12 14:53:20,020][14794] Saving new best policy, reward=5.203! | |
| [2023-05-12 14:53:24,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3325.0). Total num frames: 565248. Throughput: 0: 901.2. Samples: 141344. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:53:25,002][00161] Avg episode reward: [(0, '5.049')] | |
| [2023-05-12 14:53:27,633][14807] Updated weights for policy 0, policy_version 140 (0.0012) | |
| [2023-05-12 14:53:29,999][00161] Fps is (10 sec: 3276.9, 60 sec: 3413.3, 300 sec: 3300.2). Total num frames: 577536. Throughput: 0: 875.0. Samples: 143332. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:30,008][00161] Avg episode reward: [(0, '5.058')] | |
| [2023-05-12 14:53:34,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3299.6). Total num frames: 593920. Throughput: 0: 828.8. Samples: 146948. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:53:35,001][00161] Avg episode reward: [(0, '5.152')] | |
| [2023-05-12 14:53:39,754][14807] Updated weights for policy 0, policy_version 150 (0.0018) | |
| [2023-05-12 14:53:39,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3321.1). Total num frames: 614400. Throughput: 0: 879.4. Samples: 153280. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:40,006][00161] Avg episode reward: [(0, '5.504')] | |
| [2023-05-12 14:53:40,017][14794] Saving new best policy, reward=5.504! | |
| [2023-05-12 14:53:44,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3319.9). Total num frames: 630784. Throughput: 0: 887.4. Samples: 156280. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:53:45,008][00161] Avg episode reward: [(0, '5.512')] | |
| [2023-05-12 14:53:45,010][14794] Saving new best policy, reward=5.512! | |
| [2023-05-12 14:53:49,999][00161] Fps is (10 sec: 2867.1, 60 sec: 3345.0, 300 sec: 3297.8). Total num frames: 643072. Throughput: 0: 834.0. Samples: 160334. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:50,011][00161] Avg episode reward: [(0, '5.657')] | |
| [2023-05-12 14:53:50,025][14794] Saving new best policy, reward=5.657! | |
| [2023-05-12 14:53:53,311][14807] Updated weights for policy 0, policy_version 160 (0.0018) | |
| [2023-05-12 14:53:54,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3297.3). Total num frames: 659456. Throughput: 0: 826.7. Samples: 164870. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:53:55,005][00161] Avg episode reward: [(0, '5.689')] | |
| [2023-05-12 14:53:55,008][14794] Saving new best policy, reward=5.689! | |
| [2023-05-12 14:53:59,999][00161] Fps is (10 sec: 3686.6, 60 sec: 3413.3, 300 sec: 3316.8). Total num frames: 679936. Throughput: 0: 843.8. Samples: 167664. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:00,003][00161] Avg episode reward: [(0, '5.617')] | |
| [2023-05-12 14:54:05,004][00161] Fps is (10 sec: 3275.2, 60 sec: 3276.5, 300 sec: 3296.2). Total num frames: 692224. Throughput: 0: 837.9. Samples: 173038. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:05,007][00161] Avg episode reward: [(0, '5.446')] | |
| [2023-05-12 14:54:05,222][14807] Updated weights for policy 0, policy_version 170 (0.0016) | |
| [2023-05-12 14:54:09,999][00161] Fps is (10 sec: 2457.6, 60 sec: 3208.5, 300 sec: 3276.8). Total num frames: 704512. Throughput: 0: 784.4. Samples: 176642. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:54:10,004][00161] Avg episode reward: [(0, '5.463')] | |
| [2023-05-12 14:54:10,018][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth... | |
| [2023-05-12 14:54:14,999][00161] Fps is (10 sec: 3278.4, 60 sec: 3345.1, 300 sec: 3295.4). Total num frames: 724992. Throughput: 0: 788.9. Samples: 178834. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:54:15,005][00161] Avg episode reward: [(0, '5.832')] | |
| [2023-05-12 14:54:15,009][14794] Saving new best policy, reward=5.832! | |
| [2023-05-12 14:54:17,811][14807] Updated weights for policy 0, policy_version 180 (0.0015) | |
| [2023-05-12 14:54:19,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3313.2). Total num frames: 745472. Throughput: 0: 846.0. Samples: 185016. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:54:20,002][00161] Avg episode reward: [(0, '6.112')] | |
| [2023-05-12 14:54:20,012][14794] Saving new best policy, reward=6.112! | |
| [2023-05-12 14:54:24,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3312.4). Total num frames: 761856. Throughput: 0: 820.7. Samples: 190210. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:54:25,004][00161] Avg episode reward: [(0, '5.752')] | |
| [2023-05-12 14:54:30,001][00161] Fps is (10 sec: 2866.7, 60 sec: 3276.7, 300 sec: 3294.2). Total num frames: 774144. Throughput: 0: 799.2. Samples: 192244. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:54:30,004][00161] Avg episode reward: [(0, '5.732')] | |
| [2023-05-12 14:54:30,895][14807] Updated weights for policy 0, policy_version 190 (0.0012) | |
| [2023-05-12 14:54:34,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3310.9). Total num frames: 794624. Throughput: 0: 816.8. Samples: 197088. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:54:35,001][00161] Avg episode reward: [(0, '5.421')] | |
| [2023-05-12 14:54:40,002][00161] Fps is (10 sec: 4095.6, 60 sec: 3344.9, 300 sec: 3326.9). Total num frames: 815104. Throughput: 0: 855.3. Samples: 203360. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:40,010][00161] Avg episode reward: [(0, '5.549')] | |
| [2023-05-12 14:54:41,039][14807] Updated weights for policy 0, policy_version 200 (0.0012) | |
| [2023-05-12 14:54:44,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3276.8, 300 sec: 3309.6). Total num frames: 827392. Throughput: 0: 847.6. Samples: 205806. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:45,004][00161] Avg episode reward: [(0, '5.671')] | |
| [2023-05-12 14:54:50,000][00161] Fps is (10 sec: 2867.8, 60 sec: 3345.0, 300 sec: 3308.9). Total num frames: 843776. Throughput: 0: 819.3. Samples: 209904. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:50,002][00161] Avg episode reward: [(0, '5.528')] | |
| [2023-05-12 14:54:53,469][14807] Updated weights for policy 0, policy_version 210 (0.0013) | |
| [2023-05-12 14:54:54,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3324.1). Total num frames: 864256. Throughput: 0: 874.2. Samples: 215980. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:54:55,001][00161] Avg episode reward: [(0, '5.398')] | |
| [2023-05-12 14:55:00,000][00161] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3338.6). Total num frames: 884736. Throughput: 0: 897.0. Samples: 219202. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:55:00,002][00161] Avg episode reward: [(0, '5.643')] | |
| [2023-05-12 14:55:04,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.6, 300 sec: 3322.3). Total num frames: 897024. Throughput: 0: 865.3. Samples: 223954. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:05,005][00161] Avg episode reward: [(0, '5.784')] | |
| [2023-05-12 14:55:05,454][14807] Updated weights for policy 0, policy_version 220 (0.0016) | |
| [2023-05-12 14:55:09,999][00161] Fps is (10 sec: 3277.1, 60 sec: 3549.9, 300 sec: 3336.4). Total num frames: 917504. Throughput: 0: 858.1. Samples: 228826. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:10,001][00161] Avg episode reward: [(0, '5.997')] | |
| [2023-05-12 14:55:14,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3349.9). Total num frames: 937984. Throughput: 0: 884.8. Samples: 232060. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:55:15,001][00161] Avg episode reward: [(0, '6.580')] | |
| [2023-05-12 14:55:15,004][14794] Saving new best policy, reward=6.580! | |
| [2023-05-12 14:55:15,568][14807] Updated weights for policy 0, policy_version 230 (0.0016) | |
| [2023-05-12 14:55:20,000][00161] Fps is (10 sec: 3686.0, 60 sec: 3481.5, 300 sec: 3348.6). Total num frames: 954368. Throughput: 0: 908.4. Samples: 237966. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:20,003][00161] Avg episode reward: [(0, '6.851')] | |
| [2023-05-12 14:55:20,016][14794] Saving new best policy, reward=6.851! | |
| [2023-05-12 14:55:24,999][00161] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3333.3). Total num frames: 966656. Throughput: 0: 857.3. Samples: 241938. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:55:25,007][00161] Avg episode reward: [(0, '6.712')] | |
| [2023-05-12 14:55:28,570][14807] Updated weights for policy 0, policy_version 240 (0.0037) | |
| [2023-05-12 14:55:29,999][00161] Fps is (10 sec: 3277.2, 60 sec: 3550.0, 300 sec: 3346.2). Total num frames: 987136. Throughput: 0: 861.8. Samples: 244586. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:30,001][00161] Avg episode reward: [(0, '6.645')] | |
| [2023-05-12 14:55:35,001][00161] Fps is (10 sec: 4095.3, 60 sec: 3549.8, 300 sec: 3415.6). Total num frames: 1007616. Throughput: 0: 913.1. Samples: 250996. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:35,003][00161] Avg episode reward: [(0, '6.866')] | |
| [2023-05-12 14:55:35,013][14794] Saving new best policy, reward=6.866! | |
| [2023-05-12 14:55:39,782][14807] Updated weights for policy 0, policy_version 250 (0.0012) | |
| [2023-05-12 14:55:39,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3471.2). Total num frames: 1024000. Throughput: 0: 886.3. Samples: 255862. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:40,004][00161] Avg episode reward: [(0, '7.614')] | |
| [2023-05-12 14:55:40,020][14794] Saving new best policy, reward=7.614! | |
| [2023-05-12 14:55:44,999][00161] Fps is (10 sec: 2867.7, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 1036288. Throughput: 0: 859.3. Samples: 257870. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:55:45,005][00161] Avg episode reward: [(0, '7.541')] | |
| [2023-05-12 14:55:49,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1056768. Throughput: 0: 879.2. Samples: 263518. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:55:50,001][00161] Avg episode reward: [(0, '8.527')] | |
| [2023-05-12 14:55:50,093][14794] Saving new best policy, reward=8.527! | |
| [2023-05-12 14:55:50,951][14807] Updated weights for policy 0, policy_version 260 (0.0016) | |
| [2023-05-12 14:55:54,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 1077248. Throughput: 0: 907.0. Samples: 269642. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:55:55,006][00161] Avg episode reward: [(0, '8.683')] | |
| [2023-05-12 14:55:55,008][14794] Saving new best policy, reward=8.683! | |
| [2023-05-12 14:55:59,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3457.3). Total num frames: 1089536. Throughput: 0: 878.6. Samples: 271598. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:00,001][00161] Avg episode reward: [(0, '9.326')] | |
| [2023-05-12 14:56:00,021][14794] Saving new best policy, reward=9.326! | |
| [2023-05-12 14:56:03,856][14807] Updated weights for policy 0, policy_version 270 (0.0022) | |
| [2023-05-12 14:56:04,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1110016. Throughput: 0: 841.8. Samples: 275846. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:05,002][00161] Avg episode reward: [(0, '9.558')] | |
| [2023-05-12 14:56:05,008][14794] Saving new best policy, reward=9.558! | |
| [2023-05-12 14:56:09,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1130496. Throughput: 0: 893.7. Samples: 282154. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:10,004][00161] Avg episode reward: [(0, '8.367')] | |
| [2023-05-12 14:56:10,021][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000276_1130496.pth... | |
| [2023-05-12 14:56:10,118][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000074_303104.pth | |
| [2023-05-12 14:56:14,205][14807] Updated weights for policy 0, policy_version 280 (0.0012) | |
| [2023-05-12 14:56:14,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1146880. Throughput: 0: 904.6. Samples: 285292. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:56:15,003][00161] Avg episode reward: [(0, '7.208')] | |
| [2023-05-12 14:56:19,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3443.4). Total num frames: 1159168. Throughput: 0: 859.7. Samples: 289680. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:56:20,005][00161] Avg episode reward: [(0, '6.599')] | |
| [2023-05-12 14:56:24,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 1179648. Throughput: 0: 863.7. Samples: 294728. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 14:56:25,001][00161] Avg episode reward: [(0, '6.174')] | |
| [2023-05-12 14:56:26,416][14807] Updated weights for policy 0, policy_version 290 (0.0013) | |
| [2023-05-12 14:56:29,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1200128. Throughput: 0: 888.9. Samples: 297872. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:30,001][00161] Avg episode reward: [(0, '6.748')] | |
| [2023-05-12 14:56:34,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3471.2). Total num frames: 1216512. Throughput: 0: 888.1. Samples: 303482. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:56:35,005][00161] Avg episode reward: [(0, '6.756')] | |
| [2023-05-12 14:56:39,133][14807] Updated weights for policy 0, policy_version 300 (0.0019) | |
| [2023-05-12 14:56:39,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 1228800. Throughput: 0: 840.2. Samples: 307452. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:40,006][00161] Avg episode reward: [(0, '7.499')] | |
| [2023-05-12 14:56:44,999][00161] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 1253376. Throughput: 0: 865.7. Samples: 310556. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:56:45,002][00161] Avg episode reward: [(0, '7.215')] | |
| [2023-05-12 14:56:48,872][14807] Updated weights for policy 0, policy_version 310 (0.0018) | |
| [2023-05-12 14:56:49,999][00161] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3471.3). Total num frames: 1273856. Throughput: 0: 914.2. Samples: 316984. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:56:50,006][00161] Avg episode reward: [(0, '8.023')] | |
| [2023-05-12 14:56:54,999][00161] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1286144. Throughput: 0: 879.1. Samples: 321712. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:56:55,002][00161] Avg episode reward: [(0, '8.206')] | |
| [2023-05-12 14:57:00,002][00161] Fps is (10 sec: 2866.3, 60 sec: 3549.7, 300 sec: 3457.3). Total num frames: 1302528. Throughput: 0: 851.7. Samples: 323622. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:00,004][00161] Avg episode reward: [(0, '9.581')] | |
| [2023-05-12 14:57:00,012][14794] Saving new best policy, reward=9.581! | |
| [2023-05-12 14:57:01,645][14807] Updated weights for policy 0, policy_version 320 (0.0012) | |
| [2023-05-12 14:57:04,999][00161] Fps is (10 sec: 3686.3, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1323008. Throughput: 0: 885.8. Samples: 329542. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:05,008][00161] Avg episode reward: [(0, '9.980')] | |
| [2023-05-12 14:57:05,016][14794] Saving new best policy, reward=9.980! | |
| [2023-05-12 14:57:09,999][00161] Fps is (10 sec: 3687.5, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1339392. Throughput: 0: 902.9. Samples: 335358. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:57:10,002][00161] Avg episode reward: [(0, '10.183')] | |
| [2023-05-12 14:57:10,014][14794] Saving new best policy, reward=10.183! | |
| [2023-05-12 14:57:13,419][14807] Updated weights for policy 0, policy_version 330 (0.0012) | |
| [2023-05-12 14:57:15,000][00161] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1355776. Throughput: 0: 876.2. Samples: 337300. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:57:15,009][00161] Avg episode reward: [(0, '9.861')] | |
| [2023-05-12 14:57:19,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1372160. Throughput: 0: 855.7. Samples: 341990. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:20,004][00161] Avg episode reward: [(0, '10.331')] | |
| [2023-05-12 14:57:20,015][14794] Saving new best policy, reward=10.331! | |
| [2023-05-12 14:57:24,327][14807] Updated weights for policy 0, policy_version 340 (0.0011) | |
| [2023-05-12 14:57:24,999][00161] Fps is (10 sec: 3686.7, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1392640. Throughput: 0: 906.8. Samples: 348260. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:25,001][00161] Avg episode reward: [(0, '10.772')] | |
| [2023-05-12 14:57:25,006][14794] Saving new best policy, reward=10.772! | |
| [2023-05-12 14:57:29,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1409024. Throughput: 0: 901.2. Samples: 351110. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:30,001][00161] Avg episode reward: [(0, '10.268')] | |
| [2023-05-12 14:57:34,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 1421312. Throughput: 0: 846.2. Samples: 355064. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:35,002][00161] Avg episode reward: [(0, '10.424')] | |
| [2023-05-12 14:57:37,071][14807] Updated weights for policy 0, policy_version 350 (0.0016) | |
| [2023-05-12 14:57:39,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3457.3). Total num frames: 1445888. Throughput: 0: 869.5. Samples: 360838. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:57:40,001][00161] Avg episode reward: [(0, '11.479')] | |
| [2023-05-12 14:57:40,017][14794] Saving new best policy, reward=11.479! | |
| [2023-05-12 14:57:44,999][00161] Fps is (10 sec: 4505.6, 60 sec: 3549.9, 300 sec: 3471.2). Total num frames: 1466368. Throughput: 0: 897.4. Samples: 364002. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:45,002][00161] Avg episode reward: [(0, '11.757')] | |
| [2023-05-12 14:57:45,006][14794] Saving new best policy, reward=11.757! | |
| [2023-05-12 14:57:48,055][14807] Updated weights for policy 0, policy_version 360 (0.0015) | |
| [2023-05-12 14:57:49,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3471.2). Total num frames: 1478656. Throughput: 0: 876.8. Samples: 368998. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:57:50,008][00161] Avg episode reward: [(0, '12.464')] | |
| [2023-05-12 14:57:50,019][14794] Saving new best policy, reward=12.464! | |
| [2023-05-12 14:57:54,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1495040. Throughput: 0: 841.1. Samples: 373206. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:57:55,005][00161] Avg episode reward: [(0, '12.666')] | |
| [2023-05-12 14:57:55,007][14794] Saving new best policy, reward=12.666! | |
| [2023-05-12 14:57:59,713][14807] Updated weights for policy 0, policy_version 370 (0.0016) | |
| [2023-05-12 14:57:59,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3550.0, 300 sec: 3457.3). Total num frames: 1515520. Throughput: 0: 868.2. Samples: 376370. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:00,001][00161] Avg episode reward: [(0, '12.091')] | |
| [2023-05-12 14:58:04,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1531904. Throughput: 0: 906.8. Samples: 382796. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:58:05,003][00161] Avg episode reward: [(0, '11.757')] | |
| [2023-05-12 14:58:09,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1548288. Throughput: 0: 860.9. Samples: 387002. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:10,001][00161] Avg episode reward: [(0, '11.964')] | |
| [2023-05-12 14:58:10,016][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000378_1548288.pth... | |
| [2023-05-12 14:58:10,111][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000172_704512.pth | |
| [2023-05-12 14:58:12,506][14807] Updated weights for policy 0, policy_version 380 (0.0011) | |
| [2023-05-12 14:58:14,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 1564672. Throughput: 0: 844.0. Samples: 389092. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 14:58:15,002][00161] Avg episode reward: [(0, '12.435')] | |
| [2023-05-12 14:58:19,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 1585152. Throughput: 0: 899.3. Samples: 395532. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:20,008][00161] Avg episode reward: [(0, '12.808')] | |
| [2023-05-12 14:58:20,074][14794] Saving new best policy, reward=12.808! | |
| [2023-05-12 14:58:22,243][14807] Updated weights for policy 0, policy_version 390 (0.0011) | |
| [2023-05-12 14:58:24,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1601536. Throughput: 0: 888.3. Samples: 400812. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:25,004][00161] Avg episode reward: [(0, '12.987')] | |
| [2023-05-12 14:58:25,010][14794] Saving new best policy, reward=12.987! | |
| [2023-05-12 14:58:29,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3471.2). Total num frames: 1617920. Throughput: 0: 862.7. Samples: 402824. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:30,007][00161] Avg episode reward: [(0, '13.912')] | |
| [2023-05-12 14:58:30,019][14794] Saving new best policy, reward=13.912! | |
| [2023-05-12 14:58:35,001][00161] Fps is (10 sec: 3276.3, 60 sec: 3549.8, 300 sec: 3457.3). Total num frames: 1634304. Throughput: 0: 862.4. Samples: 407808. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:35,004][00161] Avg episode reward: [(0, '13.063')] | |
| [2023-05-12 14:58:35,136][14807] Updated weights for policy 0, policy_version 400 (0.0019) | |
| [2023-05-12 14:58:39,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 1658880. Throughput: 0: 910.2. Samples: 414164. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:40,001][00161] Avg episode reward: [(0, '13.142')] | |
| [2023-05-12 14:58:44,999][00161] Fps is (10 sec: 3687.0, 60 sec: 3413.3, 300 sec: 3485.1). Total num frames: 1671168. Throughput: 0: 897.9. Samples: 416774. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:58:45,005][00161] Avg episode reward: [(0, '14.173')] | |
| [2023-05-12 14:58:45,013][14794] Saving new best policy, reward=14.173! | |
| [2023-05-12 14:58:47,077][14807] Updated weights for policy 0, policy_version 410 (0.0012) | |
| [2023-05-12 14:58:49,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3485.1). Total num frames: 1687552. Throughput: 0: 847.6. Samples: 420936. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:58:50,008][00161] Avg episode reward: [(0, '13.832')] | |
| [2023-05-12 14:58:54,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3485.1). Total num frames: 1708032. Throughput: 0: 890.1. Samples: 427056. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:58:55,006][00161] Avg episode reward: [(0, '13.838')] | |
| [2023-05-12 14:58:57,193][14807] Updated weights for policy 0, policy_version 420 (0.0014) | |
| [2023-05-12 14:58:59,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 1728512. Throughput: 0: 914.8. Samples: 430260. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:00,005][00161] Avg episode reward: [(0, '14.479')] | |
| [2023-05-12 14:59:00,015][14794] Saving new best policy, reward=14.479! | |
| [2023-05-12 14:59:04,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 1740800. Throughput: 0: 874.0. Samples: 434862. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:59:05,001][00161] Avg episode reward: [(0, '14.766')] | |
| [2023-05-12 14:59:05,008][14794] Saving new best policy, reward=14.766! | |
| [2023-05-12 14:59:09,963][14807] Updated weights for policy 0, policy_version 430 (0.0014) | |
| [2023-05-12 14:59:09,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1761280. Throughput: 0: 862.6. Samples: 439630. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:59:10,001][00161] Avg episode reward: [(0, '14.787')] | |
| [2023-05-12 14:59:10,010][14794] Saving new best policy, reward=14.787! | |
| [2023-05-12 14:59:14,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3512.8). Total num frames: 1781760. Throughput: 0: 885.9. Samples: 442690. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 14:59:15,002][00161] Avg episode reward: [(0, '16.213')] | |
| [2023-05-12 14:59:15,004][14794] Saving new best policy, reward=16.213! | |
| [2023-05-12 14:59:19,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1798144. Throughput: 0: 911.0. Samples: 448802. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:20,005][00161] Avg episode reward: [(0, '16.542')] | |
| [2023-05-12 14:59:20,032][14794] Saving new best policy, reward=16.542! | |
| [2023-05-12 14:59:20,899][14807] Updated weights for policy 0, policy_version 440 (0.0014) | |
| [2023-05-12 14:59:25,000][00161] Fps is (10 sec: 2866.9, 60 sec: 3481.5, 300 sec: 3512.9). Total num frames: 1810432. Throughput: 0: 860.0. Samples: 452864. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:59:25,004][00161] Avg episode reward: [(0, '15.718')] | |
| [2023-05-12 14:59:29,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1830912. Throughput: 0: 857.6. Samples: 455368. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:59:30,004][00161] Avg episode reward: [(0, '15.543')] | |
| [2023-05-12 14:59:32,440][14807] Updated weights for policy 0, policy_version 450 (0.0012) | |
| [2023-05-12 14:59:35,001][00161] Fps is (10 sec: 4095.7, 60 sec: 3618.1, 300 sec: 3512.9). Total num frames: 1851392. Throughput: 0: 906.9. Samples: 461748. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:35,009][00161] Avg episode reward: [(0, '14.235')] | |
| [2023-05-12 14:59:39,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 1867776. Throughput: 0: 889.6. Samples: 467086. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:40,001][00161] Avg episode reward: [(0, '13.417')] | |
| [2023-05-12 14:59:44,999][00161] Fps is (10 sec: 2867.8, 60 sec: 3481.6, 300 sec: 3512.9). Total num frames: 1880064. Throughput: 0: 863.0. Samples: 469096. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:45,007][00161] Avg episode reward: [(0, '13.985')] | |
| [2023-05-12 14:59:45,246][14807] Updated weights for policy 0, policy_version 460 (0.0014) | |
| [2023-05-12 14:59:49,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1900544. Throughput: 0: 880.0. Samples: 474464. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 14:59:50,001][00161] Avg episode reward: [(0, '13.950')] | |
| [2023-05-12 14:59:54,757][14807] Updated weights for policy 0, policy_version 470 (0.0027) | |
| [2023-05-12 14:59:54,999][00161] Fps is (10 sec: 4505.6, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 1925120. Throughput: 0: 916.6. Samples: 480876. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 14:59:55,001][00161] Avg episode reward: [(0, '14.982')] | |
| [2023-05-12 14:59:59,999][00161] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 1937408. Throughput: 0: 898.7. Samples: 483132. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:00,004][00161] Avg episode reward: [(0, '15.599')] | |
| [2023-05-12 15:00:04,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1953792. Throughput: 0: 851.9. Samples: 487136. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:00:05,001][00161] Avg episode reward: [(0, '16.783')] | |
| [2023-05-12 15:00:05,006][14794] Saving new best policy, reward=16.783! | |
| [2023-05-12 15:00:07,450][14807] Updated weights for policy 0, policy_version 480 (0.0018) | |
| [2023-05-12 15:00:09,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 1974272. Throughput: 0: 903.3. Samples: 493512. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:00:10,007][00161] Avg episode reward: [(0, '17.224')] | |
| [2023-05-12 15:00:10,018][00161] Components not started: RolloutWorker_w0, RolloutWorker_w2, RolloutWorker_w6, RolloutWorker_w7, wait_time=600.0 seconds | |
| [2023-05-12 15:00:10,017][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000482_1974272.pth... | |
| [2023-05-12 15:00:10,144][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000276_1130496.pth | |
| [2023-05-12 15:00:10,153][14794] Saving new best policy, reward=17.224! | |
| [2023-05-12 15:00:14,999][00161] Fps is (10 sec: 3686.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 1990656. Throughput: 0: 915.1. Samples: 496548. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:15,002][00161] Avg episode reward: [(0, '18.295')] | |
| [2023-05-12 15:00:15,004][14794] Saving new best policy, reward=18.295! | |
| [2023-05-12 15:00:19,571][14807] Updated weights for policy 0, policy_version 490 (0.0016) | |
| [2023-05-12 15:00:19,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2007040. Throughput: 0: 871.5. Samples: 500966. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:00:20,002][00161] Avg episode reward: [(0, '17.915')] | |
| [2023-05-12 15:00:24,999][00161] Fps is (10 sec: 3277.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2023424. Throughput: 0: 863.1. Samples: 505924. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:25,005][00161] Avg episode reward: [(0, '16.921')] | |
| [2023-05-12 15:00:29,999][00161] Fps is (10 sec: 3686.5, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 2043904. Throughput: 0: 888.8. Samples: 509092. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:00:30,007][00161] Avg episode reward: [(0, '15.366')] | |
| [2023-05-12 15:00:30,180][14807] Updated weights for policy 0, policy_version 500 (0.0016) | |
| [2023-05-12 15:00:34,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3550.0, 300 sec: 3526.7). Total num frames: 2064384. Throughput: 0: 901.0. Samples: 515008. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:00:35,001][00161] Avg episode reward: [(0, '13.520')] | |
| [2023-05-12 15:00:39,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2076672. Throughput: 0: 850.7. Samples: 519158. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:40,004][00161] Avg episode reward: [(0, '13.032')] | |
| [2023-05-12 15:00:42,848][14807] Updated weights for policy 0, policy_version 510 (0.0016) | |
| [2023-05-12 15:00:44,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2097152. Throughput: 0: 858.7. Samples: 521774. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:45,001][00161] Avg episode reward: [(0, '12.499')] | |
| [2023-05-12 15:00:49,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2117632. Throughput: 0: 910.6. Samples: 528114. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:00:50,001][00161] Avg episode reward: [(0, '11.915')] | |
| [2023-05-12 15:00:53,423][14807] Updated weights for policy 0, policy_version 520 (0.0013) | |
| [2023-05-12 15:00:54,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2129920. Throughput: 0: 882.3. Samples: 533216. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:00:55,006][00161] Avg episode reward: [(0, '11.404')] | |
| [2023-05-12 15:01:00,001][00161] Fps is (10 sec: 2866.6, 60 sec: 3481.5, 300 sec: 3512.8). Total num frames: 2146304. Throughput: 0: 859.6. Samples: 535230. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:01:00,003][00161] Avg episode reward: [(0, '11.689')] | |
| [2023-05-12 15:01:04,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2166784. Throughput: 0: 886.4. Samples: 540852. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:01:05,001][00161] Avg episode reward: [(0, '12.460')] | |
| [2023-05-12 15:01:05,200][14807] Updated weights for policy 0, policy_version 530 (0.0015) | |
| [2023-05-12 15:01:09,999][00161] Fps is (10 sec: 4096.8, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2187264. Throughput: 0: 916.5. Samples: 547166. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:01:10,007][00161] Avg episode reward: [(0, '13.115')] | |
| [2023-05-12 15:01:14,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2199552. Throughput: 0: 891.3. Samples: 549200. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:01:15,006][00161] Avg episode reward: [(0, '14.473')] | |
| [2023-05-12 15:01:17,874][14807] Updated weights for policy 0, policy_version 540 (0.0012) | |
| [2023-05-12 15:01:19,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2220032. Throughput: 0: 855.3. Samples: 553498. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:01:20,001][00161] Avg episode reward: [(0, '15.991')] | |
| [2023-05-12 15:01:24,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2240512. Throughput: 0: 905.4. Samples: 559902. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:01:25,001][00161] Avg episode reward: [(0, '17.625')] | |
| [2023-05-12 15:01:27,329][14807] Updated weights for policy 0, policy_version 550 (0.0013) | |
| [2023-05-12 15:01:29,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2256896. Throughput: 0: 917.9. Samples: 563080. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:01:30,010][00161] Avg episode reward: [(0, '17.100')] | |
| [2023-05-12 15:01:34,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2269184. Throughput: 0: 868.6. Samples: 567202. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:01:35,002][00161] Avg episode reward: [(0, '16.702')] | |
| [2023-05-12 15:01:39,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3549.8, 300 sec: 3512.8). Total num frames: 2289664. Throughput: 0: 877.6. Samples: 572708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:01:40,007][00161] Avg episode reward: [(0, '15.707')] | |
| [2023-05-12 15:01:40,219][14807] Updated weights for policy 0, policy_version 560 (0.0025) | |
| [2023-05-12 15:01:45,001][00161] Fps is (10 sec: 4504.7, 60 sec: 3618.0, 300 sec: 3526.7). Total num frames: 2314240. Throughput: 0: 903.1. Samples: 575868. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:01:45,003][00161] Avg episode reward: [(0, '15.167')] | |
| [2023-05-12 15:01:49,999][00161] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2326528. Throughput: 0: 903.4. Samples: 581504. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:01:50,004][00161] Avg episode reward: [(0, '15.199')] | |
| [2023-05-12 15:01:51,629][14807] Updated weights for policy 0, policy_version 570 (0.0022) | |
| [2023-05-12 15:01:54,999][00161] Fps is (10 sec: 2867.7, 60 sec: 3549.9, 300 sec: 3526.8). Total num frames: 2342912. Throughput: 0: 854.3. Samples: 585608. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:01:55,005][00161] Avg episode reward: [(0, '16.170')] | |
| [2023-05-12 15:02:00,001][00161] Fps is (10 sec: 3685.7, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2363392. Throughput: 0: 876.2. Samples: 588632. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:00,007][00161] Avg episode reward: [(0, '16.420')] | |
| [2023-05-12 15:02:02,505][14807] Updated weights for policy 0, policy_version 580 (0.0011) | |
| [2023-05-12 15:02:05,003][00161] Fps is (10 sec: 4094.4, 60 sec: 3617.9, 300 sec: 3540.6). Total num frames: 2383872. Throughput: 0: 920.9. Samples: 594942. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:02:05,005][00161] Avg episode reward: [(0, '17.637')] | |
| [2023-05-12 15:02:10,000][00161] Fps is (10 sec: 3277.1, 60 sec: 3481.5, 300 sec: 3526.7). Total num frames: 2396160. Throughput: 0: 876.3. Samples: 599338. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:02:10,003][00161] Avg episode reward: [(0, '18.318')] | |
| [2023-05-12 15:02:10,010][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000585_2396160.pth... | |
| [2023-05-12 15:02:10,169][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000378_1548288.pth | |
| [2023-05-12 15:02:10,178][14794] Saving new best policy, reward=18.318! | |
| [2023-05-12 15:02:15,002][00161] Fps is (10 sec: 2867.6, 60 sec: 3549.7, 300 sec: 3526.7). Total num frames: 2412544. Throughput: 0: 849.1. Samples: 601292. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:02:15,005][00161] Avg episode reward: [(0, '17.679')] | |
| [2023-05-12 15:02:15,315][14807] Updated weights for policy 0, policy_version 590 (0.0018) | |
| [2023-05-12 15:02:20,002][00161] Fps is (10 sec: 3685.7, 60 sec: 3549.7, 300 sec: 3526.7). Total num frames: 2433024. Throughput: 0: 891.8. Samples: 607336. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:20,004][00161] Avg episode reward: [(0, '18.204')] | |
| [2023-05-12 15:02:24,999][00161] Fps is (10 sec: 4097.1, 60 sec: 3549.9, 300 sec: 3540.6). Total num frames: 2453504. Throughput: 0: 899.1. Samples: 613168. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:25,002][00161] Avg episode reward: [(0, '18.346')] | |
| [2023-05-12 15:02:25,013][14794] Saving new best policy, reward=18.346! | |
| [2023-05-12 15:02:26,256][14807] Updated weights for policy 0, policy_version 600 (0.0014) | |
| [2023-05-12 15:02:30,000][00161] Fps is (10 sec: 3277.5, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 2465792. Throughput: 0: 873.4. Samples: 615168. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:02:30,002][00161] Avg episode reward: [(0, '18.462')] | |
| [2023-05-12 15:02:30,011][14794] Saving new best policy, reward=18.462! | |
| [2023-05-12 15:02:34,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2482176. Throughput: 0: 848.3. Samples: 619678. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:35,001][00161] Avg episode reward: [(0, '19.525')] | |
| [2023-05-12 15:02:35,008][14794] Saving new best policy, reward=19.525! | |
| [2023-05-12 15:02:38,309][14807] Updated weights for policy 0, policy_version 610 (0.0017) | |
| [2023-05-12 15:02:39,999][00161] Fps is (10 sec: 3686.6, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2502656. Throughput: 0: 894.8. Samples: 625872. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:40,010][00161] Avg episode reward: [(0, '18.694')] | |
| [2023-05-12 15:02:45,006][00161] Fps is (10 sec: 3683.8, 60 sec: 3413.0, 300 sec: 3526.6). Total num frames: 2519040. Throughput: 0: 894.7. Samples: 628896. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:02:45,015][00161] Avg episode reward: [(0, '17.348')] | |
| [2023-05-12 15:02:50,001][00161] Fps is (10 sec: 3276.1, 60 sec: 3481.5, 300 sec: 3526.7). Total num frames: 2535424. Throughput: 0: 845.5. Samples: 632988. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:02:50,005][00161] Avg episode reward: [(0, '18.325')] | |
| [2023-05-12 15:02:51,229][14807] Updated weights for policy 0, policy_version 620 (0.0031) | |
| [2023-05-12 15:02:54,999][00161] Fps is (10 sec: 3689.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2555904. Throughput: 0: 865.8. Samples: 638300. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:02:55,001][00161] Avg episode reward: [(0, '18.615')] | |
| [2023-05-12 15:02:59,999][00161] Fps is (10 sec: 4097.0, 60 sec: 3550.0, 300 sec: 3540.6). Total num frames: 2576384. Throughput: 0: 892.5. Samples: 641452. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:03:00,007][00161] Avg episode reward: [(0, '17.923')] | |
| [2023-05-12 15:03:00,729][14807] Updated weights for policy 0, policy_version 630 (0.0012) | |
| [2023-05-12 15:03:04,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.8, 300 sec: 3540.6). Total num frames: 2592768. Throughput: 0: 882.5. Samples: 647048. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:03:05,007][00161] Avg episode reward: [(0, '18.966')] | |
| [2023-05-12 15:03:09,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.7, 300 sec: 3526.7). Total num frames: 2605056. Throughput: 0: 844.3. Samples: 651160. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:03:10,001][00161] Avg episode reward: [(0, '19.610')] | |
| [2023-05-12 15:03:10,016][14794] Saving new best policy, reward=19.610! | |
| [2023-05-12 15:03:13,476][14807] Updated weights for policy 0, policy_version 640 (0.0012) | |
| [2023-05-12 15:03:14,999][00161] Fps is (10 sec: 3276.7, 60 sec: 3550.0, 300 sec: 3526.7). Total num frames: 2625536. Throughput: 0: 868.9. Samples: 654268. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:03:15,004][00161] Avg episode reward: [(0, '21.347')] | |
| [2023-05-12 15:03:15,011][14794] Saving new best policy, reward=21.347! | |
| [2023-05-12 15:03:20,006][00161] Fps is (10 sec: 4093.1, 60 sec: 3549.6, 300 sec: 3540.5). Total num frames: 2646016. Throughput: 0: 910.1. Samples: 660638. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:03:20,009][00161] Avg episode reward: [(0, '22.322')] | |
| [2023-05-12 15:03:20,023][14794] Saving new best policy, reward=22.322! | |
| [2023-05-12 15:03:24,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 2658304. Throughput: 0: 869.4. Samples: 664996. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:03:25,009][00161] Avg episode reward: [(0, '22.564')] | |
| [2023-05-12 15:03:25,018][14794] Saving new best policy, reward=22.564! | |
| [2023-05-12 15:03:25,292][14807] Updated weights for policy 0, policy_version 650 (0.0012) | |
| [2023-05-12 15:03:29,999][00161] Fps is (10 sec: 2869.2, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2674688. Throughput: 0: 843.6. Samples: 666850. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:03:30,005][00161] Avg episode reward: [(0, '23.283')] | |
| [2023-05-12 15:03:30,015][14794] Saving new best policy, reward=23.283! | |
| [2023-05-12 15:03:34,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2695168. Throughput: 0: 891.4. Samples: 673098. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:03:35,001][00161] Avg episode reward: [(0, '24.490')] | |
| [2023-05-12 15:03:35,011][14794] Saving new best policy, reward=24.490! | |
| [2023-05-12 15:03:36,058][14807] Updated weights for policy 0, policy_version 660 (0.0012) | |
| [2023-05-12 15:03:40,000][00161] Fps is (10 sec: 4095.5, 60 sec: 3549.8, 300 sec: 3540.6). Total num frames: 2715648. Throughput: 0: 898.8. Samples: 678746. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:03:40,007][00161] Avg episode reward: [(0, '24.077')] | |
| [2023-05-12 15:03:45,001][00161] Fps is (10 sec: 3276.1, 60 sec: 3481.9, 300 sec: 3526.7). Total num frames: 2727936. Throughput: 0: 873.4. Samples: 680756. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:03:45,009][00161] Avg episode reward: [(0, '23.358')] | |
| [2023-05-12 15:03:48,824][14807] Updated weights for policy 0, policy_version 670 (0.0012) | |
| [2023-05-12 15:03:49,999][00161] Fps is (10 sec: 3277.2, 60 sec: 3550.0, 300 sec: 3526.7). Total num frames: 2748416. Throughput: 0: 854.8. Samples: 685512. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:03:50,003][00161] Avg episode reward: [(0, '23.104')] | |
| [2023-05-12 15:03:54,999][00161] Fps is (10 sec: 4096.8, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2768896. Throughput: 0: 905.6. Samples: 691910. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:03:55,001][00161] Avg episode reward: [(0, '22.997')] | |
| [2023-05-12 15:03:59,925][14807] Updated weights for policy 0, policy_version 680 (0.0012) | |
| [2023-05-12 15:03:59,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3540.6). Total num frames: 2785280. Throughput: 0: 897.6. Samples: 694662. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:04:00,005][00161] Avg episode reward: [(0, '23.105')] | |
| [2023-05-12 15:04:04,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 2797568. Throughput: 0: 846.8. Samples: 698740. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:04:05,002][00161] Avg episode reward: [(0, '24.376')] | |
| [2023-05-12 15:04:09,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2818048. Throughput: 0: 878.8. Samples: 704540. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:10,002][00161] Avg episode reward: [(0, '24.754')] | |
| [2023-05-12 15:04:10,016][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000688_2818048.pth... | |
| [2023-05-12 15:04:10,092][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000482_1974272.pth | |
| [2023-05-12 15:04:10,103][14794] Saving new best policy, reward=24.754! | |
| [2023-05-12 15:04:11,533][14807] Updated weights for policy 0, policy_version 690 (0.0013) | |
| [2023-05-12 15:04:14,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 2838528. Throughput: 0: 904.7. Samples: 707562. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:15,003][00161] Avg episode reward: [(0, '24.696')] | |
| [2023-05-12 15:04:19,999][00161] Fps is (10 sec: 3686.3, 60 sec: 3482.0, 300 sec: 3540.6). Total num frames: 2854912. Throughput: 0: 879.1. Samples: 712660. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:04:20,001][00161] Avg episode reward: [(0, '24.538')] | |
| [2023-05-12 15:04:24,188][14807] Updated weights for policy 0, policy_version 700 (0.0012) | |
| [2023-05-12 15:04:24,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 2867200. Throughput: 0: 852.2. Samples: 717096. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:25,001][00161] Avg episode reward: [(0, '23.672')] | |
| [2023-05-12 15:04:29,999][00161] Fps is (10 sec: 3686.5, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 2891776. Throughput: 0: 875.1. Samples: 720136. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:30,005][00161] Avg episode reward: [(0, '21.646')] | |
| [2023-05-12 15:04:33,977][14807] Updated weights for policy 0, policy_version 710 (0.0012) | |
| [2023-05-12 15:04:34,999][00161] Fps is (10 sec: 4095.8, 60 sec: 3549.8, 300 sec: 3526.7). Total num frames: 2908160. Throughput: 0: 913.4. Samples: 726614. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:04:35,002][00161] Avg episode reward: [(0, '20.079')] | |
| [2023-05-12 15:04:39,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3526.7). Total num frames: 2920448. Throughput: 0: 860.7. Samples: 730640. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:40,002][00161] Avg episode reward: [(0, '20.213')] | |
| [2023-05-12 15:04:44,999][00161] Fps is (10 sec: 3276.9, 60 sec: 3550.0, 300 sec: 3526.7). Total num frames: 2940928. Throughput: 0: 849.8. Samples: 732904. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:45,001][00161] Avg episode reward: [(0, '18.733')] | |
| [2023-05-12 15:04:46,594][14807] Updated weights for policy 0, policy_version 720 (0.0020) | |
| [2023-05-12 15:04:49,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 2961408. Throughput: 0: 900.7. Samples: 739270. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:04:50,004][00161] Avg episode reward: [(0, '19.226')] | |
| [2023-05-12 15:04:54,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 2977792. Throughput: 0: 891.4. Samples: 744654. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:04:55,005][00161] Avg episode reward: [(0, '20.089')] | |
| [2023-05-12 15:04:58,797][14807] Updated weights for policy 0, policy_version 730 (0.0014) | |
| [2023-05-12 15:04:59,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 2990080. Throughput: 0: 870.1. Samples: 746718. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:05:00,002][00161] Avg episode reward: [(0, '19.347')] | |
| [2023-05-12 15:05:04,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3014656. Throughput: 0: 872.7. Samples: 751930. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:05,001][00161] Avg episode reward: [(0, '20.393')] | |
| [2023-05-12 15:05:08,904][14807] Updated weights for policy 0, policy_version 740 (0.0014) | |
| [2023-05-12 15:05:10,002][00161] Fps is (10 sec: 4504.2, 60 sec: 3618.0, 300 sec: 3540.6). Total num frames: 3035136. Throughput: 0: 915.4. Samples: 758290. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:10,005][00161] Avg episode reward: [(0, '20.336')] | |
| [2023-05-12 15:05:14,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3047424. Throughput: 0: 899.8. Samples: 760628. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:15,004][00161] Avg episode reward: [(0, '19.710')] | |
| [2023-05-12 15:05:19,999][00161] Fps is (10 sec: 2868.0, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3063808. Throughput: 0: 846.7. Samples: 764714. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:05:20,006][00161] Avg episode reward: [(0, '18.179')] | |
| [2023-05-12 15:05:21,647][14807] Updated weights for policy 0, policy_version 750 (0.0030) | |
| [2023-05-12 15:05:25,001][00161] Fps is (10 sec: 3685.7, 60 sec: 3618.0, 300 sec: 3526.7). Total num frames: 3084288. Throughput: 0: 894.5. Samples: 770896. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:25,011][00161] Avg episode reward: [(0, '18.959')] | |
| [2023-05-12 15:05:29,999][00161] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3104768. Throughput: 0: 912.8. Samples: 773978. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:05:30,003][00161] Avg episode reward: [(0, '19.406')] | |
| [2023-05-12 15:05:32,857][14807] Updated weights for policy 0, policy_version 760 (0.0012) | |
| [2023-05-12 15:05:34,999][00161] Fps is (10 sec: 3277.4, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3117056. Throughput: 0: 874.4. Samples: 778618. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:35,002][00161] Avg episode reward: [(0, '20.337')] | |
| [2023-05-12 15:05:40,000][00161] Fps is (10 sec: 2866.8, 60 sec: 3549.8, 300 sec: 3512.8). Total num frames: 3133440. Throughput: 0: 857.9. Samples: 783262. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:40,008][00161] Avg episode reward: [(0, '19.447')] | |
| [2023-05-12 15:05:44,387][14807] Updated weights for policy 0, policy_version 770 (0.0015) | |
| [2023-05-12 15:05:44,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3153920. Throughput: 0: 883.3. Samples: 786466. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:45,001][00161] Avg episode reward: [(0, '19.820')] | |
| [2023-05-12 15:05:49,999][00161] Fps is (10 sec: 3686.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3170304. Throughput: 0: 899.7. Samples: 792416. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:50,004][00161] Avg episode reward: [(0, '20.251')] | |
| [2023-05-12 15:05:54,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3526.7). Total num frames: 3186688. Throughput: 0: 844.4. Samples: 796284. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:05:55,007][00161] Avg episode reward: [(0, '19.327')] | |
| [2023-05-12 15:05:57,184][14807] Updated weights for policy 0, policy_version 780 (0.0012) | |
| [2023-05-12 15:05:59,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3203072. Throughput: 0: 851.5. Samples: 798944. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:06:00,002][00161] Avg episode reward: [(0, '21.087')] | |
| [2023-05-12 15:06:04,999][00161] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3227648. Throughput: 0: 904.4. Samples: 805412. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:06:05,004][00161] Avg episode reward: [(0, '21.977')] | |
| [2023-05-12 15:06:07,102][14807] Updated weights for policy 0, policy_version 790 (0.0010) | |
| [2023-05-12 15:06:09,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.5, 300 sec: 3526.7). Total num frames: 3239936. Throughput: 0: 881.1. Samples: 810542. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:10,008][00161] Avg episode reward: [(0, '23.053')] | |
| [2023-05-12 15:06:10,025][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000792_3244032.pth... | |
| [2023-05-12 15:06:10,121][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000585_2396160.pth | |
| [2023-05-12 15:06:14,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3256320. Throughput: 0: 856.9. Samples: 812538. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:06:15,006][00161] Avg episode reward: [(0, '23.133')] | |
| [2023-05-12 15:06:19,449][14807] Updated weights for policy 0, policy_version 800 (0.0013) | |
| [2023-05-12 15:06:19,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3276800. Throughput: 0: 876.6. Samples: 818066. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:06:20,007][00161] Avg episode reward: [(0, '24.427')] | |
| [2023-05-12 15:06:24,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3550.0, 300 sec: 3526.7). Total num frames: 3297280. Throughput: 0: 914.7. Samples: 824420. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:25,001][00161] Avg episode reward: [(0, '25.175')] | |
| [2023-05-12 15:06:25,008][14794] Saving new best policy, reward=25.175! | |
| [2023-05-12 15:06:30,000][00161] Fps is (10 sec: 3276.6, 60 sec: 3413.3, 300 sec: 3526.7). Total num frames: 3309568. Throughput: 0: 888.0. Samples: 826428. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:06:30,008][00161] Avg episode reward: [(0, '24.277')] | |
| [2023-05-12 15:06:32,044][14807] Updated weights for policy 0, policy_version 810 (0.0012) | |
| [2023-05-12 15:06:34,999][00161] Fps is (10 sec: 2867.1, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3325952. Throughput: 0: 848.9. Samples: 830616. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:35,006][00161] Avg episode reward: [(0, '24.588')] | |
| [2023-05-12 15:06:40,002][00161] Fps is (10 sec: 3685.5, 60 sec: 3549.8, 300 sec: 3498.9). Total num frames: 3346432. Throughput: 0: 902.6. Samples: 836904. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:06:40,008][00161] Avg episode reward: [(0, '23.210')] | |
| [2023-05-12 15:06:41,995][14807] Updated weights for policy 0, policy_version 820 (0.0012) | |
| [2023-05-12 15:06:44,999][00161] Fps is (10 sec: 4096.1, 60 sec: 3549.9, 300 sec: 3526.7). Total num frames: 3366912. Throughput: 0: 913.2. Samples: 840040. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:45,009][00161] Avg episode reward: [(0, '22.182')] | |
| [2023-05-12 15:06:49,999][00161] Fps is (10 sec: 3277.8, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3379200. Throughput: 0: 865.4. Samples: 844354. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:50,002][00161] Avg episode reward: [(0, '22.447')] | |
| [2023-05-12 15:06:54,726][14807] Updated weights for policy 0, policy_version 830 (0.0012) | |
| [2023-05-12 15:06:54,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 3399680. Throughput: 0: 864.7. Samples: 849454. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:06:55,002][00161] Avg episode reward: [(0, '21.429')] | |
| [2023-05-12 15:06:59,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3512.9). Total num frames: 3420160. Throughput: 0: 890.9. Samples: 852630. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:00,001][00161] Avg episode reward: [(0, '20.401')] | |
| [2023-05-12 15:07:05,003][00161] Fps is (10 sec: 3684.9, 60 sec: 3481.4, 300 sec: 3526.7). Total num frames: 3436544. Throughput: 0: 893.3. Samples: 858268. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:05,006][00161] Avg episode reward: [(0, '21.711')] | |
| [2023-05-12 15:07:06,338][14807] Updated weights for policy 0, policy_version 840 (0.0014) | |
| [2023-05-12 15:07:09,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.9). Total num frames: 3448832. Throughput: 0: 842.1. Samples: 862316. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:10,006][00161] Avg episode reward: [(0, '21.311')] | |
| [2023-05-12 15:07:15,001][00161] Fps is (10 sec: 3277.5, 60 sec: 3549.8, 300 sec: 3512.9). Total num frames: 3469312. Throughput: 0: 864.5. Samples: 865332. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:15,004][00161] Avg episode reward: [(0, '20.818')] | |
| [2023-05-12 15:07:17,217][14807] Updated weights for policy 0, policy_version 850 (0.0015) | |
| [2023-05-12 15:07:20,000][00161] Fps is (10 sec: 4095.6, 60 sec: 3549.8, 300 sec: 3512.8). Total num frames: 3489792. Throughput: 0: 911.6. Samples: 871638. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:20,003][00161] Avg episode reward: [(0, '20.658')] | |
| [2023-05-12 15:07:24,999][00161] Fps is (10 sec: 3277.4, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 3502080. Throughput: 0: 872.4. Samples: 876158. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:25,005][00161] Avg episode reward: [(0, '20.421')] | |
| [2023-05-12 15:07:29,999][00161] Fps is (10 sec: 2867.5, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3518464. Throughput: 0: 844.8. Samples: 878058. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:30,002][00161] Avg episode reward: [(0, '21.196')] | |
| [2023-05-12 15:07:30,153][14807] Updated weights for policy 0, policy_version 860 (0.0012) | |
| [2023-05-12 15:07:34,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3526.7). Total num frames: 3543040. Throughput: 0: 882.9. Samples: 884084. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:35,001][00161] Avg episode reward: [(0, '21.304')] | |
| [2023-05-12 15:07:39,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3550.1, 300 sec: 3526.8). Total num frames: 3559424. Throughput: 0: 901.9. Samples: 890038. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:40,004][00161] Avg episode reward: [(0, '22.812')] | |
| [2023-05-12 15:07:40,771][14807] Updated weights for policy 0, policy_version 870 (0.0012) | |
| [2023-05-12 15:07:44,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3512.9). Total num frames: 3571712. Throughput: 0: 876.4. Samples: 892066. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:45,003][00161] Avg episode reward: [(0, '24.230')] | |
| [2023-05-12 15:07:49,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3592192. Throughput: 0: 850.1. Samples: 896518. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:07:50,004][00161] Avg episode reward: [(0, '25.936')] | |
| [2023-05-12 15:07:50,014][14794] Saving new best policy, reward=25.936! | |
| [2023-05-12 15:07:52,799][14807] Updated weights for policy 0, policy_version 880 (0.0013) | |
| [2023-05-12 15:07:55,023][00161] Fps is (10 sec: 4086.0, 60 sec: 3548.4, 300 sec: 3512.5). Total num frames: 3612672. Throughput: 0: 897.0. Samples: 902704. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:07:55,026][00161] Avg episode reward: [(0, '24.829')] | |
| [2023-05-12 15:07:59,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3499.0). Total num frames: 3624960. Throughput: 0: 892.4. Samples: 905488. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:00,001][00161] Avg episode reward: [(0, '25.750')] | |
| [2023-05-12 15:08:04,999][00161] Fps is (10 sec: 2874.3, 60 sec: 3413.6, 300 sec: 3512.8). Total num frames: 3641344. Throughput: 0: 842.1. Samples: 909530. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:05,001][00161] Avg episode reward: [(0, '25.266')] | |
| [2023-05-12 15:08:05,769][14807] Updated weights for policy 0, policy_version 890 (0.0027) | |
| [2023-05-12 15:08:09,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3661824. Throughput: 0: 868.5. Samples: 915240. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:08:10,001][00161] Avg episode reward: [(0, '24.576')] | |
| [2023-05-12 15:08:10,012][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000894_3661824.pth... | |
| [2023-05-12 15:08:10,099][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000688_2818048.pth | |
| [2023-05-12 15:08:15,000][00161] Fps is (10 sec: 4095.6, 60 sec: 3549.9, 300 sec: 3512.9). Total num frames: 3682304. Throughput: 0: 893.4. Samples: 918260. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:08:15,007][00161] Avg episode reward: [(0, '22.707')] | |
| [2023-05-12 15:08:15,884][14807] Updated weights for policy 0, policy_version 900 (0.0011) | |
| [2023-05-12 15:08:19,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3512.8). Total num frames: 3694592. Throughput: 0: 874.7. Samples: 923444. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:20,006][00161] Avg episode reward: [(0, '22.903')] | |
| [2023-05-12 15:08:24,999][00161] Fps is (10 sec: 2867.5, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3710976. Throughput: 0: 837.3. Samples: 927716. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:08:25,004][00161] Avg episode reward: [(0, '23.459')] | |
| [2023-05-12 15:08:28,355][14807] Updated weights for policy 0, policy_version 910 (0.0012) | |
| [2023-05-12 15:08:29,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3731456. Throughput: 0: 861.5. Samples: 930834. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:30,002][00161] Avg episode reward: [(0, '22.314')] | |
| [2023-05-12 15:08:34,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3512.9). Total num frames: 3751936. Throughput: 0: 904.7. Samples: 937228. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:35,002][00161] Avg episode reward: [(0, '21.472')] | |
| [2023-05-12 15:08:39,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3512.9). Total num frames: 3764224. Throughput: 0: 857.5. Samples: 941272. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:08:40,001][00161] Avg episode reward: [(0, '21.267')] | |
| [2023-05-12 15:08:40,584][14807] Updated weights for policy 0, policy_version 920 (0.0020) | |
| [2023-05-12 15:08:44,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3784704. Throughput: 0: 845.2. Samples: 943524. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:08:45,001][00161] Avg episode reward: [(0, '21.269')] | |
| [2023-05-12 15:08:49,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3805184. Throughput: 0: 898.6. Samples: 949966. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:08:50,001][00161] Avg episode reward: [(0, '21.632')] | |
| [2023-05-12 15:08:50,639][14807] Updated weights for policy 0, policy_version 930 (0.0012) | |
| [2023-05-12 15:08:54,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3483.0, 300 sec: 3512.8). Total num frames: 3821568. Throughput: 0: 891.6. Samples: 955360. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:08:55,004][00161] Avg episode reward: [(0, '23.602')] | |
| [2023-05-12 15:08:59,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3833856. Throughput: 0: 869.5. Samples: 957386. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:09:00,002][00161] Avg episode reward: [(0, '24.304')] | |
| [2023-05-12 15:09:03,344][14807] Updated weights for policy 0, policy_version 940 (0.0020) | |
| [2023-05-12 15:09:04,999][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3854336. Throughput: 0: 869.3. Samples: 962564. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:09:05,002][00161] Avg episode reward: [(0, '25.870')] | |
| [2023-05-12 15:09:09,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3874816. Throughput: 0: 915.1. Samples: 968894. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:09:10,008][00161] Avg episode reward: [(0, '28.284')] | |
| [2023-05-12 15:09:10,020][14794] Saving new best policy, reward=28.284! | |
| [2023-05-12 15:09:14,914][14807] Updated weights for policy 0, policy_version 950 (0.0013) | |
| [2023-05-12 15:09:14,999][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3512.8). Total num frames: 3891200. Throughput: 0: 895.7. Samples: 971140. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:09:15,001][00161] Avg episode reward: [(0, '28.033')] | |
| [2023-05-12 15:09:19,999][00161] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3512.8). Total num frames: 3903488. Throughput: 0: 842.5. Samples: 975142. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:09:20,004][00161] Avg episode reward: [(0, '27.482')] | |
| [2023-05-12 15:09:25,002][00161] Fps is (10 sec: 3685.3, 60 sec: 3618.0, 300 sec: 3512.8). Total num frames: 3928064. Throughput: 0: 889.8. Samples: 981316. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:09:25,004][00161] Avg episode reward: [(0, '26.385')] | |
| [2023-05-12 15:09:25,903][14807] Updated weights for policy 0, policy_version 960 (0.0012) | |
| [2023-05-12 15:09:30,002][00161] Fps is (10 sec: 4094.8, 60 sec: 3549.7, 300 sec: 3512.8). Total num frames: 3944448. Throughput: 0: 909.9. Samples: 984474. Policy #0 lag: (min: 0.0, avg: 0.1, max: 1.0) | |
| [2023-05-12 15:09:30,004][00161] Avg episode reward: [(0, '25.543')] | |
| [2023-05-12 15:09:34,999][00161] Fps is (10 sec: 2868.0, 60 sec: 3413.3, 300 sec: 3512.8). Total num frames: 3956736. Throughput: 0: 869.3. Samples: 989086. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:09:35,004][00161] Avg episode reward: [(0, '25.395')] | |
| [2023-05-12 15:09:38,580][14807] Updated weights for policy 0, policy_version 970 (0.0015) | |
| [2023-05-12 15:09:39,999][00161] Fps is (10 sec: 3277.8, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3977216. Throughput: 0: 859.4. Samples: 994034. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:09:40,003][00161] Avg episode reward: [(0, '22.917')] | |
| [2023-05-12 15:09:44,999][00161] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3512.8). Total num frames: 3997696. Throughput: 0: 884.5. Samples: 997188. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) | |
| [2023-05-12 15:09:45,001][00161] Avg episode reward: [(0, '22.483')] | |
| [2023-05-12 15:09:46,458][14794] Stopping Batcher_0... | |
| [2023-05-12 15:09:46,459][14794] Loop batcher_evt_loop terminating... | |
| [2023-05-12 15:09:46,459][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-05-12 15:09:46,458][00161] Component Batcher_0 stopped! | |
| [2023-05-12 15:09:46,462][00161] Component RolloutWorker_w0 process died already! Don't wait for it. | |
| [2023-05-12 15:09:46,468][00161] Component RolloutWorker_w2 process died already! Don't wait for it. | |
| [2023-05-12 15:09:46,472][00161] Component RolloutWorker_w6 process died already! Don't wait for it. | |
| [2023-05-12 15:09:46,475][00161] Component RolloutWorker_w7 process died already! Don't wait for it. | |
| [2023-05-12 15:09:46,524][14807] Weights refcount: 2 0 | |
| [2023-05-12 15:09:46,528][14807] Stopping InferenceWorker_p0-w0... | |
| [2023-05-12 15:09:46,531][14807] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-05-12 15:09:46,528][00161] Component InferenceWorker_p0-w0 stopped! | |
| [2023-05-12 15:09:46,552][14813] Stopping RolloutWorker_w4... | |
| [2023-05-12 15:09:46,549][00161] Component RolloutWorker_w5 stopped! | |
| [2023-05-12 15:09:46,556][00161] Component RolloutWorker_w4 stopped! | |
| [2023-05-12 15:09:46,557][14814] Stopping RolloutWorker_w5... | |
| [2023-05-12 15:09:46,554][14813] Loop rollout_proc4_evt_loop terminating... | |
| [2023-05-12 15:09:46,558][14814] Loop rollout_proc5_evt_loop terminating... | |
| [2023-05-12 15:09:46,565][14794] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000792_3244032.pth | |
| [2023-05-12 15:09:46,572][00161] Component RolloutWorker_w3 stopped! | |
| [2023-05-12 15:09:46,574][14811] Stopping RolloutWorker_w3... | |
| [2023-05-12 15:09:46,577][14811] Loop rollout_proc3_evt_loop terminating... | |
| [2023-05-12 15:09:46,578][14794] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-05-12 15:09:46,587][00161] Component RolloutWorker_w1 stopped! | |
| [2023-05-12 15:09:46,588][14809] Stopping RolloutWorker_w1... | |
| [2023-05-12 15:09:46,589][14809] Loop rollout_proc1_evt_loop terminating... | |
| [2023-05-12 15:09:46,748][00161] Component LearnerWorker_p0 stopped! | |
| [2023-05-12 15:09:46,755][00161] Waiting for process learner_proc0 to stop... | |
| [2023-05-12 15:09:46,761][14794] Stopping LearnerWorker_p0... | |
| [2023-05-12 15:09:46,763][14794] Loop learner_proc0_evt_loop terminating... | |
| [2023-05-12 15:09:48,815][00161] Waiting for process inference_proc0-0 to join... | |
| [2023-05-12 15:09:48,820][00161] Waiting for process rollout_proc0 to join... | |
| [2023-05-12 15:09:48,821][00161] Waiting for process rollout_proc1 to join... | |
| [2023-05-12 15:09:49,394][00161] Waiting for process rollout_proc2 to join... | |
| [2023-05-12 15:09:49,401][00161] Waiting for process rollout_proc3 to join... | |
| [2023-05-12 15:09:49,403][00161] Waiting for process rollout_proc4 to join... | |
| [2023-05-12 15:09:49,404][00161] Waiting for process rollout_proc5 to join... | |
| [2023-05-12 15:09:49,411][00161] Waiting for process rollout_proc6 to join... | |
| [2023-05-12 15:09:49,413][00161] Waiting for process rollout_proc7 to join... | |
| [2023-05-12 15:09:49,414][00161] Batcher 0 profile tree view: | |
| batching: 22.1168, releasing_batches: 0.0224 | |
| [2023-05-12 15:09:49,416][00161] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0008 | |
| wait_policy_total: 504.8019 | |
| update_model: 8.5428 | |
| weight_update: 0.0015 | |
| one_step: 0.0023 | |
| handle_policy_step: 594.3362 | |
| deserialize: 16.1731, stack: 3.6388, obs_to_device_normalize: 134.0137, forward: 302.1865, send_messages: 22.5537 | |
| prepare_outputs: 85.4514 | |
| to_cpu: 52.4346 | |
| [2023-05-12 15:09:49,417][00161] Learner 0 profile tree view: | |
| misc: 0.0058, prepare_batch: 15.9330 | |
| train: 69.1769 | |
| epoch_init: 0.0056, minibatch_init: 0.0092, losses_postprocess: 0.4942, kl_divergence: 0.5352, after_optimizer: 32.4545 | |
| calculate_losses: 21.9232 | |
| losses_init: 0.0040, forward_head: 1.5467, bptt_initial: 14.6764, tail: 0.8367, advantages_returns: 0.2248, losses: 2.4162 | |
| bptt: 1.9612 | |
| bptt_forward_core: 1.8950 | |
| update: 13.2467 | |
| clip: 1.4180 | |
| [2023-05-12 15:09:49,420][00161] Loop Runner_EvtLoop terminating... | |
| [2023-05-12 15:09:49,421][00161] Runner profile tree view: | |
| main_loop: 1175.7107 | |
| [2023-05-12 15:09:49,425][00161] Collected {0: 4005888}, FPS: 3407.2 | |
| [2023-05-12 15:10:36,017][00161] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-05-12 15:10:36,021][00161] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-05-12 15:10:36,025][00161] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-05-12 15:10:36,027][00161] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-05-12 15:10:36,029][00161] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:10:36,031][00161] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-05-12 15:10:36,033][00161] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:10:36,034][00161] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-05-12 15:10:36,035][00161] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-05-12 15:10:36,037][00161] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-05-12 15:10:36,038][00161] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-05-12 15:10:36,040][00161] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-05-12 15:10:36,041][00161] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-05-12 15:10:36,042][00161] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-05-12 15:10:36,044][00161] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-05-12 15:10:36,069][00161] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:10:36,071][00161] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:10:36,074][00161] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:10:36,088][00161] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:10:36,254][00161] Conv encoder output size: 512 | |
| [2023-05-12 15:10:36,260][00161] Policy head output size: 512 | |
| [2023-05-12 15:10:38,743][00161] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-05-12 15:10:39,862][00161] Num frames 100... | |
| [2023-05-12 15:10:39,980][00161] Num frames 200... | |
| [2023-05-12 15:10:40,099][00161] Num frames 300... | |
| [2023-05-12 15:10:40,219][00161] Num frames 400... | |
| [2023-05-12 15:10:40,333][00161] Num frames 500... | |
| [2023-05-12 15:10:40,457][00161] Num frames 600... | |
| [2023-05-12 15:10:40,584][00161] Num frames 700... | |
| [2023-05-12 15:10:40,718][00161] Avg episode rewards: #0: 18.680, true rewards: #0: 7.680 | |
| [2023-05-12 15:10:40,720][00161] Avg episode reward: 18.680, avg true_objective: 7.680 | |
| [2023-05-12 15:10:40,762][00161] Num frames 800... | |
| [2023-05-12 15:10:40,876][00161] Num frames 900... | |
| [2023-05-12 15:10:40,991][00161] Num frames 1000... | |
| [2023-05-12 15:10:41,109][00161] Num frames 1100... | |
| [2023-05-12 15:10:41,224][00161] Num frames 1200... | |
| [2023-05-12 15:10:41,338][00161] Num frames 1300... | |
| [2023-05-12 15:10:41,463][00161] Num frames 1400... | |
| [2023-05-12 15:10:41,586][00161] Num frames 1500... | |
| [2023-05-12 15:10:41,700][00161] Num frames 1600... | |
| [2023-05-12 15:10:41,822][00161] Num frames 1700... | |
| [2023-05-12 15:10:41,938][00161] Num frames 1800... | |
| [2023-05-12 15:10:42,056][00161] Num frames 1900... | |
| [2023-05-12 15:10:42,178][00161] Num frames 2000... | |
| [2023-05-12 15:10:42,298][00161] Num frames 2100... | |
| [2023-05-12 15:10:42,427][00161] Num frames 2200... | |
| [2023-05-12 15:10:42,561][00161] Num frames 2300... | |
| [2023-05-12 15:10:42,676][00161] Num frames 2400... | |
| [2023-05-12 15:10:42,793][00161] Num frames 2500... | |
| [2023-05-12 15:10:42,921][00161] Num frames 2600... | |
| [2023-05-12 15:10:43,037][00161] Num frames 2700... | |
| [2023-05-12 15:10:43,159][00161] Num frames 2800... | |
| [2023-05-12 15:10:43,294][00161] Avg episode rewards: #0: 37.839, true rewards: #0: 14.340 | |
| [2023-05-12 15:10:43,296][00161] Avg episode reward: 37.839, avg true_objective: 14.340 | |
| [2023-05-12 15:10:43,354][00161] Num frames 2900... | |
| [2023-05-12 15:10:43,515][00161] Num frames 3000... | |
| [2023-05-12 15:10:43,676][00161] Num frames 3100... | |
| [2023-05-12 15:10:43,841][00161] Num frames 3200... | |
| [2023-05-12 15:10:44,000][00161] Num frames 3300... | |
| [2023-05-12 15:10:44,156][00161] Num frames 3400... | |
| [2023-05-12 15:10:44,312][00161] Num frames 3500... | |
| [2023-05-12 15:10:44,431][00161] Avg episode rewards: #0: 29.466, true rewards: #0: 11.800 | |
| [2023-05-12 15:10:44,433][00161] Avg episode reward: 29.466, avg true_objective: 11.800 | |
| [2023-05-12 15:10:44,531][00161] Num frames 3600... | |
| [2023-05-12 15:10:44,698][00161] Num frames 3700... | |
| [2023-05-12 15:10:44,856][00161] Num frames 3800... | |
| [2023-05-12 15:10:45,023][00161] Num frames 3900... | |
| [2023-05-12 15:10:45,195][00161] Num frames 4000... | |
| [2023-05-12 15:10:45,360][00161] Num frames 4100... | |
| [2023-05-12 15:10:45,525][00161] Num frames 4200... | |
| [2023-05-12 15:10:45,706][00161] Num frames 4300... | |
| [2023-05-12 15:10:45,879][00161] Num frames 4400... | |
| [2023-05-12 15:10:46,048][00161] Num frames 4500... | |
| [2023-05-12 15:10:46,223][00161] Num frames 4600... | |
| [2023-05-12 15:10:46,425][00161] Avg episode rewards: #0: 28.967, true rewards: #0: 11.718 | |
| [2023-05-12 15:10:46,427][00161] Avg episode reward: 28.967, avg true_objective: 11.718 | |
| [2023-05-12 15:10:46,454][00161] Num frames 4700... | |
| [2023-05-12 15:10:46,640][00161] Num frames 4800... | |
| [2023-05-12 15:10:46,829][00161] Num frames 4900... | |
| [2023-05-12 15:10:46,995][00161] Num frames 5000... | |
| [2023-05-12 15:10:47,161][00161] Num frames 5100... | |
| [2023-05-12 15:10:47,325][00161] Num frames 5200... | |
| [2023-05-12 15:10:47,492][00161] Num frames 5300... | |
| [2023-05-12 15:10:47,659][00161] Num frames 5400... | |
| [2023-05-12 15:10:47,835][00161] Num frames 5500... | |
| [2023-05-12 15:10:48,004][00161] Num frames 5600... | |
| [2023-05-12 15:10:48,171][00161] Num frames 5700... | |
| [2023-05-12 15:10:48,296][00161] Num frames 5800... | |
| [2023-05-12 15:10:48,420][00161] Num frames 5900... | |
| [2023-05-12 15:10:48,536][00161] Num frames 6000... | |
| [2023-05-12 15:10:48,650][00161] Num frames 6100... | |
| [2023-05-12 15:10:48,773][00161] Num frames 6200... | |
| [2023-05-12 15:10:48,904][00161] Num frames 6300... | |
| [2023-05-12 15:10:49,053][00161] Avg episode rewards: #0: 31.356, true rewards: #0: 12.756 | |
| [2023-05-12 15:10:49,054][00161] Avg episode reward: 31.356, avg true_objective: 12.756 | |
| [2023-05-12 15:10:49,085][00161] Num frames 6400... | |
| [2023-05-12 15:10:49,210][00161] Num frames 6500... | |
| [2023-05-12 15:10:49,334][00161] Num frames 6600... | |
| [2023-05-12 15:10:49,448][00161] Num frames 6700... | |
| [2023-05-12 15:10:49,562][00161] Num frames 6800... | |
| [2023-05-12 15:10:49,684][00161] Avg episode rewards: #0: 27.263, true rewards: #0: 11.430 | |
| [2023-05-12 15:10:49,686][00161] Avg episode reward: 27.263, avg true_objective: 11.430 | |
| [2023-05-12 15:10:49,742][00161] Num frames 6900... | |
| [2023-05-12 15:10:49,864][00161] Num frames 7000... | |
| [2023-05-12 15:10:49,980][00161] Num frames 7100... | |
| [2023-05-12 15:10:50,099][00161] Num frames 7200... | |
| [2023-05-12 15:10:50,216][00161] Num frames 7300... | |
| [2023-05-12 15:10:50,333][00161] Num frames 7400... | |
| [2023-05-12 15:10:50,456][00161] Avg episode rewards: #0: 25.656, true rewards: #0: 10.656 | |
| [2023-05-12 15:10:50,458][00161] Avg episode reward: 25.656, avg true_objective: 10.656 | |
| [2023-05-12 15:10:50,510][00161] Num frames 7500... | |
| [2023-05-12 15:10:50,624][00161] Num frames 7600... | |
| [2023-05-12 15:10:50,744][00161] Num frames 7700... | |
| [2023-05-12 15:10:50,871][00161] Num frames 7800... | |
| [2023-05-12 15:10:50,985][00161] Num frames 7900... | |
| [2023-05-12 15:10:51,105][00161] Num frames 8000... | |
| [2023-05-12 15:10:51,226][00161] Num frames 8100... | |
| [2023-05-12 15:10:51,347][00161] Num frames 8200... | |
| [2023-05-12 15:10:51,554][00161] Num frames 8300... | |
| [2023-05-12 15:10:51,708][00161] Num frames 8400... | |
| [2023-05-12 15:10:51,852][00161] Num frames 8500... | |
| [2023-05-12 15:10:51,969][00161] Avg episode rewards: #0: 25.184, true rewards: #0: 10.684 | |
| [2023-05-12 15:10:51,971][00161] Avg episode reward: 25.184, avg true_objective: 10.684 | |
| [2023-05-12 15:10:52,032][00161] Num frames 8600... | |
| [2023-05-12 15:10:52,199][00161] Num frames 8700... | |
| [2023-05-12 15:10:52,345][00161] Num frames 8800... | |
| [2023-05-12 15:10:52,458][00161] Num frames 8900... | |
| [2023-05-12 15:10:52,578][00161] Num frames 9000... | |
| [2023-05-12 15:10:52,694][00161] Num frames 9100... | |
| [2023-05-12 15:10:52,850][00161] Avg episode rewards: #0: 24.097, true rewards: #0: 10.208 | |
| [2023-05-12 15:10:52,852][00161] Avg episode reward: 24.097, avg true_objective: 10.208 | |
| [2023-05-12 15:10:52,869][00161] Num frames 9200... | |
| [2023-05-12 15:10:53,053][00161] Num frames 9300... | |
| [2023-05-12 15:10:53,227][00161] Num frames 9400... | |
| [2023-05-12 15:10:53,398][00161] Num frames 9500... | |
| [2023-05-12 15:10:53,601][00161] Num frames 9600... | |
| [2023-05-12 15:10:53,789][00161] Num frames 9700... | |
| [2023-05-12 15:10:53,977][00161] Num frames 9800... | |
| [2023-05-12 15:10:54,144][00161] Num frames 9900... | |
| [2023-05-12 15:10:54,341][00161] Num frames 10000... | |
| [2023-05-12 15:10:54,636][00161] Num frames 10100... | |
| [2023-05-12 15:10:55,029][00161] Num frames 10200... | |
| [2023-05-12 15:10:55,201][00161] Num frames 10300... | |
| [2023-05-12 15:10:55,365][00161] Num frames 10400... | |
| [2023-05-12 15:10:55,548][00161] Avg episode rewards: #0: 24.467, true rewards: #0: 10.467 | |
| [2023-05-12 15:10:55,551][00161] Avg episode reward: 24.467, avg true_objective: 10.467 | |
| [2023-05-12 15:12:15,230][00161] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-05-12 15:16:02,100][00161] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-05-12 15:16:02,102][00161] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-05-12 15:16:02,104][00161] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-05-12 15:16:02,107][00161] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-05-12 15:16:02,109][00161] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:16:02,110][00161] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-05-12 15:16:02,113][00161] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-05-12 15:16:02,115][00161] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-05-12 15:16:02,116][00161] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-05-12 15:16:02,118][00161] Adding new argument 'hf_repository'='shreyansjain/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-05-12 15:16:02,120][00161] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-05-12 15:16:02,121][00161] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-05-12 15:16:02,123][00161] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-05-12 15:16:02,124][00161] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-05-12 15:16:02,126][00161] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-05-12 15:16:02,145][00161] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:16:02,149][00161] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:16:02,161][00161] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:16:02,198][00161] Conv encoder output size: 512 | |
| [2023-05-12 15:16:02,199][00161] Policy head output size: 512 | |
| [2023-05-12 15:16:02,219][00161] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-05-12 15:16:02,706][00161] Num frames 100... | |
| [2023-05-12 15:16:02,841][00161] Num frames 200... | |
| [2023-05-12 15:16:02,958][00161] Num frames 300... | |
| [2023-05-12 15:16:03,088][00161] Num frames 400... | |
| [2023-05-12 15:16:03,198][00161] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480 | |
| [2023-05-12 15:16:03,200][00161] Avg episode reward: 5.480, avg true_objective: 4.480 | |
| [2023-05-12 15:16:03,268][00161] Num frames 500... | |
| [2023-05-12 15:16:03,385][00161] Num frames 600... | |
| [2023-05-12 15:16:03,504][00161] Num frames 700... | |
| [2023-05-12 15:16:03,625][00161] Num frames 800... | |
| [2023-05-12 15:16:03,745][00161] Num frames 900... | |
| [2023-05-12 15:16:03,861][00161] Num frames 1000... | |
| [2023-05-12 15:16:03,990][00161] Num frames 1100... | |
| [2023-05-12 15:16:04,113][00161] Num frames 1200... | |
| [2023-05-12 15:16:04,238][00161] Num frames 1300... | |
| [2023-05-12 15:16:04,356][00161] Num frames 1400... | |
| [2023-05-12 15:16:04,469][00161] Num frames 1500... | |
| [2023-05-12 15:16:04,593][00161] Num frames 1600... | |
| [2023-05-12 15:16:04,715][00161] Num frames 1700... | |
| [2023-05-12 15:16:04,792][00161] Avg episode rewards: #0: 17.070, true rewards: #0: 8.570 | |
| [2023-05-12 15:16:04,795][00161] Avg episode reward: 17.070, avg true_objective: 8.570 | |
| [2023-05-12 15:16:04,906][00161] Num frames 1800... | |
| [2023-05-12 15:16:05,039][00161] Num frames 1900... | |
| [2023-05-12 15:16:05,156][00161] Num frames 2000... | |
| [2023-05-12 15:16:05,278][00161] Num frames 2100... | |
| [2023-05-12 15:16:05,400][00161] Num frames 2200... | |
| [2023-05-12 15:16:05,518][00161] Num frames 2300... | |
| [2023-05-12 15:16:05,643][00161] Num frames 2400... | |
| [2023-05-12 15:16:05,761][00161] Num frames 2500... | |
| [2023-05-12 15:16:05,857][00161] Avg episode rewards: #0: 17.447, true rewards: #0: 8.447 | |
| [2023-05-12 15:16:05,859][00161] Avg episode reward: 17.447, avg true_objective: 8.447 | |
| [2023-05-12 15:16:05,937][00161] Num frames 2600... | |
| [2023-05-12 15:16:06,063][00161] Num frames 2700... | |
| [2023-05-12 15:16:06,176][00161] Num frames 2800... | |
| [2023-05-12 15:16:06,293][00161] Num frames 2900... | |
| [2023-05-12 15:16:06,409][00161] Num frames 3000... | |
| [2023-05-12 15:16:06,535][00161] Num frames 3100... | |
| [2023-05-12 15:16:06,652][00161] Num frames 3200... | |
| [2023-05-12 15:16:06,767][00161] Avg episode rewards: #0: 16.625, true rewards: #0: 8.125 | |
| [2023-05-12 15:16:06,769][00161] Avg episode reward: 16.625, avg true_objective: 8.125 | |
| [2023-05-12 15:16:06,843][00161] Num frames 3300... | |
| [2023-05-12 15:16:06,963][00161] Num frames 3400... | |
| [2023-05-12 15:16:07,086][00161] Num frames 3500... | |
| [2023-05-12 15:16:07,207][00161] Num frames 3600... | |
| [2023-05-12 15:16:07,324][00161] Num frames 3700... | |
| [2023-05-12 15:16:07,444][00161] Num frames 3800... | |
| [2023-05-12 15:16:07,563][00161] Num frames 3900... | |
| [2023-05-12 15:16:07,682][00161] Num frames 4000... | |
| [2023-05-12 15:16:07,802][00161] Num frames 4100... | |
| [2023-05-12 15:16:07,920][00161] Num frames 4200... | |
| [2023-05-12 15:16:08,040][00161] Num frames 4300... | |
| [2023-05-12 15:16:08,165][00161] Num frames 4400... | |
| [2023-05-12 15:16:08,281][00161] Num frames 4500... | |
| [2023-05-12 15:16:08,398][00161] Num frames 4600... | |
| [2023-05-12 15:16:08,519][00161] Num frames 4700... | |
| [2023-05-12 15:16:08,637][00161] Num frames 4800... | |
| [2023-05-12 15:16:08,761][00161] Num frames 4900... | |
| [2023-05-12 15:16:08,880][00161] Num frames 5000... | |
| [2023-05-12 15:16:09,023][00161] Avg episode rewards: #0: 21.948, true rewards: #0: 10.148 | |
| [2023-05-12 15:16:09,026][00161] Avg episode reward: 21.948, avg true_objective: 10.148 | |
| [2023-05-12 15:16:09,058][00161] Num frames 5100... | |
| [2023-05-12 15:16:09,185][00161] Num frames 5200... | |
| [2023-05-12 15:16:09,305][00161] Num frames 5300... | |
| [2023-05-12 15:16:09,425][00161] Num frames 5400... | |
| [2023-05-12 15:16:09,560][00161] Num frames 5500... | |
| [2023-05-12 15:16:09,645][00161] Avg episode rewards: #0: 19.203, true rewards: #0: 9.203 | |
| [2023-05-12 15:16:09,646][00161] Avg episode reward: 19.203, avg true_objective: 9.203 | |
| [2023-05-12 15:16:09,741][00161] Num frames 5600... | |
| [2023-05-12 15:16:09,860][00161] Num frames 5700... | |
| [2023-05-12 15:16:09,981][00161] Num frames 5800... | |
| [2023-05-12 15:16:10,099][00161] Num frames 5900... | |
| [2023-05-12 15:16:10,222][00161] Num frames 6000... | |
| [2023-05-12 15:16:10,338][00161] Num frames 6100... | |
| [2023-05-12 15:16:10,466][00161] Num frames 6200... | |
| [2023-05-12 15:16:10,583][00161] Num frames 6300... | |
| [2023-05-12 15:16:10,703][00161] Num frames 6400... | |
| [2023-05-12 15:16:10,839][00161] Num frames 6500... | |
| [2023-05-12 15:16:10,955][00161] Num frames 6600... | |
| [2023-05-12 15:16:11,077][00161] Avg episode rewards: #0: 20.079, true rewards: #0: 9.507 | |
| [2023-05-12 15:16:11,079][00161] Avg episode reward: 20.079, avg true_objective: 9.507 | |
| [2023-05-12 15:16:11,143][00161] Num frames 6700... | |
| [2023-05-12 15:16:11,271][00161] Num frames 6800... | |
| [2023-05-12 15:16:11,392][00161] Num frames 6900... | |
| [2023-05-12 15:16:11,556][00161] Num frames 7000... | |
| [2023-05-12 15:16:11,723][00161] Num frames 7100... | |
| [2023-05-12 15:16:11,903][00161] Num frames 7200... | |
| [2023-05-12 15:16:12,080][00161] Num frames 7300... | |
| [2023-05-12 15:16:12,258][00161] Num frames 7400... | |
| [2023-05-12 15:16:12,443][00161] Num frames 7500... | |
| [2023-05-12 15:16:12,616][00161] Num frames 7600... | |
| [2023-05-12 15:16:12,788][00161] Num frames 7700... | |
| [2023-05-12 15:16:12,966][00161] Num frames 7800... | |
| [2023-05-12 15:16:13,133][00161] Num frames 7900... | |
| [2023-05-12 15:16:13,314][00161] Num frames 8000... | |
| [2023-05-12 15:16:13,495][00161] Num frames 8100... | |
| [2023-05-12 15:16:13,674][00161] Num frames 8200... | |
| [2023-05-12 15:16:13,855][00161] Num frames 8300... | |
| [2023-05-12 15:16:14,036][00161] Num frames 8400... | |
| [2023-05-12 15:16:14,211][00161] Num frames 8500... | |
| [2023-05-12 15:16:14,392][00161] Num frames 8600... | |
| [2023-05-12 15:16:14,569][00161] Num frames 8700... | |
| [2023-05-12 15:16:14,729][00161] Avg episode rewards: #0: 24.819, true rewards: #0: 10.944 | |
| [2023-05-12 15:16:14,731][00161] Avg episode reward: 24.819, avg true_objective: 10.944 | |
| [2023-05-12 15:16:14,821][00161] Num frames 8800... | |
| [2023-05-12 15:16:15,003][00161] Num frames 8900... | |
| [2023-05-12 15:16:15,182][00161] Num frames 9000... | |
| [2023-05-12 15:16:15,360][00161] Num frames 9100... | |
| [2023-05-12 15:16:15,540][00161] Num frames 9200... | |
| [2023-05-12 15:16:15,716][00161] Num frames 9300... | |
| [2023-05-12 15:16:15,892][00161] Num frames 9400... | |
| [2023-05-12 15:16:16,070][00161] Num frames 9500... | |
| [2023-05-12 15:16:16,253][00161] Num frames 9600... | |
| [2023-05-12 15:16:16,435][00161] Num frames 9700... | |
| [2023-05-12 15:16:16,569][00161] Num frames 9800... | |
| [2023-05-12 15:16:16,692][00161] Num frames 9900... | |
| [2023-05-12 15:16:16,816][00161] Num frames 10000... | |
| [2023-05-12 15:16:16,938][00161] Num frames 10100... | |
| [2023-05-12 15:16:17,061][00161] Num frames 10200... | |
| [2023-05-12 15:16:17,179][00161] Num frames 10300... | |
| [2023-05-12 15:16:17,300][00161] Num frames 10400... | |
| [2023-05-12 15:16:17,463][00161] Avg episode rewards: #0: 26.759, true rewards: #0: 11.648 | |
| [2023-05-12 15:16:17,464][00161] Avg episode reward: 26.759, avg true_objective: 11.648 | |
| [2023-05-12 15:16:17,492][00161] Num frames 10500... | |
| [2023-05-12 15:16:17,613][00161] Num frames 10600... | |
| [2023-05-12 15:16:17,742][00161] Num frames 10700... | |
| [2023-05-12 15:16:18,028][00161] Num frames 10800... | |
| [2023-05-12 15:16:18,162][00161] Avg episode rewards: #0: 24.767, true rewards: #0: 10.867 | |
| [2023-05-12 15:16:18,164][00161] Avg episode reward: 24.767, avg true_objective: 10.867 | |
| [2023-05-12 15:17:25,860][00161] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-05-12 15:17:29,065][00161] The model has been pushed to https://huggingface.co/shreyansjain/rl_course_vizdoom_health_gathering_supreme | |
| [2023-05-12 15:18:08,375][00161] Environment doom_basic already registered, overwriting... | |
| [2023-05-12 15:18:08,377][00161] Environment doom_two_colors_easy already registered, overwriting... | |
| [2023-05-12 15:18:08,378][00161] Environment doom_two_colors_hard already registered, overwriting... | |
| [2023-05-12 15:18:08,379][00161] Environment doom_dm already registered, overwriting... | |
| [2023-05-12 15:18:08,380][00161] Environment doom_dwango5 already registered, overwriting... | |
| [2023-05-12 15:18:08,384][00161] Environment doom_my_way_home_flat_actions already registered, overwriting... | |
| [2023-05-12 15:18:08,385][00161] Environment doom_defend_the_center_flat_actions already registered, overwriting... | |
| [2023-05-12 15:18:08,387][00161] Environment doom_my_way_home already registered, overwriting... | |
| [2023-05-12 15:18:08,388][00161] Environment doom_deadly_corridor already registered, overwriting... | |
| [2023-05-12 15:18:08,392][00161] Environment doom_defend_the_center already registered, overwriting... | |
| [2023-05-12 15:18:08,394][00161] Environment doom_defend_the_line already registered, overwriting... | |
| [2023-05-12 15:18:08,395][00161] Environment doom_health_gathering already registered, overwriting... | |
| [2023-05-12 15:18:08,396][00161] Environment doom_health_gathering_supreme already registered, overwriting... | |
| [2023-05-12 15:18:08,398][00161] Environment doom_battle already registered, overwriting... | |
| [2023-05-12 15:18:08,399][00161] Environment doom_battle2 already registered, overwriting... | |
| [2023-05-12 15:18:08,401][00161] Environment doom_duel_bots already registered, overwriting... | |
| [2023-05-12 15:18:08,402][00161] Environment doom_deathmatch_bots already registered, overwriting... | |
| [2023-05-12 15:18:08,403][00161] Environment doom_duel already registered, overwriting... | |
| [2023-05-12 15:18:08,404][00161] Environment doom_deathmatch_full already registered, overwriting... | |
| [2023-05-12 15:18:08,405][00161] Environment doom_benchmark already registered, overwriting... | |
| [2023-05-12 15:18:08,406][00161] register_encoder_factory: <function make_vizdoom_encoder at 0x7f9b6fe4d6c0> | |
| [2023-05-12 15:18:08,438][00161] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-05-12 15:18:08,441][00161] Overriding arg 'train_for_env_steps' with value 6000000 passed from command line | |
| [2023-05-12 15:18:08,448][00161] Experiment dir /content/train_dir/default_experiment already exists! | |
| [2023-05-12 15:18:08,450][00161] Resuming existing experiment from /content/train_dir/default_experiment... | |
| [2023-05-12 15:18:08,452][00161] Weights and Biases integration disabled | |
| [2023-05-12 15:18:08,455][00161] Environment var CUDA_VISIBLE_DEVICES is 0 | |
| [2023-05-12 15:18:09,872][00161] Starting experiment with the following configuration: | |
| help=False | |
| algo=APPO | |
| env=doom_health_gathering_supreme | |
| experiment=default_experiment | |
| train_dir=/content/train_dir | |
| restart_behavior=resume | |
| device=gpu | |
| seed=None | |
| num_policies=1 | |
| async_rl=True | |
| serial_mode=False | |
| batched_sampling=False | |
| num_batches_to_accumulate=2 | |
| worker_num_splits=2 | |
| policy_workers_per_policy=1 | |
| max_policy_lag=1000 | |
| num_workers=8 | |
| num_envs_per_worker=4 | |
| batch_size=1024 | |
| num_batches_per_epoch=1 | |
| num_epochs=1 | |
| rollout=32 | |
| recurrence=32 | |
| shuffle_minibatches=False | |
| gamma=0.99 | |
| reward_scale=1.0 | |
| reward_clip=1000.0 | |
| value_bootstrap=False | |
| normalize_returns=True | |
| exploration_loss_coeff=0.001 | |
| value_loss_coeff=0.5 | |
| kl_loss_coeff=0.0 | |
| exploration_loss=symmetric_kl | |
| gae_lambda=0.95 | |
| ppo_clip_ratio=0.1 | |
| ppo_clip_value=0.2 | |
| with_vtrace=False | |
| vtrace_rho=1.0 | |
| vtrace_c=1.0 | |
| optimizer=adam | |
| adam_eps=1e-06 | |
| adam_beta1=0.9 | |
| adam_beta2=0.999 | |
| max_grad_norm=4.0 | |
| learning_rate=0.0001 | |
| lr_schedule=constant | |
| lr_schedule_kl_threshold=0.008 | |
| lr_adaptive_min=1e-06 | |
| lr_adaptive_max=0.01 | |
| obs_subtract_mean=0.0 | |
| obs_scale=255.0 | |
| normalize_input=True | |
| normalize_input_keys=None | |
| decorrelate_experience_max_seconds=0 | |
| decorrelate_envs_on_one_worker=True | |
| actor_worker_gpus=[] | |
| set_workers_cpu_affinity=True | |
| force_envs_single_thread=False | |
| default_niceness=0 | |
| log_to_file=True | |
| experiment_summaries_interval=10 | |
| flush_summaries_interval=30 | |
| stats_avg=100 | |
| summaries_use_frameskip=True | |
| heartbeat_interval=20 | |
| heartbeat_reporting_interval=600 | |
| train_for_env_steps=6000000 | |
| train_for_seconds=10000000000 | |
| save_every_sec=120 | |
| keep_checkpoints=2 | |
| load_checkpoint_kind=latest | |
| save_milestones_sec=-1 | |
| save_best_every_sec=5 | |
| save_best_metric=reward | |
| save_best_after=100000 | |
| benchmark=False | |
| encoder_mlp_layers=[512, 512] | |
| encoder_conv_architecture=convnet_simple | |
| encoder_conv_mlp_layers=[512] | |
| use_rnn=True | |
| rnn_size=512 | |
| rnn_type=gru | |
| rnn_num_layers=1 | |
| decoder_mlp_layers=[] | |
| nonlinearity=elu | |
| policy_initialization=orthogonal | |
| policy_init_gain=1.0 | |
| actor_critic_share_weights=True | |
| adaptive_stddev=True | |
| continuous_tanh_scale=0.0 | |
| initial_stddev=1.0 | |
| use_env_info_cache=False | |
| env_gpu_actions=False | |
| env_gpu_observations=True | |
| env_frameskip=4 | |
| env_framestack=1 | |
| pixel_format=CHW | |
| use_record_episode_statistics=False | |
| with_wandb=False | |
| wandb_user=None | |
| wandb_project=sample_factory | |
| wandb_group=None | |
| wandb_job_type=SF | |
| wandb_tags=[] | |
| with_pbt=False | |
| pbt_mix_policies_in_one_env=True | |
| pbt_period_env_steps=5000000 | |
| pbt_start_mutation=20000000 | |
| pbt_replace_fraction=0.3 | |
| pbt_mutation_rate=0.15 | |
| pbt_replace_reward_gap=0.1 | |
| pbt_replace_reward_gap_absolute=1e-06 | |
| pbt_optimize_gamma=False | |
| pbt_target_objective=true_objective | |
| pbt_perturb_min=1.1 | |
| pbt_perturb_max=1.5 | |
| num_agents=-1 | |
| num_humans=0 | |
| num_bots=-1 | |
| start_bot_difficulty=None | |
| timelimit=None | |
| res_w=128 | |
| res_h=72 | |
| wide_aspect_ratio=False | |
| eval_env_frameskip=1 | |
| fps=35 | |
| command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000 | |
| cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000} | |
| git_hash=unknown | |
| git_repo_name=not a git repository | |
| [2023-05-12 15:18:09,876][00161] Saving configuration to /content/train_dir/default_experiment/config.json... | |
| [2023-05-12 15:18:09,883][00161] Rollout worker 0 uses device cpu | |
| [2023-05-12 15:18:09,884][00161] Rollout worker 1 uses device cpu | |
| [2023-05-12 15:18:09,888][00161] Rollout worker 2 uses device cpu | |
| [2023-05-12 15:18:09,890][00161] Rollout worker 3 uses device cpu | |
| [2023-05-12 15:18:09,892][00161] Rollout worker 4 uses device cpu | |
| [2023-05-12 15:18:09,893][00161] Rollout worker 5 uses device cpu | |
| [2023-05-12 15:18:09,894][00161] Rollout worker 6 uses device cpu | |
| [2023-05-12 15:18:09,896][00161] Rollout worker 7 uses device cpu | |
| [2023-05-12 15:18:10,002][00161] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 15:18:10,004][00161] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-05-12 15:18:10,038][00161] Starting all processes... | |
| [2023-05-12 15:18:10,039][00161] Starting process learner_proc0 | |
| [2023-05-12 15:18:10,088][00161] Starting all processes... | |
| [2023-05-12 15:18:10,094][00161] Starting process inference_proc0-0 | |
| [2023-05-12 15:18:10,094][00161] Starting process rollout_proc0 | |
| [2023-05-12 15:18:10,096][00161] Starting process rollout_proc1 | |
| [2023-05-12 15:18:10,096][00161] Starting process rollout_proc2 | |
| [2023-05-12 15:18:10,096][00161] Starting process rollout_proc3 | |
| [2023-05-12 15:18:10,097][00161] Starting process rollout_proc4 | |
| [2023-05-12 15:18:10,097][00161] Starting process rollout_proc5 | |
| [2023-05-12 15:18:10,097][00161] Starting process rollout_proc6 | |
| [2023-05-12 15:18:10,097][00161] Starting process rollout_proc7 | |
| [2023-05-12 15:18:21,918][22711] Worker 0 uses CPU cores [0] | |
| [2023-05-12 15:18:21,929][22697] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 15:18:21,929][22697] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-05-12 15:18:21,974][22697] Num visible devices: 1 | |
| [2023-05-12 15:18:22,007][22697] Starting seed is not provided | |
| [2023-05-12 15:18:22,007][22697] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 15:18:22,007][22697] Initializing actor-critic model on device cuda:0 | |
| [2023-05-12 15:18:22,008][22697] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:18:22,009][22697] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:18:22,079][22697] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:18:22,126][22715] Worker 2 uses CPU cores [0] | |
| [2023-05-12 15:18:22,170][22712] Worker 1 uses CPU cores [1] | |
| [2023-05-12 15:18:22,245][22713] Worker 4 uses CPU cores [0] | |
| [2023-05-12 15:18:22,271][22716] Worker 5 uses CPU cores [1] | |
| [2023-05-12 15:18:22,286][22717] Worker 7 uses CPU cores [1] | |
| [2023-05-12 15:18:22,343][22710] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 15:18:22,343][22710] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-05-12 15:18:22,373][22710] Num visible devices: 1 | |
| [2023-05-12 15:18:22,402][22714] Worker 3 uses CPU cores [1] | |
| [2023-05-12 15:18:22,429][22718] Worker 6 uses CPU cores [0] | |
| [2023-05-12 15:18:22,454][22697] Conv encoder output size: 512 | |
| [2023-05-12 15:18:22,454][22697] Policy head output size: 512 | |
| [2023-05-12 15:18:22,469][22697] Created Actor Critic model with architecture: | |
| [2023-05-12 15:18:22,469][22697] 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) | |
| ) | |
| ) | |
| [2023-05-12 15:18:23,933][22697] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-05-12 15:18:23,935][22697] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-05-12 15:18:23,970][22697] Loading model from checkpoint | |
| [2023-05-12 15:18:23,975][22697] Loaded experiment state at self.train_step=978, self.env_steps=4005888 | |
| [2023-05-12 15:18:23,975][22697] Initialized policy 0 weights for model version 978 | |
| [2023-05-12 15:18:23,978][22697] LearnerWorker_p0 finished initialization! | |
| [2023-05-12 15:18:23,979][22697] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-05-12 15:18:24,240][22710] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:18:24,242][22710] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:18:24,263][22710] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:18:24,385][22710] Conv encoder output size: 512 | |
| [2023-05-12 15:18:24,385][22710] Policy head output size: 512 | |
| [2023-05-12 15:18:25,682][00161] Inference worker 0-0 is ready! | |
| [2023-05-12 15:18:25,685][00161] All inference workers are ready! Signal rollout workers to start! | |
| [2023-05-12 15:18:25,820][22712] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,825][22717] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,837][22718] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,833][22716] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,842][22711] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,847][22714] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,841][22713] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:25,853][22715] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-05-12 15:18:26,700][22711] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:26,706][22713] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:26,709][22714] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:26,714][22716] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:27,752][22714] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:27,763][22716] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:27,775][22717] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:28,101][22713] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:28,109][22711] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:28,170][22718] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:28,201][22715] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:28,456][00161] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-05-12 15:18:29,336][22717] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:29,516][22711] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:29,575][22714] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:29,599][22716] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:29,996][00161] Heartbeat connected on Batcher_0 | |
| [2023-05-12 15:18:29,998][00161] Heartbeat connected on LearnerWorker_p0 | |
| [2023-05-12 15:18:30,056][00161] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-05-12 15:18:30,079][22712] Decorrelating experience for 0 frames... | |
| [2023-05-12 15:18:31,051][22716] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:31,244][00161] Heartbeat connected on RolloutWorker_w5 | |
| [2023-05-12 15:18:31,465][22712] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:32,008][22715] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:32,301][22718] Decorrelating experience for 32 frames... | |
| [2023-05-12 15:18:32,326][22713] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:32,647][22711] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:32,965][00161] Heartbeat connected on RolloutWorker_w0 | |
| [2023-05-12 15:18:33,456][00161] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 1.6. Samples: 8. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-05-12 15:18:33,458][00161] Avg episode reward: [(0, '0.320')] | |
| [2023-05-12 15:18:34,714][22712] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:34,947][22713] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:34,960][22717] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:35,134][22715] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:35,296][22718] Decorrelating experience for 64 frames... | |
| [2023-05-12 15:18:35,315][00161] Heartbeat connected on RolloutWorker_w4 | |
| [2023-05-12 15:18:38,457][00161] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 162.8. Samples: 1628. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-05-12 15:18:38,463][00161] Avg episode reward: [(0, '3.560')] | |
| [2023-05-12 15:18:38,561][22714] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:38,592][22712] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:38,777][22717] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:39,057][00161] Heartbeat connected on RolloutWorker_w3 | |
| [2023-05-12 15:18:39,119][00161] Heartbeat connected on RolloutWorker_w1 | |
| [2023-05-12 15:18:39,218][00161] Heartbeat connected on RolloutWorker_w7 | |
| [2023-05-12 15:18:39,776][22718] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:40,291][00161] Heartbeat connected on RolloutWorker_w6 | |
| [2023-05-12 15:18:41,407][22715] Decorrelating experience for 96 frames... | |
| [2023-05-12 15:18:41,683][22697] Signal inference workers to stop experience collection... | |
| [2023-05-12 15:18:41,692][22710] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-05-12 15:18:41,749][00161] Heartbeat connected on RolloutWorker_w2 | |
| [2023-05-12 15:18:41,918][22697] Signal inference workers to resume experience collection... | |
| [2023-05-12 15:18:41,919][22710] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-05-12 15:18:43,456][00161] Fps is (10 sec: 1638.4, 60 sec: 1092.3, 300 sec: 1092.3). Total num frames: 4022272. Throughput: 0: 194.3. Samples: 2914. Policy #0 lag: (min: 0.0, avg: 0.9, max: 1.0) | |
| [2023-05-12 15:18:43,458][00161] Avg episode reward: [(0, '7.028')] | |
| [2023-05-12 15:18:48,169][22710] Updated weights for policy 0, policy_version 988 (0.0025) | |
| [2023-05-12 15:18:48,456][00161] Fps is (10 sec: 4096.6, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 4046848. Throughput: 0: 447.8. Samples: 8956. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:18:48,458][00161] Avg episode reward: [(0, '14.569')] | |
| [2023-05-12 15:18:53,458][00161] Fps is (10 sec: 4095.1, 60 sec: 2293.6, 300 sec: 2293.6). Total num frames: 4063232. Throughput: 0: 579.6. Samples: 14492. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) | |
| [2023-05-12 15:18:53,461][00161] Avg episode reward: [(0, '18.060')] | |
| [2023-05-12 15:18:58,456][00161] Fps is (10 sec: 2867.2, 60 sec: 2321.1, 300 sec: 2321.1). Total num frames: 4075520. Throughput: 0: 557.1. Samples: 16712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:18:58,462][00161] Avg episode reward: [(0, '20.069')] | |
| [2023-05-12 15:19:01,961][22710] Updated weights for policy 0, policy_version 998 (0.0018) | |
| [2023-05-12 15:19:03,456][00161] Fps is (10 sec: 2867.9, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 4091904. Throughput: 0: 598.3. Samples: 20942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:19:03,462][00161] Avg episode reward: [(0, '20.825')] | |
| [2023-05-12 15:19:08,456][00161] Fps is (10 sec: 4096.0, 60 sec: 2764.8, 300 sec: 2764.8). Total num frames: 4116480. Throughput: 0: 692.1. Samples: 27684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:19:08,458][00161] Avg episode reward: [(0, '23.008')] | |
| [2023-05-12 15:19:10,995][22710] Updated weights for policy 0, policy_version 1008 (0.0019) | |
| [2023-05-12 15:19:13,456][00161] Fps is (10 sec: 4505.6, 60 sec: 2912.7, 300 sec: 2912.7). Total num frames: 4136960. Throughput: 0: 690.8. Samples: 31084. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:19:13,460][00161] Avg episode reward: [(0, '24.567')] | |
| [2023-05-12 15:19:18,457][00161] Fps is (10 sec: 3276.2, 60 sec: 2867.1, 300 sec: 2867.1). Total num frames: 4149248. Throughput: 0: 793.6. Samples: 35722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:19:18,463][00161] Avg episode reward: [(0, '25.719')] | |
| [2023-05-12 15:19:23,456][00161] Fps is (10 sec: 2867.2, 60 sec: 2904.5, 300 sec: 2904.5). Total num frames: 4165632. Throughput: 0: 851.3. Samples: 39934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:19:23,462][00161] Avg episode reward: [(0, '26.562')] | |
| [2023-05-12 15:19:24,549][22710] Updated weights for policy 0, policy_version 1018 (0.0035) | |
| [2023-05-12 15:19:28,456][00161] Fps is (10 sec: 3687.0, 60 sec: 3003.7, 300 sec: 3003.7). Total num frames: 4186112. Throughput: 0: 889.9. Samples: 42960. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-05-12 15:19:28,467][00161] Avg episode reward: [(0, '26.819')] | |
| [2023-05-12 15:19:33,456][00161] Fps is (10 sec: 4095.9, 60 sec: 3345.1, 300 sec: 3087.8). Total num frames: 4206592. Throughput: 0: 905.0. Samples: 49682. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:19:33,459][00161] Avg episode reward: [(0, '27.122')] | |
| [2023-05-12 15:19:33,540][22710] Updated weights for policy 0, policy_version 1028 (0.0027) | |
| [2023-05-12 15:19:38,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3618.2, 300 sec: 3101.3). Total num frames: 4222976. Throughput: 0: 888.3. Samples: 54464. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:19:38,459][00161] Avg episode reward: [(0, '26.159')] | |
| [2023-05-12 15:19:43,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3058.4). Total num frames: 4235264. Throughput: 0: 882.6. Samples: 56430. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:19:43,458][00161] Avg episode reward: [(0, '26.395')] | |
| [2023-05-12 15:19:47,682][22710] Updated weights for policy 0, policy_version 1038 (0.0020) | |
| [2023-05-12 15:19:48,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3072.0). Total num frames: 4251648. Throughput: 0: 889.6. Samples: 60972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:19:48,460][00161] Avg episode reward: [(0, '25.787')] | |
| [2023-05-12 15:19:53,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3550.0, 300 sec: 3180.4). Total num frames: 4276224. Throughput: 0: 885.2. Samples: 67520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:19:53,464][00161] Avg episode reward: [(0, '24.078')] | |
| [2023-05-12 15:19:58,228][22710] Updated weights for policy 0, policy_version 1048 (0.0014) | |
| [2023-05-12 15:19:58,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3185.8). Total num frames: 4292608. Throughput: 0: 875.4. Samples: 70478. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:19:58,461][00161] Avg episode reward: [(0, '23.732')] | |
| [2023-05-12 15:20:03,456][00161] Fps is (10 sec: 2867.0, 60 sec: 3549.8, 300 sec: 3147.4). Total num frames: 4304896. Throughput: 0: 860.8. Samples: 74456. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:20:03,464][00161] Avg episode reward: [(0, '23.913')] | |
| [2023-05-12 15:20:08,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3153.9). Total num frames: 4321280. Throughput: 0: 862.8. Samples: 78760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:20:08,458][00161] Avg episode reward: [(0, '24.297')] | |
| [2023-05-12 15:20:08,469][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001055_4321280.pth... | |
| [2023-05-12 15:20:08,613][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000894_3661824.pth | |
| [2023-05-12 15:20:11,391][22710] Updated weights for policy 0, policy_version 1058 (0.0025) | |
| [2023-05-12 15:20:13,456][00161] Fps is (10 sec: 3686.6, 60 sec: 3413.3, 300 sec: 3198.8). Total num frames: 4341760. Throughput: 0: 865.0. Samples: 81886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:20:13,458][00161] Avg episode reward: [(0, '25.512')] | |
| [2023-05-12 15:20:18,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3202.3). Total num frames: 4358144. Throughput: 0: 858.5. Samples: 88316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:20:18,458][00161] Avg episode reward: [(0, '25.608')] | |
| [2023-05-12 15:20:23,189][22710] Updated weights for policy 0, policy_version 1068 (0.0013) | |
| [2023-05-12 15:20:23,463][00161] Fps is (10 sec: 3274.4, 60 sec: 3481.2, 300 sec: 3205.4). Total num frames: 4374528. Throughput: 0: 843.8. Samples: 92442. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:20:23,466][00161] Avg episode reward: [(0, '26.200')] | |
| [2023-05-12 15:20:28,456][00161] Fps is (10 sec: 2867.1, 60 sec: 3345.1, 300 sec: 3174.4). Total num frames: 4386816. Throughput: 0: 845.3. Samples: 94470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:20:28,466][00161] Avg episode reward: [(0, '27.812')] | |
| [2023-05-12 15:20:33,456][00161] Fps is (10 sec: 3279.2, 60 sec: 3345.1, 300 sec: 3211.3). Total num frames: 4407296. Throughput: 0: 863.1. Samples: 99812. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:20:33,458][00161] Avg episode reward: [(0, '27.409')] | |
| [2023-05-12 15:20:34,605][22710] Updated weights for policy 0, policy_version 1078 (0.0028) | |
| [2023-05-12 15:20:38,456][00161] Fps is (10 sec: 4505.7, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 4431872. Throughput: 0: 863.8. Samples: 106392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:20:38,458][00161] Avg episode reward: [(0, '25.534')] | |
| [2023-05-12 15:20:43,458][00161] Fps is (10 sec: 3685.7, 60 sec: 3481.5, 300 sec: 3246.4). Total num frames: 4444160. Throughput: 0: 851.6. Samples: 108802. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) | |
| [2023-05-12 15:20:43,460][00161] Avg episode reward: [(0, '24.897')] | |
| [2023-05-12 15:20:47,215][22710] Updated weights for policy 0, policy_version 1088 (0.0020) | |
| [2023-05-12 15:20:48,456][00161] Fps is (10 sec: 2457.6, 60 sec: 3413.3, 300 sec: 3218.3). Total num frames: 4456448. Throughput: 0: 853.3. Samples: 112852. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:20:48,464][00161] Avg episode reward: [(0, '25.315')] | |
| [2023-05-12 15:20:53,456][00161] Fps is (10 sec: 3277.4, 60 sec: 3345.1, 300 sec: 3248.6). Total num frames: 4476928. Throughput: 0: 869.8. Samples: 117902. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:20:53,458][00161] Avg episode reward: [(0, '23.019')] | |
| [2023-05-12 15:20:58,305][22710] Updated weights for policy 0, policy_version 1098 (0.0021) | |
| [2023-05-12 15:20:58,456][00161] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 4497408. Throughput: 0: 867.8. Samples: 120938. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:20:58,460][00161] Avg episode reward: [(0, '24.188')] | |
| [2023-05-12 15:21:03,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3276.8). Total num frames: 4513792. Throughput: 0: 850.1. Samples: 126572. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:21:03,459][00161] Avg episode reward: [(0, '22.206')] | |
| [2023-05-12 15:21:08,457][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3251.2). Total num frames: 4526080. Throughput: 0: 841.6. Samples: 130310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:21:08,465][00161] Avg episode reward: [(0, '21.844')] | |
| [2023-05-12 15:21:12,355][22710] Updated weights for policy 0, policy_version 1108 (0.0021) | |
| [2023-05-12 15:21:13,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3252.0). Total num frames: 4542464. Throughput: 0: 841.1. Samples: 132320. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:21:13,461][00161] Avg episode reward: [(0, '22.108')] | |
| [2023-05-12 15:21:18,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 4562944. Throughput: 0: 851.7. Samples: 138138. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:21:18,463][00161] Avg episode reward: [(0, '21.479')] | |
| [2023-05-12 15:21:22,098][22710] Updated weights for policy 0, policy_version 1118 (0.0018) | |
| [2023-05-12 15:21:23,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.8, 300 sec: 3276.8). Total num frames: 4579328. Throughput: 0: 838.6. Samples: 144130. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:21:23,464][00161] Avg episode reward: [(0, '20.203')] | |
| [2023-05-12 15:21:28,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3254.1). Total num frames: 4591616. Throughput: 0: 825.5. Samples: 145950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:21:28,460][00161] Avg episode reward: [(0, '19.531')] | |
| [2023-05-12 15:21:33,456][00161] Fps is (10 sec: 2457.5, 60 sec: 3276.8, 300 sec: 3232.5). Total num frames: 4603904. Throughput: 0: 821.5. Samples: 149820. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:21:33,462][00161] Avg episode reward: [(0, '20.873')] | |
| [2023-05-12 15:21:36,618][22710] Updated weights for policy 0, policy_version 1128 (0.0020) | |
| [2023-05-12 15:21:38,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 4628480. Throughput: 0: 832.8. Samples: 155376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:21:38,464][00161] Avg episode reward: [(0, '22.417')] | |
| [2023-05-12 15:21:43,456][00161] Fps is (10 sec: 4505.8, 60 sec: 3413.4, 300 sec: 3297.8). Total num frames: 4648960. Throughput: 0: 837.0. Samples: 158604. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:21:43,463][00161] Avg episode reward: [(0, '21.530')] | |
| [2023-05-12 15:21:47,273][22710] Updated weights for policy 0, policy_version 1138 (0.0014) | |
| [2023-05-12 15:21:48,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3276.8). Total num frames: 4661248. Throughput: 0: 832.0. Samples: 164014. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:21:48,458][00161] Avg episode reward: [(0, '22.429')] | |
| [2023-05-12 15:21:53,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3276.8). Total num frames: 4677632. Throughput: 0: 839.5. Samples: 168088. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:21:53,462][00161] Avg episode reward: [(0, '23.061')] | |
| [2023-05-12 15:21:58,456][00161] Fps is (10 sec: 3276.7, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 4694016. Throughput: 0: 838.2. Samples: 170038. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:21:58,459][00161] Avg episode reward: [(0, '23.811')] | |
| [2023-05-12 15:21:59,930][22710] Updated weights for policy 0, policy_version 1148 (0.0014) | |
| [2023-05-12 15:22:03,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3295.9). Total num frames: 4714496. Throughput: 0: 852.9. Samples: 176520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:22:03,458][00161] Avg episode reward: [(0, '24.500')] | |
| [2023-05-12 15:22:08,456][00161] Fps is (10 sec: 3686.5, 60 sec: 3413.3, 300 sec: 3295.4). Total num frames: 4730880. Throughput: 0: 843.3. Samples: 182080. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:22:08,463][00161] Avg episode reward: [(0, '25.305')] | |
| [2023-05-12 15:22:08,473][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001155_4730880.pth... | |
| [2023-05-12 15:22:08,666][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth | |
| [2023-05-12 15:22:11,755][22710] Updated weights for policy 0, policy_version 1158 (0.0030) | |
| [2023-05-12 15:22:13,456][00161] Fps is (10 sec: 3276.7, 60 sec: 3413.3, 300 sec: 3295.0). Total num frames: 4747264. Throughput: 0: 848.2. Samples: 184120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:13,460][00161] Avg episode reward: [(0, '25.632')] | |
| [2023-05-12 15:22:18,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3276.8). Total num frames: 4759552. Throughput: 0: 853.1. Samples: 188210. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:22:18,463][00161] Avg episode reward: [(0, '26.031')] | |
| [2023-05-12 15:22:23,406][22710] Updated weights for policy 0, policy_version 1168 (0.0013) | |
| [2023-05-12 15:22:23,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3311.7). Total num frames: 4784128. Throughput: 0: 864.7. Samples: 194286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:23,458][00161] Avg episode reward: [(0, '26.980')] | |
| [2023-05-12 15:22:28,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3310.9). Total num frames: 4800512. Throughput: 0: 863.9. Samples: 197478. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:28,463][00161] Avg episode reward: [(0, '26.900')] | |
| [2023-05-12 15:22:33,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3310.2). Total num frames: 4816896. Throughput: 0: 851.9. Samples: 202350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:33,459][00161] Avg episode reward: [(0, '26.598')] | |
| [2023-05-12 15:22:36,292][22710] Updated weights for policy 0, policy_version 1178 (0.0015) | |
| [2023-05-12 15:22:38,456][00161] Fps is (10 sec: 2867.1, 60 sec: 3345.0, 300 sec: 3293.2). Total num frames: 4829184. Throughput: 0: 849.7. Samples: 206324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:38,458][00161] Avg episode reward: [(0, '25.935')] | |
| [2023-05-12 15:22:43,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3308.9). Total num frames: 4849664. Throughput: 0: 858.1. Samples: 208654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:43,462][00161] Avg episode reward: [(0, '26.116')] | |
| [2023-05-12 15:22:47,036][22710] Updated weights for policy 0, policy_version 1188 (0.0029) | |
| [2023-05-12 15:22:48,456][00161] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3324.1). Total num frames: 4870144. Throughput: 0: 859.9. Samples: 215214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:22:48,457][00161] Avg episode reward: [(0, '25.939')] | |
| [2023-05-12 15:22:53,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3323.2). Total num frames: 4886528. Throughput: 0: 848.3. Samples: 220254. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:22:53,461][00161] Avg episode reward: [(0, '26.147')] | |
| [2023-05-12 15:22:58,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3307.1). Total num frames: 4898816. Throughput: 0: 845.4. Samples: 222164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:22:58,463][00161] Avg episode reward: [(0, '25.328')] | |
| [2023-05-12 15:23:01,040][22710] Updated weights for policy 0, policy_version 1198 (0.0031) | |
| [2023-05-12 15:23:03,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3306.6). Total num frames: 4915200. Throughput: 0: 846.3. Samples: 226292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:23:03,463][00161] Avg episode reward: [(0, '26.424')] | |
| [2023-05-12 15:23:08,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3320.7). Total num frames: 4935680. Throughput: 0: 854.5. Samples: 232740. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:23:08,458][00161] Avg episode reward: [(0, '25.205')] | |
| [2023-05-12 15:23:10,868][22710] Updated weights for policy 0, policy_version 1208 (0.0016) | |
| [2023-05-12 15:23:13,456][00161] Fps is (10 sec: 3686.3, 60 sec: 3413.3, 300 sec: 3319.9). Total num frames: 4952064. Throughput: 0: 854.0. Samples: 235906. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:23:13,458][00161] Avg episode reward: [(0, '23.531')] | |
| [2023-05-12 15:23:18,457][00161] Fps is (10 sec: 3276.4, 60 sec: 3481.5, 300 sec: 3319.2). Total num frames: 4968448. Throughput: 0: 842.8. Samples: 240278. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:23:18,459][00161] Avg episode reward: [(0, '23.912')] | |
| [2023-05-12 15:23:23,456][00161] Fps is (10 sec: 2867.3, 60 sec: 3276.8, 300 sec: 3304.6). Total num frames: 4980736. Throughput: 0: 844.7. Samples: 244336. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:23:23,461][00161] Avg episode reward: [(0, '23.550')] | |
| [2023-05-12 15:23:24,864][22710] Updated weights for policy 0, policy_version 1218 (0.0017) | |
| [2023-05-12 15:23:28,456][00161] Fps is (10 sec: 3277.2, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 5001216. Throughput: 0: 856.5. Samples: 247198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:23:28,462][00161] Avg episode reward: [(0, '23.812')] | |
| [2023-05-12 15:23:33,456][00161] Fps is (10 sec: 4095.9, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 5021696. Throughput: 0: 854.6. Samples: 253672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:23:33,459][00161] Avg episode reward: [(0, '22.827')] | |
| [2023-05-12 15:23:35,160][22710] Updated weights for policy 0, policy_version 1228 (0.0015) | |
| [2023-05-12 15:23:38,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 5038080. Throughput: 0: 846.0. Samples: 258322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:23:38,465][00161] Avg episode reward: [(0, '23.443')] | |
| [2023-05-12 15:23:43,456][00161] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 5050368. Throughput: 0: 846.8. Samples: 260270. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:23:43,460][00161] Avg episode reward: [(0, '24.282')] | |
| [2023-05-12 15:23:48,329][22710] Updated weights for policy 0, policy_version 1238 (0.0034) | |
| [2023-05-12 15:23:48,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3415.7). Total num frames: 5070848. Throughput: 0: 860.8. Samples: 265030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:23:48,458][00161] Avg episode reward: [(0, '25.311')] | |
| [2023-05-12 15:23:53,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3443.4). Total num frames: 5091328. Throughput: 0: 861.0. Samples: 271484. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-05-12 15:23:53,459][00161] Avg episode reward: [(0, '26.232')] | |
| [2023-05-12 15:23:58,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 5107712. Throughput: 0: 857.4. Samples: 274490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:23:58,463][00161] Avg episode reward: [(0, '25.260')] | |
| [2023-05-12 15:23:59,745][22710] Updated weights for policy 0, policy_version 1248 (0.0018) | |
| [2023-05-12 15:24:03,457][00161] Fps is (10 sec: 2867.0, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 5120000. Throughput: 0: 847.9. Samples: 278434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:24:03,463][00161] Avg episode reward: [(0, '25.438')] | |
| [2023-05-12 15:24:08,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5136384. Throughput: 0: 850.8. Samples: 282622. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-05-12 15:24:08,459][00161] Avg episode reward: [(0, '27.248')] | |
| [2023-05-12 15:24:08,469][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001254_5136384.pth... | |
| [2023-05-12 15:24:08,618][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001055_4321280.pth | |
| [2023-05-12 15:24:12,198][22710] Updated weights for policy 0, policy_version 1258 (0.0029) | |
| [2023-05-12 15:24:13,456][00161] Fps is (10 sec: 3686.7, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 5156864. Throughput: 0: 856.4. Samples: 285738. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:24:13,458][00161] Avg episode reward: [(0, '27.366')] | |
| [2023-05-12 15:24:18,456][00161] Fps is (10 sec: 4095.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 5177344. Throughput: 0: 852.6. Samples: 292040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:24:18,461][00161] Avg episode reward: [(0, '27.684')] | |
| [2023-05-12 15:24:23,463][00161] Fps is (10 sec: 3274.4, 60 sec: 3481.2, 300 sec: 3401.7). Total num frames: 5189632. Throughput: 0: 843.0. Samples: 296264. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:24:23,466][00161] Avg episode reward: [(0, '27.194')] | |
| [2023-05-12 15:24:24,748][22710] Updated weights for policy 0, policy_version 1268 (0.0016) | |
| [2023-05-12 15:24:28,457][00161] Fps is (10 sec: 2457.4, 60 sec: 3345.0, 300 sec: 3374.0). Total num frames: 5201920. Throughput: 0: 843.2. Samples: 298216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:24:28,460][00161] Avg episode reward: [(0, '26.857')] | |
| [2023-05-12 15:24:33,461][00161] Fps is (10 sec: 3277.4, 60 sec: 3344.8, 300 sec: 3387.8). Total num frames: 5222400. Throughput: 0: 846.5. Samples: 303126. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:24:33,464][00161] Avg episode reward: [(0, '26.960')] | |
| [2023-05-12 15:24:36,023][22710] Updated weights for policy 0, policy_version 1278 (0.0021) | |
| [2023-05-12 15:24:38,456][00161] Fps is (10 sec: 4096.5, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 5242880. Throughput: 0: 846.8. Samples: 309592. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:24:38,459][00161] Avg episode reward: [(0, '26.592')] | |
| [2023-05-12 15:24:43,456][00161] Fps is (10 sec: 3688.5, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 5259264. Throughput: 0: 839.5. Samples: 312268. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:24:43,462][00161] Avg episode reward: [(0, '26.572')] | |
| [2023-05-12 15:24:48,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 5271552. Throughput: 0: 842.0. Samples: 316324. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:24:48,463][00161] Avg episode reward: [(0, '26.433')] | |
| [2023-05-12 15:24:49,215][22710] Updated weights for policy 0, policy_version 1288 (0.0039) | |
| [2023-05-12 15:24:53,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 5287936. Throughput: 0: 853.2. Samples: 321018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:24:53,463][00161] Avg episode reward: [(0, '26.639')] | |
| [2023-05-12 15:24:58,456][00161] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 5312512. Throughput: 0: 856.3. Samples: 324272. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:24:58,459][00161] Avg episode reward: [(0, '27.579')] | |
| [2023-05-12 15:24:59,457][22710] Updated weights for policy 0, policy_version 1298 (0.0015) | |
| [2023-05-12 15:25:03,458][00161] Fps is (10 sec: 4095.0, 60 sec: 3481.5, 300 sec: 3415.6). Total num frames: 5328896. Throughput: 0: 856.6. Samples: 330590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:25:03,460][00161] Avg episode reward: [(0, '27.778')] | |
| [2023-05-12 15:25:08,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 5341184. Throughput: 0: 851.4. Samples: 334572. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:25:08,463][00161] Avg episode reward: [(0, '29.597')] | |
| [2023-05-12 15:25:08,478][22697] Saving new best policy, reward=29.597! | |
| [2023-05-12 15:25:13,456][00161] Fps is (10 sec: 2458.2, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 5353472. Throughput: 0: 852.2. Samples: 336562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:25:13,461][00161] Avg episode reward: [(0, '29.826')] | |
| [2023-05-12 15:25:13,530][22710] Updated weights for policy 0, policy_version 1308 (0.0015) | |
| [2023-05-12 15:25:13,534][22697] Saving new best policy, reward=29.826! | |
| [2023-05-12 15:25:18,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 5378048. Throughput: 0: 860.4. Samples: 341838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:25:18,458][00161] Avg episode reward: [(0, '28.669')] | |
| [2023-05-12 15:25:23,194][22710] Updated weights for policy 0, policy_version 1318 (0.0018) | |
| [2023-05-12 15:25:23,456][00161] Fps is (10 sec: 4505.6, 60 sec: 3482.0, 300 sec: 3429.5). Total num frames: 5398528. Throughput: 0: 860.0. Samples: 348294. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-05-12 15:25:23,458][00161] Avg episode reward: [(0, '27.754')] | |
| [2023-05-12 15:25:28,456][00161] Fps is (10 sec: 3276.7, 60 sec: 3481.7, 300 sec: 3401.8). Total num frames: 5410816. Throughput: 0: 850.4. Samples: 350536. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) | |
| [2023-05-12 15:25:28,461][00161] Avg episode reward: [(0, '27.521')] | |
| [2023-05-12 15:25:33,456][00161] Fps is (10 sec: 2457.5, 60 sec: 3345.3, 300 sec: 3360.1). Total num frames: 5423104. Throughput: 0: 848.7. Samples: 354516. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-05-12 15:25:33,465][00161] Avg episode reward: [(0, '27.238')] | |
| [2023-05-12 15:25:37,344][22710] Updated weights for policy 0, policy_version 1328 (0.0020) | |
| [2023-05-12 15:25:38,456][00161] Fps is (10 sec: 3276.9, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5443584. Throughput: 0: 853.9. Samples: 359444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:25:38,458][00161] Avg episode reward: [(0, '25.111')] | |
| [2023-05-12 15:25:43,456][00161] Fps is (10 sec: 4096.2, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 5464064. Throughput: 0: 854.9. Samples: 362744. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:25:43,461][00161] Avg episode reward: [(0, '23.414')] | |
| [2023-05-12 15:25:47,469][22710] Updated weights for policy 0, policy_version 1338 (0.0031) | |
| [2023-05-12 15:25:48,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 5480448. Throughput: 0: 846.4. Samples: 368676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:25:48,461][00161] Avg episode reward: [(0, '24.372')] | |
| [2023-05-12 15:25:53,456][00161] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 5492736. Throughput: 0: 847.5. Samples: 372708. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:25:53,465][00161] Avg episode reward: [(0, '25.409')] | |
| [2023-05-12 15:25:58,458][00161] Fps is (10 sec: 2866.6, 60 sec: 3276.7, 300 sec: 3374.0). Total num frames: 5509120. Throughput: 0: 846.8. Samples: 374668. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:25:58,466][00161] Avg episode reward: [(0, '25.042')] | |
| [2023-05-12 15:26:00,711][22710] Updated weights for policy 0, policy_version 1348 (0.0029) | |
| [2023-05-12 15:26:03,456][00161] Fps is (10 sec: 3686.5, 60 sec: 3345.2, 300 sec: 3401.8). Total num frames: 5529600. Throughput: 0: 860.5. Samples: 380560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:26:03,466][00161] Avg episode reward: [(0, '23.433')] | |
| [2023-05-12 15:26:08,457][00161] Fps is (10 sec: 4096.2, 60 sec: 3481.5, 300 sec: 3415.6). Total num frames: 5550080. Throughput: 0: 856.2. Samples: 386824. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:26:08,460][00161] Avg episode reward: [(0, '22.979')] | |
| [2023-05-12 15:26:08,469][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001355_5550080.pth... | |
| [2023-05-12 15:26:08,664][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001155_4730880.pth | |
| [2023-05-12 15:26:12,216][22710] Updated weights for policy 0, policy_version 1358 (0.0040) | |
| [2023-05-12 15:26:13,461][00161] Fps is (10 sec: 3275.0, 60 sec: 3481.3, 300 sec: 3387.8). Total num frames: 5562368. Throughput: 0: 848.3. Samples: 388712. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:26:13,464][00161] Avg episode reward: [(0, '23.679')] | |
| [2023-05-12 15:26:18,456][00161] Fps is (10 sec: 2867.7, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5578752. Throughput: 0: 849.9. Samples: 392762. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:26:18,463][00161] Avg episode reward: [(0, '23.329')] | |
| [2023-05-12 15:26:23,456][00161] Fps is (10 sec: 3688.3, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 5599232. Throughput: 0: 860.6. Samples: 398172. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:26:23,464][00161] Avg episode reward: [(0, '23.450')] | |
| [2023-05-12 15:26:24,391][22710] Updated weights for policy 0, policy_version 1368 (0.0013) | |
| [2023-05-12 15:26:28,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 5619712. Throughput: 0: 857.0. Samples: 401310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:26:28,463][00161] Avg episode reward: [(0, '23.739')] | |
| [2023-05-12 15:26:33,456][00161] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 5632000. Throughput: 0: 845.5. Samples: 406724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:26:33,458][00161] Avg episode reward: [(0, '23.989')] | |
| [2023-05-12 15:26:37,083][22710] Updated weights for policy 0, policy_version 1378 (0.0016) | |
| [2023-05-12 15:26:38,456][00161] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 5644288. Throughput: 0: 842.5. Samples: 410622. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:26:38,465][00161] Avg episode reward: [(0, '23.383')] | |
| [2023-05-12 15:26:43,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 5660672. Throughput: 0: 842.7. Samples: 412586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:26:43,464][00161] Avg episode reward: [(0, '24.549')] | |
| [2023-05-12 15:26:48,260][22710] Updated weights for policy 0, policy_version 1388 (0.0027) | |
| [2023-05-12 15:26:48,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 5685248. Throughput: 0: 848.9. Samples: 418760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-05-12 15:26:48,463][00161] Avg episode reward: [(0, '25.485')] | |
| [2023-05-12 15:26:53,456][00161] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3415.7). Total num frames: 5701632. Throughput: 0: 840.5. Samples: 424646. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:26:53,464][00161] Avg episode reward: [(0, '22.950')] | |
| [2023-05-12 15:26:58,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3401.8). Total num frames: 5718016. Throughput: 0: 842.9. Samples: 426638. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:26:58,459][00161] Avg episode reward: [(0, '22.815')] | |
| [2023-05-12 15:27:01,711][22710] Updated weights for policy 0, policy_version 1398 (0.0017) | |
| [2023-05-12 15:27:03,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5730304. Throughput: 0: 841.8. Samples: 430642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:27:03,461][00161] Avg episode reward: [(0, '22.857')] | |
| [2023-05-12 15:27:08,456][00161] Fps is (10 sec: 3276.8, 60 sec: 3345.2, 300 sec: 3401.8). Total num frames: 5750784. Throughput: 0: 849.1. Samples: 436382. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:27:08,458][00161] Avg episode reward: [(0, '22.859')] | |
| [2023-05-12 15:27:11,935][22710] Updated weights for policy 0, policy_version 1408 (0.0017) | |
| [2023-05-12 15:27:13,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3481.9, 300 sec: 3429.5). Total num frames: 5771264. Throughput: 0: 850.9. Samples: 439602. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:27:13,458][00161] Avg episode reward: [(0, '22.883')] | |
| [2023-05-12 15:27:18,456][00161] Fps is (10 sec: 3686.3, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 5787648. Throughput: 0: 845.5. Samples: 444774. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:27:18,463][00161] Avg episode reward: [(0, '23.158')] | |
| [2023-05-12 15:27:23,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5799936. Throughput: 0: 848.1. Samples: 448786. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:27:23,464][00161] Avg episode reward: [(0, '22.899')] | |
| [2023-05-12 15:27:25,890][22710] Updated weights for policy 0, policy_version 1418 (0.0030) | |
| [2023-05-12 15:27:28,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3387.9). Total num frames: 5816320. Throughput: 0: 850.3. Samples: 450848. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) | |
| [2023-05-12 15:27:28,459][00161] Avg episode reward: [(0, '24.810')] | |
| [2023-05-12 15:27:33,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 5836800. Throughput: 0: 850.7. Samples: 457042. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) | |
| [2023-05-12 15:27:33,459][00161] Avg episode reward: [(0, '25.770')] | |
| [2023-05-12 15:27:35,909][22710] Updated weights for policy 0, policy_version 1428 (0.0012) | |
| [2023-05-12 15:27:38,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 5853184. Throughput: 0: 842.4. Samples: 462556. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:27:38,458][00161] Avg episode reward: [(0, '27.069')] | |
| [2023-05-12 15:27:43,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 5865472. Throughput: 0: 842.4. Samples: 464546. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:27:43,459][00161] Avg episode reward: [(0, '25.146')] | |
| [2023-05-12 15:27:48,456][00161] Fps is (10 sec: 2867.3, 60 sec: 3276.8, 300 sec: 3374.0). Total num frames: 5881856. Throughput: 0: 843.3. Samples: 468590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:27:48,461][00161] Avg episode reward: [(0, '24.545')] | |
| [2023-05-12 15:27:49,689][22710] Updated weights for policy 0, policy_version 1438 (0.0028) | |
| [2023-05-12 15:27:53,456][00161] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 5902336. Throughput: 0: 854.7. Samples: 474844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:27:53,462][00161] Avg episode reward: [(0, '25.359')] | |
| [2023-05-12 15:27:58,456][00161] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 5922816. Throughput: 0: 854.0. Samples: 478032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-05-12 15:27:58,461][00161] Avg episode reward: [(0, '25.412')] | |
| [2023-05-12 15:28:00,577][22710] Updated weights for policy 0, policy_version 1448 (0.0013) | |
| [2023-05-12 15:28:03,459][00161] Fps is (10 sec: 3275.9, 60 sec: 3413.2, 300 sec: 3387.8). Total num frames: 5935104. Throughput: 0: 840.3. Samples: 482588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:28:03,461][00161] Avg episode reward: [(0, '25.439')] | |
| [2023-05-12 15:28:08,456][00161] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 5951488. Throughput: 0: 841.8. Samples: 486668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-05-12 15:28:08,458][00161] Avg episode reward: [(0, '25.013')] | |
| [2023-05-12 15:28:08,474][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001453_5951488.pth... | |
| [2023-05-12 15:28:08,665][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001254_5136384.pth | |
| [2023-05-12 15:28:13,348][22710] Updated weights for policy 0, policy_version 1458 (0.0014) | |
| [2023-05-12 15:28:13,456][00161] Fps is (10 sec: 3687.4, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 5971968. Throughput: 0: 852.5. Samples: 489212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:28:13,458][00161] Avg episode reward: [(0, '25.185')] | |
| [2023-05-12 15:28:18,461][00161] Fps is (10 sec: 4093.8, 60 sec: 3413.0, 300 sec: 3429.5). Total num frames: 5992448. Throughput: 0: 858.6. Samples: 495684. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-05-12 15:28:18,464][00161] Avg episode reward: [(0, '26.132')] | |
| [2023-05-12 15:28:21,761][22697] Stopping Batcher_0... | |
| [2023-05-12 15:28:21,761][22697] Loop batcher_evt_loop terminating... | |
| [2023-05-12 15:28:21,762][00161] Component Batcher_0 stopped! | |
| [2023-05-12 15:28:21,765][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth... | |
| [2023-05-12 15:28:21,877][22710] Weights refcount: 2 0 | |
| [2023-05-12 15:28:21,884][00161] Component InferenceWorker_p0-w0 stopped! | |
| [2023-05-12 15:28:21,890][00161] Component RolloutWorker_w7 stopped! | |
| [2023-05-12 15:28:21,893][00161] Component RolloutWorker_w5 stopped! | |
| [2023-05-12 15:28:21,886][22710] Stopping InferenceWorker_p0-w0... | |
| [2023-05-12 15:28:21,896][22710] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-05-12 15:28:21,892][22717] Stopping RolloutWorker_w7... | |
| [2023-05-12 15:28:21,899][22717] Loop rollout_proc7_evt_loop terminating... | |
| [2023-05-12 15:28:21,914][00161] Component RolloutWorker_w1 stopped! | |
| [2023-05-12 15:28:21,916][22712] Stopping RolloutWorker_w1... | |
| [2023-05-12 15:28:21,917][22712] Loop rollout_proc1_evt_loop terminating... | |
| [2023-05-12 15:28:21,895][22716] Stopping RolloutWorker_w5... | |
| [2023-05-12 15:28:21,920][22716] Loop rollout_proc5_evt_loop terminating... | |
| [2023-05-12 15:28:21,940][00161] Component RolloutWorker_w3 stopped! | |
| [2023-05-12 15:28:21,942][22714] Stopping RolloutWorker_w3... | |
| [2023-05-12 15:28:21,949][22714] Loop rollout_proc3_evt_loop terminating... | |
| [2023-05-12 15:28:21,976][22711] Stopping RolloutWorker_w0... | |
| [2023-05-12 15:28:21,994][22711] Loop rollout_proc0_evt_loop terminating... | |
| [2023-05-12 15:28:21,993][00161] Component RolloutWorker_w0 stopped! | |
| [2023-05-12 15:28:22,015][00161] Component RolloutWorker_w2 stopped! | |
| [2023-05-12 15:28:22,015][22715] Stopping RolloutWorker_w2... | |
| [2023-05-12 15:28:22,029][00161] Component RolloutWorker_w6 stopped! | |
| [2023-05-12 15:28:22,031][22718] Stopping RolloutWorker_w6... | |
| [2023-05-12 15:28:22,031][22718] Loop rollout_proc6_evt_loop terminating... | |
| [2023-05-12 15:28:22,022][22715] Loop rollout_proc2_evt_loop terminating... | |
| [2023-05-12 15:28:22,042][22697] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001355_5550080.pth | |
| [2023-05-12 15:28:22,072][22713] Stopping RolloutWorker_w4... | |
| [2023-05-12 15:28:22,072][00161] Component RolloutWorker_w4 stopped! | |
| [2023-05-12 15:28:22,092][22713] Loop rollout_proc4_evt_loop terminating... | |
| [2023-05-12 15:28:22,102][22697] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth... | |
| [2023-05-12 15:28:22,389][22697] Stopping LearnerWorker_p0... | |
| [2023-05-12 15:28:22,390][22697] Loop learner_proc0_evt_loop terminating... | |
| [2023-05-12 15:28:22,401][00161] Component LearnerWorker_p0 stopped! | |
| [2023-05-12 15:28:22,403][00161] Waiting for process learner_proc0 to stop... | |
| [2023-05-12 15:28:23,959][00161] Waiting for process inference_proc0-0 to join... | |
| [2023-05-12 15:28:24,352][00161] Waiting for process rollout_proc0 to join... | |
| [2023-05-12 15:28:25,962][00161] Waiting for process rollout_proc1 to join... | |
| [2023-05-12 15:28:25,965][00161] Waiting for process rollout_proc2 to join... | |
| [2023-05-12 15:28:25,967][00161] Waiting for process rollout_proc3 to join... | |
| [2023-05-12 15:28:25,968][00161] Waiting for process rollout_proc4 to join... | |
| [2023-05-12 15:28:25,969][00161] Waiting for process rollout_proc5 to join... | |
| [2023-05-12 15:28:25,970][00161] Waiting for process rollout_proc6 to join... | |
| [2023-05-12 15:28:25,971][00161] Waiting for process rollout_proc7 to join... | |
| [2023-05-12 15:28:25,972][00161] Batcher 0 profile tree view: | |
| batching: 14.1607, releasing_batches: 0.0143 | |
| [2023-05-12 15:28:25,973][00161] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0091 | |
| wait_policy_total: 280.4199 | |
| update_model: 4.1678 | |
| weight_update: 0.0012 | |
| one_step: 0.0026 | |
| handle_policy_step: 289.6667 | |
| deserialize: 7.7935, stack: 1.6742, obs_to_device_normalize: 61.3258, forward: 145.5804, send_messages: 15.2365 | |
| prepare_outputs: 43.8332 | |
| to_cpu: 26.5021 | |
| [2023-05-12 15:28:25,975][00161] Learner 0 profile tree view: | |
| misc: 0.0030, prepare_batch: 10.0330 | |
| train: 40.8455 | |
| epoch_init: 0.0040, minibatch_init: 0.0098, losses_postprocess: 0.2881, kl_divergence: 0.3692, after_optimizer: 1.9399 | |
| calculate_losses: 12.5988 | |
| losses_init: 0.0016, forward_head: 1.1112, bptt_initial: 7.7923, tail: 0.6108, advantages_returns: 0.1711, losses: 1.6312 | |
| bptt: 1.1033 | |
| bptt_forward_core: 1.0700 | |
| update: 25.2126 | |
| clip: 0.7803 | |
| [2023-05-12 15:28:25,976][00161] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.1897, enqueue_policy_requests: 78.5061, env_step: 444.0168, overhead: 12.3809, complete_rollouts: 3.6582 | |
| save_policy_outputs: 11.4830 | |
| split_output_tensors: 5.4602 | |
| [2023-05-12 15:28:25,978][00161] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.2509, enqueue_policy_requests: 75.6875, env_step: 440.2742, overhead: 12.5337, complete_rollouts: 3.9811 | |
| save_policy_outputs: 11.4313 | |
| split_output_tensors: 5.4628 | |
| [2023-05-12 15:28:25,979][00161] Loop Runner_EvtLoop terminating... | |
| [2023-05-12 15:28:25,981][00161] Runner profile tree view: | |
| main_loop: 615.9429 | |
| [2023-05-12 15:28:25,982][00161] Collected {0: 6004736}, FPS: 3245.2 | |
| [2023-05-12 15:28:35,343][00161] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-05-12 15:28:35,345][00161] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-05-12 15:28:35,347][00161] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-05-12 15:28:35,350][00161] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-05-12 15:28:35,352][00161] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:28:35,354][00161] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-05-12 15:28:35,356][00161] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:28:35,357][00161] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-05-12 15:28:35,358][00161] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-05-12 15:28:35,359][00161] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-05-12 15:28:35,361][00161] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-05-12 15:28:35,362][00161] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-05-12 15:28:35,363][00161] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-05-12 15:28:35,364][00161] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-05-12 15:28:35,366][00161] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-05-12 15:28:35,388][00161] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:28:35,389][00161] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:28:35,408][00161] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:28:35,443][00161] Conv encoder output size: 512 | |
| [2023-05-12 15:28:35,445][00161] Policy head output size: 512 | |
| [2023-05-12 15:28:35,464][00161] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth... | |
| [2023-05-12 15:28:35,954][00161] Num frames 100... | |
| [2023-05-12 15:28:36,085][00161] Num frames 200... | |
| [2023-05-12 15:28:36,206][00161] Num frames 300... | |
| [2023-05-12 15:28:36,328][00161] Num frames 400... | |
| [2023-05-12 15:28:36,446][00161] Num frames 500... | |
| [2023-05-12 15:28:36,568][00161] Num frames 600... | |
| [2023-05-12 15:28:36,685][00161] Num frames 700... | |
| [2023-05-12 15:28:36,803][00161] Num frames 800... | |
| [2023-05-12 15:28:36,927][00161] Num frames 900... | |
| [2023-05-12 15:28:37,080][00161] Num frames 1000... | |
| [2023-05-12 15:28:37,251][00161] Num frames 1100... | |
| [2023-05-12 15:28:37,417][00161] Num frames 1200... | |
| [2023-05-12 15:28:37,576][00161] Num frames 1300... | |
| [2023-05-12 15:28:37,746][00161] Num frames 1400... | |
| [2023-05-12 15:28:37,929][00161] Num frames 1500... | |
| [2023-05-12 15:28:38,093][00161] Avg episode rewards: #0: 42.680, true rewards: #0: 15.680 | |
| [2023-05-12 15:28:38,095][00161] Avg episode reward: 42.680, avg true_objective: 15.680 | |
| [2023-05-12 15:28:38,160][00161] Num frames 1600... | |
| [2023-05-12 15:28:38,320][00161] Num frames 1700... | |
| [2023-05-12 15:28:38,480][00161] Num frames 1800... | |
| [2023-05-12 15:28:38,644][00161] Num frames 1900... | |
| [2023-05-12 15:28:38,807][00161] Num frames 2000... | |
| [2023-05-12 15:28:38,972][00161] Num frames 2100... | |
| [2023-05-12 15:28:39,142][00161] Num frames 2200... | |
| [2023-05-12 15:28:39,327][00161] Num frames 2300... | |
| [2023-05-12 15:28:39,507][00161] Num frames 2400... | |
| [2023-05-12 15:28:39,631][00161] Avg episode rewards: #0: 31.685, true rewards: #0: 12.185 | |
| [2023-05-12 15:28:39,633][00161] Avg episode reward: 31.685, avg true_objective: 12.185 | |
| [2023-05-12 15:28:39,738][00161] Num frames 2500... | |
| [2023-05-12 15:28:39,909][00161] Num frames 2600... | |
| [2023-05-12 15:28:40,076][00161] Num frames 2700... | |
| [2023-05-12 15:28:40,248][00161] Num frames 2800... | |
| [2023-05-12 15:28:40,416][00161] Num frames 2900... | |
| [2023-05-12 15:28:40,591][00161] Num frames 3000... | |
| [2023-05-12 15:28:40,759][00161] Num frames 3100... | |
| [2023-05-12 15:28:40,948][00161] Avg episode rewards: #0: 25.243, true rewards: #0: 10.577 | |
| [2023-05-12 15:28:40,951][00161] Avg episode reward: 25.243, avg true_objective: 10.577 | |
| [2023-05-12 15:28:41,000][00161] Num frames 3200... | |
| [2023-05-12 15:28:41,170][00161] Num frames 3300... | |
| [2023-05-12 15:28:41,338][00161] Num frames 3400... | |
| [2023-05-12 15:28:41,502][00161] Num frames 3500... | |
| [2023-05-12 15:28:41,671][00161] Num frames 3600... | |
| [2023-05-12 15:28:41,838][00161] Num frames 3700... | |
| [2023-05-12 15:28:42,028][00161] Avg episode rewards: #0: 21.703, true rewards: #0: 9.452 | |
| [2023-05-12 15:28:42,030][00161] Avg episode reward: 21.703, avg true_objective: 9.452 | |
| [2023-05-12 15:28:42,055][00161] Num frames 3800... | |
| [2023-05-12 15:28:42,170][00161] Num frames 3900... | |
| [2023-05-12 15:28:42,294][00161] Num frames 4000... | |
| [2023-05-12 15:28:42,422][00161] Num frames 4100... | |
| [2023-05-12 15:28:42,545][00161] Num frames 4200... | |
| [2023-05-12 15:28:42,661][00161] Num frames 4300... | |
| [2023-05-12 15:28:42,778][00161] Num frames 4400... | |
| [2023-05-12 15:28:42,896][00161] Num frames 4500... | |
| [2023-05-12 15:28:43,014][00161] Num frames 4600... | |
| [2023-05-12 15:28:43,138][00161] Num frames 4700... | |
| [2023-05-12 15:28:43,262][00161] Num frames 4800... | |
| [2023-05-12 15:28:43,380][00161] Num frames 4900... | |
| [2023-05-12 15:28:43,501][00161] Num frames 5000... | |
| [2023-05-12 15:28:43,618][00161] Num frames 5100... | |
| [2023-05-12 15:28:43,736][00161] Num frames 5200... | |
| [2023-05-12 15:28:43,856][00161] Num frames 5300... | |
| [2023-05-12 15:28:43,973][00161] Num frames 5400... | |
| [2023-05-12 15:28:44,089][00161] Num frames 5500... | |
| [2023-05-12 15:28:44,205][00161] Num frames 5600... | |
| [2023-05-12 15:28:44,325][00161] Num frames 5700... | |
| [2023-05-12 15:28:44,450][00161] Num frames 5800... | |
| [2023-05-12 15:28:44,600][00161] Avg episode rewards: #0: 29.162, true rewards: #0: 11.762 | |
| [2023-05-12 15:28:44,602][00161] Avg episode reward: 29.162, avg true_objective: 11.762 | |
| [2023-05-12 15:28:44,629][00161] Num frames 5900... | |
| [2023-05-12 15:28:44,746][00161] Num frames 6000... | |
| [2023-05-12 15:28:44,870][00161] Num frames 6100... | |
| [2023-05-12 15:28:44,996][00161] Num frames 6200... | |
| [2023-05-12 15:28:45,129][00161] Num frames 6300... | |
| [2023-05-12 15:28:45,247][00161] Num frames 6400... | |
| [2023-05-12 15:28:45,384][00161] Num frames 6500... | |
| [2023-05-12 15:28:45,503][00161] Num frames 6600... | |
| [2023-05-12 15:28:45,622][00161] Num frames 6700... | |
| [2023-05-12 15:28:45,751][00161] Num frames 6800... | |
| [2023-05-12 15:28:45,875][00161] Num frames 6900... | |
| [2023-05-12 15:28:45,998][00161] Num frames 7000... | |
| [2023-05-12 15:28:46,128][00161] Num frames 7100... | |
| [2023-05-12 15:28:46,253][00161] Num frames 7200... | |
| [2023-05-12 15:28:46,381][00161] Num frames 7300... | |
| [2023-05-12 15:28:46,501][00161] Num frames 7400... | |
| [2023-05-12 15:28:46,587][00161] Avg episode rewards: #0: 31.371, true rewards: #0: 12.372 | |
| [2023-05-12 15:28:46,589][00161] Avg episode reward: 31.371, avg true_objective: 12.372 | |
| [2023-05-12 15:28:46,683][00161] Num frames 7500... | |
| [2023-05-12 15:28:46,803][00161] Num frames 7600... | |
| [2023-05-12 15:28:46,926][00161] Num frames 7700... | |
| [2023-05-12 15:28:47,047][00161] Num frames 7800... | |
| [2023-05-12 15:28:47,162][00161] Num frames 7900... | |
| [2023-05-12 15:28:47,296][00161] Avg episode rewards: #0: 27.953, true rewards: #0: 11.381 | |
| [2023-05-12 15:28:47,298][00161] Avg episode reward: 27.953, avg true_objective: 11.381 | |
| [2023-05-12 15:28:47,345][00161] Num frames 8000... | |
| [2023-05-12 15:28:47,471][00161] Num frames 8100... | |
| [2023-05-12 15:28:47,598][00161] Num frames 8200... | |
| [2023-05-12 15:28:47,724][00161] Num frames 8300... | |
| [2023-05-12 15:28:47,846][00161] Num frames 8400... | |
| [2023-05-12 15:28:47,969][00161] Num frames 8500... | |
| [2023-05-12 15:28:48,093][00161] Num frames 8600... | |
| [2023-05-12 15:28:48,213][00161] Num frames 8700... | |
| [2023-05-12 15:28:48,342][00161] Num frames 8800... | |
| [2023-05-12 15:28:48,468][00161] Num frames 8900... | |
| [2023-05-12 15:28:48,592][00161] Num frames 9000... | |
| [2023-05-12 15:28:48,706][00161] Num frames 9100... | |
| [2023-05-12 15:28:48,823][00161] Num frames 9200... | |
| [2023-05-12 15:28:48,949][00161] Num frames 9300... | |
| [2023-05-12 15:28:49,069][00161] Num frames 9400... | |
| [2023-05-12 15:28:49,211][00161] Avg episode rewards: #0: 28.838, true rewards: #0: 11.839 | |
| [2023-05-12 15:28:49,213][00161] Avg episode reward: 28.838, avg true_objective: 11.839 | |
| [2023-05-12 15:28:49,250][00161] Num frames 9500... | |
| [2023-05-12 15:28:49,382][00161] Num frames 9600... | |
| [2023-05-12 15:28:49,504][00161] Num frames 9700... | |
| [2023-05-12 15:28:49,621][00161] Num frames 9800... | |
| [2023-05-12 15:28:49,742][00161] Num frames 9900... | |
| [2023-05-12 15:28:49,865][00161] Num frames 10000... | |
| [2023-05-12 15:28:50,012][00161] Avg episode rewards: #0: 27.088, true rewards: #0: 11.199 | |
| [2023-05-12 15:28:50,013][00161] Avg episode reward: 27.088, avg true_objective: 11.199 | |
| [2023-05-12 15:28:50,053][00161] Num frames 10100... | |
| [2023-05-12 15:28:50,170][00161] Num frames 10200... | |
| [2023-05-12 15:28:50,289][00161] Num frames 10300... | |
| [2023-05-12 15:28:50,417][00161] Num frames 10400... | |
| [2023-05-12 15:28:50,539][00161] Num frames 10500... | |
| [2023-05-12 15:28:50,655][00161] Num frames 10600... | |
| [2023-05-12 15:28:50,774][00161] Num frames 10700... | |
| [2023-05-12 15:28:50,899][00161] Num frames 10800... | |
| [2023-05-12 15:28:51,025][00161] Num frames 10900... | |
| [2023-05-12 15:28:51,145][00161] Num frames 11000... | |
| [2023-05-12 15:28:51,267][00161] Num frames 11100... | |
| [2023-05-12 15:28:51,401][00161] Num frames 11200... | |
| [2023-05-12 15:28:51,522][00161] Num frames 11300... | |
| [2023-05-12 15:28:51,660][00161] Num frames 11400... | |
| [2023-05-12 15:28:51,787][00161] Num frames 11500... | |
| [2023-05-12 15:28:51,913][00161] Num frames 11600... | |
| [2023-05-12 15:28:52,063][00161] Num frames 11700... | |
| [2023-05-12 15:28:52,233][00161] Num frames 11800... | |
| [2023-05-12 15:28:52,414][00161] Num frames 11900... | |
| [2023-05-12 15:28:52,589][00161] Num frames 12000... | |
| [2023-05-12 15:28:52,814][00161] Avg episode rewards: #0: 29.997, true rewards: #0: 12.097 | |
| [2023-05-12 15:28:52,821][00161] Avg episode reward: 29.997, avg true_objective: 12.097 | |
| [2023-05-12 15:28:52,829][00161] Num frames 12100... | |
| [2023-05-12 15:30:09,178][00161] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |
| [2023-05-12 15:30:09,895][00161] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json | |
| [2023-05-12 15:30:09,897][00161] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-05-12 15:30:09,898][00161] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-05-12 15:30:09,900][00161] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-05-12 15:30:09,902][00161] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-05-12 15:30:09,903][00161] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-05-12 15:30:09,905][00161] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-05-12 15:30:09,906][00161] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-05-12 15:30:09,908][00161] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-05-12 15:30:09,908][00161] Adding new argument 'hf_repository'='shreyansjain/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-05-12 15:30:09,909][00161] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-05-12 15:30:09,910][00161] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-05-12 15:30:09,911][00161] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-05-12 15:30:09,912][00161] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-05-12 15:30:09,913][00161] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-05-12 15:30:09,935][00161] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-05-12 15:30:09,938][00161] RunningMeanStd input shape: (1,) | |
| [2023-05-12 15:30:09,955][00161] ConvEncoder: input_channels=3 | |
| [2023-05-12 15:30:10,009][00161] Conv encoder output size: 512 | |
| [2023-05-12 15:30:10,010][00161] Policy head output size: 512 | |
| [2023-05-12 15:30:10,036][00161] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001466_6004736.pth... | |
| [2023-05-12 15:30:10,819][00161] Num frames 100... | |
| [2023-05-12 15:30:11,002][00161] Num frames 200... | |
| [2023-05-12 15:30:11,185][00161] Num frames 300... | |
| [2023-05-12 15:30:11,264][00161] Avg episode rewards: #0: 3.080, true rewards: #0: 3.080 | |
| [2023-05-12 15:30:11,266][00161] Avg episode reward: 3.080, avg true_objective: 3.080 | |
| [2023-05-12 15:30:11,437][00161] Num frames 400... | |
| [2023-05-12 15:30:11,626][00161] Num frames 500... | |
| [2023-05-12 15:30:11,818][00161] Num frames 600... | |
| [2023-05-12 15:30:12,019][00161] Num frames 700... | |
| [2023-05-12 15:30:12,243][00161] Avg episode rewards: #0: 4.940, true rewards: #0: 3.940 | |
| [2023-05-12 15:30:12,246][00161] Avg episode reward: 4.940, avg true_objective: 3.940 | |
| [2023-05-12 15:30:12,273][00161] Num frames 800... | |
| [2023-05-12 15:30:12,475][00161] Num frames 900... | |
| [2023-05-12 15:30:12,676][00161] Num frames 1000... | |
| [2023-05-12 15:30:12,874][00161] Num frames 1100... | |
| [2023-05-12 15:30:13,065][00161] Num frames 1200... | |
| [2023-05-12 15:30:13,267][00161] Num frames 1300... | |
| [2023-05-12 15:30:13,387][00161] Avg episode rewards: #0: 6.107, true rewards: #0: 4.440 | |
| [2023-05-12 15:30:13,390][00161] Avg episode reward: 6.107, avg true_objective: 4.440 | |
| [2023-05-12 15:30:13,528][00161] Num frames 1400... | |
| [2023-05-12 15:30:13,725][00161] Num frames 1500... | |
| [2023-05-12 15:30:13,911][00161] Num frames 1600... | |
| [2023-05-12 15:30:14,125][00161] Num frames 1700... | |
| [2023-05-12 15:30:14,340][00161] Num frames 1800... | |
| [2023-05-12 15:30:14,542][00161] Num frames 1900... | |
| [2023-05-12 15:30:14,775][00161] Num frames 2000... | |
| [2023-05-12 15:30:15,009][00161] Num frames 2100... | |
| [2023-05-12 15:30:15,222][00161] Num frames 2200... | |
| [2023-05-12 15:30:15,412][00161] Avg episode rewards: #0: 10.193, true rewards: #0: 5.692 | |
| [2023-05-12 15:30:15,414][00161] Avg episode reward: 10.193, avg true_objective: 5.692 | |
| [2023-05-12 15:30:15,463][00161] Num frames 2300... | |
| [2023-05-12 15:30:15,670][00161] Num frames 2400... | |
| [2023-05-12 15:30:15,883][00161] Num frames 2500... | |
| [2023-05-12 15:30:16,093][00161] Num frames 2600... | |
| [2023-05-12 15:30:16,312][00161] Num frames 2700... | |
| [2023-05-12 15:30:16,527][00161] Num frames 2800... | |
| [2023-05-12 15:30:16,738][00161] Num frames 2900... | |
| [2023-05-12 15:30:16,950][00161] Num frames 3000... | |
| [2023-05-12 15:30:17,158][00161] Num frames 3100... | |
| [2023-05-12 15:30:17,353][00161] Num frames 3200... | |
| [2023-05-12 15:30:17,566][00161] Num frames 3300... | |
| [2023-05-12 15:30:17,630][00161] Avg episode rewards: #0: 12.802, true rewards: #0: 6.602 | |
| [2023-05-12 15:30:17,632][00161] Avg episode reward: 12.802, avg true_objective: 6.602 | |
| [2023-05-12 15:30:17,801][00161] Num frames 3400... | |
| [2023-05-12 15:30:17,968][00161] Num frames 3500... | |
| [2023-05-12 15:30:18,172][00161] Num frames 3600... | |
| [2023-05-12 15:30:18,358][00161] Num frames 3700... | |
| [2023-05-12 15:30:18,541][00161] Num frames 3800... | |
| [2023-05-12 15:30:18,737][00161] Num frames 3900... | |
| [2023-05-12 15:30:18,913][00161] Num frames 4000... | |
| [2023-05-12 15:30:19,079][00161] Num frames 4100... | |
| [2023-05-12 15:30:19,219][00161] Avg episode rewards: #0: 14.237, true rewards: #0: 6.903 | |
| [2023-05-12 15:30:19,221][00161] Avg episode reward: 14.237, avg true_objective: 6.903 | |
| [2023-05-12 15:30:19,316][00161] Num frames 4200... | |
| [2023-05-12 15:30:19,480][00161] Num frames 4300... | |
| [2023-05-12 15:30:19,648][00161] Num frames 4400... | |
| [2023-05-12 15:30:19,816][00161] Num frames 4500... | |
| [2023-05-12 15:30:19,978][00161] Num frames 4600... | |
| [2023-05-12 15:30:20,135][00161] Num frames 4700... | |
| [2023-05-12 15:30:20,307][00161] Num frames 4800... | |
| [2023-05-12 15:30:20,454][00161] Num frames 4900... | |
| [2023-05-12 15:30:20,574][00161] Num frames 5000... | |
| [2023-05-12 15:30:20,690][00161] Num frames 5100... | |
| [2023-05-12 15:30:20,804][00161] Num frames 5200... | |
| [2023-05-12 15:30:20,969][00161] Avg episode rewards: #0: 15.849, true rewards: #0: 7.563 | |
| [2023-05-12 15:30:20,971][00161] Avg episode reward: 15.849, avg true_objective: 7.563 | |
| [2023-05-12 15:30:20,981][00161] Num frames 5300... | |
| [2023-05-12 15:30:21,098][00161] Num frames 5400... | |
| [2023-05-12 15:30:21,227][00161] Num frames 5500... | |
| [2023-05-12 15:30:21,351][00161] Num frames 5600... | |
| [2023-05-12 15:30:21,474][00161] Num frames 5700... | |
| [2023-05-12 15:30:21,594][00161] Num frames 5800... | |
| [2023-05-12 15:30:21,711][00161] Num frames 5900... | |
| [2023-05-12 15:30:21,832][00161] Num frames 6000... | |
| [2023-05-12 15:30:21,959][00161] Num frames 6100... | |
| [2023-05-12 15:30:22,080][00161] Num frames 6200... | |
| [2023-05-12 15:30:22,197][00161] Num frames 6300... | |
| [2023-05-12 15:30:22,320][00161] Num frames 6400... | |
| [2023-05-12 15:30:22,438][00161] Num frames 6500... | |
| [2023-05-12 15:30:22,597][00161] Avg episode rewards: #0: 17.860, true rewards: #0: 8.235 | |
| [2023-05-12 15:30:22,599][00161] Avg episode reward: 17.860, avg true_objective: 8.235 | |
| [2023-05-12 15:30:22,616][00161] Num frames 6600... | |
| [2023-05-12 15:30:22,735][00161] Num frames 6700... | |
| [2023-05-12 15:30:22,860][00161] Num frames 6800... | |
| [2023-05-12 15:30:22,993][00161] Num frames 6900... | |
| [2023-05-12 15:30:23,115][00161] Num frames 7000... | |
| [2023-05-12 15:30:23,231][00161] Num frames 7100... | |
| [2023-05-12 15:30:23,355][00161] Num frames 7200... | |
| [2023-05-12 15:30:23,476][00161] Num frames 7300... | |
| [2023-05-12 15:30:23,597][00161] Num frames 7400... | |
| [2023-05-12 15:30:23,713][00161] Num frames 7500... | |
| [2023-05-12 15:30:23,832][00161] Num frames 7600... | |
| [2023-05-12 15:30:23,950][00161] Num frames 7700... | |
| [2023-05-12 15:30:24,067][00161] Num frames 7800... | |
| [2023-05-12 15:30:24,184][00161] Num frames 7900... | |
| [2023-05-12 15:30:24,311][00161] Num frames 8000... | |
| [2023-05-12 15:30:24,429][00161] Num frames 8100... | |
| [2023-05-12 15:30:24,552][00161] Num frames 8200... | |
| [2023-05-12 15:30:24,672][00161] Num frames 8300... | |
| [2023-05-12 15:30:24,793][00161] Num frames 8400... | |
| [2023-05-12 15:30:24,863][00161] Avg episode rewards: #0: 21.012, true rewards: #0: 9.346 | |
| [2023-05-12 15:30:24,864][00161] Avg episode reward: 21.012, avg true_objective: 9.346 | |
| [2023-05-12 15:30:24,971][00161] Num frames 8500... | |
| [2023-05-12 15:30:25,093][00161] Num frames 8600... | |
| [2023-05-12 15:30:25,217][00161] Num frames 8700... | |
| [2023-05-12 15:30:25,339][00161] Num frames 8800... | |
| [2023-05-12 15:30:25,459][00161] Num frames 8900... | |
| [2023-05-12 15:30:25,588][00161] Num frames 9000... | |
| [2023-05-12 15:30:25,737][00161] Num frames 9100... | |
| [2023-05-12 15:30:25,857][00161] Num frames 9200... | |
| [2023-05-12 15:30:25,976][00161] Num frames 9300... | |
| [2023-05-12 15:30:26,101][00161] Num frames 9400... | |
| [2023-05-12 15:30:26,223][00161] Num frames 9500... | |
| [2023-05-12 15:30:26,350][00161] Num frames 9600... | |
| [2023-05-12 15:30:26,468][00161] Num frames 9700... | |
| [2023-05-12 15:30:26,588][00161] Num frames 9800... | |
| [2023-05-12 15:30:26,702][00161] Num frames 9900... | |
| [2023-05-12 15:30:26,829][00161] Num frames 10000... | |
| [2023-05-12 15:30:26,998][00161] Num frames 10100... | |
| [2023-05-12 15:30:27,161][00161] Num frames 10200... | |
| [2023-05-12 15:30:27,328][00161] Num frames 10300... | |
| [2023-05-12 15:30:27,449][00161] Num frames 10400... | |
| [2023-05-12 15:30:27,570][00161] Num frames 10500... | |
| [2023-05-12 15:30:27,640][00161] Avg episode rewards: #0: 24.711, true rewards: #0: 10.511 | |
| [2023-05-12 15:30:27,642][00161] Avg episode reward: 24.711, avg true_objective: 10.511 | |
| [2023-05-12 15:31:33,775][00161] Replay video saved to /content/train_dir/default_experiment/replay.mp4! | |