diff --git "a/sf_log.txt" "b/sf_log.txt" new file mode 100644--- /dev/null +++ "b/sf_log.txt" @@ -0,0 +1,1699 @@ +[2023-06-19 14:05:40,113][00753] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-06-19 14:05:40,117][00753] Rollout worker 0 uses device cpu +[2023-06-19 14:05:40,118][00753] Rollout worker 1 uses device cpu +[2023-06-19 14:05:40,119][00753] Rollout worker 2 uses device cpu +[2023-06-19 14:05:40,120][00753] Rollout worker 3 uses device cpu +[2023-06-19 14:05:40,122][00753] Rollout worker 4 uses device cpu +[2023-06-19 14:05:40,123][00753] Rollout worker 5 uses device cpu +[2023-06-19 14:05:40,124][00753] Rollout worker 6 uses device cpu +[2023-06-19 14:05:40,125][00753] Rollout worker 7 uses device cpu +[2023-06-19 14:05:40,277][00753] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:05:40,278][00753] InferenceWorker_p0-w0: min num requests: 2 +[2023-06-19 14:05:40,309][00753] Starting all processes... +[2023-06-19 14:05:40,310][00753] Starting process learner_proc0 +[2023-06-19 14:05:40,361][00753] Starting all processes... +[2023-06-19 14:05:40,370][00753] Starting process inference_proc0-0 +[2023-06-19 14:05:40,370][00753] Starting process rollout_proc0 +[2023-06-19 14:05:40,374][00753] Starting process rollout_proc1 +[2023-06-19 14:05:40,374][00753] Starting process rollout_proc2 +[2023-06-19 14:05:40,374][00753] Starting process rollout_proc3 +[2023-06-19 14:05:40,374][00753] Starting process rollout_proc4 +[2023-06-19 14:05:40,374][00753] Starting process rollout_proc5 +[2023-06-19 14:05:40,376][00753] Starting process rollout_proc6 +[2023-06-19 14:05:40,376][00753] Starting process rollout_proc7 +[2023-06-19 14:05:55,850][11471] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:05:55,852][11471] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-06-19 14:05:55,902][11471] Num visible devices: 1 +[2023-06-19 14:05:55,945][11471] Starting seed is not provided +[2023-06-19 14:05:55,945][11471] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:05:55,946][11471] Initializing actor-critic model on device cuda:0 +[2023-06-19 14:05:55,947][11471] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:05:55,949][11471] RunningMeanStd input shape: (1,) +[2023-06-19 14:05:56,018][11471] ConvEncoder: input_channels=3 +[2023-06-19 14:05:56,443][11492] Worker 7 uses CPU cores [1] +[2023-06-19 14:05:56,483][11487] Worker 2 uses CPU cores [0] +[2023-06-19 14:05:56,501][11489] Worker 4 uses CPU cores [0] +[2023-06-19 14:05:56,575][11485] Worker 0 uses CPU cores [0] +[2023-06-19 14:05:56,628][11491] Worker 6 uses CPU cores [0] +[2023-06-19 14:05:56,642][11486] Worker 1 uses CPU cores [1] +[2023-06-19 14:05:56,642][11488] Worker 3 uses CPU cores [1] +[2023-06-19 14:05:56,668][11484] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:05:56,668][11484] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-06-19 14:05:56,683][11490] Worker 5 uses CPU cores [1] +[2023-06-19 14:05:56,692][11484] Num visible devices: 1 +[2023-06-19 14:05:56,718][11471] Conv encoder output size: 512 +[2023-06-19 14:05:56,719][11471] Policy head output size: 512 +[2023-06-19 14:05:56,767][11471] Created Actor Critic model with architecture: +[2023-06-19 14:05:56,767][11471] 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) + ) +) +[2023-06-19 14:06:00,270][00753] Heartbeat connected on Batcher_0 +[2023-06-19 14:06:00,278][00753] Heartbeat connected on InferenceWorker_p0-w0 +[2023-06-19 14:06:00,288][00753] Heartbeat connected on RolloutWorker_w0 +[2023-06-19 14:06:00,290][00753] Heartbeat connected on RolloutWorker_w1 +[2023-06-19 14:06:00,296][00753] Heartbeat connected on RolloutWorker_w2 +[2023-06-19 14:06:00,297][00753] Heartbeat connected on RolloutWorker_w3 +[2023-06-19 14:06:00,300][00753] Heartbeat connected on RolloutWorker_w4 +[2023-06-19 14:06:00,303][00753] Heartbeat connected on RolloutWorker_w5 +[2023-06-19 14:06:00,309][00753] Heartbeat connected on RolloutWorker_w6 +[2023-06-19 14:06:00,310][00753] Heartbeat connected on RolloutWorker_w7 +[2023-06-19 14:06:04,826][11471] Using optimizer +[2023-06-19 14:06:04,827][11471] No checkpoints found +[2023-06-19 14:06:04,827][11471] Did not load from checkpoint, starting from scratch! +[2023-06-19 14:06:04,827][11471] Initialized policy 0 weights for model version 0 +[2023-06-19 14:06:04,830][11471] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:06:04,837][11471] LearnerWorker_p0 finished initialization! +[2023-06-19 14:06:04,837][00753] Heartbeat connected on LearnerWorker_p0 +[2023-06-19 14:06:05,020][11484] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:06:05,021][11484] RunningMeanStd input shape: (1,) +[2023-06-19 14:06:05,034][11484] ConvEncoder: input_channels=3 +[2023-06-19 14:06:05,138][11484] Conv encoder output size: 512 +[2023-06-19 14:06:05,139][11484] Policy head output size: 512 +[2023-06-19 14:06:05,247][00753] Inference worker 0-0 is ready! +[2023-06-19 14:06:05,250][00753] All inference workers are ready! Signal rollout workers to start! +[2023-06-19 14:06:05,344][11487] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,349][11489] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,353][11491] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,347][11485] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,409][11488] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,426][11492] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,428][11486] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:05,413][11490] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:06:07,489][11485] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,493][11489] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,495][11491] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,488][11487] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,812][11492] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,813][11486] Decorrelating experience for 0 frames... +[2023-06-19 14:06:07,821][11490] Decorrelating experience for 0 frames... +[2023-06-19 14:06:08,860][11488] Decorrelating experience for 0 frames... +[2023-06-19 14:06:09,153][11486] Decorrelating experience for 32 frames... +[2023-06-19 14:06:09,474][11489] Decorrelating experience for 32 frames... +[2023-06-19 14:06:09,478][11485] Decorrelating experience for 32 frames... +[2023-06-19 14:06:09,532][00753] 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) +[2023-06-19 14:06:09,734][11487] Decorrelating experience for 32 frames... +[2023-06-19 14:06:09,741][11491] Decorrelating experience for 32 frames... +[2023-06-19 14:06:10,838][11492] Decorrelating experience for 32 frames... +[2023-06-19 14:06:10,975][11490] Decorrelating experience for 32 frames... +[2023-06-19 14:06:11,104][11488] Decorrelating experience for 32 frames... +[2023-06-19 14:06:11,104][11487] Decorrelating experience for 64 frames... +[2023-06-19 14:06:12,281][11489] Decorrelating experience for 64 frames... +[2023-06-19 14:06:12,438][11485] Decorrelating experience for 64 frames... +[2023-06-19 14:06:12,448][11486] Decorrelating experience for 64 frames... +[2023-06-19 14:06:12,587][11488] Decorrelating experience for 64 frames... +[2023-06-19 14:06:12,708][11487] Decorrelating experience for 96 frames... +[2023-06-19 14:06:13,469][11490] Decorrelating experience for 64 frames... +[2023-06-19 14:06:13,659][00753] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 753], exiting... +[2023-06-19 14:06:13,666][11471] Stopping Batcher_0... +[2023-06-19 14:06:13,667][11471] Loop batcher_evt_loop terminating... +[2023-06-19 14:06:13,668][11471] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000000_0.pth... +[2023-06-19 14:06:13,667][00753] Runner profile tree view: +main_loop: 33.3578 +[2023-06-19 14:06:13,670][00753] Collected {0: 0}, FPS: 0.0 +[2023-06-19 14:06:13,684][11489] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... +[2023-06-19 14:06:13,687][11485] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... +[2023-06-19 14:06:13,690][11491] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... +[2023-06-19 14:06:13,688][11485] 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.SignalException: Signal SIGINT received. ViZDoom instance has been closed. + +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/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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/gymnasium/core.py", line 462, in reset + obs, info = self.env.reset(seed=seed, options=options) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 82, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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 +[2023-06-19 14:06:13,695][11485] Unhandled exception in evt loop rollout_proc0_evt_loop +[2023-06-19 14:06:13,685][11489] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] 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.SignalException: Signal SIGINT received. ViZDoom instance has been closed. + +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/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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/gymnasium/core.py", line 462, in reset + obs, info = self.env.reset(seed=seed, options=options) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 82, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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 +[2023-06-19 14:06:13,698][11489] Unhandled exception in evt loop rollout_proc4_evt_loop +[2023-06-19 14:06:13,691][11491] 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.SignalException: Signal SIGINT received. ViZDoom instance has been closed. + +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/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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/gymnasium/core.py", line 462, in reset + obs, info = self.env.reset(seed=seed, options=options) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 82, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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 +[2023-06-19 14:06:13,700][11491] Unhandled exception in evt loop rollout_proc6_evt_loop +[2023-06-19 14:06:13,775][11488] VizDoom game.init() threw an exception SignalException('Signal SIGINT received. ViZDoom instance has been closed.'). Terminate process... +[2023-06-19 14:06:13,755][11490] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] 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/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 439, in _reset + observations, rew, terminated, truncated, info = e.step(actions) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 408, in step + return self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 129, in step + obs, rew, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/algo/utils/make_env.py", line 115, in step + obs, rew, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step + observation, reward, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 469, in step + observation, reward, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 86, in step + obs, reward, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 408, in step + return self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step + obs, reward, terminated, truncated, info = self.env.step(action) + File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step + reward = self.game.make_action(actions_flattened, self.skip_frames) +vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. +[2023-06-19 14:06:13,776][11490] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop +[2023-06-19 14:06:13,785][11471] Stopping LearnerWorker_p0... +[2023-06-19 14:06:13,786][11471] Loop learner_proc0_evt_loop terminating... +[2023-06-19 14:06:13,780][11488] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() +Traceback (most recent call last): + File "/usr/local/lib/python3.10/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init + self.game.init() +vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. + +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/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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/gymnasium/core.py", line 462, in reset + obs, info = self.env.reset(seed=seed, options=options) + File "/usr/local/lib/python3.10/dist-packages/sample_factory/envs/env_wrappers.py", line 82, in reset + obs, info = self.env.reset(**kwargs) + File "/usr/local/lib/python3.10/dist-packages/gymnasium/core.py", line 414, in reset + return self.env.reset(seed=seed, options=options) + 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 +[2023-06-19 14:06:13,815][11488] Unhandled exception in evt loop rollout_proc3_evt_loop +[2023-06-19 14:06:13,879][11487] Stopping RolloutWorker_w2... +[2023-06-19 14:06:13,880][11487] Loop rollout_proc2_evt_loop terminating... +[2023-06-19 14:06:14,308][11484] Weights refcount: 2 0 +[2023-06-19 14:06:14,312][11484] Stopping InferenceWorker_p0-w0... +[2023-06-19 14:06:14,312][11484] Loop inference_proc0-0_evt_loop terminating... +[2023-06-19 14:06:15,958][11486] Decorrelating experience for 96 frames... +[2023-06-19 14:06:15,961][11492] Decorrelating experience for 64 frames... +[2023-06-19 14:06:16,215][11486] Stopping RolloutWorker_w1... +[2023-06-19 14:06:16,218][11486] Loop rollout_proc1_evt_loop terminating... +[2023-06-19 14:06:17,257][11492] Decorrelating experience for 96 frames... +[2023-06-19 14:06:17,355][11492] Stopping RolloutWorker_w7... +[2023-06-19 14:06:17,356][11492] Loop rollout_proc7_evt_loop terminating... +[2023-06-19 14:11:33,477][00753] Environment doom_basic already registered, overwriting... +[2023-06-19 14:11:33,479][00753] Environment doom_two_colors_easy already registered, overwriting... +[2023-06-19 14:11:33,481][00753] Environment doom_two_colors_hard already registered, overwriting... +[2023-06-19 14:11:33,482][00753] Environment doom_dm already registered, overwriting... +[2023-06-19 14:11:33,483][00753] Environment doom_dwango5 already registered, overwriting... +[2023-06-19 14:11:33,485][00753] Environment doom_my_way_home_flat_actions already registered, overwriting... +[2023-06-19 14:11:33,486][00753] Environment doom_defend_the_center_flat_actions already registered, overwriting... +[2023-06-19 14:11:33,488][00753] Environment doom_my_way_home already registered, overwriting... +[2023-06-19 14:11:33,489][00753] Environment doom_deadly_corridor already registered, overwriting... +[2023-06-19 14:11:33,490][00753] Environment doom_defend_the_center already registered, overwriting... +[2023-06-19 14:11:33,492][00753] Environment doom_defend_the_line already registered, overwriting... +[2023-06-19 14:11:33,493][00753] Environment doom_health_gathering already registered, overwriting... +[2023-06-19 14:11:33,494][00753] Environment doom_health_gathering_supreme already registered, overwriting... +[2023-06-19 14:11:33,495][00753] Environment doom_battle already registered, overwriting... +[2023-06-19 14:11:33,496][00753] Environment doom_battle2 already registered, overwriting... +[2023-06-19 14:11:33,498][00753] Environment doom_duel_bots already registered, overwriting... +[2023-06-19 14:11:33,499][00753] Environment doom_deathmatch_bots already registered, overwriting... +[2023-06-19 14:11:33,500][00753] Environment doom_duel already registered, overwriting... +[2023-06-19 14:11:33,501][00753] Environment doom_deathmatch_full already registered, overwriting... +[2023-06-19 14:11:33,503][00753] Environment doom_benchmark already registered, overwriting... +[2023-06-19 14:11:33,504][00753] register_encoder_factory: +[2023-06-19 14:11:33,527][00753] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-06-19 14:11:33,541][00753] Experiment dir /content/train_dir/default_experiment already exists! +[2023-06-19 14:11:33,542][00753] Resuming existing experiment from /content/train_dir/default_experiment... +[2023-06-19 14:11:33,544][00753] Weights and Biases integration disabled +[2023-06-19 14:11:33,548][00753] Environment var CUDA_VISIBLE_DEVICES is 0 + +[2023-06-19 14:11:35,485][00753] 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=4000000 +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 +[2023-06-19 14:11:35,488][00753] Saving configuration to /content/train_dir/default_experiment/config.json... +[2023-06-19 14:11:35,495][00753] Rollout worker 0 uses device cpu +[2023-06-19 14:11:35,497][00753] Rollout worker 1 uses device cpu +[2023-06-19 14:11:35,498][00753] Rollout worker 2 uses device cpu +[2023-06-19 14:11:35,499][00753] Rollout worker 3 uses device cpu +[2023-06-19 14:11:35,501][00753] Rollout worker 4 uses device cpu +[2023-06-19 14:11:35,502][00753] Rollout worker 5 uses device cpu +[2023-06-19 14:11:35,505][00753] Rollout worker 6 uses device cpu +[2023-06-19 14:11:35,507][00753] Rollout worker 7 uses device cpu +[2023-06-19 14:11:35,600][00753] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:11:35,602][00753] InferenceWorker_p0-w0: min num requests: 2 +[2023-06-19 14:11:35,631][00753] Starting all processes... +[2023-06-19 14:11:35,634][00753] Starting process learner_proc0 +[2023-06-19 14:11:35,681][00753] Starting all processes... +[2023-06-19 14:11:35,686][00753] Starting process inference_proc0-0 +[2023-06-19 14:11:35,688][00753] Starting process rollout_proc0 +[2023-06-19 14:11:35,704][00753] Starting process rollout_proc1 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc2 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc3 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc4 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc5 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc6 +[2023-06-19 14:11:35,705][00753] Starting process rollout_proc7 +[2023-06-19 14:11:50,934][15729] Worker 3 uses CPU cores [1] +[2023-06-19 14:11:51,020][15712] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:11:51,020][15712] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 +[2023-06-19 14:11:51,025][15733] Worker 7 uses CPU cores [1] +[2023-06-19 14:11:51,048][15727] Worker 1 uses CPU cores [1] +[2023-06-19 14:11:51,063][15712] Num visible devices: 1 +[2023-06-19 14:11:51,088][15731] Worker 4 uses CPU cores [0] +[2023-06-19 14:11:51,088][15730] Worker 5 uses CPU cores [1] +[2023-06-19 14:11:51,104][15726] Worker 0 uses CPU cores [0] +[2023-06-19 14:11:51,107][15712] Starting seed is not provided +[2023-06-19 14:11:51,107][15712] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:11:51,108][15712] Initializing actor-critic model on device cuda:0 +[2023-06-19 14:11:51,109][15712] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:11:51,111][15712] RunningMeanStd input shape: (1,) +[2023-06-19 14:11:51,121][15728] Worker 2 uses CPU cores [0] +[2023-06-19 14:11:51,144][15712] ConvEncoder: input_channels=3 +[2023-06-19 14:11:51,177][15725] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:11:51,178][15725] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 +[2023-06-19 14:11:51,195][15732] Worker 6 uses CPU cores [0] +[2023-06-19 14:11:51,209][15725] Num visible devices: 1 +[2023-06-19 14:11:51,306][15712] Conv encoder output size: 512 +[2023-06-19 14:11:51,306][15712] Policy head output size: 512 +[2023-06-19 14:11:51,320][15712] Created Actor Critic model with architecture: +[2023-06-19 14:11:51,320][15712] 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) + ) +) +[2023-06-19 14:11:53,852][15712] Using optimizer +[2023-06-19 14:11:53,854][15712] No checkpoints found +[2023-06-19 14:11:53,854][15712] Did not load from checkpoint, starting from scratch! +[2023-06-19 14:11:53,855][15712] Initialized policy 0 weights for model version 0 +[2023-06-19 14:11:53,863][15712] LearnerWorker_p0 finished initialization! +[2023-06-19 14:11:53,863][15712] Using GPUs [0] for process 0 (actually maps to GPUs [0]) +[2023-06-19 14:11:54,093][15725] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:11:54,094][15725] RunningMeanStd input shape: (1,) +[2023-06-19 14:11:54,113][15725] ConvEncoder: input_channels=3 +[2023-06-19 14:11:54,292][15725] Conv encoder output size: 512 +[2023-06-19 14:11:54,293][15725] Policy head output size: 512 +[2023-06-19 14:11:54,380][00753] Inference worker 0-0 is ready! +[2023-06-19 14:11:54,382][00753] All inference workers are ready! Signal rollout workers to start! +[2023-06-19 14:11:54,493][15728] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,500][15732] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,502][15731] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,504][15726] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,571][15729] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,573][15733] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,575][15727] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:54,564][15730] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:11:55,596][00753] Heartbeat connected on LearnerWorker_p0 +[2023-06-19 14:11:55,601][00753] Heartbeat connected on Batcher_0 +[2023-06-19 14:11:55,630][00753] Heartbeat connected on InferenceWorker_p0-w0 +[2023-06-19 14:11:56,353][15729] Decorrelating experience for 0 frames... +[2023-06-19 14:11:56,364][15733] Decorrelating experience for 0 frames... +[2023-06-19 14:11:56,773][15728] Decorrelating experience for 0 frames... +[2023-06-19 14:11:56,775][15731] Decorrelating experience for 0 frames... +[2023-06-19 14:11:56,778][15726] Decorrelating experience for 0 frames... +[2023-06-19 14:11:56,785][15732] Decorrelating experience for 0 frames... +[2023-06-19 14:11:57,456][15733] Decorrelating experience for 32 frames... +[2023-06-19 14:11:58,310][15731] Decorrelating experience for 32 frames... +[2023-06-19 14:11:58,375][15732] Decorrelating experience for 32 frames... +[2023-06-19 14:11:58,522][15729] Decorrelating experience for 32 frames... +[2023-06-19 14:11:58,542][15727] Decorrelating experience for 0 frames... +[2023-06-19 14:11:58,547][15730] Decorrelating experience for 0 frames... +[2023-06-19 14:11:58,549][00753] 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) +[2023-06-19 14:11:59,421][15728] Decorrelating experience for 32 frames... +[2023-06-19 14:11:59,831][15733] Decorrelating experience for 64 frames... +[2023-06-19 14:11:59,840][15730] Decorrelating experience for 32 frames... +[2023-06-19 14:12:00,246][15726] Decorrelating experience for 32 frames... +[2023-06-19 14:12:00,436][15731] Decorrelating experience for 64 frames... +[2023-06-19 14:12:01,005][15728] Decorrelating experience for 64 frames... +[2023-06-19 14:12:01,145][15732] Decorrelating experience for 64 frames... +[2023-06-19 14:12:01,148][15727] Decorrelating experience for 32 frames... +[2023-06-19 14:12:01,361][15729] Decorrelating experience for 64 frames... +[2023-06-19 14:12:01,535][15730] Decorrelating experience for 64 frames... +[2023-06-19 14:12:02,188][15728] Decorrelating experience for 96 frames... +[2023-06-19 14:12:02,238][15726] Decorrelating experience for 64 frames... +[2023-06-19 14:12:02,287][15727] Decorrelating experience for 64 frames... +[2023-06-19 14:12:02,355][15729] Decorrelating experience for 96 frames... +[2023-06-19 14:12:02,424][00753] Heartbeat connected on RolloutWorker_w2 +[2023-06-19 14:12:02,577][00753] Heartbeat connected on RolloutWorker_w3 +[2023-06-19 14:12:03,164][15731] Decorrelating experience for 96 frames... +[2023-06-19 14:12:03,436][00753] Heartbeat connected on RolloutWorker_w4 +[2023-06-19 14:12:03,549][00753] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 51.2. Samples: 256. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-06-19 14:12:03,554][00753] Avg episode reward: [(0, '0.853')] +[2023-06-19 14:12:04,017][15730] Decorrelating experience for 96 frames... +[2023-06-19 14:12:04,337][15727] Decorrelating experience for 96 frames... +[2023-06-19 14:12:04,383][15732] Decorrelating experience for 96 frames... +[2023-06-19 14:12:04,469][00753] Heartbeat connected on RolloutWorker_w5 +[2023-06-19 14:12:04,512][15726] Decorrelating experience for 96 frames... +[2023-06-19 14:12:04,731][00753] Heartbeat connected on RolloutWorker_w6 +[2023-06-19 14:12:04,799][00753] Heartbeat connected on RolloutWorker_w1 +[2023-06-19 14:12:04,819][00753] Heartbeat connected on RolloutWorker_w0 +[2023-06-19 14:12:05,781][15733] Decorrelating experience for 96 frames... +[2023-06-19 14:12:06,301][00753] Heartbeat connected on RolloutWorker_w7 +[2023-06-19 14:12:06,935][15712] Signal inference workers to stop experience collection... +[2023-06-19 14:12:06,991][15725] InferenceWorker_p0-w0: stopping experience collection +[2023-06-19 14:12:08,549][00753] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 220.6. Samples: 2206. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) +[2023-06-19 14:12:08,558][00753] Avg episode reward: [(0, '2.382')] +[2023-06-19 14:12:11,552][15712] Signal inference workers to resume experience collection... +[2023-06-19 14:12:11,552][15725] InferenceWorker_p0-w0: resuming experience collection +[2023-06-19 14:12:13,555][00753] Fps is (10 sec: 409.3, 60 sec: 273.0, 300 sec: 273.0). Total num frames: 4096. Throughput: 0: 197.8. Samples: 2968. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) +[2023-06-19 14:12:13,558][00753] Avg episode reward: [(0, '2.520')] +[2023-06-19 14:12:18,549][00753] Fps is (10 sec: 2048.0, 60 sec: 1024.0, 300 sec: 1024.0). Total num frames: 20480. Throughput: 0: 317.7. Samples: 6354. Policy #0 lag: (min: 0.0, avg: 0.8, max: 3.0) +[2023-06-19 14:12:18,551][00753] Avg episode reward: [(0, '3.413')] +[2023-06-19 14:12:23,173][15725] Updated weights for policy 0, policy_version 10 (0.0012) +[2023-06-19 14:12:23,549][00753] Fps is (10 sec: 3688.5, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 40960. Throughput: 0: 350.8. Samples: 8770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:12:23,552][00753] Avg episode reward: [(0, '4.084')] +[2023-06-19 14:12:28,549][00753] Fps is (10 sec: 4096.1, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 61440. Throughput: 0: 494.1. Samples: 14822. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:12:28,551][00753] Avg episode reward: [(0, '4.548')] +[2023-06-19 14:12:33,554][00753] Fps is (10 sec: 3684.6, 60 sec: 2223.2, 300 sec: 2223.2). Total num frames: 77824. Throughput: 0: 586.4. Samples: 20526. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:12:33,558][00753] Avg episode reward: [(0, '4.517')] +[2023-06-19 14:12:34,205][15725] Updated weights for policy 0, policy_version 20 (0.0017) +[2023-06-19 14:12:38,549][00753] Fps is (10 sec: 3276.8, 60 sec: 2355.2, 300 sec: 2355.2). Total num frames: 94208. Throughput: 0: 565.2. Samples: 22610. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:12:38,551][00753] Avg episode reward: [(0, '4.478')] +[2023-06-19 14:12:43,549][00753] Fps is (10 sec: 3278.5, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 110592. Throughput: 0: 612.8. Samples: 27578. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:12:43,551][00753] Avg episode reward: [(0, '4.381')] +[2023-06-19 14:12:43,559][15712] Saving new best policy, reward=4.381! +[2023-06-19 14:12:45,633][15725] Updated weights for policy 0, policy_version 30 (0.0021) +[2023-06-19 14:12:48,549][00753] Fps is (10 sec: 4095.9, 60 sec: 2703.3, 300 sec: 2703.3). Total num frames: 135168. Throughput: 0: 758.1. Samples: 34370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:12:48,552][00753] Avg episode reward: [(0, '4.541')] +[2023-06-19 14:12:48,556][15712] Saving new best policy, reward=4.541! +[2023-06-19 14:12:53,550][00753] Fps is (10 sec: 4095.3, 60 sec: 2755.4, 300 sec: 2755.4). Total num frames: 151552. Throughput: 0: 781.9. Samples: 37392. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:12:53,557][00753] Avg episode reward: [(0, '4.502')] +[2023-06-19 14:12:57,335][15725] Updated weights for policy 0, policy_version 40 (0.0021) +[2023-06-19 14:12:58,549][00753] Fps is (10 sec: 2867.2, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 163840. Throughput: 0: 857.1. Samples: 41534. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:12:58,556][00753] Avg episode reward: [(0, '4.432')] +[2023-06-19 14:13:03,549][00753] Fps is (10 sec: 3277.3, 60 sec: 3072.0, 300 sec: 2835.7). Total num frames: 184320. Throughput: 0: 901.1. Samples: 46902. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:13:03,554][00753] Avg episode reward: [(0, '4.480')] +[2023-06-19 14:13:07,653][15725] Updated weights for policy 0, policy_version 50 (0.0016) +[2023-06-19 14:13:08,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3413.3, 300 sec: 2925.7). Total num frames: 204800. Throughput: 0: 921.5. Samples: 50238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:13:08,551][00753] Avg episode reward: [(0, '4.520')] +[2023-06-19 14:13:13,554][00753] Fps is (10 sec: 4093.9, 60 sec: 3686.5, 300 sec: 3003.5). Total num frames: 225280. Throughput: 0: 923.6. Samples: 56388. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:13:13,557][00753] Avg episode reward: [(0, '4.386')] +[2023-06-19 14:13:18,552][00753] Fps is (10 sec: 3275.8, 60 sec: 3618.0, 300 sec: 2969.5). Total num frames: 237568. Throughput: 0: 893.6. Samples: 60738. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:13:18,554][00753] Avg episode reward: [(0, '4.350')] +[2023-06-19 14:13:20,124][15725] Updated weights for policy 0, policy_version 60 (0.0023) +[2023-06-19 14:13:23,549][00753] Fps is (10 sec: 3278.5, 60 sec: 3618.1, 300 sec: 3035.9). Total num frames: 258048. Throughput: 0: 898.3. Samples: 63032. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:13:23,551][00753] Avg episode reward: [(0, '4.358')] +[2023-06-19 14:13:28,549][00753] Fps is (10 sec: 4507.0, 60 sec: 3686.4, 300 sec: 3140.3). Total num frames: 282624. Throughput: 0: 940.1. Samples: 69884. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:13:28,551][00753] Avg episode reward: [(0, '4.463')] +[2023-06-19 14:13:29,476][15725] Updated weights for policy 0, policy_version 70 (0.0020) +[2023-06-19 14:13:33,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.7, 300 sec: 3147.5). Total num frames: 299008. Throughput: 0: 922.1. Samples: 75864. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:13:33,552][00753] Avg episode reward: [(0, '4.633')] +[2023-06-19 14:13:33,566][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000073_299008.pth... +[2023-06-19 14:13:33,703][15712] Saving new best policy, reward=4.633! +[2023-06-19 14:13:38,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3113.0). Total num frames: 311296. Throughput: 0: 898.8. Samples: 77836. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:13:38,555][00753] Avg episode reward: [(0, '4.622')] +[2023-06-19 14:13:42,437][15725] Updated weights for policy 0, policy_version 80 (0.0028) +[2023-06-19 14:13:43,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3159.8). Total num frames: 331776. Throughput: 0: 910.3. Samples: 82498. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:13:43,556][00753] Avg episode reward: [(0, '4.430')] +[2023-06-19 14:13:48,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3202.3). Total num frames: 352256. Throughput: 0: 944.7. Samples: 89412. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:13:48,551][00753] Avg episode reward: [(0, '4.335')] +[2023-06-19 14:13:51,112][15725] Updated weights for policy 0, policy_version 90 (0.0023) +[2023-06-19 14:13:53,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.5, 300 sec: 3241.2). Total num frames: 372736. Throughput: 0: 946.4. Samples: 92826. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:13:53,551][00753] Avg episode reward: [(0, '4.322')] +[2023-06-19 14:13:58,553][00753] Fps is (10 sec: 3684.9, 60 sec: 3754.4, 300 sec: 3242.6). Total num frames: 389120. Throughput: 0: 905.0. Samples: 97110. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:13:58,556][00753] Avg episode reward: [(0, '4.420')] +[2023-06-19 14:14:03,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3244.0). Total num frames: 405504. Throughput: 0: 919.6. Samples: 102116. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:14:03,553][00753] Avg episode reward: [(0, '4.471')] +[2023-06-19 14:14:03,967][15725] Updated weights for policy 0, policy_version 100 (0.0015) +[2023-06-19 14:14:08,549][00753] Fps is (10 sec: 4097.7, 60 sec: 3754.7, 300 sec: 3308.3). Total num frames: 430080. Throughput: 0: 945.2. Samples: 105566. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:14:08,556][00753] Avg episode reward: [(0, '4.427')] +[2023-06-19 14:14:13,551][00753] Fps is (10 sec: 4095.2, 60 sec: 3686.6, 300 sec: 3307.1). Total num frames: 446464. Throughput: 0: 939.4. Samples: 112158. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:13,562][00753] Avg episode reward: [(0, '4.576')] +[2023-06-19 14:14:13,795][15725] Updated weights for policy 0, policy_version 110 (0.0016) +[2023-06-19 14:14:18,556][00753] Fps is (10 sec: 3274.5, 60 sec: 3754.4, 300 sec: 3305.9). Total num frames: 462848. Throughput: 0: 903.6. Samples: 116534. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:18,558][00753] Avg episode reward: [(0, '4.581')] +[2023-06-19 14:14:23,549][00753] Fps is (10 sec: 3277.5, 60 sec: 3686.4, 300 sec: 3305.0). Total num frames: 479232. Throughput: 0: 907.4. Samples: 118670. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:14:23,558][00753] Avg episode reward: [(0, '4.547')] +[2023-06-19 14:14:25,764][15725] Updated weights for policy 0, policy_version 120 (0.0036) +[2023-06-19 14:14:28,549][00753] Fps is (10 sec: 4098.9, 60 sec: 3686.4, 300 sec: 3358.7). Total num frames: 503808. Throughput: 0: 952.0. Samples: 125338. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:28,551][00753] Avg episode reward: [(0, '4.435')] +[2023-06-19 14:14:33,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3382.5). Total num frames: 524288. Throughput: 0: 936.6. Samples: 131560. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:33,552][00753] Avg episode reward: [(0, '4.460')] +[2023-06-19 14:14:36,528][15725] Updated weights for policy 0, policy_version 130 (0.0014) +[2023-06-19 14:14:38,549][00753] Fps is (10 sec: 3276.6, 60 sec: 3754.6, 300 sec: 3353.6). Total num frames: 536576. Throughput: 0: 907.5. Samples: 133666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:14:38,555][00753] Avg episode reward: [(0, '4.480')] +[2023-06-19 14:14:43,549][00753] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3351.3). Total num frames: 552960. Throughput: 0: 910.7. Samples: 138088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:43,556][00753] Avg episode reward: [(0, '4.674')] +[2023-06-19 14:14:43,567][15712] Saving new best policy, reward=4.674! +[2023-06-19 14:14:47,558][15725] Updated weights for policy 0, policy_version 140 (0.0031) +[2023-06-19 14:14:48,549][00753] Fps is (10 sec: 4096.2, 60 sec: 3754.7, 300 sec: 3397.3). Total num frames: 577536. Throughput: 0: 951.2. Samples: 144920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:14:48,551][00753] Avg episode reward: [(0, '4.762')] +[2023-06-19 14:14:48,556][15712] Saving new best policy, reward=4.762! +[2023-06-19 14:14:53,549][00753] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3417.2). Total num frames: 598016. Throughput: 0: 948.8. Samples: 148264. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:53,552][00753] Avg episode reward: [(0, '4.571')] +[2023-06-19 14:14:58,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.7, 300 sec: 3390.6). Total num frames: 610304. Throughput: 0: 903.7. Samples: 152822. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:14:58,551][00753] Avg episode reward: [(0, '4.736')] +[2023-06-19 14:14:59,439][15725] Updated weights for policy 0, policy_version 150 (0.0018) +[2023-06-19 14:15:03,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3387.5). Total num frames: 626688. Throughput: 0: 910.6. Samples: 157506. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:15:03,551][00753] Avg episode reward: [(0, '4.615')] +[2023-06-19 14:15:08,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3427.7). Total num frames: 651264. Throughput: 0: 940.6. Samples: 160996. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:15:08,556][00753] Avg episode reward: [(0, '4.748')] +[2023-06-19 14:15:09,308][15725] Updated weights for policy 0, policy_version 160 (0.0012) +[2023-06-19 14:15:13,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.8, 300 sec: 3444.8). Total num frames: 671744. Throughput: 0: 943.2. Samples: 167780. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:15:13,553][00753] Avg episode reward: [(0, '4.610')] +[2023-06-19 14:15:18,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.8, 300 sec: 3420.2). Total num frames: 684032. Throughput: 0: 901.4. Samples: 172124. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:15:18,551][00753] Avg episode reward: [(0, '4.361')] +[2023-06-19 14:15:21,959][15725] Updated weights for policy 0, policy_version 170 (0.0021) +[2023-06-19 14:15:23,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3416.7). Total num frames: 700416. Throughput: 0: 901.8. Samples: 174248. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:15:23,555][00753] Avg episode reward: [(0, '4.512')] +[2023-06-19 14:15:28,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3452.3). Total num frames: 724992. Throughput: 0: 945.1. Samples: 180618. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:15:28,556][00753] Avg episode reward: [(0, '4.620')] +[2023-06-19 14:15:31,122][15725] Updated weights for policy 0, policy_version 180 (0.0019) +[2023-06-19 14:15:33,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3467.3). Total num frames: 745472. Throughput: 0: 935.0. Samples: 186994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:15:33,558][00753] Avg episode reward: [(0, '4.729')] +[2023-06-19 14:15:33,567][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000182_745472.pth... +[2023-06-19 14:15:38,549][00753] Fps is (10 sec: 3276.6, 60 sec: 3686.4, 300 sec: 3444.4). Total num frames: 757760. Throughput: 0: 907.2. Samples: 189088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:15:38,552][00753] Avg episode reward: [(0, '4.905')] +[2023-06-19 14:15:38,556][15712] Saving new best policy, reward=4.905! +[2023-06-19 14:15:43,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3440.6). Total num frames: 774144. Throughput: 0: 900.0. Samples: 193322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:15:43,554][00753] Avg episode reward: [(0, '4.924')] +[2023-06-19 14:15:43,565][15712] Saving new best policy, reward=4.924! +[2023-06-19 14:15:44,200][15725] Updated weights for policy 0, policy_version 190 (0.0025) +[2023-06-19 14:15:48,549][00753] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3454.9). Total num frames: 794624. Throughput: 0: 944.5. Samples: 200008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:15:48,551][00753] Avg episode reward: [(0, '4.913')] +[2023-06-19 14:15:53,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3468.5). Total num frames: 815104. Throughput: 0: 941.1. Samples: 203346. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-06-19 14:15:53,551][00753] Avg episode reward: [(0, '4.802')] +[2023-06-19 14:15:53,776][15725] Updated weights for policy 0, policy_version 200 (0.0026) +[2023-06-19 14:15:58,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3464.5). Total num frames: 831488. Throughput: 0: 893.8. Samples: 208000. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:15:58,551][00753] Avg episode reward: [(0, '4.682')] +[2023-06-19 14:16:03,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3444.0). Total num frames: 843776. Throughput: 0: 897.2. Samples: 212500. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-06-19 14:16:03,551][00753] Avg episode reward: [(0, '4.617')] +[2023-06-19 14:16:06,146][15725] Updated weights for policy 0, policy_version 210 (0.0031) +[2023-06-19 14:16:08,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3473.4). Total num frames: 868352. Throughput: 0: 926.1. Samples: 215922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:16:08,552][00753] Avg episode reward: [(0, '4.709')] +[2023-06-19 14:16:13,551][00753] Fps is (10 sec: 4504.7, 60 sec: 3618.0, 300 sec: 3485.6). Total num frames: 888832. Throughput: 0: 933.7. Samples: 222636. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:16:13,554][00753] Avg episode reward: [(0, '4.876')] +[2023-06-19 14:16:16,872][15725] Updated weights for policy 0, policy_version 220 (0.0039) +[2023-06-19 14:16:18,549][00753] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3481.6). Total num frames: 905216. Throughput: 0: 887.2. Samples: 226920. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:16:18,551][00753] Avg episode reward: [(0, '4.941')] +[2023-06-19 14:16:18,554][15712] Saving new best policy, reward=4.941! +[2023-06-19 14:16:23,549][00753] Fps is (10 sec: 2867.8, 60 sec: 3618.1, 300 sec: 3462.3). Total num frames: 917504. Throughput: 0: 886.1. Samples: 228962. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-06-19 14:16:23,551][00753] Avg episode reward: [(0, '4.965')] +[2023-06-19 14:16:23,571][15712] Saving new best policy, reward=4.965! +[2023-06-19 14:16:28,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3474.0). Total num frames: 937984. Throughput: 0: 906.7. Samples: 234122. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-06-19 14:16:28,551][00753] Avg episode reward: [(0, '5.020')] +[2023-06-19 14:16:28,554][15712] Saving new best policy, reward=5.020! +[2023-06-19 14:16:29,550][15725] Updated weights for policy 0, policy_version 230 (0.0033) +[2023-06-19 14:16:33,552][00753] Fps is (10 sec: 4094.8, 60 sec: 3549.7, 300 sec: 3485.3). Total num frames: 958464. Throughput: 0: 898.8. Samples: 240456. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:16:33,555][00753] Avg episode reward: [(0, '4.905')] +[2023-06-19 14:16:38,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3618.2, 300 sec: 3481.6). Total num frames: 974848. Throughput: 0: 873.1. Samples: 242636. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:16:38,553][00753] Avg episode reward: [(0, '4.889')] +[2023-06-19 14:16:41,209][15725] Updated weights for policy 0, policy_version 240 (0.0027) +[2023-06-19 14:16:43,551][00753] Fps is (10 sec: 2867.5, 60 sec: 3549.7, 300 sec: 3463.6). Total num frames: 987136. Throughput: 0: 868.8. Samples: 247098. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:16:43,556][00753] Avg episode reward: [(0, '4.894')] +[2023-06-19 14:16:48,549][00753] Fps is (10 sec: 3686.2, 60 sec: 3618.1, 300 sec: 3488.7). Total num frames: 1011712. Throughput: 0: 912.6. Samples: 253566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:16:48,554][00753] Avg episode reward: [(0, '5.113')] +[2023-06-19 14:16:48,562][15712] Saving new best policy, reward=5.113! +[2023-06-19 14:16:51,108][15725] Updated weights for policy 0, policy_version 250 (0.0024) +[2023-06-19 14:16:53,549][00753] Fps is (10 sec: 4506.6, 60 sec: 3618.1, 300 sec: 3499.0). Total num frames: 1032192. Throughput: 0: 910.2. Samples: 256882. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:16:53,559][00753] Avg episode reward: [(0, '5.085')] +[2023-06-19 14:16:58,549][00753] Fps is (10 sec: 3686.6, 60 sec: 3618.1, 300 sec: 3554.5). Total num frames: 1048576. Throughput: 0: 877.2. Samples: 262106. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:16:58,552][00753] Avg episode reward: [(0, '5.168')] +[2023-06-19 14:16:58,558][15712] Saving new best policy, reward=5.168! +[2023-06-19 14:17:03,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3596.1). Total num frames: 1060864. Throughput: 0: 875.8. Samples: 266332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:17:03,554][00753] Avg episode reward: [(0, '5.222')] +[2023-06-19 14:17:03,562][15712] Saving new best policy, reward=5.222! +[2023-06-19 14:17:04,022][15725] Updated weights for policy 0, policy_version 260 (0.0022) +[2023-06-19 14:17:08,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1085440. Throughput: 0: 903.7. Samples: 269628. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:17:08,555][00753] Avg episode reward: [(0, '5.602')] +[2023-06-19 14:17:08,561][15712] Saving new best policy, reward=5.602! +[2023-06-19 14:17:12,955][15725] Updated weights for policy 0, policy_version 270 (0.0015) +[2023-06-19 14:17:13,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3618.3, 300 sec: 3679.5). Total num frames: 1105920. Throughput: 0: 942.3. Samples: 276526. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:17:13,551][00753] Avg episode reward: [(0, '5.298')] +[2023-06-19 14:17:18,549][00753] Fps is (10 sec: 3686.3, 60 sec: 3618.1, 300 sec: 3665.6). Total num frames: 1122304. Throughput: 0: 908.5. Samples: 281338. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:17:18,551][00753] Avg episode reward: [(0, '5.483')] +[2023-06-19 14:17:23,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3637.8). Total num frames: 1134592. Throughput: 0: 908.1. Samples: 283500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:17:23,555][00753] Avg episode reward: [(0, '5.635')] +[2023-06-19 14:17:23,569][15712] Saving new best policy, reward=5.635! +[2023-06-19 14:17:25,750][15725] Updated weights for policy 0, policy_version 280 (0.0024) +[2023-06-19 14:17:28,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1159168. Throughput: 0: 938.5. Samples: 289328. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:17:28,557][00753] Avg episode reward: [(0, '5.970')] +[2023-06-19 14:17:28,561][15712] Saving new best policy, reward=5.970! +[2023-06-19 14:17:33,550][00753] Fps is (10 sec: 4505.1, 60 sec: 3686.5, 300 sec: 3679.4). Total num frames: 1179648. Throughput: 0: 946.8. Samples: 296174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:17:33,555][00753] Avg episode reward: [(0, '5.947')] +[2023-06-19 14:17:33,568][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000288_1179648.pth... +[2023-06-19 14:17:33,725][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000073_299008.pth +[2023-06-19 14:17:35,383][15725] Updated weights for policy 0, policy_version 290 (0.0012) +[2023-06-19 14:17:38,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1196032. Throughput: 0: 921.2. Samples: 298338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:17:38,555][00753] Avg episode reward: [(0, '5.886')] +[2023-06-19 14:17:43,549][00753] Fps is (10 sec: 2867.5, 60 sec: 3686.5, 300 sec: 3637.8). Total num frames: 1208320. Throughput: 0: 898.4. Samples: 302536. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:17:43,551][00753] Avg episode reward: [(0, '5.922')] +[2023-06-19 14:17:47,180][15725] Updated weights for policy 0, policy_version 300 (0.0012) +[2023-06-19 14:17:48,549][00753] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1232896. Throughput: 0: 948.3. Samples: 309006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:17:48,555][00753] Avg episode reward: [(0, '6.287')] +[2023-06-19 14:17:48,560][15712] Saving new best policy, reward=6.287! +[2023-06-19 14:17:53,551][00753] Fps is (10 sec: 4914.2, 60 sec: 3754.5, 300 sec: 3707.2). Total num frames: 1257472. Throughput: 0: 951.4. Samples: 312444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:17:53,556][00753] Avg episode reward: [(0, '6.755')] +[2023-06-19 14:17:53,564][15712] Saving new best policy, reward=6.755! +[2023-06-19 14:17:57,871][15725] Updated weights for policy 0, policy_version 310 (0.0021) +[2023-06-19 14:17:58,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1269760. Throughput: 0: 913.1. Samples: 317614. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:17:58,551][00753] Avg episode reward: [(0, '6.949')] +[2023-06-19 14:17:58,556][15712] Saving new best policy, reward=6.949! +[2023-06-19 14:18:03,549][00753] Fps is (10 sec: 2867.8, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1286144. Throughput: 0: 902.0. Samples: 321930. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:18:03,551][00753] Avg episode reward: [(0, '7.182')] +[2023-06-19 14:18:03,565][15712] Saving new best policy, reward=7.182! +[2023-06-19 14:18:08,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1306624. Throughput: 0: 927.5. Samples: 325236. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:18:08,551][00753] Avg episode reward: [(0, '7.397')] +[2023-06-19 14:18:08,557][15712] Saving new best policy, reward=7.397! +[2023-06-19 14:18:08,855][15725] Updated weights for policy 0, policy_version 320 (0.0015) +[2023-06-19 14:18:13,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3707.3). Total num frames: 1331200. Throughput: 0: 952.1. Samples: 332174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:18:13,551][00753] Avg episode reward: [(0, '7.721')] +[2023-06-19 14:18:13,568][15712] Saving new best policy, reward=7.721! +[2023-06-19 14:18:18,551][00753] Fps is (10 sec: 3685.6, 60 sec: 3686.3, 300 sec: 3679.4). Total num frames: 1343488. Throughput: 0: 904.4. Samples: 336874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:18:18,556][00753] Avg episode reward: [(0, '7.759')] +[2023-06-19 14:18:18,565][15712] Saving new best policy, reward=7.759! +[2023-06-19 14:18:20,572][15725] Updated weights for policy 0, policy_version 330 (0.0012) +[2023-06-19 14:18:23,549][00753] Fps is (10 sec: 2867.1, 60 sec: 3754.7, 300 sec: 3651.7). Total num frames: 1359872. Throughput: 0: 901.9. Samples: 338922. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:18:23,553][00753] Avg episode reward: [(0, '7.919')] +[2023-06-19 14:18:23,571][15712] Saving new best policy, reward=7.919! +[2023-06-19 14:18:28,549][00753] Fps is (10 sec: 3687.1, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1380352. Throughput: 0: 937.2. Samples: 344708. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:18:28,556][00753] Avg episode reward: [(0, '7.680')] +[2023-06-19 14:18:30,848][15725] Updated weights for policy 0, policy_version 340 (0.0029) +[2023-06-19 14:18:33,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3686.5, 300 sec: 3693.3). Total num frames: 1400832. Throughput: 0: 948.0. Samples: 351666. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:18:33,551][00753] Avg episode reward: [(0, '7.957')] +[2023-06-19 14:18:33,620][15712] Saving new best policy, reward=7.957! +[2023-06-19 14:18:38,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1417216. Throughput: 0: 922.4. Samples: 353950. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:18:38,555][00753] Avg episode reward: [(0, '8.508')] +[2023-06-19 14:18:38,557][15712] Saving new best policy, reward=8.508! +[2023-06-19 14:18:43,506][15725] Updated weights for policy 0, policy_version 350 (0.0011) +[2023-06-19 14:18:43,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3665.6). Total num frames: 1433600. Throughput: 0: 901.3. Samples: 358172. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:18:43,553][00753] Avg episode reward: [(0, '8.359')] +[2023-06-19 14:18:48,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1454080. Throughput: 0: 942.8. Samples: 364354. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:18:48,557][00753] Avg episode reward: [(0, '8.789')] +[2023-06-19 14:18:48,560][15712] Saving new best policy, reward=8.789! +[2023-06-19 14:18:52,602][15725] Updated weights for policy 0, policy_version 360 (0.0012) +[2023-06-19 14:18:53,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3686.5, 300 sec: 3693.4). Total num frames: 1478656. Throughput: 0: 944.8. Samples: 367750. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:18:53,555][00753] Avg episode reward: [(0, '9.441')] +[2023-06-19 14:18:53,565][15712] Saving new best policy, reward=9.441! +[2023-06-19 14:18:58,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1490944. Throughput: 0: 911.6. Samples: 373196. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:18:58,552][00753] Avg episode reward: [(0, '10.522')] +[2023-06-19 14:18:58,559][15712] Saving new best policy, reward=10.522! +[2023-06-19 14:19:03,551][00753] Fps is (10 sec: 2867.1, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1507328. Throughput: 0: 902.2. Samples: 377470. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:19:03,559][00753] Avg episode reward: [(0, '10.809')] +[2023-06-19 14:19:03,574][15712] Saving new best policy, reward=10.809! +[2023-06-19 14:19:05,541][15725] Updated weights for policy 0, policy_version 370 (0.0017) +[2023-06-19 14:19:08,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1527808. Throughput: 0: 921.6. Samples: 380394. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:19:08,551][00753] Avg episode reward: [(0, '11.409')] +[2023-06-19 14:19:08,554][15712] Saving new best policy, reward=11.409! +[2023-06-19 14:19:13,549][00753] Fps is (10 sec: 4096.2, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 1548288. Throughput: 0: 945.1. Samples: 387238. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:19:13,551][00753] Avg episode reward: [(0, '10.759')] +[2023-06-19 14:19:14,763][15725] Updated weights for policy 0, policy_version 380 (0.0015) +[2023-06-19 14:19:18,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.5, 300 sec: 3679.5). Total num frames: 1564672. Throughput: 0: 906.5. Samples: 392460. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:19:18,553][00753] Avg episode reward: [(0, '10.834')] +[2023-06-19 14:19:23,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1581056. Throughput: 0: 904.3. Samples: 394642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:19:23,551][00753] Avg episode reward: [(0, '11.892')] +[2023-06-19 14:19:23,564][15712] Saving new best policy, reward=11.892! +[2023-06-19 14:19:27,241][15725] Updated weights for policy 0, policy_version 390 (0.0029) +[2023-06-19 14:19:28,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1601536. Throughput: 0: 934.3. Samples: 400214. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:19:28,551][00753] Avg episode reward: [(0, '12.358')] +[2023-06-19 14:19:28,558][15712] Saving new best policy, reward=12.358! +[2023-06-19 14:19:33,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 1622016. Throughput: 0: 949.3. Samples: 407074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:19:33,552][00753] Avg episode reward: [(0, '12.535')] +[2023-06-19 14:19:33,568][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth... +[2023-06-19 14:19:33,673][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000182_745472.pth +[2023-06-19 14:19:33,687][15712] Saving new best policy, reward=12.535! +[2023-06-19 14:19:37,498][15725] Updated weights for policy 0, policy_version 400 (0.0040) +[2023-06-19 14:19:38,550][00753] Fps is (10 sec: 3685.9, 60 sec: 3686.3, 300 sec: 3679.4). Total num frames: 1638400. Throughput: 0: 926.7. Samples: 409452. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:19:38,553][00753] Avg episode reward: [(0, '12.930')] +[2023-06-19 14:19:38,557][15712] Saving new best policy, reward=12.930! +[2023-06-19 14:19:43,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1654784. Throughput: 0: 901.6. Samples: 413768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:19:43,553][00753] Avg episode reward: [(0, '13.460')] +[2023-06-19 14:19:43,568][15712] Saving new best policy, reward=13.460! +[2023-06-19 14:19:48,549][00753] Fps is (10 sec: 3686.9, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1675264. Throughput: 0: 942.2. Samples: 419870. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0) +[2023-06-19 14:19:48,553][00753] Avg episode reward: [(0, '13.915')] +[2023-06-19 14:19:48,561][15712] Saving new best policy, reward=13.915! +[2023-06-19 14:19:49,080][15725] Updated weights for policy 0, policy_version 410 (0.0030) +[2023-06-19 14:19:53,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1699840. Throughput: 0: 953.1. Samples: 423282. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:19:53,551][00753] Avg episode reward: [(0, '14.676')] +[2023-06-19 14:19:53,560][15712] Saving new best policy, reward=14.676! +[2023-06-19 14:19:58,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1716224. Throughput: 0: 923.9. Samples: 428812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:19:58,553][00753] Avg episode reward: [(0, '14.714')] +[2023-06-19 14:19:58,557][15712] Saving new best policy, reward=14.714! +[2023-06-19 14:19:59,953][15725] Updated weights for policy 0, policy_version 420 (0.0023) +[2023-06-19 14:20:03,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1728512. Throughput: 0: 906.0. Samples: 433232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:20:03,558][00753] Avg episode reward: [(0, '14.795')] +[2023-06-19 14:20:03,567][15712] Saving new best policy, reward=14.795! +[2023-06-19 14:20:08,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1748992. Throughput: 0: 918.4. Samples: 435972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:20:08,551][00753] Avg episode reward: [(0, '14.436')] +[2023-06-19 14:20:10,658][15725] Updated weights for policy 0, policy_version 430 (0.0012) +[2023-06-19 14:20:13,549][00753] Fps is (10 sec: 4505.5, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1773568. Throughput: 0: 949.2. Samples: 442926. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:20:13,551][00753] Avg episode reward: [(0, '14.408')] +[2023-06-19 14:20:18,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1789952. Throughput: 0: 915.9. Samples: 448290. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:20:18,555][00753] Avg episode reward: [(0, '14.170')] +[2023-06-19 14:20:22,322][15725] Updated weights for policy 0, policy_version 440 (0.0017) +[2023-06-19 14:20:23,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1802240. Throughput: 0: 910.7. Samples: 450434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:20:23,558][00753] Avg episode reward: [(0, '14.235')] +[2023-06-19 14:20:28,549][00753] Fps is (10 sec: 3276.9, 60 sec: 3686.4, 300 sec: 3651.7). Total num frames: 1822720. Throughput: 0: 932.1. Samples: 455712. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:20:28,554][00753] Avg episode reward: [(0, '15.125')] +[2023-06-19 14:20:28,559][15712] Saving new best policy, reward=15.125! +[2023-06-19 14:20:32,398][15725] Updated weights for policy 0, policy_version 450 (0.0021) +[2023-06-19 14:20:33,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 1847296. Throughput: 0: 949.4. Samples: 462594. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:20:33,557][00753] Avg episode reward: [(0, '14.947')] +[2023-06-19 14:20:38,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3693.3). Total num frames: 1863680. Throughput: 0: 935.8. Samples: 465392. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:20:38,554][00753] Avg episode reward: [(0, '15.479')] +[2023-06-19 14:20:38,563][15712] Saving new best policy, reward=15.479! +[2023-06-19 14:20:43,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1875968. Throughput: 0: 906.8. Samples: 469620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:20:43,553][00753] Avg episode reward: [(0, '14.941')] +[2023-06-19 14:20:45,104][15725] Updated weights for policy 0, policy_version 460 (0.0024) +[2023-06-19 14:20:48,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1900544. Throughput: 0: 940.4. Samples: 475548. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:20:48,554][00753] Avg episode reward: [(0, '16.035')] +[2023-06-19 14:20:48,557][15712] Saving new best policy, reward=16.035! +[2023-06-19 14:20:53,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1921024. Throughput: 0: 953.5. Samples: 478878. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:20:53,551][00753] Avg episode reward: [(0, '16.908')] +[2023-06-19 14:20:53,560][15712] Saving new best policy, reward=16.908! +[2023-06-19 14:20:53,975][15725] Updated weights for policy 0, policy_version 470 (0.0018) +[2023-06-19 14:20:58,552][00753] Fps is (10 sec: 3685.1, 60 sec: 3686.2, 300 sec: 3707.2). Total num frames: 1937408. Throughput: 0: 930.4. Samples: 484798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:20:58,558][00753] Avg episode reward: [(0, '17.941')] +[2023-06-19 14:20:58,560][15712] Saving new best policy, reward=17.941! +[2023-06-19 14:21:03,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 1953792. Throughput: 0: 904.8. Samples: 489004. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:21:03,553][00753] Avg episode reward: [(0, '17.809')] +[2023-06-19 14:21:06,862][15725] Updated weights for policy 0, policy_version 480 (0.0031) +[2023-06-19 14:21:08,549][00753] Fps is (10 sec: 3277.9, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 1970176. Throughput: 0: 914.3. Samples: 491576. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:21:08,556][00753] Avg episode reward: [(0, '17.267')] +[2023-06-19 14:21:13,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 1994752. Throughput: 0: 948.5. Samples: 498396. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:21:13,554][00753] Avg episode reward: [(0, '16.821')] +[2023-06-19 14:21:15,876][15725] Updated weights for policy 0, policy_version 490 (0.0017) +[2023-06-19 14:21:18,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2011136. Throughput: 0: 923.1. Samples: 504132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:21:18,551][00753] Avg episode reward: [(0, '17.097')] +[2023-06-19 14:21:23,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2027520. Throughput: 0: 908.7. Samples: 506284. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:21:23,551][00753] Avg episode reward: [(0, '16.392')] +[2023-06-19 14:21:28,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3693.4). Total num frames: 2048000. Throughput: 0: 925.6. Samples: 511272. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:21:28,552][15725] Updated weights for policy 0, policy_version 500 (0.0012) +[2023-06-19 14:21:28,550][00753] Avg episode reward: [(0, '18.095')] +[2023-06-19 14:21:28,562][15712] Saving new best policy, reward=18.095! +[2023-06-19 14:21:33,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2068480. Throughput: 0: 945.6. Samples: 518098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:21:33,554][00753] Avg episode reward: [(0, '18.358')] +[2023-06-19 14:21:33,567][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth... +[2023-06-19 14:21:33,678][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000288_1179648.pth +[2023-06-19 14:21:33,685][15712] Saving new best policy, reward=18.358! +[2023-06-19 14:21:38,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2084864. Throughput: 0: 938.0. Samples: 521088. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:21:38,551][00753] Avg episode reward: [(0, '20.300')] +[2023-06-19 14:21:38,564][15712] Saving new best policy, reward=20.300! +[2023-06-19 14:21:38,816][15725] Updated weights for policy 0, policy_version 510 (0.0032) +[2023-06-19 14:21:43,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2101248. Throughput: 0: 899.4. Samples: 525266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:21:43,556][00753] Avg episode reward: [(0, '19.890')] +[2023-06-19 14:21:48,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2117632. Throughput: 0: 924.3. Samples: 530596. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:21:48,554][00753] Avg episode reward: [(0, '20.911')] +[2023-06-19 14:21:48,556][15712] Saving new best policy, reward=20.911! +[2023-06-19 14:21:50,633][15725] Updated weights for policy 0, policy_version 520 (0.0020) +[2023-06-19 14:21:53,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2142208. Throughput: 0: 942.9. Samples: 534006. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:21:53,551][00753] Avg episode reward: [(0, '20.340')] +[2023-06-19 14:21:58,550][00753] Fps is (10 sec: 4095.6, 60 sec: 3686.5, 300 sec: 3721.1). Total num frames: 2158592. Throughput: 0: 931.3. Samples: 540306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:21:58,552][00753] Avg episode reward: [(0, '20.661')] +[2023-06-19 14:22:01,536][15725] Updated weights for policy 0, policy_version 530 (0.0022) +[2023-06-19 14:22:03,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2174976. Throughput: 0: 898.7. Samples: 544572. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:22:03,555][00753] Avg episode reward: [(0, '20.566')] +[2023-06-19 14:22:08,549][00753] Fps is (10 sec: 3277.2, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 2191360. Throughput: 0: 898.5. Samples: 546718. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:22:08,556][00753] Avg episode reward: [(0, '20.566')] +[2023-06-19 14:22:12,406][15725] Updated weights for policy 0, policy_version 540 (0.0014) +[2023-06-19 14:22:13,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2215936. Throughput: 0: 940.4. Samples: 553588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:22:13,557][00753] Avg episode reward: [(0, '20.341')] +[2023-06-19 14:22:18,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2232320. Throughput: 0: 922.7. Samples: 559618. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:22:18,554][00753] Avg episode reward: [(0, '20.097')] +[2023-06-19 14:22:23,549][00753] Fps is (10 sec: 3276.7, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2248704. Throughput: 0: 901.9. Samples: 561672. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:22:23,555][00753] Avg episode reward: [(0, '19.525')] +[2023-06-19 14:22:24,055][15725] Updated weights for policy 0, policy_version 550 (0.0016) +[2023-06-19 14:22:28,550][00753] Fps is (10 sec: 3276.4, 60 sec: 3618.1, 300 sec: 3679.5). Total num frames: 2265088. Throughput: 0: 914.8. Samples: 566434. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) +[2023-06-19 14:22:28,554][00753] Avg episode reward: [(0, '20.315')] +[2023-06-19 14:22:33,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2289664. Throughput: 0: 949.5. Samples: 573322. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:22:33,552][00753] Avg episode reward: [(0, '19.414')] +[2023-06-19 14:22:34,035][15725] Updated weights for policy 0, policy_version 560 (0.0024) +[2023-06-19 14:22:38,549][00753] Fps is (10 sec: 4506.1, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2310144. Throughput: 0: 950.5. Samples: 576778. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:22:38,555][00753] Avg episode reward: [(0, '20.310')] +[2023-06-19 14:22:43,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2322432. Throughput: 0: 907.2. Samples: 581128. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:22:43,553][00753] Avg episode reward: [(0, '20.931')] +[2023-06-19 14:22:43,567][15712] Saving new best policy, reward=20.931! +[2023-06-19 14:22:46,923][15725] Updated weights for policy 0, policy_version 570 (0.0023) +[2023-06-19 14:22:48,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3665.6). Total num frames: 2338816. Throughput: 0: 924.1. Samples: 586156. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:22:48,557][00753] Avg episode reward: [(0, '20.626')] +[2023-06-19 14:22:53,551][00753] Fps is (10 sec: 4095.1, 60 sec: 3686.3, 300 sec: 3707.2). Total num frames: 2363392. Throughput: 0: 953.1. Samples: 589610. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:22:53,553][00753] Avg episode reward: [(0, '19.179')] +[2023-06-19 14:22:55,696][15725] Updated weights for policy 0, policy_version 580 (0.0040) +[2023-06-19 14:22:58,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2383872. Throughput: 0: 949.6. Samples: 596318. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:22:58,554][00753] Avg episode reward: [(0, '18.110')] +[2023-06-19 14:23:03,549][00753] Fps is (10 sec: 3687.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2400256. Throughput: 0: 909.9. Samples: 600564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:03,556][00753] Avg episode reward: [(0, '18.247')] +[2023-06-19 14:23:08,363][15725] Updated weights for policy 0, policy_version 590 (0.0023) +[2023-06-19 14:23:08,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2416640. Throughput: 0: 913.3. Samples: 602772. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:23:08,551][00753] Avg episode reward: [(0, '18.553')] +[2023-06-19 14:23:13,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.3). Total num frames: 2437120. Throughput: 0: 956.2. Samples: 609464. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:23:13,551][00753] Avg episode reward: [(0, '20.628')] +[2023-06-19 14:23:17,184][15725] Updated weights for policy 0, policy_version 600 (0.0013) +[2023-06-19 14:23:18,550][00753] Fps is (10 sec: 4095.5, 60 sec: 3754.6, 300 sec: 3721.1). Total num frames: 2457600. Throughput: 0: 945.2. Samples: 615858. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:18,552][00753] Avg episode reward: [(0, '21.862')] +[2023-06-19 14:23:18,630][15712] Saving new best policy, reward=21.862! +[2023-06-19 14:23:23,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2473984. Throughput: 0: 915.7. Samples: 617986. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:23:23,557][00753] Avg episode reward: [(0, '22.522')] +[2023-06-19 14:23:23,575][15712] Saving new best policy, reward=22.522! +[2023-06-19 14:23:28,549][00753] Fps is (10 sec: 3277.2, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2490368. Throughput: 0: 912.5. Samples: 622192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:23:28,555][00753] Avg episode reward: [(0, '24.060')] +[2023-06-19 14:23:28,557][15712] Saving new best policy, reward=24.060! +[2023-06-19 14:23:30,128][15725] Updated weights for policy 0, policy_version 610 (0.0024) +[2023-06-19 14:23:33,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2510848. Throughput: 0: 952.6. Samples: 629022. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:33,554][00753] Avg episode reward: [(0, '23.716')] +[2023-06-19 14:23:33,626][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000614_2514944.pth... +[2023-06-19 14:23:33,740][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000397_1626112.pth +[2023-06-19 14:23:38,549][00753] Fps is (10 sec: 4095.9, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2531328. Throughput: 0: 950.4. Samples: 632374. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:38,551][00753] Avg episode reward: [(0, '23.141')] +[2023-06-19 14:23:40,137][15725] Updated weights for policy 0, policy_version 620 (0.0024) +[2023-06-19 14:23:43,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 2547712. Throughput: 0: 909.4. Samples: 637240. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:23:43,553][00753] Avg episode reward: [(0, '23.405')] +[2023-06-19 14:23:48,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3679.5). Total num frames: 2564096. Throughput: 0: 919.2. Samples: 641926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:48,551][00753] Avg episode reward: [(0, '23.322')] +[2023-06-19 14:23:51,573][15725] Updated weights for policy 0, policy_version 630 (0.0020) +[2023-06-19 14:23:53,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3721.1). Total num frames: 2588672. Throughput: 0: 948.3. Samples: 645444. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:53,552][00753] Avg episode reward: [(0, '22.911')] +[2023-06-19 14:23:58,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2609152. Throughput: 0: 953.2. Samples: 652360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:23:58,553][00753] Avg episode reward: [(0, '23.911')] +[2023-06-19 14:24:02,120][15725] Updated weights for policy 0, policy_version 640 (0.0029) +[2023-06-19 14:24:03,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2625536. Throughput: 0: 909.4. Samples: 656780. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:24:03,556][00753] Avg episode reward: [(0, '23.875')] +[2023-06-19 14:24:08,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2637824. Throughput: 0: 910.4. Samples: 658952. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:24:08,553][00753] Avg episode reward: [(0, '23.861')] +[2023-06-19 14:24:13,158][15725] Updated weights for policy 0, policy_version 650 (0.0026) +[2023-06-19 14:24:13,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2662400. Throughput: 0: 957.3. Samples: 665270. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:24:13,554][00753] Avg episode reward: [(0, '22.964')] +[2023-06-19 14:24:18,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2682880. Throughput: 0: 957.2. Samples: 672098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:24:18,551][00753] Avg episode reward: [(0, '24.281')] +[2023-06-19 14:24:18,554][15712] Saving new best policy, reward=24.281! +[2023-06-19 14:24:23,552][00753] Fps is (10 sec: 3685.2, 60 sec: 3754.5, 300 sec: 3721.1). Total num frames: 2699264. Throughput: 0: 930.1. Samples: 674230. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:24:23,555][00753] Avg episode reward: [(0, '24.904')] +[2023-06-19 14:24:23,571][15712] Saving new best policy, reward=24.904! +[2023-06-19 14:24:24,509][15725] Updated weights for policy 0, policy_version 660 (0.0019) +[2023-06-19 14:24:28,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3693.3). Total num frames: 2711552. Throughput: 0: 916.7. Samples: 678492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:24:28,555][00753] Avg episode reward: [(0, '25.365')] +[2023-06-19 14:24:28,624][15712] Saving new best policy, reward=25.365! +[2023-06-19 14:24:33,549][00753] Fps is (10 sec: 3687.6, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2736128. Throughput: 0: 954.4. Samples: 684872. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:24:33,553][00753] Avg episode reward: [(0, '25.712')] +[2023-06-19 14:24:33,567][15712] Saving new best policy, reward=25.712! +[2023-06-19 14:24:34,939][15725] Updated weights for policy 0, policy_version 670 (0.0015) +[2023-06-19 14:24:38,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 2756608. Throughput: 0: 951.5. Samples: 688260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:24:38,558][00753] Avg episode reward: [(0, '25.987')] +[2023-06-19 14:24:38,561][15712] Saving new best policy, reward=25.987! +[2023-06-19 14:24:43,550][00753] Fps is (10 sec: 3686.0, 60 sec: 3754.6, 300 sec: 3721.1). Total num frames: 2772992. Throughput: 0: 911.0. Samples: 693356. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) +[2023-06-19 14:24:43,555][00753] Avg episode reward: [(0, '26.816')] +[2023-06-19 14:24:43,567][15712] Saving new best policy, reward=26.816! +[2023-06-19 14:24:47,293][15725] Updated weights for policy 0, policy_version 680 (0.0026) +[2023-06-19 14:24:48,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3686.4, 300 sec: 3679.5). Total num frames: 2785280. Throughput: 0: 911.0. Samples: 697774. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:24:48,559][00753] Avg episode reward: [(0, '26.980')] +[2023-06-19 14:24:48,612][15712] Saving new best policy, reward=26.980! +[2023-06-19 14:24:53,549][00753] Fps is (10 sec: 3686.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2809856. Throughput: 0: 933.1. Samples: 700942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:24:53,551][00753] Avg episode reward: [(0, '25.967')] +[2023-06-19 14:24:56,664][15725] Updated weights for policy 0, policy_version 690 (0.0042) +[2023-06-19 14:24:58,549][00753] Fps is (10 sec: 4915.2, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2834432. Throughput: 0: 948.0. Samples: 707932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:24:58,551][00753] Avg episode reward: [(0, '26.305')] +[2023-06-19 14:25:03,549][00753] Fps is (10 sec: 3686.3, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 2846720. Throughput: 0: 909.8. Samples: 713040. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:25:03,555][00753] Avg episode reward: [(0, '25.463')] +[2023-06-19 14:25:08,549][00753] Fps is (10 sec: 2867.0, 60 sec: 3754.6, 300 sec: 3693.3). Total num frames: 2863104. Throughput: 0: 910.6. Samples: 715204. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:25:08,552][00753] Avg episode reward: [(0, '26.561')] +[2023-06-19 14:25:09,222][15725] Updated weights for policy 0, policy_version 700 (0.0020) +[2023-06-19 14:25:13,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 2883584. Throughput: 0: 944.7. Samples: 721002. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:25:13,553][00753] Avg episode reward: [(0, '24.632')] +[2023-06-19 14:25:17,882][15725] Updated weights for policy 0, policy_version 710 (0.0019) +[2023-06-19 14:25:18,554][00753] Fps is (10 sec: 4503.5, 60 sec: 3754.3, 300 sec: 3748.8). Total num frames: 2908160. Throughput: 0: 960.1. Samples: 728082. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:25:18,557][00753] Avg episode reward: [(0, '25.128')] +[2023-06-19 14:25:23,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.9, 300 sec: 3735.0). Total num frames: 2924544. Throughput: 0: 942.0. Samples: 730652. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:25:23,557][00753] Avg episode reward: [(0, '26.490')] +[2023-06-19 14:25:28,549][00753] Fps is (10 sec: 2868.7, 60 sec: 3754.7, 300 sec: 3693.3). Total num frames: 2936832. Throughput: 0: 925.0. Samples: 734980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:25:28,552][00753] Avg episode reward: [(0, '25.926')] +[2023-06-19 14:25:30,767][15725] Updated weights for policy 0, policy_version 720 (0.0015) +[2023-06-19 14:25:33,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2961408. Throughput: 0: 960.0. Samples: 740972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:25:33,557][00753] Avg episode reward: [(0, '26.396')] +[2023-06-19 14:25:33,569][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000723_2961408.pth... +[2023-06-19 14:25:33,682][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000505_2068480.pth +[2023-06-19 14:25:38,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 2981888. Throughput: 0: 966.6. Samples: 744438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:25:38,551][00753] Avg episode reward: [(0, '26.917')] +[2023-06-19 14:25:39,966][15725] Updated weights for policy 0, policy_version 730 (0.0018) +[2023-06-19 14:25:43,549][00753] Fps is (10 sec: 3686.3, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 2998272. Throughput: 0: 934.6. Samples: 749990. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:25:43,551][00753] Avg episode reward: [(0, '27.643')] +[2023-06-19 14:25:43,566][15712] Saving new best policy, reward=27.643! +[2023-06-19 14:25:48,549][00753] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3707.2). Total num frames: 3014656. Throughput: 0: 914.7. Samples: 754202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:25:48,553][00753] Avg episode reward: [(0, '26.404')] +[2023-06-19 14:25:52,564][15725] Updated weights for policy 0, policy_version 740 (0.0031) +[2023-06-19 14:25:53,549][00753] Fps is (10 sec: 3686.5, 60 sec: 3754.7, 300 sec: 3721.2). Total num frames: 3035136. Throughput: 0: 931.7. Samples: 757128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:25:53,555][00753] Avg episode reward: [(0, '25.247')] +[2023-06-19 14:25:58,549][00753] Fps is (10 sec: 4096.2, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3055616. Throughput: 0: 958.3. Samples: 764124. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:25:58,551][00753] Avg episode reward: [(0, '24.583')] +[2023-06-19 14:26:02,437][15725] Updated weights for policy 0, policy_version 750 (0.0018) +[2023-06-19 14:26:03,553][00753] Fps is (10 sec: 3684.9, 60 sec: 3754.4, 300 sec: 3734.9). Total num frames: 3072000. Throughput: 0: 919.1. Samples: 769442. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:26:03,560][00753] Avg episode reward: [(0, '23.439')] +[2023-06-19 14:26:08,549][00753] Fps is (10 sec: 3276.7, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3088384. Throughput: 0: 909.7. Samples: 771588. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:08,557][00753] Avg episode reward: [(0, '23.079')] +[2023-06-19 14:26:13,549][00753] Fps is (10 sec: 3687.9, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3108864. Throughput: 0: 933.6. Samples: 776994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:13,551][00753] Avg episode reward: [(0, '22.671')] +[2023-06-19 14:26:14,083][15725] Updated weights for policy 0, policy_version 760 (0.0023) +[2023-06-19 14:26:18,549][00753] Fps is (10 sec: 4505.6, 60 sec: 3755.0, 300 sec: 3748.9). Total num frames: 3133440. Throughput: 0: 955.6. Samples: 783974. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:18,551][00753] Avg episode reward: [(0, '22.104')] +[2023-06-19 14:26:23,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3735.0). Total num frames: 3149824. Throughput: 0: 942.7. Samples: 786860. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:23,551][00753] Avg episode reward: [(0, '22.932')] +[2023-06-19 14:26:24,534][15725] Updated weights for policy 0, policy_version 770 (0.0028) +[2023-06-19 14:26:28,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3754.7, 300 sec: 3707.2). Total num frames: 3162112. Throughput: 0: 915.8. Samples: 791202. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:28,554][00753] Avg episode reward: [(0, '23.194')] +[2023-06-19 14:26:33,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3182592. Throughput: 0: 945.4. Samples: 796746. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:26:33,556][00753] Avg episode reward: [(0, '24.083')] +[2023-06-19 14:26:35,617][15725] Updated weights for policy 0, policy_version 780 (0.0019) +[2023-06-19 14:26:38,549][00753] Fps is (10 sec: 4505.7, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3207168. Throughput: 0: 954.8. Samples: 800094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:26:38,551][00753] Avg episode reward: [(0, '25.015')] +[2023-06-19 14:26:43,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3754.7, 300 sec: 3748.9). Total num frames: 3223552. Throughput: 0: 931.2. Samples: 806028. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:26:43,554][00753] Avg episode reward: [(0, '25.565')] +[2023-06-19 14:26:47,089][15725] Updated weights for policy 0, policy_version 790 (0.0024) +[2023-06-19 14:26:48,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3721.1). Total num frames: 3239936. Throughput: 0: 909.1. Samples: 810348. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:26:48,554][00753] Avg episode reward: [(0, '26.374')] +[2023-06-19 14:26:53,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3721.1). Total num frames: 3256320. Throughput: 0: 917.5. Samples: 812876. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) +[2023-06-19 14:26:53,552][00753] Avg episode reward: [(0, '26.270')] +[2023-06-19 14:26:57,599][15725] Updated weights for policy 0, policy_version 800 (0.0023) +[2023-06-19 14:26:58,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3735.0). Total num frames: 3276800. Throughput: 0: 941.8. Samples: 819376. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:26:58,551][00753] Avg episode reward: [(0, '26.020')] +[2023-06-19 14:27:03,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3754.9, 300 sec: 3748.9). Total num frames: 3297280. Throughput: 0: 905.3. Samples: 824712. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:27:03,551][00753] Avg episode reward: [(0, '26.398')] +[2023-06-19 14:27:08,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3707.2). Total num frames: 3309568. Throughput: 0: 885.5. Samples: 826706. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:27:08,551][00753] Avg episode reward: [(0, '25.847')] +[2023-06-19 14:27:10,903][15725] Updated weights for policy 0, policy_version 810 (0.0028) +[2023-06-19 14:27:13,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3618.1, 300 sec: 3707.2). Total num frames: 3325952. Throughput: 0: 896.4. Samples: 831542. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:27:13,551][00753] Avg episode reward: [(0, '25.049')] +[2023-06-19 14:27:18,549][00753] Fps is (10 sec: 4095.9, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3350528. Throughput: 0: 921.3. Samples: 838206. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:27:18,552][00753] Avg episode reward: [(0, '23.905')] +[2023-06-19 14:27:20,181][15725] Updated weights for policy 0, policy_version 820 (0.0016) +[2023-06-19 14:27:23,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3618.1, 300 sec: 3735.0). Total num frames: 3366912. Throughput: 0: 912.2. Samples: 841144. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:27:23,552][00753] Avg episode reward: [(0, '22.080')] +[2023-06-19 14:27:28,549][00753] Fps is (10 sec: 2867.3, 60 sec: 3618.1, 300 sec: 3693.3). Total num frames: 3379200. Throughput: 0: 870.4. Samples: 845198. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:27:28,550][00753] Avg episode reward: [(0, '22.160')] +[2023-06-19 14:27:33,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3549.9, 300 sec: 3679.5). Total num frames: 3395584. Throughput: 0: 886.9. Samples: 850260. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:27:33,556][00753] Avg episode reward: [(0, '23.197')] +[2023-06-19 14:27:33,568][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000829_3395584.pth... +[2023-06-19 14:27:33,688][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000614_2514944.pth +[2023-06-19 14:27:33,811][15725] Updated weights for policy 0, policy_version 830 (0.0038) +[2023-06-19 14:27:38,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3721.1). Total num frames: 3420160. Throughput: 0: 903.5. Samples: 853532. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:27:38,551][00753] Avg episode reward: [(0, '24.463')] +[2023-06-19 14:27:43,549][00753] Fps is (10 sec: 4095.9, 60 sec: 3549.8, 300 sec: 3721.1). Total num frames: 3436544. Throughput: 0: 891.9. Samples: 859512. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) +[2023-06-19 14:27:43,557][00753] Avg episode reward: [(0, '24.208')] +[2023-06-19 14:27:44,183][15725] Updated weights for policy 0, policy_version 840 (0.0018) +[2023-06-19 14:27:48,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 3448832. Throughput: 0: 858.9. Samples: 863362. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:27:48,554][00753] Avg episode reward: [(0, '24.357')] +[2023-06-19 14:27:53,549][00753] Fps is (10 sec: 2867.3, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 3465216. Throughput: 0: 860.0. Samples: 865408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:27:53,551][00753] Avg episode reward: [(0, '24.807')] +[2023-06-19 14:27:56,880][15725] Updated weights for policy 0, policy_version 850 (0.0036) +[2023-06-19 14:27:58,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3679.5). Total num frames: 3485696. Throughput: 0: 886.2. Samples: 871422. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:27:58,551][00753] Avg episode reward: [(0, '26.831')] +[2023-06-19 14:28:03,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3693.3). Total num frames: 3506176. Throughput: 0: 871.5. Samples: 877424. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:03,556][00753] Avg episode reward: [(0, '24.616')] +[2023-06-19 14:28:08,553][00753] Fps is (10 sec: 3275.4, 60 sec: 3481.4, 300 sec: 3665.5). Total num frames: 3518464. Throughput: 0: 850.9. Samples: 879436. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:08,558][00753] Avg episode reward: [(0, '23.077')] +[2023-06-19 14:28:09,151][15725] Updated weights for policy 0, policy_version 860 (0.0025) +[2023-06-19 14:28:13,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3534848. Throughput: 0: 850.8. Samples: 883482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:13,551][00753] Avg episode reward: [(0, '23.620')] +[2023-06-19 14:28:18,549][00753] Fps is (10 sec: 3687.9, 60 sec: 3413.3, 300 sec: 3665.6). Total num frames: 3555328. Throughput: 0: 877.3. Samples: 889738. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:18,559][00753] Avg episode reward: [(0, '24.873')] +[2023-06-19 14:28:19,918][15725] Updated weights for policy 0, policy_version 870 (0.0017) +[2023-06-19 14:28:23,551][00753] Fps is (10 sec: 4095.2, 60 sec: 3481.5, 300 sec: 3679.4). Total num frames: 3575808. Throughput: 0: 879.1. Samples: 893092. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:28:23,553][00753] Avg episode reward: [(0, '24.180')] +[2023-06-19 14:28:28,549][00753] Fps is (10 sec: 3276.9, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3588096. Throughput: 0: 850.4. Samples: 897782. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:28:28,556][00753] Avg episode reward: [(0, '24.184')] +[2023-06-19 14:28:33,462][15725] Updated weights for policy 0, policy_version 880 (0.0012) +[2023-06-19 14:28:33,549][00753] Fps is (10 sec: 2867.7, 60 sec: 3481.6, 300 sec: 3637.8). Total num frames: 3604480. Throughput: 0: 851.5. Samples: 901678. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:28:33,556][00753] Avg episode reward: [(0, '24.410')] +[2023-06-19 14:28:38,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3651.7). Total num frames: 3624960. Throughput: 0: 871.8. Samples: 904640. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:28:38,552][00753] Avg episode reward: [(0, '25.314')] +[2023-06-19 14:28:43,296][15725] Updated weights for policy 0, policy_version 890 (0.0020) +[2023-06-19 14:28:43,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3665.6). Total num frames: 3645440. Throughput: 0: 878.7. Samples: 910964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:43,556][00753] Avg episode reward: [(0, '24.791')] +[2023-06-19 14:28:48,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 3657728. Throughput: 0: 848.1. Samples: 915590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:48,551][00753] Avg episode reward: [(0, '23.805')] +[2023-06-19 14:28:53,549][00753] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3610.0). Total num frames: 3674112. Throughput: 0: 849.8. Samples: 917674. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:28:53,552][00753] Avg episode reward: [(0, '24.707')] +[2023-06-19 14:28:56,371][15725] Updated weights for policy 0, policy_version 900 (0.0060) +[2023-06-19 14:28:58,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3623.9). Total num frames: 3694592. Throughput: 0: 884.7. Samples: 923292. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:28:58,551][00753] Avg episode reward: [(0, '24.907')] +[2023-06-19 14:29:03,549][00753] Fps is (10 sec: 4095.9, 60 sec: 3481.6, 300 sec: 3651.7). Total num frames: 3715072. Throughput: 0: 898.5. Samples: 930170. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:03,553][00753] Avg episode reward: [(0, '23.733')] +[2023-06-19 14:29:06,068][15725] Updated weights for policy 0, policy_version 910 (0.0025) +[2023-06-19 14:29:08,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3550.1, 300 sec: 3623.9). Total num frames: 3731456. Throughput: 0: 876.2. Samples: 932518. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:08,552][00753] Avg episode reward: [(0, '23.744')] +[2023-06-19 14:29:13,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3610.0). Total num frames: 3747840. Throughput: 0: 867.5. Samples: 936818. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:13,556][00753] Avg episode reward: [(0, '25.003')] +[2023-06-19 14:29:18,308][15725] Updated weights for policy 0, policy_version 920 (0.0016) +[2023-06-19 14:29:18,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3549.9, 300 sec: 3624.0). Total num frames: 3768320. Throughput: 0: 912.9. Samples: 942760. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:18,551][00753] Avg episode reward: [(0, '26.885')] +[2023-06-19 14:29:23,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3550.0, 300 sec: 3651.7). Total num frames: 3788800. Throughput: 0: 922.8. Samples: 946164. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:29:23,551][00753] Avg episode reward: [(0, '26.821')] +[2023-06-19 14:29:28,551][00753] Fps is (10 sec: 3685.7, 60 sec: 3618.0, 300 sec: 3623.9). Total num frames: 3805184. Throughput: 0: 905.7. Samples: 951722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:29:28,558][00753] Avg episode reward: [(0, '26.204')] +[2023-06-19 14:29:29,146][15725] Updated weights for policy 0, policy_version 930 (0.0015) +[2023-06-19 14:29:33,549][00753] Fps is (10 sec: 3276.7, 60 sec: 3618.1, 300 sec: 3610.0). Total num frames: 3821568. Throughput: 0: 897.5. Samples: 955980. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) +[2023-06-19 14:29:33,552][00753] Avg episode reward: [(0, '26.791')] +[2023-06-19 14:29:33,567][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000933_3821568.pth... +[2023-06-19 14:29:33,771][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000723_2961408.pth +[2023-06-19 14:29:38,549][00753] Fps is (10 sec: 3687.1, 60 sec: 3618.1, 300 sec: 3623.9). Total num frames: 3842048. Throughput: 0: 913.5. Samples: 958782. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) +[2023-06-19 14:29:38,550][00753] Avg episode reward: [(0, '26.335')] +[2023-06-19 14:29:40,204][15725] Updated weights for policy 0, policy_version 940 (0.0014) +[2023-06-19 14:29:43,549][00753] Fps is (10 sec: 4096.1, 60 sec: 3618.1, 300 sec: 3651.7). Total num frames: 3862528. Throughput: 0: 940.5. Samples: 965614. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:43,560][00753] Avg episode reward: [(0, '24.612')] +[2023-06-19 14:29:48,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3878912. Throughput: 0: 904.0. Samples: 970850. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:29:48,555][00753] Avg episode reward: [(0, '24.456')] +[2023-06-19 14:29:51,972][15725] Updated weights for policy 0, policy_version 950 (0.0013) +[2023-06-19 14:29:53,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3596.1). Total num frames: 3895296. Throughput: 0: 898.0. Samples: 972926. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:29:53,553][00753] Avg episode reward: [(0, '24.337')] +[2023-06-19 14:29:58,549][00753] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3623.9). Total num frames: 3915776. Throughput: 0: 922.4. Samples: 978328. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:29:58,554][00753] Avg episode reward: [(0, '25.835')] +[2023-06-19 14:30:02,029][15725] Updated weights for policy 0, policy_version 960 (0.0026) +[2023-06-19 14:30:03,549][00753] Fps is (10 sec: 4096.0, 60 sec: 3686.4, 300 sec: 3637.8). Total num frames: 3936256. Throughput: 0: 942.3. Samples: 985164. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:30:03,551][00753] Avg episode reward: [(0, '25.912')] +[2023-06-19 14:30:08,554][00753] Fps is (10 sec: 3684.5, 60 sec: 3686.1, 300 sec: 3623.9). Total num frames: 3952640. Throughput: 0: 925.9. Samples: 987834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) +[2023-06-19 14:30:08,556][00753] Avg episode reward: [(0, '27.207')] +[2023-06-19 14:30:13,549][00753] Fps is (10 sec: 3276.8, 60 sec: 3686.4, 300 sec: 3596.2). Total num frames: 3969024. Throughput: 0: 898.0. Samples: 992132. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) +[2023-06-19 14:30:13,557][00753] Avg episode reward: [(0, '27.661')] +[2023-06-19 14:30:13,567][15712] Saving new best policy, reward=27.661! +[2023-06-19 14:30:14,814][15725] Updated weights for policy 0, policy_version 970 (0.0025) +[2023-06-19 14:30:18,549][00753] Fps is (10 sec: 3688.3, 60 sec: 3686.4, 300 sec: 3610.0). Total num frames: 3989504. Throughput: 0: 932.0. Samples: 997918. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) +[2023-06-19 14:30:18,557][00753] Avg episode reward: [(0, '29.371')] +[2023-06-19 14:30:18,560][15712] Saving new best policy, reward=29.371! +[2023-06-19 14:30:22,031][00753] Component Batcher_0 stopped! +[2023-06-19 14:30:22,029][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-06-19 14:30:22,056][15729] Stopping RolloutWorker_w3... +[2023-06-19 14:30:22,030][15712] Stopping Batcher_0... +[2023-06-19 14:30:22,057][00753] Component RolloutWorker_w3 stopped! +[2023-06-19 14:30:22,073][15712] Loop batcher_evt_loop terminating... +[2023-06-19 14:30:22,065][15729] Loop rollout_proc3_evt_loop terminating... +[2023-06-19 14:30:22,076][00753] Component RolloutWorker_w4 stopped! +[2023-06-19 14:30:22,080][00753] Component RolloutWorker_w5 stopped! +[2023-06-19 14:30:22,075][15731] Stopping RolloutWorker_w4... +[2023-06-19 14:30:22,085][15731] Loop rollout_proc4_evt_loop terminating... +[2023-06-19 14:30:22,077][15730] Stopping RolloutWorker_w5... +[2023-06-19 14:30:22,092][00753] Component RolloutWorker_w1 stopped! +[2023-06-19 14:30:22,091][15727] Stopping RolloutWorker_w1... +[2023-06-19 14:30:22,104][00753] Component RolloutWorker_w0 stopped! +[2023-06-19 14:30:22,107][15726] Stopping RolloutWorker_w0... +[2023-06-19 14:30:22,108][15726] Loop rollout_proc0_evt_loop terminating... +[2023-06-19 14:30:22,094][15730] Loop rollout_proc5_evt_loop terminating... +[2023-06-19 14:30:22,113][00753] Component RolloutWorker_w6 stopped! +[2023-06-19 14:30:22,118][15732] Stopping RolloutWorker_w6... +[2023-06-19 14:30:22,103][15727] Loop rollout_proc1_evt_loop terminating... +[2023-06-19 14:30:22,120][00753] Component RolloutWorker_w2 stopped! +[2023-06-19 14:30:22,125][15728] Stopping RolloutWorker_w2... +[2023-06-19 14:30:22,126][15728] Loop rollout_proc2_evt_loop terminating... +[2023-06-19 14:30:22,126][15732] Loop rollout_proc6_evt_loop terminating... +[2023-06-19 14:30:22,147][15733] Stopping RolloutWorker_w7... +[2023-06-19 14:30:22,147][00753] Component RolloutWorker_w7 stopped! +[2023-06-19 14:30:22,150][15733] Loop rollout_proc7_evt_loop terminating... +[2023-06-19 14:30:22,164][15725] Weights refcount: 2 0 +[2023-06-19 14:30:22,169][15725] Stopping InferenceWorker_p0-w0... +[2023-06-19 14:30:22,172][15725] Loop inference_proc0-0_evt_loop terminating... +[2023-06-19 14:30:22,169][00753] Component InferenceWorker_p0-w0 stopped! +[2023-06-19 14:30:22,230][15712] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000829_3395584.pth +[2023-06-19 14:30:22,245][15712] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-06-19 14:30:22,371][15712] Stopping LearnerWorker_p0... +[2023-06-19 14:30:22,372][15712] Loop learner_proc0_evt_loop terminating... +[2023-06-19 14:30:22,370][00753] Component LearnerWorker_p0 stopped! +[2023-06-19 14:30:22,378][00753] Waiting for process learner_proc0 to stop... +[2023-06-19 14:30:24,169][00753] Waiting for process inference_proc0-0 to join... +[2023-06-19 14:30:24,176][00753] Waiting for process rollout_proc0 to join... +[2023-06-19 14:30:25,777][00753] Waiting for process rollout_proc1 to join... +[2023-06-19 14:30:26,139][00753] Waiting for process rollout_proc2 to join... +[2023-06-19 14:30:26,145][00753] Waiting for process rollout_proc3 to join... +[2023-06-19 14:30:26,146][00753] Waiting for process rollout_proc4 to join... +[2023-06-19 14:30:26,148][00753] Waiting for process rollout_proc5 to join... +[2023-06-19 14:30:26,149][00753] Waiting for process rollout_proc6 to join... +[2023-06-19 14:30:26,151][00753] Waiting for process rollout_proc7 to join... +[2023-06-19 14:30:26,153][00753] Batcher 0 profile tree view: +batching: 28.3181, releasing_batches: 0.0196 +[2023-06-19 14:30:26,156][00753] InferenceWorker_p0-w0 profile tree view: +wait_policy: 0.0001 + wait_policy_total: 481.4413 +update_model: 8.0245 + weight_update: 0.0025 +one_step: 0.0180 + handle_policy_step: 573.0894 + deserialize: 15.2663, stack: 3.0542, obs_to_device_normalize: 112.6684, forward: 311.2599, send_messages: 28.2131 + prepare_outputs: 76.1728 + to_cpu: 43.4564 +[2023-06-19 14:30:26,161][00753] Learner 0 profile tree view: +misc: 0.0051, prepare_batch: 19.5693 +train: 74.6204 + epoch_init: 0.0189, minibatch_init: 0.0090, losses_postprocess: 0.6263, kl_divergence: 0.6649, after_optimizer: 3.7719 + calculate_losses: 25.3343 + losses_init: 0.0046, forward_head: 1.2514, bptt_initial: 16.9429, tail: 1.0722, advantages_returns: 0.2578, losses: 3.4928 + bptt: 1.9604 + bptt_forward_core: 1.8777 + update: 43.5924 + clip: 32.7360 +[2023-06-19 14:30:26,162][00753] RolloutWorker_w0 profile tree view: +wait_for_trajectories: 0.3329, enqueue_policy_requests: 130.0667, env_step: 837.8421, overhead: 21.4076, complete_rollouts: 6.9483 +save_policy_outputs: 19.2290 + split_output_tensors: 9.0097 +[2023-06-19 14:30:26,164][00753] RolloutWorker_w7 profile tree view: +wait_for_trajectories: 0.2819, enqueue_policy_requests: 131.4119, env_step: 834.9022, overhead: 21.4959, complete_rollouts: 6.7752 +save_policy_outputs: 19.4500 + split_output_tensors: 9.4796 +[2023-06-19 14:30:26,165][00753] Loop Runner_EvtLoop terminating... +[2023-06-19 14:30:26,167][00753] Runner profile tree view: +main_loop: 1130.5358 +[2023-06-19 14:30:26,168][00753] Collected {0: 4005888}, FPS: 3543.4 +[2023-06-19 14:30:38,058][00753] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-06-19 14:30:38,060][00753] Overriding arg 'num_workers' with value 1 passed from command line +[2023-06-19 14:30:38,062][00753] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-06-19 14:30:38,063][00753] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-06-19 14:30:38,066][00753] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-06-19 14:30:38,071][00753] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-06-19 14:30:38,074][00753] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! +[2023-06-19 14:30:38,076][00753] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-06-19 14:30:38,078][00753] Adding new argument 'push_to_hub'=False that is not in the saved config file! +[2023-06-19 14:30:38,080][00753] Adding new argument 'hf_repository'=None that is not in the saved config file! +[2023-06-19 14:30:38,084][00753] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-06-19 14:30:38,088][00753] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-06-19 14:30:38,089][00753] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-06-19 14:30:38,091][00753] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-06-19 14:30:38,094][00753] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-06-19 14:30:38,109][00753] Doom resolution: 160x120, resize resolution: (128, 72) +[2023-06-19 14:30:38,111][00753] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:30:38,114][00753] RunningMeanStd input shape: (1,) +[2023-06-19 14:30:38,129][00753] ConvEncoder: input_channels=3 +[2023-06-19 14:30:38,255][00753] Conv encoder output size: 512 +[2023-06-19 14:30:38,257][00753] Policy head output size: 512 +[2023-06-19 14:30:41,544][00753] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-06-19 14:30:43,145][00753] Num frames 100... +[2023-06-19 14:30:43,365][00753] Num frames 200... +[2023-06-19 14:30:43,617][00753] Num frames 300... +[2023-06-19 14:30:43,826][00753] Num frames 400... +[2023-06-19 14:30:44,044][00753] Num frames 500... +[2023-06-19 14:30:44,352][00753] Num frames 600... +[2023-06-19 14:30:44,695][00753] Num frames 700... +[2023-06-19 14:30:44,966][00753] Num frames 800... +[2023-06-19 14:30:45,217][00753] Num frames 900... +[2023-06-19 14:30:45,479][00753] Num frames 1000... +[2023-06-19 14:30:45,616][00753] Num frames 1100... +[2023-06-19 14:30:45,737][00753] Num frames 1200... +[2023-06-19 14:30:45,862][00753] Num frames 1300... +[2023-06-19 14:30:45,989][00753] Num frames 1400... +[2023-06-19 14:30:46,114][00753] Num frames 1500... +[2023-06-19 14:30:46,236][00753] Num frames 1600... +[2023-06-19 14:30:46,357][00753] Num frames 1700... +[2023-06-19 14:30:46,481][00753] Num frames 1800... +[2023-06-19 14:30:46,610][00753] Num frames 1900... +[2023-06-19 14:30:46,731][00753] Num frames 2000... +[2023-06-19 14:30:46,853][00753] Num frames 2100... +[2023-06-19 14:30:46,905][00753] Avg episode rewards: #0: 50.999, true rewards: #0: 21.000 +[2023-06-19 14:30:46,908][00753] Avg episode reward: 50.999, avg true_objective: 21.000 +[2023-06-19 14:30:47,025][00753] Num frames 2200... +[2023-06-19 14:30:47,149][00753] Num frames 2300... +[2023-06-19 14:30:47,271][00753] Num frames 2400... +[2023-06-19 14:30:47,395][00753] Num frames 2500... +[2023-06-19 14:30:47,517][00753] Num frames 2600... +[2023-06-19 14:30:47,646][00753] Num frames 2700... +[2023-06-19 14:30:47,772][00753] Num frames 2800... +[2023-06-19 14:30:47,897][00753] Num frames 2900... +[2023-06-19 14:30:48,025][00753] Num frames 3000... +[2023-06-19 14:30:48,149][00753] Num frames 3100... +[2023-06-19 14:30:48,274][00753] Num frames 3200... +[2023-06-19 14:30:48,395][00753] Num frames 3300... +[2023-06-19 14:30:48,517][00753] Num frames 3400... +[2023-06-19 14:30:48,654][00753] Num frames 3500... +[2023-06-19 14:30:48,778][00753] Num frames 3600... +[2023-06-19 14:30:48,904][00753] Num frames 3700... +[2023-06-19 14:30:49,035][00753] Num frames 3800... +[2023-06-19 14:30:49,172][00753] Num frames 3900... +[2023-06-19 14:30:49,308][00753] Num frames 4000... +[2023-06-19 14:30:49,437][00753] Num frames 4100... +[2023-06-19 14:30:49,574][00753] Num frames 4200... +[2023-06-19 14:30:49,626][00753] Avg episode rewards: #0: 55.999, true rewards: #0: 21.000 +[2023-06-19 14:30:49,628][00753] Avg episode reward: 55.999, avg true_objective: 21.000 +[2023-06-19 14:30:49,762][00753] Num frames 4300... +[2023-06-19 14:30:49,891][00753] Num frames 4400... +[2023-06-19 14:30:50,027][00753] Num frames 4500... +[2023-06-19 14:30:50,150][00753] Num frames 4600... +[2023-06-19 14:30:50,280][00753] Num frames 4700... +[2023-06-19 14:30:50,352][00753] Avg episode rewards: #0: 40.039, true rewards: #0: 15.707 +[2023-06-19 14:30:50,354][00753] Avg episode reward: 40.039, avg true_objective: 15.707 +[2023-06-19 14:30:50,466][00753] Num frames 4800... +[2023-06-19 14:30:50,605][00753] Num frames 4900... +[2023-06-19 14:30:50,735][00753] Num frames 5000... +[2023-06-19 14:30:50,863][00753] Num frames 5100... +[2023-06-19 14:30:50,995][00753] Num frames 5200... +[2023-06-19 14:30:51,126][00753] Num frames 5300... +[2023-06-19 14:30:51,252][00753] Num frames 5400... +[2023-06-19 14:30:51,374][00753] Avg episode rewards: #0: 33.369, true rewards: #0: 13.620 +[2023-06-19 14:30:51,381][00753] Avg episode reward: 33.369, avg true_objective: 13.620 +[2023-06-19 14:30:51,452][00753] Num frames 5500... +[2023-06-19 14:30:51,578][00753] Num frames 5600... +[2023-06-19 14:30:51,712][00753] Num frames 5700... +[2023-06-19 14:30:51,845][00753] Num frames 5800... +[2023-06-19 14:30:51,977][00753] Num frames 5900... +[2023-06-19 14:30:52,101][00753] Num frames 6000... +[2023-06-19 14:30:52,239][00753] Num frames 6100... +[2023-06-19 14:30:52,420][00753] Num frames 6200... +[2023-06-19 14:30:52,612][00753] Num frames 6300... +[2023-06-19 14:30:52,802][00753] Num frames 6400... +[2023-06-19 14:30:52,989][00753] Num frames 6500... +[2023-06-19 14:30:53,174][00753] Num frames 6600... +[2023-06-19 14:30:53,354][00753] Num frames 6700... +[2023-06-19 14:30:53,536][00753] Num frames 6800... +[2023-06-19 14:30:53,717][00753] Num frames 6900... +[2023-06-19 14:30:53,902][00753] Num frames 7000... +[2023-06-19 14:30:54,079][00753] Num frames 7100... +[2023-06-19 14:30:54,313][00753] Avg episode rewards: #0: 35.797, true rewards: #0: 14.398 +[2023-06-19 14:30:54,315][00753] Avg episode reward: 35.797, avg true_objective: 14.398 +[2023-06-19 14:30:54,319][00753] Num frames 7200... +[2023-06-19 14:30:54,491][00753] Num frames 7300... +[2023-06-19 14:30:54,669][00753] Num frames 7400... +[2023-06-19 14:30:54,849][00753] Num frames 7500... +[2023-06-19 14:30:55,027][00753] Num frames 7600... +[2023-06-19 14:30:55,203][00753] Num frames 7700... +[2023-06-19 14:30:55,381][00753] Num frames 7800... +[2023-06-19 14:30:55,556][00753] Num frames 7900... +[2023-06-19 14:30:55,737][00753] Num frames 8000... +[2023-06-19 14:30:55,923][00753] Num frames 8100... +[2023-06-19 14:30:56,110][00753] Num frames 8200... +[2023-06-19 14:30:56,259][00753] Num frames 8300... +[2023-06-19 14:30:56,380][00753] Num frames 8400... +[2023-06-19 14:30:56,503][00753] Num frames 8500... +[2023-06-19 14:30:56,628][00753] Num frames 8600... +[2023-06-19 14:30:56,791][00753] Avg episode rewards: #0: 35.645, true rewards: #0: 14.478 +[2023-06-19 14:30:56,793][00753] Avg episode reward: 35.645, avg true_objective: 14.478 +[2023-06-19 14:30:56,814][00753] Num frames 8700... +[2023-06-19 14:30:56,940][00753] Num frames 8800... +[2023-06-19 14:30:57,064][00753] Num frames 8900... +[2023-06-19 14:30:57,190][00753] Num frames 9000... +[2023-06-19 14:30:57,310][00753] Num frames 9100... +[2023-06-19 14:30:57,428][00753] Num frames 9200... +[2023-06-19 14:30:57,559][00753] Num frames 9300... +[2023-06-19 14:30:57,682][00753] Num frames 9400... +[2023-06-19 14:30:57,813][00753] Num frames 9500... +[2023-06-19 14:30:57,942][00753] Num frames 9600... +[2023-06-19 14:30:58,022][00753] Avg episode rewards: #0: 33.885, true rewards: #0: 13.743 +[2023-06-19 14:30:58,024][00753] Avg episode reward: 33.885, avg true_objective: 13.743 +[2023-06-19 14:30:58,123][00753] Num frames 9700... +[2023-06-19 14:30:58,249][00753] Num frames 9800... +[2023-06-19 14:30:58,370][00753] Num frames 9900... +[2023-06-19 14:30:58,494][00753] Num frames 10000... +[2023-06-19 14:30:58,615][00753] Num frames 10100... +[2023-06-19 14:30:58,785][00753] Avg episode rewards: #0: 30.997, true rewards: #0: 12.748 +[2023-06-19 14:30:58,786][00753] Avg episode reward: 30.997, avg true_objective: 12.748 +[2023-06-19 14:30:58,793][00753] Num frames 10200... +[2023-06-19 14:30:58,931][00753] Num frames 10300... +[2023-06-19 14:30:59,066][00753] Num frames 10400... +[2023-06-19 14:30:59,196][00753] Num frames 10500... +[2023-06-19 14:30:59,315][00753] Num frames 10600... +[2023-06-19 14:30:59,444][00753] Num frames 10700... +[2023-06-19 14:30:59,565][00753] Num frames 10800... +[2023-06-19 14:30:59,690][00753] Num frames 10900... +[2023-06-19 14:30:59,814][00753] Num frames 11000... +[2023-06-19 14:30:59,945][00753] Num frames 11100... +[2023-06-19 14:31:00,068][00753] Num frames 11200... +[2023-06-19 14:31:00,193][00753] Num frames 11300... +[2023-06-19 14:31:00,321][00753] Num frames 11400... +[2023-06-19 14:31:00,441][00753] Num frames 11500... +[2023-06-19 14:31:00,563][00753] Num frames 11600... +[2023-06-19 14:31:00,691][00753] Num frames 11700... +[2023-06-19 14:31:00,817][00753] Num frames 11800... +[2023-06-19 14:31:00,953][00753] Num frames 11900... +[2023-06-19 14:31:01,031][00753] Avg episode rewards: #0: 32.462, true rewards: #0: 13.240 +[2023-06-19 14:31:01,032][00753] Avg episode reward: 32.462, avg true_objective: 13.240 +[2023-06-19 14:31:01,134][00753] Num frames 12000... +[2023-06-19 14:31:01,258][00753] Num frames 12100... +[2023-06-19 14:31:01,378][00753] Num frames 12200... +[2023-06-19 14:31:01,521][00753] Num frames 12300... +[2023-06-19 14:31:01,649][00753] Num frames 12400... +[2023-06-19 14:31:01,787][00753] Num frames 12500... +[2023-06-19 14:31:01,918][00753] Num frames 12600... +[2023-06-19 14:31:01,998][00753] Avg episode rewards: #0: 30.620, true rewards: #0: 12.620 +[2023-06-19 14:31:02,000][00753] Avg episode reward: 30.620, avg true_objective: 12.620 +[2023-06-19 14:32:18,953][00753] Replay video saved to /content/train_dir/default_experiment/replay.mp4! +[2023-06-19 14:33:47,781][00753] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json +[2023-06-19 14:33:47,783][00753] Overriding arg 'num_workers' with value 1 passed from command line +[2023-06-19 14:33:47,785][00753] Adding new argument 'no_render'=True that is not in the saved config file! +[2023-06-19 14:33:47,786][00753] Adding new argument 'save_video'=True that is not in the saved config file! +[2023-06-19 14:33:47,788][00753] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! +[2023-06-19 14:33:47,790][00753] Adding new argument 'video_name'=None that is not in the saved config file! +[2023-06-19 14:33:47,794][00753] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! +[2023-06-19 14:33:47,796][00753] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! +[2023-06-19 14:33:47,798][00753] Adding new argument 'push_to_hub'=True that is not in the saved config file! +[2023-06-19 14:33:47,799][00753] Adding new argument 'hf_repository'='Ditrip/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! +[2023-06-19 14:33:47,800][00753] Adding new argument 'policy_index'=0 that is not in the saved config file! +[2023-06-19 14:33:47,801][00753] Adding new argument 'eval_deterministic'=False that is not in the saved config file! +[2023-06-19 14:33:47,802][00753] Adding new argument 'train_script'=None that is not in the saved config file! +[2023-06-19 14:33:47,804][00753] Adding new argument 'enjoy_script'=None that is not in the saved config file! +[2023-06-19 14:33:47,806][00753] Using frameskip 1 and render_action_repeat=4 for evaluation +[2023-06-19 14:33:47,833][00753] RunningMeanStd input shape: (3, 72, 128) +[2023-06-19 14:33:47,839][00753] RunningMeanStd input shape: (1,) +[2023-06-19 14:33:47,856][00753] ConvEncoder: input_channels=3 +[2023-06-19 14:33:47,911][00753] Conv encoder output size: 512 +[2023-06-19 14:33:47,913][00753] Policy head output size: 512 +[2023-06-19 14:33:47,941][00753] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... +[2023-06-19 14:33:48,658][00753] Num frames 100... +[2023-06-19 14:33:48,835][00753] Num frames 200... +[2023-06-19 14:33:49,014][00753] Num frames 300... +[2023-06-19 14:33:49,203][00753] Num frames 400... +[2023-06-19 14:33:49,388][00753] Num frames 500... +[2023-06-19 14:33:49,573][00753] Num frames 600... +[2023-06-19 14:33:49,761][00753] Num frames 700... +[2023-06-19 14:33:49,949][00753] Num frames 800... +[2023-06-19 14:33:50,002][00753] Avg episode rewards: #0: 17.000, true rewards: #0: 8.000 +[2023-06-19 14:33:50,004][00753] Avg episode reward: 17.000, avg true_objective: 8.000 +[2023-06-19 14:33:50,193][00753] Num frames 900... +[2023-06-19 14:33:50,379][00753] Num frames 1000... +[2023-06-19 14:33:50,565][00753] Num frames 1100... +[2023-06-19 14:33:50,740][00753] Num frames 1200... +[2023-06-19 14:33:50,869][00753] Num frames 1300... +[2023-06-19 14:33:50,996][00753] Num frames 1400... +[2023-06-19 14:33:51,122][00753] Num frames 1500... +[2023-06-19 14:33:51,254][00753] Num frames 1600... +[2023-06-19 14:33:51,380][00753] Num frames 1700... +[2023-06-19 14:33:51,512][00753] Num frames 1800... +[2023-06-19 14:33:51,645][00753] Num frames 1900... +[2023-06-19 14:33:51,774][00753] Num frames 2000... +[2023-06-19 14:33:51,907][00753] Num frames 2100... +[2023-06-19 14:33:52,031][00753] Num frames 2200... +[2023-06-19 14:33:52,155][00753] Num frames 2300... +[2023-06-19 14:33:52,291][00753] Num frames 2400... +[2023-06-19 14:33:52,418][00753] Num frames 2500... +[2023-06-19 14:33:52,564][00753] Num frames 2600... +[2023-06-19 14:33:52,693][00753] Num frames 2700... +[2023-06-19 14:33:52,816][00753] Num frames 2800... +[2023-06-19 14:33:52,951][00753] Num frames 2900... +[2023-06-19 14:33:53,003][00753] Avg episode rewards: #0: 37.500, true rewards: #0: 14.500 +[2023-06-19 14:33:53,004][00753] Avg episode reward: 37.500, avg true_objective: 14.500 +[2023-06-19 14:33:53,134][00753] Num frames 3000... +[2023-06-19 14:33:53,264][00753] Num frames 3100... +[2023-06-19 14:33:53,394][00753] Num frames 3200... +[2023-06-19 14:33:53,520][00753] Num frames 3300... +[2023-06-19 14:33:53,640][00753] Num frames 3400... +[2023-06-19 14:33:53,777][00753] Num frames 3500... +[2023-06-19 14:33:53,902][00753] Num frames 3600... +[2023-06-19 14:33:54,040][00753] Num frames 3700... +[2023-06-19 14:33:54,166][00753] Num frames 3800... +[2023-06-19 14:33:54,295][00753] Num frames 3900... +[2023-06-19 14:33:54,423][00753] Num frames 4000... +[2023-06-19 14:33:54,554][00753] Num frames 4100... +[2023-06-19 14:33:54,677][00753] Num frames 4200... +[2023-06-19 14:33:54,813][00753] Num frames 4300... +[2023-06-19 14:33:54,937][00753] Num frames 4400... +[2023-06-19 14:33:55,059][00753] Num frames 4500... +[2023-06-19 14:33:55,192][00753] Num frames 4600... +[2023-06-19 14:33:55,316][00753] Num frames 4700... +[2023-06-19 14:33:55,449][00753] Avg episode rewards: #0: 40.519, true rewards: #0: 15.853 +[2023-06-19 14:33:55,451][00753] Avg episode reward: 40.519, avg true_objective: 15.853 +[2023-06-19 14:33:55,520][00753] Num frames 4800... +[2023-06-19 14:33:55,645][00753] Num frames 4900... +[2023-06-19 14:33:55,777][00753] Num frames 5000... +[2023-06-19 14:33:55,905][00753] Num frames 5100... +[2023-06-19 14:33:56,043][00753] Num frames 5200... +[2023-06-19 14:33:56,173][00753] Num frames 5300... +[2023-06-19 14:33:56,300][00753] Num frames 5400... +[2023-06-19 14:33:56,431][00753] Num frames 5500... +[2023-06-19 14:33:56,565][00753] Num frames 5600... +[2023-06-19 14:33:56,695][00753] Num frames 5700... +[2023-06-19 14:33:56,819][00753] Num frames 5800... +[2023-06-19 14:33:56,956][00753] Num frames 5900... +[2023-06-19 14:33:57,081][00753] Num frames 6000... +[2023-06-19 14:33:57,219][00753] Num frames 6100... +[2023-06-19 14:33:57,344][00753] Num frames 6200... +[2023-06-19 14:33:57,474][00753] Num frames 6300... +[2023-06-19 14:33:57,605][00753] Num frames 6400... +[2023-06-19 14:33:57,732][00753] Num frames 6500... +[2023-06-19 14:33:57,856][00753] Avg episode rewards: #0: 41.597, true rewards: #0: 16.348 +[2023-06-19 14:33:57,858][00753] Avg episode reward: 41.597, avg true_objective: 16.348 +[2023-06-19 14:33:57,938][00753] Num frames 6600... +[2023-06-19 14:33:58,059][00753] Num frames 6700... +[2023-06-19 14:33:58,194][00753] Num frames 6800... +[2023-06-19 14:33:58,320][00753] Num frames 6900... +[2023-06-19 14:33:58,445][00753] Avg episode rewards: #0: 34.308, true rewards: #0: 13.908 +[2023-06-19 14:33:58,448][00753] Avg episode reward: 34.308, avg true_objective: 13.908 +[2023-06-19 14:33:58,511][00753] Num frames 7000... +[2023-06-19 14:33:58,647][00753] Num frames 7100... +[2023-06-19 14:33:58,771][00753] Num frames 7200... +[2023-06-19 14:33:58,895][00753] Num frames 7300... +[2023-06-19 14:33:59,023][00753] Num frames 7400... +[2023-06-19 14:33:59,157][00753] Num frames 7500... +[2023-06-19 14:33:59,281][00753] Num frames 7600... +[2023-06-19 14:33:59,446][00753] Avg episode rewards: #0: 30.983, true rewards: #0: 12.817 +[2023-06-19 14:33:59,448][00753] Avg episode reward: 30.983, avg true_objective: 12.817 +[2023-06-19 14:33:59,463][00753] Num frames 7700... +[2023-06-19 14:33:59,601][00753] Num frames 7800... +[2023-06-19 14:33:59,724][00753] Num frames 7900... +[2023-06-19 14:33:59,855][00753] Num frames 8000... +[2023-06-19 14:33:59,983][00753] Num frames 8100... +[2023-06-19 14:34:00,115][00753] Num frames 8200... +[2023-06-19 14:34:00,245][00753] Num frames 8300... +[2023-06-19 14:34:00,378][00753] Num frames 8400... +[2023-06-19 14:34:00,466][00753] Avg episode rewards: #0: 29.323, true rewards: #0: 12.037 +[2023-06-19 14:34:00,468][00753] Avg episode reward: 29.323, avg true_objective: 12.037 +[2023-06-19 14:34:00,563][00753] Num frames 8500... +[2023-06-19 14:34:00,694][00753] Num frames 8600... +[2023-06-19 14:34:00,867][00753] Num frames 8700... +[2023-06-19 14:34:01,050][00753] Num frames 8800... +[2023-06-19 14:34:01,236][00753] Num frames 8900... +[2023-06-19 14:34:01,420][00753] Num frames 9000... +[2023-06-19 14:34:01,607][00753] Num frames 9100... +[2023-06-19 14:34:01,812][00753] Num frames 9200... +[2023-06-19 14:34:02,016][00753] Num frames 9300... +[2023-06-19 14:34:02,202][00753] Num frames 9400... +[2023-06-19 14:34:02,381][00753] Num frames 9500... +[2023-06-19 14:34:02,560][00753] Num frames 9600... +[2023-06-19 14:34:02,743][00753] Num frames 9700... +[2023-06-19 14:34:02,930][00753] Num frames 9800... +[2023-06-19 14:34:03,053][00753] Avg episode rewards: #0: 29.792, true rewards: #0: 12.292 +[2023-06-19 14:34:03,055][00753] Avg episode reward: 29.792, avg true_objective: 12.292 +[2023-06-19 14:34:03,177][00753] Num frames 9900... +[2023-06-19 14:34:03,363][00753] Num frames 10000... +[2023-06-19 14:34:03,547][00753] Num frames 10100... +[2023-06-19 14:34:03,737][00753] Num frames 10200... +[2023-06-19 14:34:03,930][00753] Num frames 10300... +[2023-06-19 14:34:04,129][00753] Avg episode rewards: #0: 27.419, true rewards: #0: 11.530 +[2023-06-19 14:34:04,132][00753] Avg episode reward: 27.419, avg true_objective: 11.530 +[2023-06-19 14:34:04,179][00753] Num frames 10400... +[2023-06-19 14:34:04,359][00753] Num frames 10500... +[2023-06-19 14:34:04,535][00753] Num frames 10600... +[2023-06-19 14:34:04,716][00753] Num frames 10700... +[2023-06-19 14:34:04,916][00753] Avg episode rewards: #0: 25.293, true rewards: #0: 10.793 +[2023-06-19 14:34:04,918][00753] Avg episode reward: 25.293, avg true_objective: 10.793 +[2023-06-19 14:35:11,109][00753] Replay video saved to /content/train_dir/default_experiment/replay.mp4!