[2023-02-26 15:53:47,916][09579] Saving configuration to /content/train_dir/default_experiment/config.json... [2023-02-26 15:53:47,920][09579] Rollout worker 0 uses device cpu [2023-02-26 15:53:47,922][09579] Rollout worker 1 uses device cpu [2023-02-26 15:53:47,923][09579] Rollout worker 2 uses device cpu [2023-02-26 15:53:47,927][09579] Rollout worker 3 uses device cpu [2023-02-26 15:53:47,928][09579] Rollout worker 4 uses device cpu [2023-02-26 15:53:47,931][09579] Rollout worker 5 uses device cpu [2023-02-26 15:53:47,934][09579] Rollout worker 6 uses device cpu [2023-02-26 15:53:47,936][09579] Rollout worker 7 uses device cpu [2023-02-26 15:53:48,195][09579] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-26 15:53:48,218][09579] InferenceWorker_p0-w0: min num requests: 2 [2023-02-26 15:53:48,308][09579] Starting all processes... [2023-02-26 15:53:48,310][09579] Starting process learner_proc0 [2023-02-26 15:53:48,460][09579] Starting all processes... [2023-02-26 15:53:48,522][09579] Starting process inference_proc0-0 [2023-02-26 15:53:48,523][09579] Starting process rollout_proc0 [2023-02-26 15:53:48,527][09579] Starting process rollout_proc1 [2023-02-26 15:53:48,532][09579] Starting process rollout_proc2 [2023-02-26 15:53:48,532][09579] Starting process rollout_proc3 [2023-02-26 15:53:48,532][09579] Starting process rollout_proc4 [2023-02-26 15:53:48,532][09579] Starting process rollout_proc5 [2023-02-26 15:53:48,532][09579] Starting process rollout_proc6 [2023-02-26 15:53:48,533][09579] Starting process rollout_proc7 [2023-02-26 15:54:01,750][15346] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-26 15:54:01,756][15346] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 [2023-02-26 15:54:01,807][15332] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-26 15:54:01,808][15332] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 [2023-02-26 15:54:02,077][15352] Worker 1 uses CPU cores [1] [2023-02-26 15:54:02,132][15353] Worker 2 uses CPU cores [0] [2023-02-26 15:54:02,348][15356] Worker 5 uses CPU cores [1] [2023-02-26 15:54:02,358][15347] Worker 0 uses CPU cores [0] [2023-02-26 15:54:02,455][15355] Worker 4 uses CPU cores [0] [2023-02-26 15:54:02,464][15358] Worker 7 uses CPU cores [1] [2023-02-26 15:54:02,479][15354] Worker 3 uses CPU cores [1] [2023-02-26 15:54:02,551][15357] Worker 6 uses CPU cores [0] [2023-02-26 15:54:03,003][15332] Num visible devices: 1 [2023-02-26 15:54:03,008][15346] Num visible devices: 1 [2023-02-26 15:54:03,009][15332] Starting seed is not provided [2023-02-26 15:54:03,010][15332] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-26 15:54:03,011][15332] Initializing actor-critic model on device cuda:0 [2023-02-26 15:54:03,011][15332] RunningMeanStd input shape: (3, 72, 128) [2023-02-26 15:54:03,014][15332] RunningMeanStd input shape: (1,) [2023-02-26 15:54:03,034][15332] ConvEncoder: input_channels=3 [2023-02-26 15:54:03,434][15332] Conv encoder output size: 512 [2023-02-26 15:54:03,435][15332] Policy head output size: 512 [2023-02-26 15:54:03,516][15332] Created Actor Critic model with architecture: [2023-02-26 15:54:03,518][15332] ActorCriticSharedWeights( (obs_normalizer): ObservationNormalizer( (running_mean_std): RunningMeanStdDictInPlace( (running_mean_std): ModuleDict( (obs): RunningMeanStdInPlace() ) ) ) (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace) (encoder): VizdoomEncoder( (basic_encoder): ConvEncoder( (enc): RecursiveScriptModule( original_name=ConvEncoderImpl (conv_head): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Conv2d) (1): RecursiveScriptModule(original_name=ELU) (2): RecursiveScriptModule(original_name=Conv2d) (3): RecursiveScriptModule(original_name=ELU) (4): RecursiveScriptModule(original_name=Conv2d) (5): RecursiveScriptModule(original_name=ELU) ) (mlp_layers): RecursiveScriptModule( original_name=Sequential (0): RecursiveScriptModule(original_name=Linear) (1): RecursiveScriptModule(original_name=ELU) ) ) ) ) (core): ModelCoreRNN( (core): GRU(512, 512) ) (decoder): MlpDecoder( (mlp): Identity() ) (critic_linear): Linear(in_features=512, out_features=1, bias=True) (action_parameterization): ActionParameterizationDefault( (distribution_linear): Linear(in_features=512, out_features=5, bias=True) ) ) [2023-02-26 15:54:08,166][09579] Heartbeat connected on Batcher_0 [2023-02-26 15:54:08,196][09579] Heartbeat connected on InferenceWorker_p0-w0 [2023-02-26 15:54:08,244][09579] Heartbeat connected on RolloutWorker_w0 [2023-02-26 15:54:08,249][09579] Heartbeat connected on RolloutWorker_w1 [2023-02-26 15:54:08,254][09579] Heartbeat connected on RolloutWorker_w2 [2023-02-26 15:54:08,259][09579] Heartbeat connected on RolloutWorker_w3 [2023-02-26 15:54:08,265][09579] Heartbeat connected on RolloutWorker_w4 [2023-02-26 15:54:08,270][09579] Heartbeat connected on RolloutWorker_w5 [2023-02-26 15:54:08,294][09579] Heartbeat connected on RolloutWorker_w6 [2023-02-26 15:54:08,300][09579] Heartbeat connected on RolloutWorker_w7 [2023-02-26 15:54:12,162][15332] Using optimizer [2023-02-26 15:54:12,163][15332] No checkpoints found [2023-02-26 15:54:12,163][15332] Did not load from checkpoint, starting from scratch! [2023-02-26 15:54:12,164][15332] Initialized policy 0 weights for model version 0 [2023-02-26 15:54:12,167][15332] LearnerWorker_p0 finished initialization! [2023-02-26 15:54:12,168][09579] Heartbeat connected on LearnerWorker_p0 [2023-02-26 15:54:12,175][15332] Using GPUs [0] for process 0 (actually maps to GPUs [0]) [2023-02-26 15:54:12,297][15346] RunningMeanStd input shape: (3, 72, 128) [2023-02-26 15:54:12,299][15346] RunningMeanStd input shape: (1,) [2023-02-26 15:54:12,314][15346] ConvEncoder: input_channels=3 [2023-02-26 15:54:12,420][15346] Conv encoder output size: 512 [2023-02-26 15:54:12,421][15346] Policy head output size: 512 [2023-02-26 15:54:13,145][09579] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-26 15:54:14,787][09579] Inference worker 0-0 is ready! [2023-02-26 15:54:14,789][09579] All inference workers are ready! Signal rollout workers to start! [2023-02-26 15:54:14,923][15352] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,919][15358] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,928][15354] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,940][15356] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,962][15357] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,971][15347] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,973][15353] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:14,984][15355] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 15:54:15,136][15354] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... [2023-02-26 15:54:15,139][15354] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init self.game.init() vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/signal_slot/signal_slot.py", line 355, in _process_signal slot_callable(*args) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init env_runner.init(self.timing) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init self._reset() File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0 File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 125, in reset obs, info = self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sample_factory/algo/utils/make_env.py", line 110, in reset obs, info = self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset return self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 379, in reset obs, info = self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sample_factory/envs/env_wrappers.py", line 84, in reset obs, info = self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/gym/core.py", line 323, in reset return self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset return self.env.reset(**kwargs) File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset self._ensure_initialized() File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized self.initialize() File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize self._game_init() File "/usr/local/lib/python3.8/dist-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init raise EnvCriticalError() sample_factory.envs.env_utils.EnvCriticalError [2023-02-26 15:54:15,142][15354] Unhandled exception in evt loop rollout_proc3_evt_loop [2023-02-26 15:54:15,906][15355] Decorrelating experience for 0 frames... [2023-02-26 15:54:15,908][15353] Decorrelating experience for 0 frames... [2023-02-26 15:54:16,165][15358] Decorrelating experience for 0 frames... [2023-02-26 15:54:16,295][15352] Decorrelating experience for 0 frames... [2023-02-26 15:54:16,389][15353] Decorrelating experience for 32 frames... [2023-02-26 15:54:16,972][15358] Decorrelating experience for 32 frames... [2023-02-26 15:54:17,071][15357] Decorrelating experience for 0 frames... [2023-02-26 15:54:17,081][15352] Decorrelating experience for 32 frames... [2023-02-26 15:54:17,218][15347] Decorrelating experience for 0 frames... [2023-02-26 15:54:17,528][15352] Decorrelating experience for 64 frames... [2023-02-26 15:54:18,144][09579] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-26 15:54:18,161][15357] Decorrelating experience for 32 frames... [2023-02-26 15:54:18,225][15353] Decorrelating experience for 64 frames... [2023-02-26 15:54:18,330][15347] Decorrelating experience for 32 frames... [2023-02-26 15:54:18,335][15355] Decorrelating experience for 32 frames... [2023-02-26 15:54:19,242][15352] Decorrelating experience for 96 frames... [2023-02-26 15:54:19,340][15356] Decorrelating experience for 0 frames... [2023-02-26 15:54:20,235][15358] Decorrelating experience for 64 frames... [2023-02-26 15:54:20,238][15356] Decorrelating experience for 32 frames... [2023-02-26 15:54:20,937][15353] Decorrelating experience for 96 frames... [2023-02-26 15:54:21,009][15357] Decorrelating experience for 64 frames... [2023-02-26 15:54:21,555][15355] Decorrelating experience for 64 frames... [2023-02-26 15:54:21,565][15347] Decorrelating experience for 64 frames... [2023-02-26 15:54:21,847][15356] Decorrelating experience for 64 frames... [2023-02-26 15:54:22,363][15358] Decorrelating experience for 96 frames... [2023-02-26 15:54:22,634][15356] Decorrelating experience for 96 frames... [2023-02-26 15:54:23,144][09579] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-26 15:54:23,888][15357] Decorrelating experience for 96 frames... [2023-02-26 15:54:24,134][15347] Decorrelating experience for 96 frames... [2023-02-26 15:54:24,321][15355] Decorrelating experience for 96 frames... [2023-02-26 15:54:28,144][09579] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 75.2. Samples: 1128. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) [2023-02-26 15:54:28,151][09579] Avg episode reward: [(0, '1.749')] [2023-02-26 15:54:29,502][15332] Signal inference workers to stop experience collection... [2023-02-26 15:54:29,512][15346] InferenceWorker_p0-w0: stopping experience collection [2023-02-26 15:54:31,879][15332] Signal inference workers to resume experience collection... [2023-02-26 15:54:31,880][15346] InferenceWorker_p0-w0: resuming experience collection [2023-02-26 15:54:33,144][09579] Fps is (10 sec: 409.6, 60 sec: 204.8, 300 sec: 204.8). Total num frames: 4096. Throughput: 0: 158.1. Samples: 3162. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) [2023-02-26 15:54:33,149][09579] Avg episode reward: [(0, '3.228')] [2023-02-26 15:54:38,144][09579] Fps is (10 sec: 2457.6, 60 sec: 983.0, 300 sec: 983.0). Total num frames: 24576. Throughput: 0: 214.6. Samples: 5366. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:54:38,149][09579] Avg episode reward: [(0, '3.852')] [2023-02-26 15:54:43,144][09579] Fps is (10 sec: 3276.8, 60 sec: 1228.8, 300 sec: 1228.8). Total num frames: 36864. Throughput: 0: 315.7. Samples: 9472. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2023-02-26 15:54:43,149][09579] Avg episode reward: [(0, '3.914')] [2023-02-26 15:54:43,390][15346] Updated weights for policy 0, policy_version 10 (0.0013) [2023-02-26 15:54:48,145][09579] Fps is (10 sec: 2457.5, 60 sec: 1404.3, 300 sec: 1404.3). Total num frames: 49152. Throughput: 0: 370.4. Samples: 12964. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2023-02-26 15:54:48,154][09579] Avg episode reward: [(0, '4.410')] [2023-02-26 15:54:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 65536. Throughput: 0: 381.8. Samples: 15272. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:54:53,151][09579] Avg episode reward: [(0, '4.353')] [2023-02-26 15:54:56,971][15346] Updated weights for policy 0, policy_version 20 (0.0015) [2023-02-26 15:54:58,144][09579] Fps is (10 sec: 3276.9, 60 sec: 1820.5, 300 sec: 1820.5). Total num frames: 81920. Throughput: 0: 460.0. Samples: 20698. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:54:58,152][09579] Avg episode reward: [(0, '4.387')] [2023-02-26 15:55:03,144][09579] Fps is (10 sec: 2867.2, 60 sec: 1884.2, 300 sec: 1884.2). Total num frames: 94208. Throughput: 0: 533.6. Samples: 24010. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2023-02-26 15:55:03,150][09579] Avg episode reward: [(0, '4.250')] [2023-02-26 15:55:08,145][09579] Fps is (10 sec: 2457.6, 60 sec: 1936.3, 300 sec: 1936.3). Total num frames: 106496. Throughput: 0: 573.8. Samples: 25820. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:55:08,153][09579] Avg episode reward: [(0, '4.351')] [2023-02-26 15:55:08,158][15332] Saving new best policy, reward=4.351! [2023-02-26 15:55:13,144][09579] Fps is (10 sec: 2457.6, 60 sec: 1979.7, 300 sec: 1979.7). Total num frames: 118784. Throughput: 0: 638.8. Samples: 29876. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:55:13,147][09579] Avg episode reward: [(0, '4.417')] [2023-02-26 15:55:13,158][15332] Saving new best policy, reward=4.417! [2023-02-26 15:55:13,973][15346] Updated weights for policy 0, policy_version 30 (0.0025) [2023-02-26 15:55:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 2252.8, 300 sec: 2079.5). Total num frames: 135168. Throughput: 0: 698.1. Samples: 34576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 15:55:18,148][09579] Avg episode reward: [(0, '4.443')] [2023-02-26 15:55:18,152][15332] Saving new best policy, reward=4.443! [2023-02-26 15:55:23,144][09579] Fps is (10 sec: 2867.2, 60 sec: 2457.6, 300 sec: 2106.5). Total num frames: 147456. Throughput: 0: 696.4. Samples: 36702. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:55:23,153][09579] Avg episode reward: [(0, '4.427')] [2023-02-26 15:55:28,144][09579] Fps is (10 sec: 2457.6, 60 sec: 2662.4, 300 sec: 2129.9). Total num frames: 159744. Throughput: 0: 681.1. Samples: 40120. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:55:28,148][09579] Avg episode reward: [(0, '4.386')] [2023-02-26 15:55:29,043][15346] Updated weights for policy 0, policy_version 40 (0.0045) [2023-02-26 15:55:33,145][09579] Fps is (10 sec: 2867.2, 60 sec: 2867.2, 300 sec: 2201.6). Total num frames: 176128. Throughput: 0: 700.9. Samples: 44506. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:55:33,148][09579] Avg episode reward: [(0, '4.493')] [2023-02-26 15:55:33,161][15332] Saving new best policy, reward=4.493! [2023-02-26 15:55:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 2798.9, 300 sec: 2264.9). Total num frames: 192512. Throughput: 0: 711.6. Samples: 47294. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:55:38,147][09579] Avg episode reward: [(0, '4.312')] [2023-02-26 15:55:41,160][15346] Updated weights for policy 0, policy_version 50 (0.0021) [2023-02-26 15:55:43,144][09579] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2321.1). Total num frames: 208896. Throughput: 0: 695.8. Samples: 52010. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:55:43,146][09579] Avg episode reward: [(0, '4.360')] [2023-02-26 15:55:43,162][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000051_208896.pth... [2023-02-26 15:55:48,144][09579] Fps is (10 sec: 2457.6, 60 sec: 2799.0, 300 sec: 2285.1). Total num frames: 217088. Throughput: 0: 698.9. Samples: 55462. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:55:48,153][09579] Avg episode reward: [(0, '4.296')] [2023-02-26 15:55:53,144][09579] Fps is (10 sec: 2457.6, 60 sec: 2798.9, 300 sec: 2334.7). Total num frames: 233472. Throughput: 0: 701.6. Samples: 57390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:55:53,153][09579] Avg episode reward: [(0, '4.398')] [2023-02-26 15:55:55,558][15346] Updated weights for policy 0, policy_version 60 (0.0019) [2023-02-26 15:55:58,145][09579] Fps is (10 sec: 3686.2, 60 sec: 2867.2, 300 sec: 2418.6). Total num frames: 253952. Throughput: 0: 732.2. Samples: 62824. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:55:58,152][09579] Avg episode reward: [(0, '4.279')] [2023-02-26 15:56:03,144][09579] Fps is (10 sec: 3276.8, 60 sec: 2867.2, 300 sec: 2420.4). Total num frames: 266240. Throughput: 0: 730.0. Samples: 67424. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:56:03,151][09579] Avg episode reward: [(0, '4.373')] [2023-02-26 15:56:08,144][09579] Fps is (10 sec: 2457.7, 60 sec: 2867.2, 300 sec: 2422.0). Total num frames: 278528. Throughput: 0: 721.2. Samples: 69158. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:56:08,152][09579] Avg episode reward: [(0, '4.544')] [2023-02-26 15:56:08,157][15332] Saving new best policy, reward=4.544! [2023-02-26 15:56:11,105][15346] Updated weights for policy 0, policy_version 70 (0.0021) [2023-02-26 15:56:13,146][09579] Fps is (10 sec: 2457.2, 60 sec: 2867.1, 300 sec: 2423.4). Total num frames: 290816. Throughput: 0: 725.2. Samples: 72756. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:56:13,148][09579] Avg episode reward: [(0, '4.619')] [2023-02-26 15:56:13,217][15332] Saving new best policy, reward=4.619! [2023-02-26 15:56:18,144][09579] Fps is (10 sec: 3276.8, 60 sec: 2935.5, 300 sec: 2490.4). Total num frames: 311296. Throughput: 0: 748.3. Samples: 78178. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:56:18,148][09579] Avg episode reward: [(0, '4.413')] [2023-02-26 15:56:23,152][09579] Fps is (10 sec: 3274.8, 60 sec: 2935.1, 300 sec: 2489.0). Total num frames: 323584. Throughput: 0: 745.2. Samples: 80832. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:56:23,157][09579] Avg episode reward: [(0, '4.366')] [2023-02-26 15:56:23,506][15346] Updated weights for policy 0, policy_version 80 (0.0022) [2023-02-26 15:56:28,150][09579] Fps is (10 sec: 2456.2, 60 sec: 2935.2, 300 sec: 2487.8). Total num frames: 335872. Throughput: 0: 719.6. Samples: 84398. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-26 15:56:28,154][09579] Avg episode reward: [(0, '4.460')] [2023-02-26 15:56:33,144][09579] Fps is (10 sec: 2869.4, 60 sec: 2935.5, 300 sec: 2516.1). Total num frames: 352256. Throughput: 0: 729.5. Samples: 88288. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:56:33,152][09579] Avg episode reward: [(0, '4.655')] [2023-02-26 15:56:33,163][15332] Saving new best policy, reward=4.655! [2023-02-26 15:56:37,455][15346] Updated weights for policy 0, policy_version 90 (0.0020) [2023-02-26 15:56:38,144][09579] Fps is (10 sec: 3278.6, 60 sec: 2935.5, 300 sec: 2542.3). Total num frames: 368640. Throughput: 0: 748.4. Samples: 91070. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:56:38,152][09579] Avg episode reward: [(0, '4.506')] [2023-02-26 15:56:43,145][09579] Fps is (10 sec: 3276.7, 60 sec: 2935.5, 300 sec: 2566.8). Total num frames: 385024. Throughput: 0: 746.8. Samples: 96432. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:56:43,152][09579] Avg episode reward: [(0, '4.450')] [2023-02-26 15:56:48,147][09579] Fps is (10 sec: 2866.5, 60 sec: 3003.6, 300 sec: 2563.3). Total num frames: 397312. Throughput: 0: 727.8. Samples: 100178. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:56:48,152][09579] Avg episode reward: [(0, '4.563')] [2023-02-26 15:56:51,631][15346] Updated weights for policy 0, policy_version 100 (0.0023) [2023-02-26 15:56:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3003.7, 300 sec: 2585.6). Total num frames: 413696. Throughput: 0: 733.4. Samples: 102162. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:56:53,148][09579] Avg episode reward: [(0, '4.533')] [2023-02-26 15:56:58,144][09579] Fps is (10 sec: 3687.4, 60 sec: 3003.8, 300 sec: 2631.4). Total num frames: 434176. Throughput: 0: 784.6. Samples: 108062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:56:58,152][09579] Avg episode reward: [(0, '4.520')] [2023-02-26 15:57:01,501][15346] Updated weights for policy 0, policy_version 110 (0.0023) [2023-02-26 15:57:03,147][09579] Fps is (10 sec: 4095.0, 60 sec: 3140.1, 300 sec: 2674.4). Total num frames: 454656. Throughput: 0: 799.5. Samples: 114156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:57:03,150][09579] Avg episode reward: [(0, '4.567')] [2023-02-26 15:57:08,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 2668.3). Total num frames: 466944. Throughput: 0: 784.5. Samples: 116130. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:57:08,150][09579] Avg episode reward: [(0, '4.526')] [2023-02-26 15:57:13,144][09579] Fps is (10 sec: 2867.9, 60 sec: 3208.6, 300 sec: 2685.2). Total num frames: 483328. Throughput: 0: 798.3. Samples: 120318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:57:13,150][09579] Avg episode reward: [(0, '4.516')] [2023-02-26 15:57:14,596][15346] Updated weights for policy 0, policy_version 120 (0.0015) [2023-02-26 15:57:18,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3208.5, 300 sec: 2723.3). Total num frames: 503808. Throughput: 0: 853.4. Samples: 126692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:57:18,149][09579] Avg episode reward: [(0, '4.700')] [2023-02-26 15:57:18,154][15332] Saving new best policy, reward=4.700! [2023-02-26 15:57:23,146][09579] Fps is (10 sec: 4095.1, 60 sec: 3345.4, 300 sec: 2759.4). Total num frames: 524288. Throughput: 0: 859.6. Samples: 129752. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:57:23,150][09579] Avg episode reward: [(0, '4.521')] [2023-02-26 15:57:26,182][15346] Updated weights for policy 0, policy_version 130 (0.0023) [2023-02-26 15:57:28,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3345.4, 300 sec: 2751.7). Total num frames: 536576. Throughput: 0: 836.6. Samples: 134080. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:57:28,148][09579] Avg episode reward: [(0, '4.520')] [2023-02-26 15:57:33,144][09579] Fps is (10 sec: 2867.8, 60 sec: 3345.1, 300 sec: 2764.8). Total num frames: 552960. Throughput: 0: 853.6. Samples: 138590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:57:33,152][09579] Avg episode reward: [(0, '4.451')] [2023-02-26 15:57:37,671][15346] Updated weights for policy 0, policy_version 140 (0.0028) [2023-02-26 15:57:38,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 2797.3). Total num frames: 573440. Throughput: 0: 879.3. Samples: 141730. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:57:38,152][09579] Avg episode reward: [(0, '4.650')] [2023-02-26 15:57:43,145][09579] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 2828.2). Total num frames: 593920. Throughput: 0: 889.3. Samples: 148082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:57:43,148][09579] Avg episode reward: [(0, '4.552')] [2023-02-26 15:57:43,168][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000145_593920.pth... [2023-02-26 15:57:48,152][09579] Fps is (10 sec: 3274.2, 60 sec: 3481.3, 300 sec: 2819.5). Total num frames: 606208. Throughput: 0: 842.3. Samples: 152062. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:57:48,155][09579] Avg episode reward: [(0, '4.380')] [2023-02-26 15:57:50,916][15346] Updated weights for policy 0, policy_version 150 (0.0019) [2023-02-26 15:57:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 2830.0). Total num frames: 622592. Throughput: 0: 844.4. Samples: 154126. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:57:53,147][09579] Avg episode reward: [(0, '4.553')] [2023-02-26 15:57:58,144][09579] Fps is (10 sec: 3689.3, 60 sec: 3481.6, 300 sec: 2858.1). Total num frames: 643072. Throughput: 0: 880.1. Samples: 159922. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:57:58,146][09579] Avg episode reward: [(0, '4.651')] [2023-02-26 15:58:01,024][15346] Updated weights for policy 0, policy_version 160 (0.0022) [2023-02-26 15:58:03,149][09579] Fps is (10 sec: 3684.7, 60 sec: 3413.2, 300 sec: 2867.1). Total num frames: 659456. Throughput: 0: 871.3. Samples: 165906. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:58:03,152][09579] Avg episode reward: [(0, '4.644')] [2023-02-26 15:58:08,146][09579] Fps is (10 sec: 2866.7, 60 sec: 3413.2, 300 sec: 2858.5). Total num frames: 671744. Throughput: 0: 848.1. Samples: 167914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:08,154][09579] Avg episode reward: [(0, '4.675')] [2023-02-26 15:58:13,144][09579] Fps is (10 sec: 2868.5, 60 sec: 3413.3, 300 sec: 2867.2). Total num frames: 688128. Throughput: 0: 844.5. Samples: 172082. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:58:13,149][09579] Avg episode reward: [(0, '4.539')] [2023-02-26 15:58:14,320][15346] Updated weights for policy 0, policy_version 170 (0.0019) [2023-02-26 15:58:18,144][09579] Fps is (10 sec: 4096.7, 60 sec: 3481.6, 300 sec: 2909.0). Total num frames: 712704. Throughput: 0: 886.6. Samples: 178488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:18,153][09579] Avg episode reward: [(0, '4.448')] [2023-02-26 15:58:23,148][09579] Fps is (10 sec: 4094.7, 60 sec: 3413.3, 300 sec: 2916.3). Total num frames: 729088. Throughput: 0: 887.0. Samples: 181650. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:23,151][09579] Avg episode reward: [(0, '4.418')] [2023-02-26 15:58:25,070][15346] Updated weights for policy 0, policy_version 180 (0.0014) [2023-02-26 15:58:28,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 2923.4). Total num frames: 745472. Throughput: 0: 841.1. Samples: 185930. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:28,152][09579] Avg episode reward: [(0, '4.388')] [2023-02-26 15:58:33,144][09579] Fps is (10 sec: 2868.1, 60 sec: 3413.3, 300 sec: 2914.5). Total num frames: 757760. Throughput: 0: 850.7. Samples: 190338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:33,147][09579] Avg episode reward: [(0, '4.584')] [2023-02-26 15:58:37,346][15346] Updated weights for policy 0, policy_version 190 (0.0018) [2023-02-26 15:58:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 2936.8). Total num frames: 778240. Throughput: 0: 874.1. Samples: 193460. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:38,147][09579] Avg episode reward: [(0, '4.549')] [2023-02-26 15:58:43,150][09579] Fps is (10 sec: 4093.9, 60 sec: 3413.0, 300 sec: 2958.2). Total num frames: 798720. Throughput: 0: 885.2. Samples: 199760. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:58:43,157][09579] Avg episode reward: [(0, '4.518')] [2023-02-26 15:58:48,147][09579] Fps is (10 sec: 3276.0, 60 sec: 3413.6, 300 sec: 2949.1). Total num frames: 811008. Throughput: 0: 831.3. Samples: 203312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:58:48,151][09579] Avg episode reward: [(0, '4.771')] [2023-02-26 15:58:48,157][15332] Saving new best policy, reward=4.771! [2023-02-26 15:58:51,564][15346] Updated weights for policy 0, policy_version 200 (0.0012) [2023-02-26 15:58:53,145][09579] Fps is (10 sec: 2049.0, 60 sec: 3276.8, 300 sec: 2925.7). Total num frames: 819200. Throughput: 0: 821.7. Samples: 204888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:58:53,154][09579] Avg episode reward: [(0, '4.769')] [2023-02-26 15:58:58,144][09579] Fps is (10 sec: 2048.5, 60 sec: 3140.3, 300 sec: 2917.5). Total num frames: 831488. Throughput: 0: 801.5. Samples: 208148. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:58:58,151][09579] Avg episode reward: [(0, '4.792')] [2023-02-26 15:58:58,156][15332] Saving new best policy, reward=4.792! [2023-02-26 15:59:03,144][09579] Fps is (10 sec: 3276.9, 60 sec: 3208.8, 300 sec: 2937.8). Total num frames: 851968. Throughput: 0: 786.8. Samples: 213894. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 15:59:03,150][09579] Avg episode reward: [(0, '4.517')] [2023-02-26 15:59:04,281][15346] Updated weights for policy 0, policy_version 210 (0.0036) [2023-02-26 15:59:08,150][09579] Fps is (10 sec: 3684.3, 60 sec: 3276.6, 300 sec: 2943.5). Total num frames: 868352. Throughput: 0: 784.7. Samples: 216962. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:59:08,155][09579] Avg episode reward: [(0, '4.679')] [2023-02-26 15:59:13,145][09579] Fps is (10 sec: 3276.7, 60 sec: 3276.8, 300 sec: 2999.1). Total num frames: 884736. Throughput: 0: 778.2. Samples: 220948. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:59:13,151][09579] Avg episode reward: [(0, '4.781')] [2023-02-26 15:59:18,056][15346] Updated weights for policy 0, policy_version 220 (0.0015) [2023-02-26 15:59:18,145][09579] Fps is (10 sec: 3278.6, 60 sec: 3140.2, 300 sec: 3054.6). Total num frames: 901120. Throughput: 0: 783.4. Samples: 225590. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 15:59:18,147][09579] Avg episode reward: [(0, '4.850')] [2023-02-26 15:59:18,153][15332] Saving new best policy, reward=4.850! [2023-02-26 15:59:23,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3208.7, 300 sec: 3124.1). Total num frames: 921600. Throughput: 0: 778.4. Samples: 228490. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 15:59:23,147][09579] Avg episode reward: [(0, '4.913')] [2023-02-26 15:59:23,159][15332] Saving new best policy, reward=4.913! [2023-02-26 15:59:28,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3208.5, 300 sec: 3165.7). Total num frames: 937984. Throughput: 0: 763.7. Samples: 234122. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 15:59:28,147][09579] Avg episode reward: [(0, '4.813')] [2023-02-26 15:59:29,566][15346] Updated weights for policy 0, policy_version 230 (0.0025) [2023-02-26 15:59:33,151][09579] Fps is (10 sec: 2865.3, 60 sec: 3208.2, 300 sec: 3137.9). Total num frames: 950272. Throughput: 0: 771.3. Samples: 238024. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-26 15:59:33,156][09579] Avg episode reward: [(0, '4.895')] [2023-02-26 15:59:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3140.3, 300 sec: 3151.8). Total num frames: 966656. Throughput: 0: 784.3. Samples: 240182. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 15:59:38,154][09579] Avg episode reward: [(0, '4.825')] [2023-02-26 15:59:41,560][15346] Updated weights for policy 0, policy_version 240 (0.0033) [2023-02-26 15:59:43,144][09579] Fps is (10 sec: 3688.9, 60 sec: 3140.5, 300 sec: 3179.6). Total num frames: 987136. Throughput: 0: 854.7. Samples: 246610. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 15:59:43,147][09579] Avg episode reward: [(0, '4.878')] [2023-02-26 15:59:43,158][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000241_987136.pth... [2023-02-26 15:59:43,278][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000051_208896.pth [2023-02-26 15:59:48,154][09579] Fps is (10 sec: 4091.9, 60 sec: 3276.4, 300 sec: 3193.4). Total num frames: 1007616. Throughput: 0: 851.6. Samples: 252224. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:59:48,160][09579] Avg episode reward: [(0, '4.821')] [2023-02-26 15:59:53,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3179.6). Total num frames: 1019904. Throughput: 0: 828.6. Samples: 254244. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 15:59:53,151][09579] Avg episode reward: [(0, '4.858')] [2023-02-26 15:59:54,193][15346] Updated weights for policy 0, policy_version 250 (0.0019) [2023-02-26 15:59:58,144][09579] Fps is (10 sec: 2870.1, 60 sec: 3413.3, 300 sec: 3193.5). Total num frames: 1036288. Throughput: 0: 833.7. Samples: 258462. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 15:59:58,148][09579] Avg episode reward: [(0, '5.059')] [2023-02-26 15:59:58,160][15332] Saving new best policy, reward=5.059! [2023-02-26 16:00:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3221.3). Total num frames: 1056768. Throughput: 0: 869.0. Samples: 264694. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:00:03,151][09579] Avg episode reward: [(0, '5.054')] [2023-02-26 16:00:04,842][15346] Updated weights for policy 0, policy_version 260 (0.0014) [2023-02-26 16:00:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.7, 300 sec: 3235.1). Total num frames: 1073152. Throughput: 0: 873.8. Samples: 267810. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:00:08,150][09579] Avg episode reward: [(0, '4.930')] [2023-02-26 16:00:13,145][09579] Fps is (10 sec: 2867.0, 60 sec: 3345.0, 300 sec: 3221.3). Total num frames: 1085440. Throughput: 0: 838.2. Samples: 271842. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:00:13,153][09579] Avg episode reward: [(0, '4.862')] [2023-02-26 16:00:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3235.1). Total num frames: 1101824. Throughput: 0: 848.9. Samples: 276220. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:00:18,153][09579] Avg episode reward: [(0, '4.964')] [2023-02-26 16:00:18,682][15346] Updated weights for policy 0, policy_version 270 (0.0014) [2023-02-26 16:00:23,145][09579] Fps is (10 sec: 3686.6, 60 sec: 3345.1, 300 sec: 3262.9). Total num frames: 1122304. Throughput: 0: 868.0. Samples: 279242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:00:23,152][09579] Avg episode reward: [(0, '4.957')] [2023-02-26 16:00:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3262.9). Total num frames: 1138688. Throughput: 0: 854.8. Samples: 285078. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:00:28,148][09579] Avg episode reward: [(0, '4.880')] [2023-02-26 16:00:29,797][15346] Updated weights for policy 0, policy_version 280 (0.0012) [2023-02-26 16:00:33,146][09579] Fps is (10 sec: 3276.4, 60 sec: 3413.6, 300 sec: 3262.9). Total num frames: 1155072. Throughput: 0: 820.4. Samples: 289134. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:00:33,151][09579] Avg episode reward: [(0, '4.992')] [2023-02-26 16:00:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3262.9). Total num frames: 1171456. Throughput: 0: 820.8. Samples: 291180. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:00:38,147][09579] Avg episode reward: [(0, '4.982')] [2023-02-26 16:00:41,688][15346] Updated weights for policy 0, policy_version 290 (0.0037) [2023-02-26 16:00:43,144][09579] Fps is (10 sec: 3687.0, 60 sec: 3413.3, 300 sec: 3304.6). Total num frames: 1191936. Throughput: 0: 869.3. Samples: 297582. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:00:43,147][09579] Avg episode reward: [(0, '5.068')] [2023-02-26 16:00:43,161][15332] Saving new best policy, reward=5.068! [2023-02-26 16:00:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.6, 300 sec: 3304.6). Total num frames: 1208320. Throughput: 0: 855.4. Samples: 303186. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:00:48,149][09579] Avg episode reward: [(0, '5.268')] [2023-02-26 16:00:48,159][15332] Saving new best policy, reward=5.268! [2023-02-26 16:00:53,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3290.7). Total num frames: 1224704. Throughput: 0: 829.5. Samples: 305136. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:00:53,153][09579] Avg episode reward: [(0, '5.129')] [2023-02-26 16:00:54,641][15346] Updated weights for policy 0, policy_version 300 (0.0037) [2023-02-26 16:00:58,147][09579] Fps is (10 sec: 2866.5, 60 sec: 3344.9, 300 sec: 3290.7). Total num frames: 1236992. Throughput: 0: 833.2. Samples: 309338. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:00:58,150][09579] Avg episode reward: [(0, '4.995')] [2023-02-26 16:01:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 1261568. Throughput: 0: 880.0. Samples: 315822. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:01:03,153][09579] Avg episode reward: [(0, '4.841')] [2023-02-26 16:01:04,915][15346] Updated weights for policy 0, policy_version 310 (0.0021) [2023-02-26 16:01:08,144][09579] Fps is (10 sec: 4097.0, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 1277952. Throughput: 0: 883.7. Samples: 319010. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-26 16:01:08,150][09579] Avg episode reward: [(0, '4.959')] [2023-02-26 16:01:13,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3332.3). Total num frames: 1294336. Throughput: 0: 846.7. Samples: 323180. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:01:13,149][09579] Avg episode reward: [(0, '5.035')] [2023-02-26 16:01:17,925][15346] Updated weights for policy 0, policy_version 320 (0.0021) [2023-02-26 16:01:18,145][09579] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3346.3). Total num frames: 1310720. Throughput: 0: 865.8. Samples: 328092. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:01:18,149][09579] Avg episode reward: [(0, '5.065')] [2023-02-26 16:01:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3374.1). Total num frames: 1331200. Throughput: 0: 889.7. Samples: 331216. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:01:23,149][09579] Avg episode reward: [(0, '5.045')] [2023-02-26 16:01:28,144][09579] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 1347584. Throughput: 0: 881.1. Samples: 337230. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:01:28,149][09579] Avg episode reward: [(0, '5.412')] [2023-02-26 16:01:28,155][15332] Saving new best policy, reward=5.412! [2023-02-26 16:01:28,719][15346] Updated weights for policy 0, policy_version 330 (0.0014) [2023-02-26 16:01:33,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.7, 300 sec: 3374.0). Total num frames: 1363968. Throughput: 0: 844.6. Samples: 341192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:01:33,153][09579] Avg episode reward: [(0, '5.217')] [2023-02-26 16:01:38,145][09579] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3374.0). Total num frames: 1380352. Throughput: 0: 848.8. Samples: 343330. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:01:38,147][09579] Avg episode reward: [(0, '5.178')] [2023-02-26 16:01:40,850][15346] Updated weights for policy 0, policy_version 340 (0.0027) [2023-02-26 16:01:43,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 1400832. Throughput: 0: 894.8. Samples: 349600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:01:43,147][09579] Avg episode reward: [(0, '4.921')] [2023-02-26 16:01:43,156][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000342_1400832.pth... [2023-02-26 16:01:43,302][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000145_593920.pth [2023-02-26 16:01:48,149][09579] Fps is (10 sec: 3684.7, 60 sec: 3481.3, 300 sec: 3401.7). Total num frames: 1417216. Throughput: 0: 874.3. Samples: 355170. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:01:48,152][09579] Avg episode reward: [(0, '5.019')] [2023-02-26 16:01:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1429504. Throughput: 0: 848.2. Samples: 357178. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:01:53,147][09579] Avg episode reward: [(0, '5.078')] [2023-02-26 16:01:53,283][15346] Updated weights for policy 0, policy_version 350 (0.0013) [2023-02-26 16:01:58,144][09579] Fps is (10 sec: 2868.6, 60 sec: 3481.7, 300 sec: 3360.1). Total num frames: 1445888. Throughput: 0: 850.0. Samples: 361428. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:01:58,146][09579] Avg episode reward: [(0, '5.159')] [2023-02-26 16:02:03,145][09579] Fps is (10 sec: 3686.1, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 1466368. Throughput: 0: 879.3. Samples: 367660. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:02:03,149][09579] Avg episode reward: [(0, '5.115')] [2023-02-26 16:02:04,384][15346] Updated weights for policy 0, policy_version 360 (0.0019) [2023-02-26 16:02:08,150][09579] Fps is (10 sec: 4093.7, 60 sec: 3481.3, 300 sec: 3401.7). Total num frames: 1486848. Throughput: 0: 879.4. Samples: 370794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:02:08,153][09579] Avg episode reward: [(0, '5.244')] [2023-02-26 16:02:13,144][09579] Fps is (10 sec: 3277.0, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1499136. Throughput: 0: 836.9. Samples: 374892. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:02:13,147][09579] Avg episode reward: [(0, '5.237')] [2023-02-26 16:02:17,574][15346] Updated weights for policy 0, policy_version 370 (0.0024) [2023-02-26 16:02:18,145][09579] Fps is (10 sec: 2868.8, 60 sec: 3413.4, 300 sec: 3360.1). Total num frames: 1515520. Throughput: 0: 853.8. Samples: 379612. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:02:18,147][09579] Avg episode reward: [(0, '5.318')] [2023-02-26 16:02:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 1536000. Throughput: 0: 875.3. Samples: 382720. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:02:23,152][09579] Avg episode reward: [(0, '5.287')] [2023-02-26 16:02:28,115][15346] Updated weights for policy 0, policy_version 380 (0.0024) [2023-02-26 16:02:28,144][09579] Fps is (10 sec: 4096.1, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 1556480. Throughput: 0: 870.4. Samples: 388770. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:02:28,147][09579] Avg episode reward: [(0, '5.337')] [2023-02-26 16:02:33,150][09579] Fps is (10 sec: 3275.0, 60 sec: 3413.0, 300 sec: 3373.9). Total num frames: 1568768. Throughput: 0: 833.5. Samples: 392680. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:02:33,153][09579] Avg episode reward: [(0, '5.509')] [2023-02-26 16:02:33,168][15332] Saving new best policy, reward=5.509! [2023-02-26 16:02:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1585152. Throughput: 0: 833.9. Samples: 394704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:02:38,146][09579] Avg episode reward: [(0, '5.607')] [2023-02-26 16:02:38,150][15332] Saving new best policy, reward=5.607! [2023-02-26 16:02:40,892][15346] Updated weights for policy 0, policy_version 390 (0.0029) [2023-02-26 16:02:43,144][09579] Fps is (10 sec: 3688.5, 60 sec: 3413.3, 300 sec: 3388.0). Total num frames: 1605632. Throughput: 0: 877.1. Samples: 400896. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:02:43,152][09579] Avg episode reward: [(0, '5.792')] [2023-02-26 16:02:43,165][15332] Saving new best policy, reward=5.792! [2023-02-26 16:02:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.6, 300 sec: 3387.9). Total num frames: 1622016. Throughput: 0: 859.1. Samples: 406318. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:02:48,149][09579] Avg episode reward: [(0, '5.793')] [2023-02-26 16:02:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1634304. Throughput: 0: 833.7. Samples: 408306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:02:53,147][09579] Avg episode reward: [(0, '5.401')] [2023-02-26 16:02:53,246][15346] Updated weights for policy 0, policy_version 400 (0.0012) [2023-02-26 16:02:58,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.2). Total num frames: 1650688. Throughput: 0: 840.9. Samples: 412732. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:02:58,152][09579] Avg episode reward: [(0, '5.260')] [2023-02-26 16:03:03,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 1675264. Throughput: 0: 874.4. Samples: 418958. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-26 16:03:03,151][09579] Avg episode reward: [(0, '5.364')] [2023-02-26 16:03:04,233][15346] Updated weights for policy 0, policy_version 410 (0.0012) [2023-02-26 16:03:08,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3413.7, 300 sec: 3401.8). Total num frames: 1691648. Throughput: 0: 874.5. Samples: 422072. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:03:08,147][09579] Avg episode reward: [(0, '5.497')] [2023-02-26 16:03:13,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1703936. Throughput: 0: 828.3. Samples: 426042. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:03:13,151][09579] Avg episode reward: [(0, '5.428')] [2023-02-26 16:03:17,479][15346] Updated weights for policy 0, policy_version 420 (0.0015) [2023-02-26 16:03:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 1720320. Throughput: 0: 850.7. Samples: 430956. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:03:18,147][09579] Avg episode reward: [(0, '5.576')] [2023-02-26 16:03:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3374.0). Total num frames: 1740800. Throughput: 0: 875.2. Samples: 434086. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:03:23,147][09579] Avg episode reward: [(0, '5.501')] [2023-02-26 16:03:27,873][15346] Updated weights for policy 0, policy_version 430 (0.0015) [2023-02-26 16:03:28,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1761280. Throughput: 0: 868.8. Samples: 439994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:03:28,149][09579] Avg episode reward: [(0, '5.280')] [2023-02-26 16:03:33,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.6, 300 sec: 3374.0). Total num frames: 1773568. Throughput: 0: 835.2. Samples: 443902. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:03:33,147][09579] Avg episode reward: [(0, '5.056')] [2023-02-26 16:03:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3360.2). Total num frames: 1789952. Throughput: 0: 838.1. Samples: 446022. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:03:38,152][09579] Avg episode reward: [(0, '5.166')] [2023-02-26 16:03:40,380][15346] Updated weights for policy 0, policy_version 440 (0.0017) [2023-02-26 16:03:43,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 1810432. Throughput: 0: 883.3. Samples: 452482. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:03:43,153][09579] Avg episode reward: [(0, '5.463')] [2023-02-26 16:03:43,165][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000442_1810432.pth... [2023-02-26 16:03:43,268][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000241_987136.pth [2023-02-26 16:03:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 1826816. Throughput: 0: 867.0. Samples: 457972. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:03:48,146][09579] Avg episode reward: [(0, '5.283')] [2023-02-26 16:03:52,933][15346] Updated weights for policy 0, policy_version 450 (0.0014) [2023-02-26 16:03:53,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 1843200. Throughput: 0: 840.7. Samples: 459902. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:03:53,147][09579] Avg episode reward: [(0, '5.270')] [2023-02-26 16:03:58,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 1859584. Throughput: 0: 855.6. Samples: 464544. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:03:58,150][09579] Avg episode reward: [(0, '5.429')] [2023-02-26 16:04:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3429.6). Total num frames: 1880064. Throughput: 0: 881.6. Samples: 470626. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:03,154][09579] Avg episode reward: [(0, '5.346')] [2023-02-26 16:04:03,617][15346] Updated weights for policy 0, policy_version 460 (0.0013) [2023-02-26 16:04:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 1896448. Throughput: 0: 875.6. Samples: 473488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:08,147][09579] Avg episode reward: [(0, '5.306')] [2023-02-26 16:04:13,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3415.7). Total num frames: 1908736. Throughput: 0: 832.0. Samples: 477434. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:04:13,147][09579] Avg episode reward: [(0, '5.271')] [2023-02-26 16:04:17,317][15346] Updated weights for policy 0, policy_version 470 (0.0013) [2023-02-26 16:04:18,145][09579] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 1925120. Throughput: 0: 853.9. Samples: 482326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:18,148][09579] Avg episode reward: [(0, '5.147')] [2023-02-26 16:04:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 1945600. Throughput: 0: 874.0. Samples: 485352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:23,146][09579] Avg episode reward: [(0, '5.223')] [2023-02-26 16:04:28,145][09579] Fps is (10 sec: 3686.2, 60 sec: 3345.0, 300 sec: 3429.6). Total num frames: 1961984. Throughput: 0: 854.0. Samples: 490912. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:04:28,148][09579] Avg episode reward: [(0, '5.419')] [2023-02-26 16:04:28,294][15346] Updated weights for policy 0, policy_version 480 (0.0026) [2023-02-26 16:04:33,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 1974272. Throughput: 0: 817.9. Samples: 494776. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:04:33,148][09579] Avg episode reward: [(0, '5.585')] [2023-02-26 16:04:38,144][09579] Fps is (10 sec: 3277.1, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 1994752. Throughput: 0: 824.3. Samples: 496994. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:04:38,146][09579] Avg episode reward: [(0, '5.808')] [2023-02-26 16:04:38,161][15332] Saving new best policy, reward=5.808! [2023-02-26 16:04:41,036][15346] Updated weights for policy 0, policy_version 490 (0.0018) [2023-02-26 16:04:43,145][09579] Fps is (10 sec: 4095.9, 60 sec: 3413.3, 300 sec: 3415.8). Total num frames: 2015232. Throughput: 0: 858.4. Samples: 503174. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:04:43,147][09579] Avg episode reward: [(0, '5.703')] [2023-02-26 16:04:48,145][09579] Fps is (10 sec: 3686.2, 60 sec: 3413.3, 300 sec: 3429.5). Total num frames: 2031616. Throughput: 0: 838.1. Samples: 508340. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:04:48,149][09579] Avg episode reward: [(0, '5.774')] [2023-02-26 16:04:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 2043904. Throughput: 0: 818.6. Samples: 510326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:53,147][09579] Avg episode reward: [(0, '5.993')] [2023-02-26 16:04:53,157][15332] Saving new best policy, reward=5.993! [2023-02-26 16:04:54,108][15346] Updated weights for policy 0, policy_version 500 (0.0025) [2023-02-26 16:04:58,144][09579] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 2060288. Throughput: 0: 833.3. Samples: 514932. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:04:58,147][09579] Avg episode reward: [(0, '5.807')] [2023-02-26 16:05:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 2080768. Throughput: 0: 860.0. Samples: 521026. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:05:03,147][09579] Avg episode reward: [(0, '6.082')] [2023-02-26 16:05:03,158][15332] Saving new best policy, reward=6.082! [2023-02-26 16:05:04,633][15346] Updated weights for policy 0, policy_version 510 (0.0012) [2023-02-26 16:05:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3429.5). Total num frames: 2097152. Throughput: 0: 851.9. Samples: 523688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:05:08,153][09579] Avg episode reward: [(0, '5.876')] [2023-02-26 16:05:13,145][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 2109440. Throughput: 0: 816.5. Samples: 527656. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:05:13,153][09579] Avg episode reward: [(0, '5.692')] [2023-02-26 16:05:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 2125824. Throughput: 0: 834.2. Samples: 532314. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:05:18,146][09579] Avg episode reward: [(0, '5.524')] [2023-02-26 16:05:18,531][15346] Updated weights for policy 0, policy_version 520 (0.0017) [2023-02-26 16:05:23,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 2146304. Throughput: 0: 849.1. Samples: 535204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-26 16:05:23,152][09579] Avg episode reward: [(0, '5.866')] [2023-02-26 16:05:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3415.7). Total num frames: 2162688. Throughput: 0: 834.5. Samples: 540726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:05:28,150][09579] Avg episode reward: [(0, '5.972')] [2023-02-26 16:05:30,605][15346] Updated weights for policy 0, policy_version 530 (0.0018) [2023-02-26 16:05:33,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 2174976. Throughput: 0: 806.9. Samples: 544648. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:05:33,148][09579] Avg episode reward: [(0, '5.952')] [2023-02-26 16:05:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 2195456. Throughput: 0: 815.2. Samples: 547008. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:05:38,150][09579] Avg episode reward: [(0, '6.088')] [2023-02-26 16:05:38,153][15332] Saving new best policy, reward=6.088! [2023-02-26 16:05:42,132][15346] Updated weights for policy 0, policy_version 540 (0.0023) [2023-02-26 16:05:43,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 2215936. Throughput: 0: 850.0. Samples: 553180. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:05:43,152][09579] Avg episode reward: [(0, '6.144')] [2023-02-26 16:05:43,164][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000541_2215936.pth... [2023-02-26 16:05:43,285][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000342_1400832.pth [2023-02-26 16:05:43,295][15332] Saving new best policy, reward=6.144! [2023-02-26 16:05:48,148][09579] Fps is (10 sec: 3275.7, 60 sec: 3276.6, 300 sec: 3401.7). Total num frames: 2228224. Throughput: 0: 825.1. Samples: 558158. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:05:48,155][09579] Avg episode reward: [(0, '6.225')] [2023-02-26 16:05:48,162][15332] Saving new best policy, reward=6.225! [2023-02-26 16:05:53,144][09579] Fps is (10 sec: 2457.6, 60 sec: 3276.8, 300 sec: 3401.8). Total num frames: 2240512. Throughput: 0: 807.9. Samples: 560044. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:05:53,153][09579] Avg episode reward: [(0, '6.097')] [2023-02-26 16:05:55,593][15346] Updated weights for policy 0, policy_version 550 (0.0037) [2023-02-26 16:05:58,144][09579] Fps is (10 sec: 3277.8, 60 sec: 3345.1, 300 sec: 3387.9). Total num frames: 2260992. Throughput: 0: 825.8. Samples: 564818. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:05:58,153][09579] Avg episode reward: [(0, '6.619')] [2023-02-26 16:05:58,156][15332] Saving new best policy, reward=6.619! [2023-02-26 16:06:03,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3401.8). Total num frames: 2281472. Throughput: 0: 857.9. Samples: 570918. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:06:03,151][09579] Avg episode reward: [(0, '6.616')] [2023-02-26 16:06:06,445][15346] Updated weights for policy 0, policy_version 560 (0.0017) [2023-02-26 16:06:08,146][09579] Fps is (10 sec: 3685.8, 60 sec: 3345.0, 300 sec: 3401.7). Total num frames: 2297856. Throughput: 0: 853.3. Samples: 573602. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:06:08,152][09579] Avg episode reward: [(0, '6.588')] [2023-02-26 16:06:13,145][09579] Fps is (10 sec: 2867.0, 60 sec: 3345.0, 300 sec: 3387.9). Total num frames: 2310144. Throughput: 0: 817.7. Samples: 577524. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:06:13,153][09579] Avg episode reward: [(0, '6.400')] [2023-02-26 16:06:18,144][09579] Fps is (10 sec: 3277.3, 60 sec: 3413.3, 300 sec: 3387.9). Total num frames: 2330624. Throughput: 0: 848.4. Samples: 582826. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:06:18,147][09579] Avg episode reward: [(0, '6.288')] [2023-02-26 16:06:19,001][15346] Updated weights for policy 0, policy_version 570 (0.0013) [2023-02-26 16:06:23,144][09579] Fps is (10 sec: 4096.2, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 2351104. Throughput: 0: 865.1. Samples: 585938. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:06:23,147][09579] Avg episode reward: [(0, '6.534')] [2023-02-26 16:06:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 2367488. Throughput: 0: 847.1. Samples: 591300. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:06:28,147][09579] Avg episode reward: [(0, '6.788')] [2023-02-26 16:06:28,151][15332] Saving new best policy, reward=6.788! [2023-02-26 16:06:31,650][15346] Updated weights for policy 0, policy_version 580 (0.0012) [2023-02-26 16:06:33,144][09579] Fps is (10 sec: 2457.6, 60 sec: 3345.1, 300 sec: 3374.0). Total num frames: 2375680. Throughput: 0: 823.7. Samples: 595224. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:06:33,152][09579] Avg episode reward: [(0, '6.982')] [2023-02-26 16:06:33,170][15332] Saving new best policy, reward=6.982! [2023-02-26 16:06:38,146][09579] Fps is (10 sec: 2457.3, 60 sec: 3276.7, 300 sec: 3360.1). Total num frames: 2392064. Throughput: 0: 834.3. Samples: 597590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:06:38,152][09579] Avg episode reward: [(0, '7.520')] [2023-02-26 16:06:38,164][15332] Saving new best policy, reward=7.520! [2023-02-26 16:06:43,145][09579] Fps is (10 sec: 3276.5, 60 sec: 3208.5, 300 sec: 3360.2). Total num frames: 2408448. Throughput: 0: 823.9. Samples: 601894. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0) [2023-02-26 16:06:43,147][09579] Avg episode reward: [(0, '8.104')] [2023-02-26 16:06:43,158][15332] Saving new best policy, reward=8.104! [2023-02-26 16:06:46,435][15346] Updated weights for policy 0, policy_version 590 (0.0033) [2023-02-26 16:06:48,144][09579] Fps is (10 sec: 2457.9, 60 sec: 3140.4, 300 sec: 3346.2). Total num frames: 2416640. Throughput: 0: 768.5. Samples: 605502. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:06:48,147][09579] Avg episode reward: [(0, '8.057')] [2023-02-26 16:06:53,145][09579] Fps is (10 sec: 2457.7, 60 sec: 3208.5, 300 sec: 3346.2). Total num frames: 2433024. Throughput: 0: 752.3. Samples: 607454. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:06:53,148][09579] Avg episode reward: [(0, '8.057')] [2023-02-26 16:06:58,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 2449408. Throughput: 0: 765.2. Samples: 611958. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:06:58,147][09579] Avg episode reward: [(0, '7.027')] [2023-02-26 16:06:59,530][15346] Updated weights for policy 0, policy_version 600 (0.0015) [2023-02-26 16:07:03,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3140.3, 300 sec: 3332.4). Total num frames: 2469888. Throughput: 0: 785.1. Samples: 618154. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:07:03,153][09579] Avg episode reward: [(0, '7.092')] [2023-02-26 16:07:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3140.3, 300 sec: 3346.2). Total num frames: 2486272. Throughput: 0: 778.4. Samples: 620966. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:07:08,147][09579] Avg episode reward: [(0, '7.397')] [2023-02-26 16:07:12,141][15346] Updated weights for policy 0, policy_version 610 (0.0012) [2023-02-26 16:07:13,145][09579] Fps is (10 sec: 2867.0, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 2498560. Throughput: 0: 747.4. Samples: 624934. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:13,153][09579] Avg episode reward: [(0, '7.648')] [2023-02-26 16:07:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3072.0, 300 sec: 3318.5). Total num frames: 2514944. Throughput: 0: 770.9. Samples: 629914. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:18,153][09579] Avg episode reward: [(0, '7.678')] [2023-02-26 16:07:22,966][15346] Updated weights for policy 0, policy_version 620 (0.0014) [2023-02-26 16:07:23,145][09579] Fps is (10 sec: 4096.2, 60 sec: 3140.3, 300 sec: 3332.3). Total num frames: 2539520. Throughput: 0: 789.1. Samples: 633100. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:23,147][09579] Avg episode reward: [(0, '7.323')] [2023-02-26 16:07:28,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3140.3, 300 sec: 3346.3). Total num frames: 2555904. Throughput: 0: 818.5. Samples: 638724. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:28,149][09579] Avg episode reward: [(0, '7.351')] [2023-02-26 16:07:33,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3208.5, 300 sec: 3332.3). Total num frames: 2568192. Throughput: 0: 829.4. Samples: 642826. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:07:33,148][09579] Avg episode reward: [(0, '7.305')] [2023-02-26 16:07:36,256][15346] Updated weights for policy 0, policy_version 630 (0.0013) [2023-02-26 16:07:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3208.6, 300 sec: 3318.5). Total num frames: 2584576. Throughput: 0: 837.0. Samples: 645120. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:38,153][09579] Avg episode reward: [(0, '7.691')] [2023-02-26 16:07:43,145][09579] Fps is (10 sec: 4095.9, 60 sec: 3345.1, 300 sec: 3346.2). Total num frames: 2609152. Throughput: 0: 880.4. Samples: 651576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:07:43,147][09579] Avg episode reward: [(0, '8.117')] [2023-02-26 16:07:43,164][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth... [2023-02-26 16:07:43,277][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000442_1810432.pth [2023-02-26 16:07:43,289][15332] Saving new best policy, reward=8.117! [2023-02-26 16:07:46,390][15346] Updated weights for policy 0, policy_version 640 (0.0013) [2023-02-26 16:07:48,147][09579] Fps is (10 sec: 4094.9, 60 sec: 3481.4, 300 sec: 3360.1). Total num frames: 2625536. Throughput: 0: 856.8. Samples: 656712. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:07:48,153][09579] Avg episode reward: [(0, '8.014')] [2023-02-26 16:07:53,146][09579] Fps is (10 sec: 2866.9, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 2637824. Throughput: 0: 839.8. Samples: 658756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:07:53,152][09579] Avg episode reward: [(0, '8.237')] [2023-02-26 16:07:53,167][15332] Saving new best policy, reward=8.237! [2023-02-26 16:07:58,144][09579] Fps is (10 sec: 2868.0, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2654208. Throughput: 0: 850.1. Samples: 663186. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:07:58,147][09579] Avg episode reward: [(0, '7.754')] [2023-02-26 16:07:59,593][15346] Updated weights for policy 0, policy_version 650 (0.0042) [2023-02-26 16:08:03,144][09579] Fps is (10 sec: 3686.8, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 2674688. Throughput: 0: 877.3. Samples: 669392. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:08:03,148][09579] Avg episode reward: [(0, '7.916')] [2023-02-26 16:08:08,146][09579] Fps is (10 sec: 3685.8, 60 sec: 3413.2, 300 sec: 3346.2). Total num frames: 2691072. Throughput: 0: 865.5. Samples: 672050. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:08:08,149][09579] Avg episode reward: [(0, '7.566')] [2023-02-26 16:08:12,248][15346] Updated weights for policy 0, policy_version 660 (0.0019) [2023-02-26 16:08:13,145][09579] Fps is (10 sec: 2867.1, 60 sec: 3413.4, 300 sec: 3332.3). Total num frames: 2703360. Throughput: 0: 829.7. Samples: 676062. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:08:13,147][09579] Avg episode reward: [(0, '7.481')] [2023-02-26 16:08:18,144][09579] Fps is (10 sec: 2867.7, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2719744. Throughput: 0: 845.6. Samples: 680878. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:08:18,154][09579] Avg episode reward: [(0, '7.244')] [2023-02-26 16:08:23,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2740224. Throughput: 0: 863.8. Samples: 683992. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:08:23,151][09579] Avg episode reward: [(0, '8.047')] [2023-02-26 16:08:23,316][15346] Updated weights for policy 0, policy_version 670 (0.0019) [2023-02-26 16:08:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2756608. Throughput: 0: 843.3. Samples: 689526. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:08:28,146][09579] Avg episode reward: [(0, '8.056')] [2023-02-26 16:08:33,145][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2768896. Throughput: 0: 814.0. Samples: 693338. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:08:33,150][09579] Avg episode reward: [(0, '8.391')] [2023-02-26 16:08:33,164][15332] Saving new best policy, reward=8.391! [2023-02-26 16:08:37,000][15346] Updated weights for policy 0, policy_version 680 (0.0015) [2023-02-26 16:08:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 2789376. Throughput: 0: 815.8. Samples: 695464. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:08:38,147][09579] Avg episode reward: [(0, '7.825')] [2023-02-26 16:08:43,144][09579] Fps is (10 sec: 4096.1, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2809856. Throughput: 0: 857.9. Samples: 701792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:08:43,152][09579] Avg episode reward: [(0, '7.887')] [2023-02-26 16:08:48,106][15346] Updated weights for policy 0, policy_version 690 (0.0022) [2023-02-26 16:08:48,145][09579] Fps is (10 sec: 3686.1, 60 sec: 3345.2, 300 sec: 3332.3). Total num frames: 2826240. Throughput: 0: 834.1. Samples: 706926. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:08:48,154][09579] Avg episode reward: [(0, '8.145')] [2023-02-26 16:08:53,145][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2838528. Throughput: 0: 816.5. Samples: 708790. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:08:53,148][09579] Avg episode reward: [(0, '8.571')] [2023-02-26 16:08:53,160][15332] Saving new best policy, reward=8.571! [2023-02-26 16:08:58,144][09579] Fps is (10 sec: 2867.4, 60 sec: 3345.1, 300 sec: 3304.6). Total num frames: 2854912. Throughput: 0: 827.8. Samples: 713312. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:08:58,151][09579] Avg episode reward: [(0, '8.827')] [2023-02-26 16:08:58,160][15332] Saving new best policy, reward=8.827! [2023-02-26 16:09:00,819][15346] Updated weights for policy 0, policy_version 700 (0.0021) [2023-02-26 16:09:03,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2875392. Throughput: 0: 858.8. Samples: 719524. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:09:03,147][09579] Avg episode reward: [(0, '9.314')] [2023-02-26 16:09:03,159][15332] Saving new best policy, reward=9.314! [2023-02-26 16:09:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.2, 300 sec: 3332.3). Total num frames: 2891776. Throughput: 0: 850.3. Samples: 722256. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:09:08,153][09579] Avg episode reward: [(0, '9.613')] [2023-02-26 16:09:08,156][15332] Saving new best policy, reward=9.613! [2023-02-26 16:09:13,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2904064. Throughput: 0: 811.7. Samples: 726052. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:09:13,147][09579] Avg episode reward: [(0, '9.883')] [2023-02-26 16:09:13,165][15332] Saving new best policy, reward=9.883! [2023-02-26 16:09:14,043][15346] Updated weights for policy 0, policy_version 710 (0.0013) [2023-02-26 16:09:18,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3304.6). Total num frames: 2920448. Throughput: 0: 836.1. Samples: 730962. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0) [2023-02-26 16:09:18,151][09579] Avg episode reward: [(0, '10.394')] [2023-02-26 16:09:18,155][15332] Saving new best policy, reward=10.394! [2023-02-26 16:09:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 2940928. Throughput: 0: 858.0. Samples: 734076. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:09:23,153][09579] Avg episode reward: [(0, '10.730')] [2023-02-26 16:09:23,166][15332] Saving new best policy, reward=10.730! [2023-02-26 16:09:24,584][15346] Updated weights for policy 0, policy_version 720 (0.0012) [2023-02-26 16:09:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 2957312. Throughput: 0: 840.6. Samples: 739620. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:09:28,150][09579] Avg episode reward: [(0, '10.208')] [2023-02-26 16:09:33,146][09579] Fps is (10 sec: 2866.7, 60 sec: 3345.0, 300 sec: 3304.5). Total num frames: 2969600. Throughput: 0: 813.8. Samples: 743548. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:09:33,151][09579] Avg episode reward: [(0, '9.725')] [2023-02-26 16:09:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3276.8, 300 sec: 3290.7). Total num frames: 2985984. Throughput: 0: 821.0. Samples: 745736. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:09:38,151][09579] Avg episode reward: [(0, '10.191')] [2023-02-26 16:09:38,170][15346] Updated weights for policy 0, policy_version 730 (0.0024) [2023-02-26 16:09:43,145][09579] Fps is (10 sec: 4096.6, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 3010560. Throughput: 0: 856.7. Samples: 751864. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) [2023-02-26 16:09:43,148][09579] Avg episode reward: [(0, '10.034')] [2023-02-26 16:09:43,165][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000735_3010560.pth... [2023-02-26 16:09:43,284][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000541_2215936.pth [2023-02-26 16:09:48,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3026944. Throughput: 0: 835.5. Samples: 757122. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:09:48,149][09579] Avg episode reward: [(0, '10.611')] [2023-02-26 16:09:49,644][15346] Updated weights for policy 0, policy_version 740 (0.0012) [2023-02-26 16:09:53,144][09579] Fps is (10 sec: 2867.3, 60 sec: 3345.1, 300 sec: 3318.5). Total num frames: 3039232. Throughput: 0: 818.9. Samples: 759108. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:09:53,151][09579] Avg episode reward: [(0, '11.014')] [2023-02-26 16:09:53,164][15332] Saving new best policy, reward=11.014! [2023-02-26 16:09:58,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3345.1, 300 sec: 3304.6). Total num frames: 3055616. Throughput: 0: 840.8. Samples: 763886. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:09:58,152][09579] Avg episode reward: [(0, '11.193')] [2023-02-26 16:09:58,161][15332] Saving new best policy, reward=11.193! [2023-02-26 16:10:01,229][15346] Updated weights for policy 0, policy_version 750 (0.0020) [2023-02-26 16:10:03,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3080192. Throughput: 0: 871.9. Samples: 770198. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:10:03,147][09579] Avg episode reward: [(0, '10.954')] [2023-02-26 16:10:08,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.3). Total num frames: 3092480. Throughput: 0: 866.1. Samples: 773052. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:08,152][09579] Avg episode reward: [(0, '10.787')] [2023-02-26 16:10:13,145][09579] Fps is (10 sec: 2867.1, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3108864. Throughput: 0: 833.0. Samples: 777104. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:13,153][09579] Avg episode reward: [(0, '10.172')] [2023-02-26 16:10:14,094][15346] Updated weights for policy 0, policy_version 760 (0.0014) [2023-02-26 16:10:18,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 3125248. Throughput: 0: 851.6. Samples: 781868. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:10:18,152][09579] Avg episode reward: [(0, '10.912')] [2023-02-26 16:10:23,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3145728. Throughput: 0: 868.0. Samples: 784794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:10:23,148][09579] Avg episode reward: [(0, '11.110')] [2023-02-26 16:10:24,897][15346] Updated weights for policy 0, policy_version 770 (0.0023) [2023-02-26 16:10:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3346.2). Total num frames: 3162112. Throughput: 0: 857.2. Samples: 790436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:10:28,146][09579] Avg episode reward: [(0, '11.360')] [2023-02-26 16:10:28,153][15332] Saving new best policy, reward=11.360! [2023-02-26 16:10:33,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3318.5). Total num frames: 3174400. Throughput: 0: 830.7. Samples: 794502. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:10:33,155][09579] Avg episode reward: [(0, '11.956')] [2023-02-26 16:10:33,170][15332] Saving new best policy, reward=11.956! [2023-02-26 16:10:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3304.6). Total num frames: 3190784. Throughput: 0: 832.1. Samples: 796552. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:38,146][09579] Avg episode reward: [(0, '13.448')] [2023-02-26 16:10:38,158][15332] Saving new best policy, reward=13.448! [2023-02-26 16:10:38,441][15346] Updated weights for policy 0, policy_version 780 (0.0019) [2023-02-26 16:10:43,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3346.3). Total num frames: 3215360. Throughput: 0: 866.4. Samples: 802874. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:43,147][09579] Avg episode reward: [(0, '14.052')] [2023-02-26 16:10:43,160][15332] Saving new best policy, reward=14.052! [2023-02-26 16:10:48,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 3231744. Throughput: 0: 846.4. Samples: 808286. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:48,147][09579] Avg episode reward: [(0, '13.871')] [2023-02-26 16:10:49,318][15346] Updated weights for policy 0, policy_version 790 (0.0014) [2023-02-26 16:10:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3244032. Throughput: 0: 827.4. Samples: 810286. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:10:53,151][09579] Avg episode reward: [(0, '15.668')] [2023-02-26 16:10:53,163][15332] Saving new best policy, reward=15.668! [2023-02-26 16:10:58,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 3260416. Throughput: 0: 836.9. Samples: 814762. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:10:58,151][09579] Avg episode reward: [(0, '14.602')] [2023-02-26 16:11:01,466][15346] Updated weights for policy 0, policy_version 800 (0.0026) [2023-02-26 16:11:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3345.1, 300 sec: 3332.4). Total num frames: 3280896. Throughput: 0: 873.6. Samples: 821180. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:11:03,147][09579] Avg episode reward: [(0, '13.928')] [2023-02-26 16:11:08,148][09579] Fps is (10 sec: 3685.0, 60 sec: 3413.1, 300 sec: 3346.2). Total num frames: 3297280. Throughput: 0: 874.6. Samples: 824154. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:11:08,157][09579] Avg episode reward: [(0, '13.583')] [2023-02-26 16:11:13,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3413.4, 300 sec: 3332.3). Total num frames: 3313664. Throughput: 0: 836.8. Samples: 828094. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:13,150][09579] Avg episode reward: [(0, '12.512')] [2023-02-26 16:11:14,370][15346] Updated weights for policy 0, policy_version 810 (0.0024) [2023-02-26 16:11:18,145][09579] Fps is (10 sec: 3277.9, 60 sec: 3413.3, 300 sec: 3318.5). Total num frames: 3330048. Throughput: 0: 858.0. Samples: 833114. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:18,147][09579] Avg episode reward: [(0, '13.466')] [2023-02-26 16:11:23,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3332.3). Total num frames: 3350528. Throughput: 0: 883.5. Samples: 836310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:23,147][09579] Avg episode reward: [(0, '13.792')] [2023-02-26 16:11:24,303][15346] Updated weights for policy 0, policy_version 820 (0.0014) [2023-02-26 16:11:28,145][09579] Fps is (10 sec: 3686.1, 60 sec: 3413.3, 300 sec: 3360.1). Total num frames: 3366912. Throughput: 0: 874.5. Samples: 842228. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:11:28,153][09579] Avg episode reward: [(0, '14.462')] [2023-02-26 16:11:33,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3383296. Throughput: 0: 845.2. Samples: 846322. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:11:33,152][09579] Avg episode reward: [(0, '14.606')] [2023-02-26 16:11:37,570][15346] Updated weights for policy 0, policy_version 830 (0.0034) [2023-02-26 16:11:38,144][09579] Fps is (10 sec: 3277.1, 60 sec: 3481.6, 300 sec: 3360.1). Total num frames: 3399680. Throughput: 0: 851.9. Samples: 848620. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:38,147][09579] Avg episode reward: [(0, '14.449')] [2023-02-26 16:11:43,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3420160. Throughput: 0: 889.6. Samples: 854794. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:43,147][09579] Avg episode reward: [(0, '14.452')] [2023-02-26 16:11:43,159][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth... [2023-02-26 16:11:43,278][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000637_2609152.pth [2023-02-26 16:11:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3413.3, 300 sec: 3401.8). Total num frames: 3436544. Throughput: 0: 866.9. Samples: 860190. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:11:48,152][09579] Avg episode reward: [(0, '14.257')] [2023-02-26 16:11:48,444][15346] Updated weights for policy 0, policy_version 840 (0.0024) [2023-02-26 16:11:53,145][09579] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3452928. Throughput: 0: 845.8. Samples: 862214. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:11:53,153][09579] Avg episode reward: [(0, '13.777')] [2023-02-26 16:11:58,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3469312. Throughput: 0: 861.3. Samples: 866854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:11:58,154][09579] Avg episode reward: [(0, '13.547')] [2023-02-26 16:12:00,471][15346] Updated weights for policy 0, policy_version 850 (0.0019) [2023-02-26 16:12:03,144][09579] Fps is (10 sec: 3686.7, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3489792. Throughput: 0: 892.4. Samples: 873274. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:12:03,156][09579] Avg episode reward: [(0, '13.713')] [2023-02-26 16:12:08,152][09579] Fps is (10 sec: 4092.9, 60 sec: 3549.6, 300 sec: 3429.5). Total num frames: 3510272. Throughput: 0: 889.8. Samples: 876358. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:12:08,160][09579] Avg episode reward: [(0, '14.462')] [2023-02-26 16:12:12,936][15346] Updated weights for policy 0, policy_version 860 (0.0021) [2023-02-26 16:12:13,145][09579] Fps is (10 sec: 3276.7, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3522560. Throughput: 0: 846.7. Samples: 880330. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:12:13,149][09579] Avg episode reward: [(0, '14.813')] [2023-02-26 16:12:18,144][09579] Fps is (10 sec: 2869.4, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3538944. Throughput: 0: 865.0. Samples: 885246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:12:18,152][09579] Avg episode reward: [(0, '14.992')] [2023-02-26 16:12:23,144][09579] Fps is (10 sec: 3686.5, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3559424. Throughput: 0: 884.8. Samples: 888436. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:12:23,154][09579] Avg episode reward: [(0, '15.942')] [2023-02-26 16:12:23,166][15332] Saving new best policy, reward=15.942! [2023-02-26 16:12:23,472][15346] Updated weights for policy 0, policy_version 870 (0.0014) [2023-02-26 16:12:28,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.7, 300 sec: 3415.6). Total num frames: 3575808. Throughput: 0: 881.3. Samples: 894454. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:12:28,147][09579] Avg episode reward: [(0, '16.210')] [2023-02-26 16:12:28,154][15332] Saving new best policy, reward=16.210! [2023-02-26 16:12:33,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3592192. Throughput: 0: 849.5. Samples: 898418. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:12:33,150][09579] Avg episode reward: [(0, '16.367')] [2023-02-26 16:12:33,169][15332] Saving new best policy, reward=16.367! [2023-02-26 16:12:36,852][15346] Updated weights for policy 0, policy_version 880 (0.0016) [2023-02-26 16:12:38,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3387.9). Total num frames: 3608576. Throughput: 0: 852.8. Samples: 900590. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:12:38,150][09579] Avg episode reward: [(0, '16.565')] [2023-02-26 16:12:38,152][15332] Saving new best policy, reward=16.565! [2023-02-26 16:12:43,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3629056. Throughput: 0: 885.6. Samples: 906704. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:12:43,151][09579] Avg episode reward: [(0, '16.510')] [2023-02-26 16:12:46,937][15346] Updated weights for policy 0, policy_version 890 (0.0013) [2023-02-26 16:12:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3415.7). Total num frames: 3645440. Throughput: 0: 867.4. Samples: 912308. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:12:48,149][09579] Avg episode reward: [(0, '16.272')] [2023-02-26 16:12:53,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.4, 300 sec: 3401.8). Total num frames: 3657728. Throughput: 0: 844.5. Samples: 914352. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:12:53,149][09579] Avg episode reward: [(0, '15.806')] [2023-02-26 16:12:58,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3401.8). Total num frames: 3678208. Throughput: 0: 857.6. Samples: 918920. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0) [2023-02-26 16:12:58,147][09579] Avg episode reward: [(0, '15.969')] [2023-02-26 16:12:59,759][15346] Updated weights for policy 0, policy_version 900 (0.0013) [2023-02-26 16:13:03,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3481.6, 300 sec: 3415.7). Total num frames: 3698688. Throughput: 0: 888.4. Samples: 925226. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:13:03,147][09579] Avg episode reward: [(0, '15.531')] [2023-02-26 16:13:08,147][09579] Fps is (10 sec: 3685.5, 60 sec: 3413.6, 300 sec: 3429.5). Total num frames: 3715072. Throughput: 0: 889.1. Samples: 928450. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:13:08,153][09579] Avg episode reward: [(0, '15.497')] [2023-02-26 16:13:11,432][15346] Updated weights for policy 0, policy_version 910 (0.0016) [2023-02-26 16:13:13,145][09579] Fps is (10 sec: 3276.6, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3731456. Throughput: 0: 846.3. Samples: 932538. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:13:13,149][09579] Avg episode reward: [(0, '14.432')] [2023-02-26 16:13:18,144][09579] Fps is (10 sec: 3277.6, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3747840. Throughput: 0: 864.3. Samples: 937312. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:13:18,152][09579] Avg episode reward: [(0, '14.164')] [2023-02-26 16:13:22,628][15346] Updated weights for policy 0, policy_version 920 (0.0022) [2023-02-26 16:13:23,144][09579] Fps is (10 sec: 3686.6, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3768320. Throughput: 0: 887.3. Samples: 940520. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:13:23,147][09579] Avg episode reward: [(0, '14.816')] [2023-02-26 16:13:28,144][09579] Fps is (10 sec: 4096.0, 60 sec: 3549.9, 300 sec: 3457.3). Total num frames: 3788800. Throughput: 0: 891.9. Samples: 946838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) [2023-02-26 16:13:28,151][09579] Avg episode reward: [(0, '16.161')] [2023-02-26 16:13:33,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3801088. Throughput: 0: 856.0. Samples: 950830. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:13:33,167][09579] Avg episode reward: [(0, '15.620')] [2023-02-26 16:13:35,540][15346] Updated weights for policy 0, policy_version 930 (0.0016) [2023-02-26 16:13:38,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3481.6, 300 sec: 3415.6). Total num frames: 3817472. Throughput: 0: 856.5. Samples: 952896. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:13:38,147][09579] Avg episode reward: [(0, '16.715')] [2023-02-26 16:13:38,149][15332] Saving new best policy, reward=16.715! [2023-02-26 16:13:43,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3429.5). Total num frames: 3837952. Throughput: 0: 889.6. Samples: 958950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:13:43,153][09579] Avg episode reward: [(0, '16.287')] [2023-02-26 16:13:43,163][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000937_3837952.pth... [2023-02-26 16:13:43,171][09579] No heartbeat for components: RolloutWorker_w3 (1174 seconds) [2023-02-26 16:13:43,333][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000735_3010560.pth [2023-02-26 16:13:45,842][15346] Updated weights for policy 0, policy_version 940 (0.0021) [2023-02-26 16:13:48,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3854336. Throughput: 0: 877.0. Samples: 964690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:13:48,153][09579] Avg episode reward: [(0, '16.698')] [2023-02-26 16:13:53,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3549.9, 300 sec: 3443.4). Total num frames: 3870720. Throughput: 0: 849.6. Samples: 966682. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:13:53,147][09579] Avg episode reward: [(0, '17.061')] [2023-02-26 16:13:53,166][15332] Saving new best policy, reward=17.061! [2023-02-26 16:13:58,144][09579] Fps is (10 sec: 2867.2, 60 sec: 3413.3, 300 sec: 3415.6). Total num frames: 3883008. Throughput: 0: 851.4. Samples: 970852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:13:58,151][09579] Avg episode reward: [(0, '18.056')] [2023-02-26 16:13:58,153][15332] Saving new best policy, reward=18.056! [2023-02-26 16:13:59,171][15346] Updated weights for policy 0, policy_version 950 (0.0020) [2023-02-26 16:14:03,144][09579] Fps is (10 sec: 3686.4, 60 sec: 3481.6, 300 sec: 3443.4). Total num frames: 3907584. Throughput: 0: 889.2. Samples: 977326. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:14:03,149][09579] Avg episode reward: [(0, '18.027')] [2023-02-26 16:14:08,145][09579] Fps is (10 sec: 4505.4, 60 sec: 3550.0, 300 sec: 3471.2). Total num frames: 3928064. Throughput: 0: 887.9. Samples: 980474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:14:08,148][09579] Avg episode reward: [(0, '18.275')] [2023-02-26 16:14:08,152][15332] Saving new best policy, reward=18.275! [2023-02-26 16:14:10,090][15346] Updated weights for policy 0, policy_version 960 (0.0012) [2023-02-26 16:14:13,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3481.6, 300 sec: 3457.3). Total num frames: 3940352. Throughput: 0: 841.1. Samples: 984686. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) [2023-02-26 16:14:13,150][09579] Avg episode reward: [(0, '20.218')] [2023-02-26 16:14:13,159][15332] Saving new best policy, reward=20.218! [2023-02-26 16:14:18,144][09579] Fps is (10 sec: 2048.1, 60 sec: 3345.1, 300 sec: 3415.6). Total num frames: 3948544. Throughput: 0: 829.0. Samples: 988134. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0) [2023-02-26 16:14:18,147][09579] Avg episode reward: [(0, '19.826')] [2023-02-26 16:14:23,144][09579] Fps is (10 sec: 2048.0, 60 sec: 3208.5, 300 sec: 3401.8). Total num frames: 3960832. Throughput: 0: 827.7. Samples: 990142. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:14:23,147][09579] Avg episode reward: [(0, '19.406')] [2023-02-26 16:14:25,754][15346] Updated weights for policy 0, policy_version 970 (0.0021) [2023-02-26 16:14:28,144][09579] Fps is (10 sec: 3276.8, 60 sec: 3208.5, 300 sec: 3429.6). Total num frames: 3981312. Throughput: 0: 801.1. Samples: 995000. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) [2023-02-26 16:14:28,147][09579] Avg episode reward: [(0, '19.936')] [2023-02-26 16:14:33,145][09579] Fps is (10 sec: 3276.6, 60 sec: 3208.5, 300 sec: 3415.6). Total num frames: 3993600. Throughput: 0: 775.1. Samples: 999572. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0) [2023-02-26 16:14:33,148][09579] Avg episode reward: [(0, '19.949')] [2023-02-26 16:14:36,328][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-26 16:14:36,335][15332] Stopping Batcher_0... [2023-02-26 16:14:36,348][15332] Loop batcher_evt_loop terminating... [2023-02-26 16:14:36,341][09579] Component Batcher_0 stopped! [2023-02-26 16:14:36,349][09579] Component RolloutWorker_w3 process died already! Don't wait for it. [2023-02-26 16:14:36,419][15346] Weights refcount: 2 0 [2023-02-26 16:14:36,436][15346] Stopping InferenceWorker_p0-w0... [2023-02-26 16:14:36,434][09579] Component RolloutWorker_w7 stopped! [2023-02-26 16:14:36,439][09579] Component InferenceWorker_p0-w0 stopped! [2023-02-26 16:14:36,444][15358] Stopping RolloutWorker_w7... [2023-02-26 16:14:36,448][15358] Loop rollout_proc7_evt_loop terminating... [2023-02-26 16:14:36,452][15357] Stopping RolloutWorker_w6... [2023-02-26 16:14:36,453][15357] Loop rollout_proc6_evt_loop terminating... [2023-02-26 16:14:36,437][15346] Loop inference_proc0-0_evt_loop terminating... [2023-02-26 16:14:36,452][09579] Component RolloutWorker_w6 stopped! [2023-02-26 16:14:36,492][09579] Component RolloutWorker_w5 stopped! [2023-02-26 16:14:36,499][15356] Stopping RolloutWorker_w5... [2023-02-26 16:14:36,501][15352] Stopping RolloutWorker_w1... [2023-02-26 16:14:36,502][09579] Component RolloutWorker_w1 stopped! [2023-02-26 16:14:36,507][09579] Component RolloutWorker_w2 stopped! [2023-02-26 16:14:36,508][09579] Component RolloutWorker_w4 stopped! [2023-02-26 16:14:36,507][15355] Stopping RolloutWorker_w4... [2023-02-26 16:14:36,524][09579] Component RolloutWorker_w0 stopped! [2023-02-26 16:14:36,521][15347] Stopping RolloutWorker_w0... [2023-02-26 16:14:36,526][15347] Loop rollout_proc0_evt_loop terminating... [2023-02-26 16:14:36,501][15352] Loop rollout_proc1_evt_loop terminating... [2023-02-26 16:14:36,499][15356] Loop rollout_proc5_evt_loop terminating... [2023-02-26 16:14:36,504][15353] Stopping RolloutWorker_w2... [2023-02-26 16:14:36,532][15353] Loop rollout_proc2_evt_loop terminating... [2023-02-26 16:14:36,525][15355] Loop rollout_proc4_evt_loop terminating... [2023-02-26 16:14:36,546][15332] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000835_3420160.pth [2023-02-26 16:14:36,554][15332] Saving new best policy, reward=20.755! [2023-02-26 16:14:36,787][15332] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-26 16:14:37,010][09579] Component LearnerWorker_p0 stopped! [2023-02-26 16:14:37,016][09579] Waiting for process learner_proc0 to stop... [2023-02-26 16:14:37,022][15332] Stopping LearnerWorker_p0... [2023-02-26 16:14:37,022][15332] Loop learner_proc0_evt_loop terminating... [2023-02-26 16:14:39,066][09579] Waiting for process inference_proc0-0 to join... [2023-02-26 16:14:39,295][09579] Waiting for process rollout_proc0 to join... [2023-02-26 16:14:39,297][09579] Waiting for process rollout_proc1 to join... [2023-02-26 16:14:39,535][09579] Waiting for process rollout_proc2 to join... [2023-02-26 16:14:39,537][09579] Waiting for process rollout_proc3 to join... [2023-02-26 16:14:39,540][09579] Waiting for process rollout_proc4 to join... [2023-02-26 16:14:39,543][09579] Waiting for process rollout_proc5 to join... [2023-02-26 16:14:39,546][09579] Waiting for process rollout_proc6 to join... [2023-02-26 16:14:39,548][09579] Waiting for process rollout_proc7 to join... [2023-02-26 16:14:39,550][09579] Batcher 0 profile tree view: batching: 25.8113, releasing_batches: 0.0284 [2023-02-26 16:14:39,553][09579] InferenceWorker_p0-w0 profile tree view: wait_policy: 0.0000 wait_policy_total: 591.1108 update_model: 8.3980 weight_update: 0.0014 one_step: 0.0103 handle_policy_step: 576.5063 deserialize: 16.2946, stack: 3.3472, obs_to_device_normalize: 125.0995, forward: 288.1556, send_messages: 25.6306 prepare_outputs: 89.2956 to_cpu: 55.6094 [2023-02-26 16:14:39,557][09579] Learner 0 profile tree view: misc: 0.0058, prepare_batch: 16.2769 train: 75.7995 epoch_init: 0.0066, minibatch_init: 0.0068, losses_postprocess: 0.6441, kl_divergence: 0.5340, after_optimizer: 32.5365 calculate_losses: 26.8532 losses_init: 0.0072, forward_head: 1.7874, bptt_initial: 17.8638, tail: 1.2133, advantages_returns: 0.2995, losses: 3.1396 bptt: 2.2276 bptt_forward_core: 2.1170 update: 14.5919 clip: 1.4673 [2023-02-26 16:14:39,558][09579] RolloutWorker_w0 profile tree view: wait_for_trajectories: 0.4551, enqueue_policy_requests: 163.2893, env_step: 915.8918, overhead: 26.3425, complete_rollouts: 8.3376 save_policy_outputs: 24.6039 split_output_tensors: 12.1983 [2023-02-26 16:14:39,561][09579] RolloutWorker_w7 profile tree view: wait_for_trajectories: 0.4369, enqueue_policy_requests: 206.9612, env_step: 869.3657, overhead: 25.9594, complete_rollouts: 6.5315 save_policy_outputs: 24.0744 split_output_tensors: 11.4171 [2023-02-26 16:14:39,563][09579] Loop Runner_EvtLoop terminating... [2023-02-26 16:14:39,565][09579] Runner profile tree view: main_loop: 1251.2572 [2023-02-26 16:14:39,578][09579] Collected {0: 4005888}, FPS: 3201.5 [2023-02-26 16:14:39,691][09579] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-26 16:14:39,693][09579] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-26 16:14:39,696][09579] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-26 16:14:39,698][09579] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-26 16:14:39,701][09579] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-26 16:14:39,702][09579] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-26 16:14:39,704][09579] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! [2023-02-26 16:14:39,705][09579] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-26 16:14:39,706][09579] Adding new argument 'push_to_hub'=False that is not in the saved config file! [2023-02-26 16:14:39,707][09579] Adding new argument 'hf_repository'=None that is not in the saved config file! [2023-02-26 16:14:39,711][09579] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-26 16:14:39,712][09579] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-26 16:14:39,714][09579] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-26 16:14:39,715][09579] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-26 16:14:39,718][09579] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-26 16:14:39,743][09579] Doom resolution: 160x120, resize resolution: (128, 72) [2023-02-26 16:14:39,746][09579] RunningMeanStd input shape: (3, 72, 128) [2023-02-26 16:14:39,750][09579] RunningMeanStd input shape: (1,) [2023-02-26 16:14:39,768][09579] ConvEncoder: input_channels=3 [2023-02-26 16:14:40,419][09579] Conv encoder output size: 512 [2023-02-26 16:14:40,421][09579] Policy head output size: 512 [2023-02-26 16:14:42,803][09579] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-26 16:14:44,058][09579] Num frames 100... [2023-02-26 16:14:44,172][09579] Num frames 200... [2023-02-26 16:14:44,287][09579] Num frames 300... [2023-02-26 16:14:44,400][09579] Num frames 400... [2023-02-26 16:14:44,519][09579] Num frames 500... [2023-02-26 16:14:44,633][09579] Num frames 600... [2023-02-26 16:14:44,747][09579] Num frames 700... [2023-02-26 16:14:44,885][09579] Avg episode rewards: #0: 12.680, true rewards: #0: 7.680 [2023-02-26 16:14:44,887][09579] Avg episode reward: 12.680, avg true_objective: 7.680 [2023-02-26 16:14:44,928][09579] Num frames 800... [2023-02-26 16:14:45,039][09579] Num frames 900... [2023-02-26 16:14:45,155][09579] Num frames 1000... [2023-02-26 16:14:45,272][09579] Num frames 1100... [2023-02-26 16:14:45,418][09579] Avg episode rewards: #0: 9.420, true rewards: #0: 5.920 [2023-02-26 16:14:45,420][09579] Avg episode reward: 9.420, avg true_objective: 5.920 [2023-02-26 16:14:45,442][09579] Num frames 1200... [2023-02-26 16:14:45,558][09579] Num frames 1300... [2023-02-26 16:14:45,668][09579] Num frames 1400... [2023-02-26 16:14:45,780][09579] Num frames 1500... [2023-02-26 16:14:45,894][09579] Num frames 1600... [2023-02-26 16:14:46,007][09579] Num frames 1700... [2023-02-26 16:14:46,122][09579] Num frames 1800... [2023-02-26 16:14:46,236][09579] Num frames 1900... [2023-02-26 16:14:46,405][09579] Avg episode rewards: #0: 12.997, true rewards: #0: 6.663 [2023-02-26 16:14:46,407][09579] Avg episode reward: 12.997, avg true_objective: 6.663 [2023-02-26 16:14:46,412][09579] Num frames 2000... [2023-02-26 16:14:46,530][09579] Num frames 2100... [2023-02-26 16:14:46,656][09579] Num frames 2200... [2023-02-26 16:14:46,775][09579] Num frames 2300... [2023-02-26 16:14:46,901][09579] Num frames 2400... [2023-02-26 16:14:47,017][09579] Num frames 2500... [2023-02-26 16:14:47,140][09579] Num frames 2600... [2023-02-26 16:14:47,254][09579] Num frames 2700... [2023-02-26 16:14:47,375][09579] Num frames 2800... [2023-02-26 16:14:47,487][09579] Num frames 2900... [2023-02-26 16:14:47,600][09579] Num frames 3000... [2023-02-26 16:14:47,717][09579] Num frames 3100... [2023-02-26 16:14:47,868][09579] Num frames 3200... [2023-02-26 16:14:48,026][09579] Num frames 3300... [2023-02-26 16:14:48,204][09579] Num frames 3400... [2023-02-26 16:14:48,375][09579] Num frames 3500... [2023-02-26 16:14:48,489][09579] Avg episode rewards: #0: 18.088, true rewards: #0: 8.837 [2023-02-26 16:14:48,491][09579] Avg episode reward: 18.088, avg true_objective: 8.837 [2023-02-26 16:14:48,603][09579] Num frames 3600... [2023-02-26 16:14:48,761][09579] Num frames 3700... [2023-02-26 16:14:48,919][09579] Num frames 3800... [2023-02-26 16:14:49,078][09579] Num frames 3900... [2023-02-26 16:14:49,243][09579] Num frames 4000... [2023-02-26 16:14:49,395][09579] Num frames 4100... [2023-02-26 16:14:49,548][09579] Num frames 4200... [2023-02-26 16:14:49,709][09579] Num frames 4300... [2023-02-26 16:14:49,884][09579] Num frames 4400... [2023-02-26 16:14:50,045][09579] Num frames 4500... [2023-02-26 16:14:50,219][09579] Num frames 4600... [2023-02-26 16:14:50,387][09579] Num frames 4700... [2023-02-26 16:14:50,560][09579] Num frames 4800... [2023-02-26 16:14:50,720][09579] Num frames 4900... [2023-02-26 16:14:50,880][09579] Num frames 5000... [2023-02-26 16:14:51,041][09579] Num frames 5100... [2023-02-26 16:14:51,201][09579] Num frames 5200... [2023-02-26 16:14:51,307][09579] Avg episode rewards: #0: 21.862, true rewards: #0: 10.462 [2023-02-26 16:14:51,309][09579] Avg episode reward: 21.862, avg true_objective: 10.462 [2023-02-26 16:14:51,403][09579] Num frames 5300... [2023-02-26 16:14:51,523][09579] Num frames 5400... [2023-02-26 16:14:51,635][09579] Num frames 5500... [2023-02-26 16:14:51,753][09579] Num frames 5600... [2023-02-26 16:14:51,866][09579] Num frames 5700... [2023-02-26 16:14:51,983][09579] Num frames 5800... [2023-02-26 16:14:52,099][09579] Num frames 5900... [2023-02-26 16:14:52,227][09579] Avg episode rewards: #0: 20.445, true rewards: #0: 9.945 [2023-02-26 16:14:52,229][09579] Avg episode reward: 20.445, avg true_objective: 9.945 [2023-02-26 16:14:52,272][09579] Num frames 6000... [2023-02-26 16:14:52,391][09579] Num frames 6100... [2023-02-26 16:14:52,509][09579] Num frames 6200... [2023-02-26 16:14:52,619][09579] Num frames 6300... [2023-02-26 16:14:52,729][09579] Num frames 6400... [2023-02-26 16:14:52,843][09579] Num frames 6500... [2023-02-26 16:14:52,957][09579] Num frames 6600... [2023-02-26 16:14:53,070][09579] Num frames 6700... [2023-02-26 16:14:53,185][09579] Num frames 6800... [2023-02-26 16:14:53,308][09579] Num frames 6900... [2023-02-26 16:14:53,421][09579] Num frames 7000... [2023-02-26 16:14:53,581][09579] Avg episode rewards: #0: 20.982, true rewards: #0: 10.124 [2023-02-26 16:14:53,584][09579] Avg episode reward: 20.982, avg true_objective: 10.124 [2023-02-26 16:14:53,603][09579] Num frames 7100... [2023-02-26 16:14:53,724][09579] Num frames 7200... [2023-02-26 16:14:53,855][09579] Num frames 7300... [2023-02-26 16:14:53,970][09579] Num frames 7400... [2023-02-26 16:14:54,086][09579] Num frames 7500... [2023-02-26 16:14:54,210][09579] Num frames 7600... [2023-02-26 16:14:54,333][09579] Num frames 7700... [2023-02-26 16:14:54,449][09579] Num frames 7800... [2023-02-26 16:14:54,565][09579] Num frames 7900... [2023-02-26 16:14:54,679][09579] Num frames 8000... [2023-02-26 16:14:54,823][09579] Avg episode rewards: #0: 20.974, true rewards: #0: 10.099 [2023-02-26 16:14:54,824][09579] Avg episode reward: 20.974, avg true_objective: 10.099 [2023-02-26 16:14:54,855][09579] Num frames 8100... [2023-02-26 16:14:54,977][09579] Num frames 8200... [2023-02-26 16:14:55,096][09579] Num frames 8300... [2023-02-26 16:14:55,222][09579] Num frames 8400... [2023-02-26 16:14:55,388][09579] Avg episode rewards: #0: 19.328, true rewards: #0: 9.439 [2023-02-26 16:14:55,391][09579] Avg episode reward: 19.328, avg true_objective: 9.439 [2023-02-26 16:14:55,401][09579] Num frames 8500... [2023-02-26 16:14:55,532][09579] Num frames 8600... [2023-02-26 16:14:55,657][09579] Num frames 8700... [2023-02-26 16:14:55,780][09579] Num frames 8800... [2023-02-26 16:14:55,905][09579] Num frames 8900... [2023-02-26 16:14:56,019][09579] Num frames 9000... [2023-02-26 16:14:56,131][09579] Num frames 9100... [2023-02-26 16:14:56,298][09579] Avg episode rewards: #0: 18.799, true rewards: #0: 9.199 [2023-02-26 16:14:56,303][09579] Avg episode reward: 18.799, avg true_objective: 9.199 [2023-02-26 16:14:56,309][09579] Num frames 9200... [2023-02-26 16:15:56,052][09579] Replay video saved to /content/train_dir/default_experiment/replay.mp4! [2023-02-26 16:18:00,075][09579] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json [2023-02-26 16:18:00,077][09579] Overriding arg 'num_workers' with value 1 passed from command line [2023-02-26 16:18:00,080][09579] Adding new argument 'no_render'=True that is not in the saved config file! [2023-02-26 16:18:00,082][09579] Adding new argument 'save_video'=True that is not in the saved config file! [2023-02-26 16:18:00,084][09579] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! [2023-02-26 16:18:00,085][09579] Adding new argument 'video_name'=None that is not in the saved config file! [2023-02-26 16:18:00,086][09579] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! [2023-02-26 16:18:00,087][09579] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! [2023-02-26 16:18:00,088][09579] Adding new argument 'push_to_hub'=True that is not in the saved config file! [2023-02-26 16:18:00,089][09579] Adding new argument 'hf_repository'='iammartian0/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! [2023-02-26 16:18:00,090][09579] Adding new argument 'policy_index'=0 that is not in the saved config file! [2023-02-26 16:18:00,092][09579] Adding new argument 'eval_deterministic'=False that is not in the saved config file! [2023-02-26 16:18:00,093][09579] Adding new argument 'train_script'=None that is not in the saved config file! [2023-02-26 16:18:00,094][09579] Adding new argument 'enjoy_script'=None that is not in the saved config file! [2023-02-26 16:18:00,095][09579] Using frameskip 1 and render_action_repeat=4 for evaluation [2023-02-26 16:18:00,124][09579] RunningMeanStd input shape: (3, 72, 128) [2023-02-26 16:18:00,127][09579] RunningMeanStd input shape: (1,) [2023-02-26 16:18:00,140][09579] ConvEncoder: input_channels=3 [2023-02-26 16:18:00,177][09579] Conv encoder output size: 512 [2023-02-26 16:18:00,182][09579] Policy head output size: 512 [2023-02-26 16:18:00,202][09579] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... [2023-02-26 16:18:00,640][09579] Num frames 100... [2023-02-26 16:18:00,769][09579] Num frames 200... [2023-02-26 16:18:00,890][09579] Num frames 300... [2023-02-26 16:18:01,003][09579] Num frames 400... [2023-02-26 16:18:01,117][09579] Num frames 500... [2023-02-26 16:18:01,240][09579] Num frames 600... [2023-02-26 16:18:01,350][09579] Num frames 700... [2023-02-26 16:18:01,445][09579] Avg episode rewards: #0: 13.360, true rewards: #0: 7.360 [2023-02-26 16:18:01,447][09579] Avg episode reward: 13.360, avg true_objective: 7.360 [2023-02-26 16:18:01,528][09579] Num frames 800... [2023-02-26 16:18:01,644][09579] Num frames 900... [2023-02-26 16:18:01,763][09579] Num frames 1000... [2023-02-26 16:18:01,883][09579] Num frames 1100... [2023-02-26 16:18:02,006][09579] Num frames 1200... [2023-02-26 16:18:02,123][09579] Num frames 1300... [2023-02-26 16:18:02,240][09579] Num frames 1400... [2023-02-26 16:18:02,371][09579] Num frames 1500... [2023-02-26 16:18:02,501][09579] Num frames 1600... [2023-02-26 16:18:02,614][09579] Num frames 1700... [2023-02-26 16:18:02,735][09579] Num frames 1800... [2023-02-26 16:18:02,848][09579] Num frames 1900... [2023-02-26 16:18:02,968][09579] Num frames 2000... [2023-02-26 16:18:03,082][09579] Num frames 2100... [2023-02-26 16:18:03,199][09579] Num frames 2200... [2023-02-26 16:18:03,325][09579] Num frames 2300... [2023-02-26 16:18:03,445][09579] Num frames 2400... [2023-02-26 16:18:03,615][09579] Num frames 2500... [2023-02-26 16:18:03,779][09579] Num frames 2600... [2023-02-26 16:18:03,940][09579] Num frames 2700... [2023-02-26 16:18:04,107][09579] Num frames 2800... [2023-02-26 16:18:04,235][09579] Avg episode rewards: #0: 32.180, true rewards: #0: 14.180 [2023-02-26 16:18:04,238][09579] Avg episode reward: 32.180, avg true_objective: 14.180 [2023-02-26 16:18:04,355][09579] Num frames 2900... [2023-02-26 16:18:04,524][09579] Num frames 3000... [2023-02-26 16:18:04,687][09579] Num frames 3100... [2023-02-26 16:18:04,855][09579] Num frames 3200... [2023-02-26 16:18:05,018][09579] Num frames 3300... [2023-02-26 16:18:05,178][09579] Num frames 3400... [2023-02-26 16:18:05,343][09579] Num frames 3500... [2023-02-26 16:18:05,515][09579] Num frames 3600... [2023-02-26 16:18:05,671][09579] Num frames 3700... [2023-02-26 16:18:05,833][09579] Num frames 3800... [2023-02-26 16:18:05,948][09579] Avg episode rewards: #0: 29.093, true rewards: #0: 12.760 [2023-02-26 16:18:05,950][09579] Avg episode reward: 29.093, avg true_objective: 12.760 [2023-02-26 16:18:06,068][09579] Num frames 3900... [2023-02-26 16:18:06,233][09579] Num frames 4000... [2023-02-26 16:18:06,397][09579] Num frames 4100... [2023-02-26 16:18:06,558][09579] Num frames 4200... [2023-02-26 16:18:06,719][09579] Num frames 4300... [2023-02-26 16:18:06,888][09579] Num frames 4400... [2023-02-26 16:18:07,053][09579] Num frames 4500... [2023-02-26 16:18:07,191][09579] Num frames 4600... [2023-02-26 16:18:07,300][09579] Num frames 4700... [2023-02-26 16:18:07,439][09579] Num frames 4800... [2023-02-26 16:18:07,551][09579] Num frames 4900... [2023-02-26 16:18:07,663][09579] Num frames 5000... [2023-02-26 16:18:07,771][09579] Num frames 5100... [2023-02-26 16:18:07,891][09579] Num frames 5200... [2023-02-26 16:18:07,952][09579] Avg episode rewards: #0: 29.510, true rewards: #0: 13.010 [2023-02-26 16:18:07,954][09579] Avg episode reward: 29.510, avg true_objective: 13.010 [2023-02-26 16:18:08,073][09579] Num frames 5300... [2023-02-26 16:18:08,198][09579] Num frames 5400... [2023-02-26 16:18:08,318][09579] Num frames 5500... [2023-02-26 16:18:08,430][09579] Num frames 5600... [2023-02-26 16:18:08,547][09579] Num frames 5700... [2023-02-26 16:18:08,661][09579] Num frames 5800... [2023-02-26 16:18:08,769][09579] Num frames 5900... [2023-02-26 16:18:08,899][09579] Num frames 6000... [2023-02-26 16:18:09,021][09579] Num frames 6100... [2023-02-26 16:18:09,137][09579] Num frames 6200... [2023-02-26 16:18:09,256][09579] Num frames 6300... [2023-02-26 16:18:09,368][09579] Num frames 6400... [2023-02-26 16:18:09,485][09579] Num frames 6500... [2023-02-26 16:18:09,598][09579] Num frames 6600... [2023-02-26 16:18:09,712][09579] Num frames 6700... [2023-02-26 16:18:09,828][09579] Num frames 6800... [2023-02-26 16:18:09,956][09579] Num frames 6900... [2023-02-26 16:18:10,071][09579] Num frames 7000... [2023-02-26 16:18:10,188][09579] Num frames 7100... [2023-02-26 16:18:10,312][09579] Num frames 7200... [2023-02-26 16:18:10,426][09579] Num frames 7300... [2023-02-26 16:18:10,488][09579] Avg episode rewards: #0: 34.608, true rewards: #0: 14.608 [2023-02-26 16:18:10,489][09579] Avg episode reward: 34.608, avg true_objective: 14.608 [2023-02-26 16:18:10,613][09579] Num frames 7400... [2023-02-26 16:18:10,735][09579] Num frames 7500... [2023-02-26 16:18:10,863][09579] Num frames 7600... [2023-02-26 16:18:11,034][09579] Avg episode rewards: #0: 29.980, true rewards: #0: 12.813 [2023-02-26 16:18:11,036][09579] Avg episode reward: 29.980, avg true_objective: 12.813 [2023-02-26 16:18:11,055][09579] Num frames 7700... [2023-02-26 16:18:11,176][09579] Num frames 7800... [2023-02-26 16:18:11,289][09579] Num frames 7900... [2023-02-26 16:18:11,404][09579] Num frames 8000... [2023-02-26 16:18:11,525][09579] Num frames 8100... [2023-02-26 16:18:11,640][09579] Num frames 8200... [2023-02-26 16:18:11,756][09579] Num frames 8300... [2023-02-26 16:18:11,874][09579] Num frames 8400... [2023-02-26 16:18:12,001][09579] Avg episode rewards: #0: 27.937, true rewards: #0: 12.080 [2023-02-26 16:18:12,003][09579] Avg episode reward: 27.937, avg true_objective: 12.080 [2023-02-26 16:18:12,062][09579] Num frames 8500... [2023-02-26 16:18:12,188][09579] Num frames 8600... [2023-02-26 16:18:12,320][09579] Num frames 8700... [2023-02-26 16:18:12,447][09579] Num frames 8800... [2023-02-26 16:18:12,579][09579] Num frames 8900... [2023-02-26 16:18:12,701][09579] Num frames 9000... [2023-02-26 16:18:12,829][09579] Num frames 9100... [2023-02-26 16:18:12,958][09579] Avg episode rewards: #0: 26.321, true rewards: #0: 11.446 [2023-02-26 16:18:12,959][09579] Avg episode reward: 26.321, avg true_objective: 11.446 [2023-02-26 16:18:13,015][09579] Num frames 9200... [2023-02-26 16:18:13,137][09579] Num frames 9300... [2023-02-26 16:18:13,257][09579] Num frames 9400... [2023-02-26 16:18:13,371][09579] Num frames 9500... [2023-02-26 16:18:13,486][09579] Num frames 9600... [2023-02-26 16:18:13,608][09579] Num frames 9700... [2023-02-26 16:18:13,724][09579] Num frames 9800... [2023-02-26 16:18:13,848][09579] Num frames 9900... [2023-02-26 16:18:13,984][09579] Num frames 10000... [2023-02-26 16:18:14,121][09579] Num frames 10100... [2023-02-26 16:18:14,250][09579] Num frames 10200... [2023-02-26 16:18:14,376][09579] Num frames 10300... [2023-02-26 16:18:14,428][09579] Avg episode rewards: #0: 26.222, true rewards: #0: 11.444 [2023-02-26 16:18:14,431][09579] Avg episode reward: 26.222, avg true_objective: 11.444 [2023-02-26 16:18:14,562][09579] Num frames 10400... [2023-02-26 16:18:14,688][09579] Num frames 10500... [2023-02-26 16:18:14,810][09579] Num frames 10600... [2023-02-26 16:18:14,927][09579] Num frames 10700... [2023-02-26 16:18:15,045][09579] Num frames 10800... [2023-02-26 16:18:15,160][09579] Num frames 10900... [2023-02-26 16:18:15,285][09579] Num frames 11000... [2023-02-26 16:18:15,345][09579] Avg episode rewards: #0: 24.704, true rewards: #0: 11.004 [2023-02-26 16:18:15,348][09579] Avg episode reward: 24.704, avg true_objective: 11.004 [2023-02-26 16:19:26,442][09579] Replay video saved to /content/train_dir/default_experiment/replay.mp4!