| [2023-08-17 11:34:50,384][121125] Saving configuration to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json... | |
| [2023-08-17 11:34:50,404][121125] Rollout worker 0 uses device cpu | |
| [2023-08-17 11:34:50,404][121125] Rollout worker 1 uses device cpu | |
| [2023-08-17 11:34:50,405][121125] Rollout worker 2 uses device cpu | |
| [2023-08-17 11:34:50,405][121125] Rollout worker 3 uses device cpu | |
| [2023-08-17 11:34:50,406][121125] Rollout worker 4 uses device cpu | |
| [2023-08-17 11:34:50,406][121125] Rollout worker 5 uses device cpu | |
| [2023-08-17 11:34:50,406][121125] Rollout worker 6 uses device cpu | |
| [2023-08-17 11:34:50,406][121125] Rollout worker 7 uses device cpu | |
| [2023-08-17 11:34:50,440][121125] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 11:34:50,441][121125] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-08-17 11:34:50,458][121125] Starting all processes... | |
| [2023-08-17 11:34:50,458][121125] Starting process learner_proc0 | |
| [2023-08-17 11:34:50,508][121125] Starting all processes... | |
| [2023-08-17 11:34:50,512][121125] Starting process inference_proc0-0 | |
| [2023-08-17 11:34:50,512][121125] Starting process rollout_proc0 | |
| [2023-08-17 11:34:50,513][121125] Starting process rollout_proc1 | |
| [2023-08-17 11:34:50,514][121125] Starting process rollout_proc2 | |
| [2023-08-17 11:34:50,514][121125] Starting process rollout_proc3 | |
| [2023-08-17 11:34:50,514][121125] Starting process rollout_proc4 | |
| [2023-08-17 11:34:50,514][121125] Starting process rollout_proc5 | |
| [2023-08-17 11:34:50,514][121125] Starting process rollout_proc6 | |
| [2023-08-17 11:34:50,515][121125] Starting process rollout_proc7 | |
| [2023-08-17 11:34:51,414][121211] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 11:34:51,414][121211] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-08-17 11:34:51,424][121211] Num visible devices: 1 | |
| [2023-08-17 11:34:51,443][121211] Starting seed is not provided | |
| [2023-08-17 11:34:51,444][121211] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 11:34:51,444][121211] Initializing actor-critic model on device cuda:0 | |
| [2023-08-17 11:34:51,444][121211] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 11:34:51,445][121211] RunningMeanStd input shape: (1,) | |
| [2023-08-17 11:34:51,456][121211] ConvEncoder: input_channels=3 | |
| [2023-08-17 11:34:51,528][121211] Conv encoder output size: 512 | |
| [2023-08-17 11:34:51,528][121211] Policy head output size: 512 | |
| [2023-08-17 11:34:51,541][121211] Created Actor Critic model with architecture: | |
| [2023-08-17 11:34:51,541][121211] 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) | |
| ) | |
| ) | |
| [2023-08-17 11:34:51,559][121232] Worker 6 uses CPU cores [18, 19, 20] | |
| [2023-08-17 11:34:51,561][121228] Worker 3 uses CPU cores [9, 10, 11] | |
| [2023-08-17 11:34:51,567][121230] Worker 5 uses CPU cores [15, 16, 17] | |
| [2023-08-17 11:34:51,567][121226] Worker 0 uses CPU cores [0, 1, 2] | |
| [2023-08-17 11:34:51,573][121224] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 11:34:51,573][121224] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-08-17 11:34:51,581][121224] Num visible devices: 1 | |
| [2023-08-17 11:34:51,590][121225] Worker 1 uses CPU cores [3, 4, 5] | |
| [2023-08-17 11:34:51,593][121229] Worker 4 uses CPU cores [12, 13, 14] | |
| [2023-08-17 11:34:51,613][121231] Worker 7 uses CPU cores [21, 22, 23] | |
| [2023-08-17 11:34:51,628][121227] Worker 2 uses CPU cores [6, 7, 8] | |
| [2023-08-17 11:34:53,156][121211] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-08-17 11:34:53,157][121211] No checkpoints found | |
| [2023-08-17 11:34:53,157][121211] Did not load from checkpoint, starting from scratch! | |
| [2023-08-17 11:34:53,157][121211] Initialized policy 0 weights for model version 0 | |
| [2023-08-17 11:34:53,158][121211] LearnerWorker_p0 finished initialization! | |
| [2023-08-17 11:34:53,158][121211] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 11:34:53,455][121125] 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) | |
| [2023-08-17 11:34:53,703][121224] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 11:34:53,703][121224] RunningMeanStd input shape: (1,) | |
| [2023-08-17 11:34:53,710][121224] ConvEncoder: input_channels=3 | |
| [2023-08-17 11:34:53,760][121224] Conv encoder output size: 512 | |
| [2023-08-17 11:34:53,760][121224] Policy head output size: 512 | |
| [2023-08-17 11:34:54,313][121125] Inference worker 0-0 is ready! | |
| [2023-08-17 11:34:54,314][121125] All inference workers are ready! Signal rollout workers to start! | |
| [2023-08-17 11:34:54,329][121229] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,329][121226] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,329][121231] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,329][121232] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,330][121227] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,330][121228] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,333][121225] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,333][121230] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 11:34:54,460][121227] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process... | |
| [2023-08-17 11:34:54,461][121227] EvtLoop [rollout_proc2_evt_loop, process=rollout_proc2] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=() | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-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 "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init | |
| env_runner.init(self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init | |
| self._reset() | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-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 "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset | |
| return self.env.reset(seed=seed, options=options) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset | |
| return self.env.reset(**kwargs) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 462, in reset | |
| obs, info = self.env.reset(seed=seed, options=options) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 82, in reset | |
| obs, info = self.env.reset(**kwargs) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset | |
| return self.env.reset(seed=seed, options=options) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset | |
| return self.env.reset(**kwargs) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset | |
| self._ensure_initialized() | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized | |
| self.initialize() | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize | |
| self._game_init() | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init | |
| raise EnvCriticalError() | |
| sample_factory.envs.env_utils.EnvCriticalError | |
| [2023-08-17 11:34:54,462][121227] Unhandled exception in evt loop rollout_proc2_evt_loop | |
| [2023-08-17 11:34:54,535][121231] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,544][121226] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,548][121232] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,550][121228] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,550][121230] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,728][121231] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,746][121229] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:54,747][121228] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,747][121230] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,748][121232] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,934][121229] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,934][121226] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:54,954][121230] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:54,954][121228] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:54,955][121232] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:55,137][121226] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:55,138][121229] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:55,138][121231] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:55,138][121225] Decorrelating experience for 0 frames... | |
| [2023-08-17 11:34:55,144][121232] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,336][121225] Decorrelating experience for 32 frames... | |
| [2023-08-17 11:34:55,338][121231] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,367][121228] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,519][121225] Decorrelating experience for 64 frames... | |
| [2023-08-17 11:34:55,524][121226] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,734][121230] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,737][121229] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:55,742][121225] Decorrelating experience for 96 frames... | |
| [2023-08-17 11:34:56,232][121211] Signal inference workers to stop experience collection... | |
| [2023-08-17 11:34:56,234][121224] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-08-17 11:34:57,320][121211] Signal inference workers to resume experience collection... | |
| [2023-08-17 11:34:57,320][121224] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-08-17 11:34:58,455][121125] Fps is (10 sec: 6553.7, 60 sec: 6553.7, 300 sec: 6553.7). Total num frames: 32768. Throughput: 0: 566.8. Samples: 2834. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-08-17 11:34:58,456][121125] Avg episode reward: [(0, '3.897')] | |
| [2023-08-17 11:34:58,583][121224] Updated weights for policy 0, policy_version 10 (0.0188) | |
| [2023-08-17 11:34:59,640][121224] Updated weights for policy 0, policy_version 20 (0.0006) | |
| [2023-08-17 11:35:00,607][121224] Updated weights for policy 0, policy_version 30 (0.0005) | |
| [2023-08-17 11:35:01,567][121224] Updated weights for policy 0, policy_version 40 (0.0005) | |
| [2023-08-17 11:35:02,584][121224] Updated weights for policy 0, policy_version 50 (0.0006) | |
| [2023-08-17 11:35:03,455][121125] Fps is (10 sec: 23347.3, 60 sec: 23347.3, 300 sec: 23347.3). Total num frames: 233472. Throughput: 0: 5847.0. Samples: 58470. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-08-17 11:35:03,456][121125] Avg episode reward: [(0, '4.655')] | |
| [2023-08-17 11:35:03,457][121211] Saving new best policy, reward=4.655! | |
| [2023-08-17 11:35:03,725][121224] Updated weights for policy 0, policy_version 60 (0.0006) | |
| [2023-08-17 11:35:04,740][121224] Updated weights for policy 0, policy_version 70 (0.0006) | |
| [2023-08-17 11:35:05,714][121224] Updated weights for policy 0, policy_version 80 (0.0005) | |
| [2023-08-17 11:35:06,667][121224] Updated weights for policy 0, policy_version 90 (0.0005) | |
| [2023-08-17 11:35:07,660][121224] Updated weights for policy 0, policy_version 100 (0.0005) | |
| [2023-08-17 11:35:08,455][121125] Fps is (10 sec: 40959.9, 60 sec: 29491.3, 300 sec: 29491.3). Total num frames: 442368. Throughput: 0: 5926.0. Samples: 88890. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-08-17 11:35:08,456][121125] Avg episode reward: [(0, '4.598')] | |
| [2023-08-17 11:35:08,628][121224] Updated weights for policy 0, policy_version 110 (0.0005) | |
| [2023-08-17 11:35:09,699][121224] Updated weights for policy 0, policy_version 120 (0.0006) | |
| [2023-08-17 11:35:10,436][121125] Heartbeat connected on Batcher_0 | |
| [2023-08-17 11:35:10,438][121125] Heartbeat connected on LearnerWorker_p0 | |
| [2023-08-17 11:35:10,442][121125] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-08-17 11:35:10,444][121125] Heartbeat connected on RolloutWorker_w0 | |
| [2023-08-17 11:35:10,446][121125] Heartbeat connected on RolloutWorker_w1 | |
| [2023-08-17 11:35:10,450][121125] Heartbeat connected on RolloutWorker_w3 | |
| [2023-08-17 11:35:10,453][121125] Heartbeat connected on RolloutWorker_w4 | |
| [2023-08-17 11:35:10,455][121125] Heartbeat connected on RolloutWorker_w5 | |
| [2023-08-17 11:35:10,456][121125] Heartbeat connected on RolloutWorker_w6 | |
| [2023-08-17 11:35:10,459][121125] Heartbeat connected on RolloutWorker_w7 | |
| [2023-08-17 11:35:10,742][121224] Updated weights for policy 0, policy_version 130 (0.0005) | |
| [2023-08-17 11:35:11,789][121224] Updated weights for policy 0, policy_version 140 (0.0005) | |
| [2023-08-17 11:35:12,785][121224] Updated weights for policy 0, policy_version 150 (0.0005) | |
| [2023-08-17 11:35:13,455][121125] Fps is (10 sec: 40550.2, 60 sec: 31948.8, 300 sec: 31948.8). Total num frames: 638976. Throughput: 0: 7468.3. Samples: 149366. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0) | |
| [2023-08-17 11:35:13,456][121125] Avg episode reward: [(0, '4.646')] | |
| [2023-08-17 11:35:13,856][121224] Updated weights for policy 0, policy_version 160 (0.0007) | |
| [2023-08-17 11:35:14,953][121224] Updated weights for policy 0, policy_version 170 (0.0007) | |
| [2023-08-17 11:35:15,042][121230] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance5'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,042][121229] EvtLoop [rollout_proc4_evt_loop, process=rollout_proc4] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance4'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,043][121230] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc5_evt_loop | |
| [2023-08-17 11:35:15,043][121229] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc4_evt_loop | |
| [2023-08-17 11:35:15,042][121228] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance3'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,044][121228] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc3_evt_loop | |
| [2023-08-17 11:35:15,043][121231] EvtLoop [rollout_proc7_evt_loop, process=rollout_proc7] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance7'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,044][121231] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc7_evt_loop | |
| [2023-08-17 11:35:15,046][121232] EvtLoop [rollout_proc6_evt_loop, process=rollout_proc6] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance6'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,047][121232] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc6_evt_loop | |
| [2023-08-17 11:35:15,046][121225] EvtLoop [rollout_proc1_evt_loop, process=rollout_proc1] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance1'), args=(1, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,047][121225] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc1_evt_loop | |
| [2023-08-17 11:35:15,042][121226] EvtLoop [rollout_proc0_evt_loop, process=rollout_proc0] unhandled exception in slot='advance_rollouts' connected to emitter=Emitter(object_id='InferenceWorker_p0-w0', signal_name='advance0'), args=(0, 0) | |
| Traceback (most recent call last): | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal | |
| slot_callable(*args) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 241, in advance_rollouts | |
| complete_rollouts, episodic_stats = runner.advance_rollouts(policy_id, self.timing) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 634, in advance_rollouts | |
| new_obs, rewards, terminated, truncated, infos = e.step(actions) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 129, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 115, in step | |
| obs, rew, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 33, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step | |
| observation, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 86, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/nix/store/b84h28azn9cg3h9940zb3b3x2569sykl-python3-3.10.12-env/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step | |
| return self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 54, in step | |
| obs, reward, terminated, truncated, info = self.env.step(action) | |
| File "/home/patonw/code/learn/deep-rl-class/.mypy/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 452, in step | |
| reward = self.game.make_action(actions_flattened, self.skip_frames) | |
| vizdoom.vizdoom.SignalException: Signal SIGINT received. ViZDoom instance has been closed. | |
| [2023-08-17 11:35:15,048][121226] Unhandled exception Signal SIGINT received. ViZDoom instance has been closed. in evt loop rollout_proc0_evt_loop | |
| [2023-08-17 11:35:15,058][121125] Keyboard interrupt detected in the event loop EvtLoop [Runner_EvtLoop, process=main process 121125], exiting... | |
| [2023-08-17 11:35:15,059][121125] Runner profile tree view: | |
| main_loop: 24.6015 | |
| [2023-08-17 11:35:15,060][121211] Stopping Batcher_0... | |
| [2023-08-17 11:35:15,060][121211] Loop batcher_evt_loop terminating... | |
| [2023-08-17 11:35:15,060][121125] Collected {0: 696320}, FPS: 28303.9 | |
| [2023-08-17 11:35:15,061][121211] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000170_696320.pth... | |
| [2023-08-17 11:35:15,107][121211] Stopping LearnerWorker_p0... | |
| [2023-08-17 11:35:15,108][121211] Loop learner_proc0_evt_loop terminating... | |
| [2023-08-17 11:35:15,121][121224] Weights refcount: 2 0 | |
| [2023-08-17 11:35:15,123][121224] Stopping InferenceWorker_p0-w0... | |
| [2023-08-17 11:35:15,123][121224] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-08-17 12:08:48,041][131794] Saving configuration to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json... | |
| [2023-08-17 12:08:48,053][131794] Rollout worker 0 uses device cpu | |
| [2023-08-17 12:08:48,054][131794] Rollout worker 1 uses device cpu | |
| [2023-08-17 12:08:48,054][131794] Rollout worker 2 uses device cpu | |
| [2023-08-17 12:08:48,055][131794] Rollout worker 3 uses device cpu | |
| [2023-08-17 12:08:48,055][131794] Rollout worker 4 uses device cpu | |
| [2023-08-17 12:08:48,055][131794] Rollout worker 5 uses device cpu | |
| [2023-08-17 12:08:48,056][131794] Rollout worker 6 uses device cpu | |
| [2023-08-17 12:08:48,056][131794] Rollout worker 7 uses device cpu | |
| [2023-08-17 12:08:48,086][131794] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 12:08:48,087][131794] InferenceWorker_p0-w0: min num requests: 2 | |
| [2023-08-17 12:08:48,104][131794] Starting all processes... | |
| [2023-08-17 12:08:48,105][131794] Starting process learner_proc0 | |
| [2023-08-17 12:08:48,154][131794] Starting all processes... | |
| [2023-08-17 12:08:48,158][131794] Starting process inference_proc0-0 | |
| [2023-08-17 12:08:48,158][131794] Starting process rollout_proc0 | |
| [2023-08-17 12:08:48,158][131794] Starting process rollout_proc1 | |
| [2023-08-17 12:08:48,159][131794] Starting process rollout_proc2 | |
| [2023-08-17 12:08:48,159][131794] Starting process rollout_proc3 | |
| [2023-08-17 12:08:48,160][131794] Starting process rollout_proc4 | |
| [2023-08-17 12:08:48,161][131794] Starting process rollout_proc5 | |
| [2023-08-17 12:08:48,162][131794] Starting process rollout_proc6 | |
| [2023-08-17 12:08:48,162][131794] Starting process rollout_proc7 | |
| [2023-08-17 12:08:49,071][131864] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 12:08:49,071][131864] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0 | |
| [2023-08-17 12:08:49,082][131864] Num visible devices: 1 | |
| [2023-08-17 12:08:49,101][131864] Starting seed is not provided | |
| [2023-08-17 12:08:49,102][131864] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 12:08:49,102][131864] Initializing actor-critic model on device cuda:0 | |
| [2023-08-17 12:08:49,102][131864] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 12:08:49,102][131864] RunningMeanStd input shape: (1,) | |
| [2023-08-17 12:08:49,111][131864] ConvEncoder: input_channels=3 | |
| [2023-08-17 12:08:49,128][131877] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 12:08:49,128][131877] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0 | |
| [2023-08-17 12:08:49,131][131877] Num visible devices: 1 | |
| [2023-08-17 12:08:49,176][131864] Conv encoder output size: 512 | |
| [2023-08-17 12:08:49,176][131864] Policy head output size: 512 | |
| [2023-08-17 12:08:49,183][131864] Created Actor Critic model with architecture: | |
| [2023-08-17 12:08:49,183][131864] 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) | |
| ) | |
| ) | |
| [2023-08-17 12:08:49,230][131885] Worker 7 uses CPU cores [21, 22, 23] | |
| [2023-08-17 12:08:49,237][131880] Worker 2 uses CPU cores [6, 7, 8] | |
| [2023-08-17 12:08:49,239][131884] Worker 6 uses CPU cores [18, 19, 20] | |
| [2023-08-17 12:08:49,240][131879] Worker 0 uses CPU cores [0, 1, 2] | |
| [2023-08-17 12:08:49,241][131883] Worker 5 uses CPU cores [15, 16, 17] | |
| [2023-08-17 12:08:49,242][131881] Worker 3 uses CPU cores [9, 10, 11] | |
| [2023-08-17 12:08:49,247][131882] Worker 4 uses CPU cores [12, 13, 14] | |
| [2023-08-17 12:08:49,280][131878] Worker 1 uses CPU cores [3, 4, 5] | |
| [2023-08-17 12:08:50,303][131864] Using optimizer <class 'torch.optim.adam.Adam'> | |
| [2023-08-17 12:08:50,303][131864] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000170_696320.pth... | |
| [2023-08-17 12:08:50,319][131864] Loading model from checkpoint | |
| [2023-08-17 12:08:50,321][131864] Loaded experiment state at self.train_step=170, self.env_steps=696320 | |
| [2023-08-17 12:08:50,322][131864] Initialized policy 0 weights for model version 170 | |
| [2023-08-17 12:08:50,322][131864] LearnerWorker_p0 finished initialization! | |
| [2023-08-17 12:08:50,323][131864] Using GPUs [0] for process 0 (actually maps to GPUs [0]) | |
| [2023-08-17 12:08:50,883][131877] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 12:08:50,883][131877] RunningMeanStd input shape: (1,) | |
| [2023-08-17 12:08:50,890][131877] ConvEncoder: input_channels=3 | |
| [2023-08-17 12:08:50,941][131877] Conv encoder output size: 512 | |
| [2023-08-17 12:08:50,941][131877] Policy head output size: 512 | |
| [2023-08-17 12:08:51,065][131794] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 696320. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0) | |
| [2023-08-17 12:08:51,490][131794] Inference worker 0-0 is ready! | |
| [2023-08-17 12:08:51,491][131794] All inference workers are ready! Signal rollout workers to start! | |
| [2023-08-17 12:08:51,506][131880] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,506][131884] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,506][131881] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,506][131885] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,508][131879] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,508][131878] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,508][131882] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,508][131883] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:08:51,714][131885] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,715][131883] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,715][131882] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,720][131881] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,735][131884] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,743][131880] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,900][131882] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:51,906][131885] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:51,906][131881] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:51,910][131878] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:51,920][131884] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:51,931][131880] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:51,956][131883] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:52,104][131878] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:52,108][131882] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,116][131879] Decorrelating experience for 0 frames... | |
| [2023-08-17 12:08:52,124][131881] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,131][131884] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,182][131880] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,299][131878] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,301][131879] Decorrelating experience for 32 frames... | |
| [2023-08-17 12:08:52,315][131885] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,441][131882] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,485][131884] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,502][131878] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,530][131879] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,680][131881] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,728][131883] Decorrelating experience for 64 frames... | |
| [2023-08-17 12:08:52,732][131885] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,869][131879] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,919][131883] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:52,923][131880] Decorrelating experience for 96 frames... | |
| [2023-08-17 12:08:53,218][131864] Signal inference workers to stop experience collection... | |
| [2023-08-17 12:08:53,246][131877] InferenceWorker_p0-w0: stopping experience collection | |
| [2023-08-17 12:08:54,097][131864] Signal inference workers to resume experience collection... | |
| [2023-08-17 12:08:54,097][131877] InferenceWorker_p0-w0: resuming experience collection | |
| [2023-08-17 12:08:55,323][131877] Updated weights for policy 0, policy_version 180 (0.0180) | |
| [2023-08-17 12:08:56,065][131794] Fps is (10 sec: 13926.5, 60 sec: 13926.5, 300 sec: 13926.5). Total num frames: 765952. Throughput: 0: 662.8. Samples: 3314. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0) | |
| [2023-08-17 12:08:56,066][131794] Avg episode reward: [(0, '4.760')] | |
| [2023-08-17 12:08:56,070][131864] Saving new best policy, reward=4.760! | |
| [2023-08-17 12:08:56,305][131877] Updated weights for policy 0, policy_version 190 (0.0006) | |
| [2023-08-17 12:08:57,286][131877] Updated weights for policy 0, policy_version 200 (0.0006) | |
| [2023-08-17 12:08:58,252][131877] Updated weights for policy 0, policy_version 210 (0.0007) | |
| [2023-08-17 12:08:59,223][131877] Updated weights for policy 0, policy_version 220 (0.0006) | |
| [2023-08-17 12:09:00,213][131877] Updated weights for policy 0, policy_version 230 (0.0006) | |
| [2023-08-17 12:09:01,065][131794] Fps is (10 sec: 27853.0, 60 sec: 27853.0, 300 sec: 27853.0). Total num frames: 974848. Throughput: 0: 6506.0. Samples: 65060. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:01,067][131794] Avg episode reward: [(0, '4.894')] | |
| [2023-08-17 12:09:01,068][131864] Saving new best policy, reward=4.894! | |
| [2023-08-17 12:09:01,199][131877] Updated weights for policy 0, policy_version 240 (0.0006) | |
| [2023-08-17 12:09:02,167][131877] Updated weights for policy 0, policy_version 250 (0.0006) | |
| [2023-08-17 12:09:03,131][131877] Updated weights for policy 0, policy_version 260 (0.0006) | |
| [2023-08-17 12:09:04,168][131877] Updated weights for policy 0, policy_version 270 (0.0007) | |
| [2023-08-17 12:09:05,171][131877] Updated weights for policy 0, policy_version 280 (0.0007) | |
| [2023-08-17 12:09:06,065][131794] Fps is (10 sec: 41779.5, 60 sec: 32495.2, 300 sec: 32495.2). Total num frames: 1183744. Throughput: 0: 6420.3. Samples: 96304. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0) | |
| [2023-08-17 12:09:06,066][131794] Avg episode reward: [(0, '5.072')] | |
| [2023-08-17 12:09:06,069][131864] Saving new best policy, reward=5.072! | |
| [2023-08-17 12:09:06,158][131877] Updated weights for policy 0, policy_version 290 (0.0007) | |
| [2023-08-17 12:09:07,207][131877] Updated weights for policy 0, policy_version 300 (0.0006) | |
| [2023-08-17 12:09:08,081][131794] Heartbeat connected on Batcher_0 | |
| [2023-08-17 12:09:08,084][131794] Heartbeat connected on LearnerWorker_p0 | |
| [2023-08-17 12:09:08,089][131794] Heartbeat connected on InferenceWorker_p0-w0 | |
| [2023-08-17 12:09:08,090][131794] Heartbeat connected on RolloutWorker_w0 | |
| [2023-08-17 12:09:08,093][131794] Heartbeat connected on RolloutWorker_w1 | |
| [2023-08-17 12:09:08,094][131794] Heartbeat connected on RolloutWorker_w2 | |
| [2023-08-17 12:09:08,097][131794] Heartbeat connected on RolloutWorker_w3 | |
| [2023-08-17 12:09:08,098][131794] Heartbeat connected on RolloutWorker_w4 | |
| [2023-08-17 12:09:08,102][131794] Heartbeat connected on RolloutWorker_w5 | |
| [2023-08-17 12:09:08,102][131794] Heartbeat connected on RolloutWorker_w6 | |
| [2023-08-17 12:09:08,105][131794] Heartbeat connected on RolloutWorker_w7 | |
| [2023-08-17 12:09:08,269][131877] Updated weights for policy 0, policy_version 310 (0.0007) | |
| [2023-08-17 12:09:09,317][131877] Updated weights for policy 0, policy_version 320 (0.0007) | |
| [2023-08-17 12:09:10,353][131877] Updated weights for policy 0, policy_version 330 (0.0006) | |
| [2023-08-17 12:09:11,065][131794] Fps is (10 sec: 40140.7, 60 sec: 33996.9, 300 sec: 33996.9). Total num frames: 1376256. Throughput: 0: 7819.2. Samples: 156384. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-08-17 12:09:11,066][131794] Avg episode reward: [(0, '5.895')] | |
| [2023-08-17 12:09:11,067][131864] Saving new best policy, reward=5.895! | |
| [2023-08-17 12:09:11,382][131877] Updated weights for policy 0, policy_version 340 (0.0006) | |
| [2023-08-17 12:09:12,356][131877] Updated weights for policy 0, policy_version 350 (0.0007) | |
| [2023-08-17 12:09:13,358][131877] Updated weights for policy 0, policy_version 360 (0.0006) | |
| [2023-08-17 12:09:14,367][131877] Updated weights for policy 0, policy_version 370 (0.0006) | |
| [2023-08-17 12:09:15,414][131877] Updated weights for policy 0, policy_version 380 (0.0006) | |
| [2023-08-17 12:09:16,065][131794] Fps is (10 sec: 39731.1, 60 sec: 35389.6, 300 sec: 35389.6). Total num frames: 1581056. Throughput: 0: 8668.8. Samples: 216718. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-08-17 12:09:16,066][131794] Avg episode reward: [(0, '5.889')] | |
| [2023-08-17 12:09:16,442][131877] Updated weights for policy 0, policy_version 390 (0.0006) | |
| [2023-08-17 12:09:17,456][131877] Updated weights for policy 0, policy_version 400 (0.0006) | |
| [2023-08-17 12:09:18,507][131877] Updated weights for policy 0, policy_version 410 (0.0006) | |
| [2023-08-17 12:09:19,530][131877] Updated weights for policy 0, policy_version 420 (0.0007) | |
| [2023-08-17 12:09:20,560][131877] Updated weights for policy 0, policy_version 430 (0.0007) | |
| [2023-08-17 12:09:21,065][131794] Fps is (10 sec: 40550.8, 60 sec: 36181.5, 300 sec: 36181.5). Total num frames: 1781760. Throughput: 0: 8212.2. Samples: 246364. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:21,066][131794] Avg episode reward: [(0, '6.038')] | |
| [2023-08-17 12:09:21,066][131864] Saving new best policy, reward=6.038! | |
| [2023-08-17 12:09:21,554][131877] Updated weights for policy 0, policy_version 440 (0.0006) | |
| [2023-08-17 12:09:22,574][131877] Updated weights for policy 0, policy_version 450 (0.0007) | |
| [2023-08-17 12:09:23,579][131877] Updated weights for policy 0, policy_version 460 (0.0006) | |
| [2023-08-17 12:09:24,534][131877] Updated weights for policy 0, policy_version 470 (0.0006) | |
| [2023-08-17 12:09:25,469][131877] Updated weights for policy 0, policy_version 480 (0.0006) | |
| [2023-08-17 12:09:26,065][131794] Fps is (10 sec: 40960.0, 60 sec: 36981.1, 300 sec: 36981.1). Total num frames: 1990656. Throughput: 0: 8786.5. Samples: 307528. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:26,066][131794] Avg episode reward: [(0, '8.814')] | |
| [2023-08-17 12:09:26,068][131864] Saving new best policy, reward=8.814! | |
| [2023-08-17 12:09:26,467][131877] Updated weights for policy 0, policy_version 490 (0.0007) | |
| [2023-08-17 12:09:27,472][131877] Updated weights for policy 0, policy_version 500 (0.0007) | |
| [2023-08-17 12:09:28,481][131877] Updated weights for policy 0, policy_version 510 (0.0006) | |
| [2023-08-17 12:09:29,497][131877] Updated weights for policy 0, policy_version 520 (0.0006) | |
| [2023-08-17 12:09:30,455][131877] Updated weights for policy 0, policy_version 530 (0.0007) | |
| [2023-08-17 12:09:31,065][131794] Fps is (10 sec: 40959.8, 60 sec: 37376.1, 300 sec: 37376.1). Total num frames: 2191360. Throughput: 0: 9247.0. Samples: 369878. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-08-17 12:09:31,066][131794] Avg episode reward: [(0, '10.505')] | |
| [2023-08-17 12:09:31,067][131864] Saving new best policy, reward=10.505! | |
| [2023-08-17 12:09:31,504][131877] Updated weights for policy 0, policy_version 540 (0.0006) | |
| [2023-08-17 12:09:32,471][131877] Updated weights for policy 0, policy_version 550 (0.0006) | |
| [2023-08-17 12:09:33,439][131877] Updated weights for policy 0, policy_version 560 (0.0006) | |
| [2023-08-17 12:09:34,495][131877] Updated weights for policy 0, policy_version 570 (0.0007) | |
| [2023-08-17 12:09:35,483][131877] Updated weights for policy 0, policy_version 580 (0.0006) | |
| [2023-08-17 12:09:36,065][131794] Fps is (10 sec: 40550.4, 60 sec: 37774.3, 300 sec: 37774.3). Total num frames: 2396160. Throughput: 0: 8903.2. Samples: 400642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0) | |
| [2023-08-17 12:09:36,066][131794] Avg episode reward: [(0, '13.981')] | |
| [2023-08-17 12:09:36,069][131864] Saving new best policy, reward=13.981! | |
| [2023-08-17 12:09:36,506][131877] Updated weights for policy 0, policy_version 590 (0.0007) | |
| [2023-08-17 12:09:37,541][131877] Updated weights for policy 0, policy_version 600 (0.0006) | |
| [2023-08-17 12:09:38,535][131877] Updated weights for policy 0, policy_version 610 (0.0007) | |
| [2023-08-17 12:09:39,574][131877] Updated weights for policy 0, policy_version 620 (0.0006) | |
| [2023-08-17 12:09:40,629][131877] Updated weights for policy 0, policy_version 630 (0.0007) | |
| [2023-08-17 12:09:41,065][131794] Fps is (10 sec: 40550.4, 60 sec: 38010.9, 300 sec: 38010.9). Total num frames: 2596864. Throughput: 0: 10165.2. Samples: 460746. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:41,066][131794] Avg episode reward: [(0, '16.720')] | |
| [2023-08-17 12:09:41,067][131864] Saving new best policy, reward=16.720! | |
| [2023-08-17 12:09:41,662][131877] Updated weights for policy 0, policy_version 640 (0.0006) | |
| [2023-08-17 12:09:42,705][131877] Updated weights for policy 0, policy_version 650 (0.0007) | |
| [2023-08-17 12:09:43,682][131877] Updated weights for policy 0, policy_version 660 (0.0006) | |
| [2023-08-17 12:09:44,707][131877] Updated weights for policy 0, policy_version 670 (0.0007) | |
| [2023-08-17 12:09:45,654][131877] Updated weights for policy 0, policy_version 680 (0.0006) | |
| [2023-08-17 12:09:46,065][131794] Fps is (10 sec: 40550.4, 60 sec: 38279.1, 300 sec: 38279.1). Total num frames: 2801664. Throughput: 0: 10135.5. Samples: 521158. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0) | |
| [2023-08-17 12:09:46,066][131794] Avg episode reward: [(0, '15.224')] | |
| [2023-08-17 12:09:46,644][131877] Updated weights for policy 0, policy_version 690 (0.0006) | |
| [2023-08-17 12:09:47,596][131877] Updated weights for policy 0, policy_version 700 (0.0006) | |
| [2023-08-17 12:09:48,566][131877] Updated weights for policy 0, policy_version 710 (0.0006) | |
| [2023-08-17 12:09:49,544][131877] Updated weights for policy 0, policy_version 720 (0.0006) | |
| [2023-08-17 12:09:50,566][131877] Updated weights for policy 0, policy_version 730 (0.0007) | |
| [2023-08-17 12:09:51,065][131794] Fps is (10 sec: 41369.5, 60 sec: 38570.7, 300 sec: 38570.7). Total num frames: 3010560. Throughput: 0: 10141.9. Samples: 552690. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:51,066][131794] Avg episode reward: [(0, '16.889')] | |
| [2023-08-17 12:09:51,067][131864] Saving new best policy, reward=16.889! | |
| [2023-08-17 12:09:51,497][131877] Updated weights for policy 0, policy_version 740 (0.0006) | |
| [2023-08-17 12:09:52,458][131877] Updated weights for policy 0, policy_version 750 (0.0006) | |
| [2023-08-17 12:09:53,420][131877] Updated weights for policy 0, policy_version 760 (0.0006) | |
| [2023-08-17 12:09:54,449][131877] Updated weights for policy 0, policy_version 770 (0.0007) | |
| [2023-08-17 12:09:55,425][131877] Updated weights for policy 0, policy_version 780 (0.0007) | |
| [2023-08-17 12:09:56,065][131794] Fps is (10 sec: 41779.2, 60 sec: 40891.8, 300 sec: 38817.5). Total num frames: 3219456. Throughput: 0: 10201.7. Samples: 615458. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:09:56,066][131794] Avg episode reward: [(0, '18.774')] | |
| [2023-08-17 12:09:56,069][131864] Saving new best policy, reward=18.774! | |
| [2023-08-17 12:09:56,434][131877] Updated weights for policy 0, policy_version 790 (0.0006) | |
| [2023-08-17 12:09:57,381][131877] Updated weights for policy 0, policy_version 800 (0.0007) | |
| [2023-08-17 12:09:58,323][131877] Updated weights for policy 0, policy_version 810 (0.0006) | |
| [2023-08-17 12:09:59,287][131877] Updated weights for policy 0, policy_version 820 (0.0006) | |
| [2023-08-17 12:10:00,214][131877] Updated weights for policy 0, policy_version 830 (0.0006) | |
| [2023-08-17 12:10:01,065][131794] Fps is (10 sec: 42188.9, 60 sec: 40960.0, 300 sec: 39087.6). Total num frames: 3432448. Throughput: 0: 10286.3. Samples: 679604. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:10:01,066][131794] Avg episode reward: [(0, '21.885')] | |
| [2023-08-17 12:10:01,067][131864] Saving new best policy, reward=21.885! | |
| [2023-08-17 12:10:01,201][131877] Updated weights for policy 0, policy_version 840 (0.0006) | |
| [2023-08-17 12:10:02,187][131877] Updated weights for policy 0, policy_version 850 (0.0006) | |
| [2023-08-17 12:10:03,190][131877] Updated weights for policy 0, policy_version 860 (0.0007) | |
| [2023-08-17 12:10:04,150][131877] Updated weights for policy 0, policy_version 870 (0.0006) | |
| [2023-08-17 12:10:05,158][131877] Updated weights for policy 0, policy_version 880 (0.0006) | |
| [2023-08-17 12:10:06,065][131794] Fps is (10 sec: 41779.0, 60 sec: 40891.7, 300 sec: 39212.4). Total num frames: 3637248. Throughput: 0: 10318.1. Samples: 710680. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0) | |
| [2023-08-17 12:10:06,066][131794] Avg episode reward: [(0, '19.364')] | |
| [2023-08-17 12:10:06,176][131877] Updated weights for policy 0, policy_version 890 (0.0007) | |
| [2023-08-17 12:10:07,147][131877] Updated weights for policy 0, policy_version 900 (0.0006) | |
| [2023-08-17 12:10:08,101][131877] Updated weights for policy 0, policy_version 910 (0.0007) | |
| [2023-08-17 12:10:09,146][131877] Updated weights for policy 0, policy_version 920 (0.0007) | |
| [2023-08-17 12:10:10,146][131877] Updated weights for policy 0, policy_version 930 (0.0006) | |
| [2023-08-17 12:10:11,065][131794] Fps is (10 sec: 41369.6, 60 sec: 41164.8, 300 sec: 39372.8). Total num frames: 3846144. Throughput: 0: 10327.7. Samples: 772274. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0) | |
| [2023-08-17 12:10:11,066][131794] Avg episode reward: [(0, '19.007')] | |
| [2023-08-17 12:10:11,109][131877] Updated weights for policy 0, policy_version 940 (0.0006) | |
| [2023-08-17 12:10:12,081][131877] Updated weights for policy 0, policy_version 950 (0.0007) | |
| [2023-08-17 12:10:13,110][131877] Updated weights for policy 0, policy_version 960 (0.0007) | |
| [2023-08-17 12:10:14,089][131877] Updated weights for policy 0, policy_version 970 (0.0006) | |
| [2023-08-17 12:10:14,877][131864] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-08-17 12:10:14,877][131794] Component Batcher_0 stopped! | |
| [2023-08-17 12:10:14,877][131864] Stopping Batcher_0... | |
| [2023-08-17 12:10:14,889][131864] Loop batcher_evt_loop terminating... | |
| [2023-08-17 12:10:14,890][131877] Weights refcount: 2 0 | |
| [2023-08-17 12:10:14,891][131877] Stopping InferenceWorker_p0-w0... | |
| [2023-08-17 12:10:14,891][131877] Loop inference_proc0-0_evt_loop terminating... | |
| [2023-08-17 12:10:14,891][131794] Component InferenceWorker_p0-w0 stopped! | |
| [2023-08-17 12:10:14,910][131864] Saving /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-08-17 12:10:14,930][131881] Stopping RolloutWorker_w3... | |
| [2023-08-17 12:10:14,930][131881] Loop rollout_proc3_evt_loop terminating... | |
| [2023-08-17 12:10:14,930][131794] Component RolloutWorker_w3 stopped! | |
| [2023-08-17 12:10:14,935][131882] Stopping RolloutWorker_w4... | |
| [2023-08-17 12:10:14,935][131878] Stopping RolloutWorker_w1... | |
| [2023-08-17 12:10:14,935][131878] Loop rollout_proc1_evt_loop terminating... | |
| [2023-08-17 12:10:14,935][131882] Loop rollout_proc4_evt_loop terminating... | |
| [2023-08-17 12:10:14,935][131794] Component RolloutWorker_w4 stopped! | |
| [2023-08-17 12:10:14,936][131884] Stopping RolloutWorker_w6... | |
| [2023-08-17 12:10:14,936][131794] Component RolloutWorker_w1 stopped! | |
| [2023-08-17 12:10:14,936][131884] Loop rollout_proc6_evt_loop terminating... | |
| [2023-08-17 12:10:14,936][131794] Component RolloutWorker_w6 stopped! | |
| [2023-08-17 12:10:14,938][131879] Stopping RolloutWorker_w0... | |
| [2023-08-17 12:10:14,938][131879] Loop rollout_proc0_evt_loop terminating... | |
| [2023-08-17 12:10:14,938][131794] Component RolloutWorker_w0 stopped! | |
| [2023-08-17 12:10:14,940][131883] Stopping RolloutWorker_w5... | |
| [2023-08-17 12:10:14,940][131794] Component RolloutWorker_w5 stopped! | |
| [2023-08-17 12:10:14,940][131883] Loop rollout_proc5_evt_loop terminating... | |
| [2023-08-17 12:10:14,940][131885] Stopping RolloutWorker_w7... | |
| [2023-08-17 12:10:14,940][131885] Loop rollout_proc7_evt_loop terminating... | |
| [2023-08-17 12:10:14,940][131794] Component RolloutWorker_w7 stopped! | |
| [2023-08-17 12:10:14,963][131880] Stopping RolloutWorker_w2... | |
| [2023-08-17 12:10:14,963][131880] Loop rollout_proc2_evt_loop terminating... | |
| [2023-08-17 12:10:14,963][131794] Component RolloutWorker_w2 stopped! | |
| [2023-08-17 12:10:14,973][131864] Stopping LearnerWorker_p0... | |
| [2023-08-17 12:10:14,974][131864] Loop learner_proc0_evt_loop terminating... | |
| [2023-08-17 12:10:14,974][131794] Component LearnerWorker_p0 stopped! | |
| [2023-08-17 12:10:14,975][131794] Waiting for process learner_proc0 to stop... | |
| [2023-08-17 12:10:15,620][131794] Waiting for process inference_proc0-0 to join... | |
| [2023-08-17 12:10:15,620][131794] Waiting for process rollout_proc0 to join... | |
| [2023-08-17 12:10:15,629][131794] Waiting for process rollout_proc1 to join... | |
| [2023-08-17 12:10:15,630][131794] Waiting for process rollout_proc2 to join... | |
| [2023-08-17 12:10:15,630][131794] Waiting for process rollout_proc3 to join... | |
| [2023-08-17 12:10:15,631][131794] Waiting for process rollout_proc4 to join... | |
| [2023-08-17 12:10:15,632][131794] Waiting for process rollout_proc5 to join... | |
| [2023-08-17 12:10:15,632][131794] Waiting for process rollout_proc6 to join... | |
| [2023-08-17 12:10:15,633][131794] Waiting for process rollout_proc7 to join... | |
| [2023-08-17 12:10:15,633][131794] Batcher 0 profile tree view: | |
| batching: 6.7047, releasing_batches: 0.0087 | |
| [2023-08-17 12:10:15,634][131794] InferenceWorker_p0-w0 profile tree view: | |
| wait_policy: 0.0000 | |
| wait_policy_total: 2.0680 | |
| update_model: 1.3116 | |
| weight_update: 0.0007 | |
| one_step: 0.0012 | |
| handle_policy_step: 74.7597 | |
| deserialize: 3.1557, stack: 0.3403, obs_to_device_normalize: 17.0704, forward: 37.2802, send_messages: 4.8157 | |
| prepare_outputs: 8.7975 | |
| to_cpu: 5.6577 | |
| [2023-08-17 12:10:15,634][131794] Learner 0 profile tree view: | |
| misc: 0.0028, prepare_batch: 4.0784 | |
| train: 9.7538 | |
| epoch_init: 0.0026, minibatch_init: 0.0026, losses_postprocess: 0.2418, kl_divergence: 0.1909, after_optimizer: 0.2499 | |
| calculate_losses: 3.4695 | |
| losses_init: 0.0014, forward_head: 0.2537, bptt_initial: 2.0322, tail: 0.2342, advantages_returns: 0.0568, losses: 0.4473 | |
| bptt: 0.3786 | |
| bptt_forward_core: 0.3600 | |
| update: 5.4474 | |
| clip: 2.7340 | |
| [2023-08-17 12:10:15,635][131794] RolloutWorker_w0 profile tree view: | |
| wait_for_trajectories: 0.0615, enqueue_policy_requests: 2.6644, env_step: 37.2031, overhead: 3.5782, complete_rollouts: 0.0881 | |
| save_policy_outputs: 3.6697 | |
| split_output_tensors: 1.7077 | |
| [2023-08-17 12:10:15,635][131794] RolloutWorker_w7 profile tree view: | |
| wait_for_trajectories: 0.0601, enqueue_policy_requests: 2.6081, env_step: 35.6438, overhead: 3.4090, complete_rollouts: 0.0854 | |
| save_policy_outputs: 3.4689 | |
| split_output_tensors: 1.6294 | |
| [2023-08-17 12:10:15,636][131794] Loop Runner_EvtLoop terminating... | |
| [2023-08-17 12:10:15,637][131794] Runner profile tree view: | |
| main_loop: 87.5323 | |
| [2023-08-17 12:10:15,637][131794] Collected {0: 4005888}, FPS: 37809.7 | |
| [2023-08-17 12:11:06,264][131794] Loading existing experiment configuration from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json | |
| [2023-08-17 12:11:06,264][131794] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-08-17 12:11:06,265][131794] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-08-17 12:11:06,265][131794] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-08-17 12:11:06,265][131794] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-08-17 12:11:06,266][131794] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-08-17 12:11:06,266][131794] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-08-17 12:11:06,266][131794] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-08-17 12:11:06,266][131794] Adding new argument 'push_to_hub'=False that is not in the saved config file! | |
| [2023-08-17 12:11:06,267][131794] Adding new argument 'hf_repository'=None that is not in the saved config file! | |
| [2023-08-17 12:11:06,267][131794] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-08-17 12:11:06,267][131794] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-08-17 12:11:06,268][131794] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-08-17 12:11:06,268][131794] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-08-17 12:11:06,268][131794] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-08-17 12:11:06,274][131794] Doom resolution: 160x120, resize resolution: (128, 72) | |
| [2023-08-17 12:11:06,275][131794] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 12:11:06,275][131794] RunningMeanStd input shape: (1,) | |
| [2023-08-17 12:11:06,283][131794] ConvEncoder: input_channels=3 | |
| [2023-08-17 12:11:06,348][131794] Conv encoder output size: 512 | |
| [2023-08-17 12:11:06,349][131794] Policy head output size: 512 | |
| [2023-08-17 12:11:07,473][131794] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-08-17 12:11:08,166][131794] Num frames 100... | |
| [2023-08-17 12:11:08,225][131794] Num frames 200... | |
| [2023-08-17 12:11:08,283][131794] Num frames 300... | |
| [2023-08-17 12:11:08,341][131794] Num frames 400... | |
| [2023-08-17 12:11:08,400][131794] Num frames 500... | |
| [2023-08-17 12:11:08,457][131794] Num frames 600... | |
| [2023-08-17 12:11:08,516][131794] Num frames 700... | |
| [2023-08-17 12:11:08,574][131794] Num frames 800... | |
| [2023-08-17 12:11:08,632][131794] Num frames 900... | |
| [2023-08-17 12:11:08,694][131794] Num frames 1000... | |
| [2023-08-17 12:11:08,753][131794] Num frames 1100... | |
| [2023-08-17 12:11:08,811][131794] Num frames 1200... | |
| [2023-08-17 12:11:08,869][131794] Num frames 1300... | |
| [2023-08-17 12:11:08,928][131794] Num frames 1400... | |
| [2023-08-17 12:11:09,003][131794] Avg episode rewards: #0: 31.400, true rewards: #0: 14.400 | |
| [2023-08-17 12:11:09,004][131794] Avg episode reward: 31.400, avg true_objective: 14.400 | |
| [2023-08-17 12:11:09,040][131794] Num frames 1500... | |
| [2023-08-17 12:11:09,097][131794] Num frames 1600... | |
| [2023-08-17 12:11:09,154][131794] Num frames 1700... | |
| [2023-08-17 12:11:09,212][131794] Num frames 1800... | |
| [2023-08-17 12:11:09,297][131794] Avg episode rewards: #0: 18.780, true rewards: #0: 9.280 | |
| [2023-08-17 12:11:09,298][131794] Avg episode reward: 18.780, avg true_objective: 9.280 | |
| [2023-08-17 12:11:09,323][131794] Num frames 1900... | |
| [2023-08-17 12:11:09,382][131794] Num frames 2000... | |
| [2023-08-17 12:11:09,439][131794] Num frames 2100... | |
| [2023-08-17 12:11:09,498][131794] Num frames 2200... | |
| [2023-08-17 12:11:09,574][131794] Avg episode rewards: #0: 14.467, true rewards: #0: 7.467 | |
| [2023-08-17 12:11:09,574][131794] Avg episode reward: 14.467, avg true_objective: 7.467 | |
| [2023-08-17 12:11:09,610][131794] Num frames 2300... | |
| [2023-08-17 12:11:09,670][131794] Num frames 2400... | |
| [2023-08-17 12:11:09,729][131794] Num frames 2500... | |
| [2023-08-17 12:11:09,789][131794] Num frames 2600... | |
| [2023-08-17 12:11:09,847][131794] Num frames 2700... | |
| [2023-08-17 12:11:09,906][131794] Num frames 2800... | |
| [2023-08-17 12:11:09,963][131794] Num frames 2900... | |
| [2023-08-17 12:11:10,021][131794] Num frames 3000... | |
| [2023-08-17 12:11:10,079][131794] Num frames 3100... | |
| [2023-08-17 12:11:10,138][131794] Num frames 3200... | |
| [2023-08-17 12:11:10,200][131794] Num frames 3300... | |
| [2023-08-17 12:11:10,259][131794] Num frames 3400... | |
| [2023-08-17 12:11:10,317][131794] Num frames 3500... | |
| [2023-08-17 12:11:10,375][131794] Num frames 3600... | |
| [2023-08-17 12:11:10,433][131794] Num frames 3700... | |
| [2023-08-17 12:11:10,492][131794] Num frames 3800... | |
| [2023-08-17 12:11:10,550][131794] Num frames 3900... | |
| [2023-08-17 12:11:10,610][131794] Num frames 4000... | |
| [2023-08-17 12:11:10,668][131794] Num frames 4100... | |
| [2023-08-17 12:11:10,727][131794] Num frames 4200... | |
| [2023-08-17 12:11:10,794][131794] Avg episode rewards: #0: 22.560, true rewards: #0: 10.560 | |
| [2023-08-17 12:11:10,794][131794] Avg episode reward: 22.560, avg true_objective: 10.560 | |
| [2023-08-17 12:11:10,840][131794] Num frames 4300... | |
| [2023-08-17 12:11:10,898][131794] Num frames 4400... | |
| [2023-08-17 12:11:10,959][131794] Num frames 4500... | |
| [2023-08-17 12:11:11,017][131794] Num frames 4600... | |
| [2023-08-17 12:11:11,076][131794] Num frames 4700... | |
| [2023-08-17 12:11:11,134][131794] Num frames 4800... | |
| [2023-08-17 12:11:11,242][131794] Avg episode rewards: #0: 20.392, true rewards: #0: 9.792 | |
| [2023-08-17 12:11:11,243][131794] Avg episode reward: 20.392, avg true_objective: 9.792 | |
| [2023-08-17 12:11:11,246][131794] Num frames 4900... | |
| [2023-08-17 12:11:11,303][131794] Num frames 5000... | |
| [2023-08-17 12:11:11,363][131794] Num frames 5100... | |
| [2023-08-17 12:11:11,421][131794] Num frames 5200... | |
| [2023-08-17 12:11:11,479][131794] Num frames 5300... | |
| [2023-08-17 12:11:11,537][131794] Num frames 5400... | |
| [2023-08-17 12:11:11,594][131794] Num frames 5500... | |
| [2023-08-17 12:11:11,651][131794] Num frames 5600... | |
| [2023-08-17 12:11:11,709][131794] Num frames 5700... | |
| [2023-08-17 12:11:11,799][131794] Avg episode rewards: #0: 19.933, true rewards: #0: 9.600 | |
| [2023-08-17 12:11:11,799][131794] Avg episode reward: 19.933, avg true_objective: 9.600 | |
| [2023-08-17 12:11:11,823][131794] Num frames 5800... | |
| [2023-08-17 12:11:11,881][131794] Num frames 5900... | |
| [2023-08-17 12:11:11,940][131794] Num frames 6000... | |
| [2023-08-17 12:11:11,998][131794] Num frames 6100... | |
| [2023-08-17 12:11:12,056][131794] Num frames 6200... | |
| [2023-08-17 12:11:12,113][131794] Num frames 6300... | |
| [2023-08-17 12:11:12,170][131794] Num frames 6400... | |
| [2023-08-17 12:11:12,260][131794] Avg episode rewards: #0: 19.234, true rewards: #0: 9.234 | |
| [2023-08-17 12:11:12,260][131794] Avg episode reward: 19.234, avg true_objective: 9.234 | |
| [2023-08-17 12:11:12,282][131794] Num frames 6500... | |
| [2023-08-17 12:11:12,340][131794] Num frames 6600... | |
| [2023-08-17 12:11:12,398][131794] Num frames 6700... | |
| [2023-08-17 12:11:12,455][131794] Num frames 6800... | |
| [2023-08-17 12:11:12,513][131794] Num frames 6900... | |
| [2023-08-17 12:11:12,609][131794] Avg episode rewards: #0: 17.720, true rewards: #0: 8.720 | |
| [2023-08-17 12:11:12,609][131794] Avg episode reward: 17.720, avg true_objective: 8.720 | |
| [2023-08-17 12:11:12,624][131794] Num frames 7000... | |
| [2023-08-17 12:11:12,683][131794] Num frames 7100... | |
| [2023-08-17 12:11:12,757][131794] Avg episode rewards: #0: 16.040, true rewards: #0: 7.929 | |
| [2023-08-17 12:11:12,757][131794] Avg episode reward: 16.040, avg true_objective: 7.929 | |
| [2023-08-17 12:11:12,794][131794] Num frames 7200... | |
| [2023-08-17 12:11:12,852][131794] Num frames 7300... | |
| [2023-08-17 12:11:12,910][131794] Num frames 7400... | |
| [2023-08-17 12:11:12,968][131794] Num frames 7500... | |
| [2023-08-17 12:11:13,027][131794] Num frames 7600... | |
| [2023-08-17 12:11:13,084][131794] Num frames 7700... | |
| [2023-08-17 12:11:13,142][131794] Num frames 7800... | |
| [2023-08-17 12:11:13,200][131794] Num frames 7900... | |
| [2023-08-17 12:11:13,298][131794] Avg episode rewards: #0: 16.278, true rewards: #0: 7.978 | |
| [2023-08-17 12:11:13,299][131794] Avg episode reward: 16.278, avg true_objective: 7.978 | |
| [2023-08-17 12:11:20,895][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4! | |
| [2023-08-17 12:52:38,482][131794] Loading existing experiment configuration from /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/config.json | |
| [2023-08-17 12:52:38,483][131794] Overriding arg 'num_workers' with value 1 passed from command line | |
| [2023-08-17 12:52:38,483][131794] Adding new argument 'no_render'=True that is not in the saved config file! | |
| [2023-08-17 12:52:38,483][131794] Adding new argument 'save_video'=True that is not in the saved config file! | |
| [2023-08-17 12:52:38,484][131794] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file! | |
| [2023-08-17 12:52:38,484][131794] Adding new argument 'video_name'=None that is not in the saved config file! | |
| [2023-08-17 12:52:38,485][131794] Adding new argument 'max_num_frames'=100000 that is not in the saved config file! | |
| [2023-08-17 12:52:38,485][131794] Adding new argument 'max_num_episodes'=10 that is not in the saved config file! | |
| [2023-08-17 12:52:38,486][131794] Adding new argument 'push_to_hub'=True that is not in the saved config file! | |
| [2023-08-17 12:52:38,486][131794] Adding new argument 'hf_repository'='patonw/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file! | |
| [2023-08-17 12:52:38,486][131794] Adding new argument 'policy_index'=0 that is not in the saved config file! | |
| [2023-08-17 12:52:38,487][131794] Adding new argument 'eval_deterministic'=False that is not in the saved config file! | |
| [2023-08-17 12:52:38,487][131794] Adding new argument 'train_script'=None that is not in the saved config file! | |
| [2023-08-17 12:52:38,487][131794] Adding new argument 'enjoy_script'=None that is not in the saved config file! | |
| [2023-08-17 12:52:38,488][131794] Using frameskip 1 and render_action_repeat=4 for evaluation | |
| [2023-08-17 12:52:38,491][131794] RunningMeanStd input shape: (3, 72, 128) | |
| [2023-08-17 12:52:38,492][131794] RunningMeanStd input shape: (1,) | |
| [2023-08-17 12:52:38,497][131794] ConvEncoder: input_channels=3 | |
| [2023-08-17 12:52:38,518][131794] Conv encoder output size: 512 | |
| [2023-08-17 12:52:38,519][131794] Policy head output size: 512 | |
| [2023-08-17 12:52:38,534][131794] Loading state from checkpoint /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth... | |
| [2023-08-17 12:52:38,832][131794] Num frames 100... | |
| [2023-08-17 12:52:38,889][131794] Num frames 200... | |
| [2023-08-17 12:52:38,952][131794] Num frames 300... | |
| [2023-08-17 12:52:39,009][131794] Num frames 400... | |
| [2023-08-17 12:52:39,065][131794] Num frames 500... | |
| [2023-08-17 12:52:39,122][131794] Num frames 600... | |
| [2023-08-17 12:52:39,178][131794] Num frames 700... | |
| [2023-08-17 12:52:39,237][131794] Num frames 800... | |
| [2023-08-17 12:52:39,293][131794] Num frames 900... | |
| [2023-08-17 12:52:39,349][131794] Num frames 1000... | |
| [2023-08-17 12:52:39,406][131794] Num frames 1100... | |
| [2023-08-17 12:52:39,462][131794] Num frames 1200... | |
| [2023-08-17 12:52:39,520][131794] Num frames 1300... | |
| [2023-08-17 12:52:39,576][131794] Num frames 1400... | |
| [2023-08-17 12:52:39,633][131794] Num frames 1500... | |
| [2023-08-17 12:52:39,691][131794] Num frames 1600... | |
| [2023-08-17 12:52:39,748][131794] Num frames 1700... | |
| [2023-08-17 12:52:39,804][131794] Num frames 1800... | |
| [2023-08-17 12:52:39,860][131794] Num frames 1900... | |
| [2023-08-17 12:52:39,917][131794] Num frames 2000... | |
| [2023-08-17 12:52:39,997][131794] Avg episode rewards: #0: 47.479, true rewards: #0: 20.480 | |
| [2023-08-17 12:52:39,998][131794] Avg episode reward: 47.479, avg true_objective: 20.480 | |
| [2023-08-17 12:52:40,027][131794] Num frames 2100... | |
| [2023-08-17 12:52:40,084][131794] Num frames 2200... | |
| [2023-08-17 12:52:40,142][131794] Num frames 2300... | |
| [2023-08-17 12:52:40,199][131794] Num frames 2400... | |
| [2023-08-17 12:52:40,256][131794] Num frames 2500... | |
| [2023-08-17 12:52:40,312][131794] Num frames 2600... | |
| [2023-08-17 12:52:40,368][131794] Num frames 2700... | |
| [2023-08-17 12:52:40,424][131794] Num frames 2800... | |
| [2023-08-17 12:52:40,522][131794] Avg episode rewards: #0: 30.900, true rewards: #0: 14.400 | |
| [2023-08-17 12:52:40,523][131794] Avg episode reward: 30.900, avg true_objective: 14.400 | |
| [2023-08-17 12:52:40,535][131794] Num frames 2900... | |
| [2023-08-17 12:52:40,591][131794] Num frames 3000... | |
| [2023-08-17 12:52:40,648][131794] Num frames 3100... | |
| [2023-08-17 12:52:40,704][131794] Num frames 3200... | |
| [2023-08-17 12:52:40,760][131794] Num frames 3300... | |
| [2023-08-17 12:52:40,815][131794] Num frames 3400... | |
| [2023-08-17 12:52:40,899][131794] Avg episode rewards: #0: 23.853, true rewards: #0: 11.520 | |
| [2023-08-17 12:52:40,899][131794] Avg episode reward: 23.853, avg true_objective: 11.520 | |
| [2023-08-17 12:52:40,925][131794] Num frames 3500... | |
| [2023-08-17 12:52:40,981][131794] Num frames 3600... | |
| [2023-08-17 12:52:41,039][131794] Num frames 3700... | |
| [2023-08-17 12:52:41,096][131794] Num frames 3800... | |
| [2023-08-17 12:52:41,153][131794] Num frames 3900... | |
| [2023-08-17 12:52:41,211][131794] Num frames 4000... | |
| [2023-08-17 12:52:41,270][131794] Num frames 4100... | |
| [2023-08-17 12:52:41,328][131794] Num frames 4200... | |
| [2023-08-17 12:52:41,386][131794] Num frames 4300... | |
| [2023-08-17 12:52:41,446][131794] Num frames 4400... | |
| [2023-08-17 12:52:41,525][131794] Avg episode rewards: #0: 22.870, true rewards: #0: 11.120 | |
| [2023-08-17 12:52:41,526][131794] Avg episode reward: 22.870, avg true_objective: 11.120 | |
| [2023-08-17 12:52:41,555][131794] Num frames 4500... | |
| [2023-08-17 12:52:41,612][131794] Num frames 4600... | |
| [2023-08-17 12:52:41,668][131794] Num frames 4700... | |
| [2023-08-17 12:52:41,725][131794] Num frames 4800... | |
| [2023-08-17 12:52:41,781][131794] Num frames 4900... | |
| [2023-08-17 12:52:41,868][131794] Avg episode rewards: #0: 20.322, true rewards: #0: 9.922 | |
| [2023-08-17 12:52:41,869][131794] Avg episode reward: 20.322, avg true_objective: 9.922 | |
| [2023-08-17 12:52:41,891][131794] Num frames 5000... | |
| [2023-08-17 12:52:41,948][131794] Num frames 5100... | |
| [2023-08-17 12:52:42,004][131794] Num frames 5200... | |
| [2023-08-17 12:52:42,063][131794] Num frames 5300... | |
| [2023-08-17 12:52:42,119][131794] Num frames 5400... | |
| [2023-08-17 12:52:42,175][131794] Num frames 5500... | |
| [2023-08-17 12:52:42,231][131794] Num frames 5600... | |
| [2023-08-17 12:52:42,287][131794] Num frames 5700... | |
| [2023-08-17 12:52:42,344][131794] Num frames 5800... | |
| [2023-08-17 12:52:42,400][131794] Num frames 5900... | |
| [2023-08-17 12:52:42,456][131794] Num frames 6000... | |
| [2023-08-17 12:52:42,513][131794] Num frames 6100... | |
| [2023-08-17 12:52:42,567][131794] Num frames 6200... | |
| [2023-08-17 12:52:42,621][131794] Num frames 6300... | |
| [2023-08-17 12:52:42,675][131794] Num frames 6400... | |
| [2023-08-17 12:52:42,762][131794] Avg episode rewards: #0: 22.108, true rewards: #0: 10.775 | |
| [2023-08-17 12:52:42,763][131794] Avg episode reward: 22.108, avg true_objective: 10.775 | |
| [2023-08-17 12:52:42,781][131794] Num frames 6500... | |
| [2023-08-17 12:52:42,836][131794] Num frames 6600... | |
| [2023-08-17 12:52:42,889][131794] Num frames 6700... | |
| [2023-08-17 12:52:42,944][131794] Num frames 6800... | |
| [2023-08-17 12:52:42,997][131794] Num frames 6900... | |
| [2023-08-17 12:52:43,051][131794] Num frames 7000... | |
| [2023-08-17 12:52:43,107][131794] Num frames 7100... | |
| [2023-08-17 12:52:43,162][131794] Num frames 7200... | |
| [2023-08-17 12:52:43,217][131794] Num frames 7300... | |
| [2023-08-17 12:52:43,285][131794] Avg episode rewards: #0: 21.751, true rewards: #0: 10.466 | |
| [2023-08-17 12:52:43,285][131794] Avg episode reward: 21.751, avg true_objective: 10.466 | |
| [2023-08-17 12:52:43,325][131794] Num frames 7400... | |
| [2023-08-17 12:52:43,381][131794] Num frames 7500... | |
| [2023-08-17 12:52:43,435][131794] Num frames 7600... | |
| [2023-08-17 12:52:43,490][131794] Num frames 7700... | |
| [2023-08-17 12:52:43,544][131794] Num frames 7800... | |
| [2023-08-17 12:52:43,602][131794] Num frames 7900... | |
| [2023-08-17 12:52:43,657][131794] Num frames 8000... | |
| [2023-08-17 12:52:43,711][131794] Num frames 8100... | |
| [2023-08-17 12:52:43,766][131794] Num frames 8200... | |
| [2023-08-17 12:52:43,824][131794] Num frames 8300... | |
| [2023-08-17 12:52:43,881][131794] Num frames 8400... | |
| [2023-08-17 12:52:43,959][131794] Avg episode rewards: #0: 22.183, true rewards: #0: 10.557 | |
| [2023-08-17 12:52:43,960][131794] Avg episode reward: 22.183, avg true_objective: 10.557 | |
| [2023-08-17 12:52:43,991][131794] Num frames 8500... | |
| [2023-08-17 12:52:44,048][131794] Num frames 8600... | |
| [2023-08-17 12:52:44,105][131794] Num frames 8700... | |
| [2023-08-17 12:52:44,162][131794] Num frames 8800... | |
| [2023-08-17 12:52:44,218][131794] Num frames 8900... | |
| [2023-08-17 12:52:44,272][131794] Num frames 9000... | |
| [2023-08-17 12:52:44,328][131794] Num frames 9100... | |
| [2023-08-17 12:52:44,383][131794] Num frames 9200... | |
| [2023-08-17 12:52:44,437][131794] Num frames 9300... | |
| [2023-08-17 12:52:44,492][131794] Num frames 9400... | |
| [2023-08-17 12:52:44,548][131794] Avg episode rewards: #0: 22.229, true rewards: #0: 10.451 | |
| [2023-08-17 12:52:44,549][131794] Avg episode reward: 22.229, avg true_objective: 10.451 | |
| [2023-08-17 12:52:44,599][131794] Num frames 9500... | |
| [2023-08-17 12:52:44,655][131794] Num frames 9600... | |
| [2023-08-17 12:52:44,709][131794] Num frames 9700... | |
| [2023-08-17 12:52:44,763][131794] Num frames 9800... | |
| [2023-08-17 12:52:44,835][131794] Avg episode rewards: #0: 20.835, true rewards: #0: 9.835 | |
| [2023-08-17 12:52:44,835][131794] Avg episode reward: 20.835, avg true_objective: 9.835 | |
| [2023-08-17 12:52:54,306][131794] Replay video saved to /home/patonw/code/learn/deep-rl-class/notebooks/unit8/train_dir/default_experiment/replay.mp4! | |