Upload . with huggingface_hub

.summary/0/events.out.tfevents.1687392329.mihirs-MacBook-Air.local

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f63543400f815854cc7a6521374edd91dab94363ee912e21a1392754f1c78c7
+size 2343

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 8.33 +/- 5.78
+      value: 10.73 +/- 4.77
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000001637_6114688.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be770681681e0c1fcaac55e5c7ff45fedb6b1d68448575fa6db8e99885d52c30
+size 34928851

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 8000000,
+  "train_for_env_steps": 4000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be5aa12e08eb81381c9c151c92e64119b04e1cc6968c49faf063d19e376bb766
-size 16517477
+oid sha256:fae0e012497eea482d79cfa1324e2b488401a505f438be4ef39cc768ea49be6e
+size 22048753

sf_log.txt

@@ -9950,3 +9950,607 @@ main_loop: 23380.8911
 [2023-06-21 19:17:03,450][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1198
 [2023-06-21 19:17:04,899][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1198
 [2023-06-21 19:17:05,230][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1198
+[2023-06-21 19:17:13,689][62782] The model has been pushed to https://huggingface.co/mihirdeo16/vizdoom_health_gathering_supreme
+[2023-06-21 19:17:23,503][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1199
+[2023-06-21 19:17:24,937][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1199
+[2023-06-21 19:17:25,270][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1199
+[2023-06-21 19:17:43,528][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1200
+[2023-06-21 19:17:44,988][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1200
+[2023-06-21 19:17:45,287][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1200
+[2023-06-21 19:18:03,538][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1201
+[2023-06-21 19:18:05,035][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1201
+[2023-06-21 19:18:05,319][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1201
+[2023-06-21 19:18:23,543][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1202
+[2023-06-21 19:18:25,067][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1202
+[2023-06-21 19:18:25,331][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1202
+[2023-06-21 19:18:43,577][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1203
+[2023-06-21 19:18:45,091][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1203
+[2023-06-21 19:18:45,368][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1203
+[2023-06-21 19:19:03,619][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1204
+[2023-06-21 19:19:05,106][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1204
+[2023-06-21 19:19:05,385][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1204
+[2023-06-21 19:19:23,676][78408] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1205
+[2023-06-21 19:19:25,133][78405] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1205
+[2023-06-21 19:19:25,439][78409] Another process currently holds the lock /var/folders/t0/cgrmhypx1kg2h122jm20kbnm0000gn/T/sf2_md/doom_002.lockfile, attempt: 1205
+[2023-06-21 19:19:30,406][78404] VizDoom game.init() threw an exception ViZDoomErrorException('Unexpected ViZDoom instance crash.'). Terminate process...
+[2023-06-21 19:19:30,426][78404] 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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init
+    self.game.init()
+vizdoom.vizdoom.ViZDoomErrorException: Unexpected ViZDoom instance crash.
+
+During handling of the above exception, another exception occurred:
+
+Traceback (most recent call last):
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
+    env_runner.init(self.timing)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
+    self._reset()
+  File "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 462, in reset
+    obs, info = self.env.reset(seed=seed, options=options)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 82, in reset
+    obs, info = self.env.reset(**kwargs)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 414, in reset
+    return self.env.reset(seed=seed, options=options)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
+    return self.env.reset(**kwargs)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
+    self._ensure_initialized()
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
+    self.initialize()
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
+    self._game_init()
+  File "/Users/md/opt/miniconda3/envs/hf/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
+[2023-06-21 19:19:30,439][78404] Unhandled exception  in evt loop rollout_proc2_evt_loop
+[2023-06-21 19:19:31,063][78408] Decorrelating experience for 32 frames...
+[2023-06-21 19:19:31,698][78405] Decorrelating experience for 32 frames...
+[2023-06-21 19:19:32,297][78409] Decorrelating experience for 64 frames...
+[2023-06-21 19:19:32,548][78408] Decorrelating experience for 64 frames...
+[2023-06-21 19:19:33,144][78405] Decorrelating experience for 64 frames...
+[2023-06-21 19:19:34,607][78409] Decorrelating experience for 96 frames...
+[2023-06-21 19:19:34,789][78408] Decorrelating experience for 96 frames...
+[2023-06-21 19:19:35,458][78405] Decorrelating experience for 96 frames...
+[2023-06-21 19:19:37,212][78409] Stopping RolloutWorker_w6...
+[2023-06-21 19:19:37,212][78409] Loop rollout_proc6_evt_loop terminating...
+[2023-06-21 19:19:38,966][78405] 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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
+    slot_callable(*args)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
+    env_runner.init(self.timing)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
+    self._reset()
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 439, in _reset
+    observations, rew, terminated, truncated, info = e.step(actions)
+  File "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step
+    return self.env.step(action)
+  File "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 469, in step
+    observation, reward, terminated, truncated, info = self.env.step(action)
+  File "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/lib/python3.10/site-packages/gymnasium/core.py", line 408, in step
+    return self.env.step(action)
+  File "/Users/md/opt/miniconda3/envs/hf/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 "/Users/md/opt/miniconda3/envs/hf/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.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly.
+[2023-06-21 19:19:38,971][78405] Unhandled exception Controlled ViZDoom instance exited unexpectedly. in evt loop rollout_proc3_evt_loop
+[2023-06-21 20:05:30,124][03300] Saving configuration to /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/config.json...
+[2023-06-21 20:05:30,146][03300] Rollout worker 0 uses device cpu
+[2023-06-21 20:05:30,147][03300] Rollout worker 1 uses device cpu
+[2023-06-21 20:05:30,148][03300] Rollout worker 2 uses device cpu
+[2023-06-21 20:05:30,148][03300] Rollout worker 3 uses device cpu
+[2023-06-21 20:05:30,148][03300] Rollout worker 4 uses device cpu
+[2023-06-21 20:05:30,148][03300] Rollout worker 5 uses device cpu
+[2023-06-21 20:05:30,149][03300] Rollout worker 6 uses device cpu
+[2023-06-21 20:05:30,149][03300] Rollout worker 7 uses device cpu
+[2023-06-21 20:05:30,359][03300] InferenceWorker_p0-w0: min num requests: 2
+[2023-06-21 20:05:30,393][03300] Starting all processes...
+[2023-06-21 20:05:30,394][03300] Starting process learner_proc0
+[2023-06-21 20:05:30,448][03300] Starting all processes...
+[2023-06-21 20:05:30,452][03300] Starting process inference_proc0-0
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc0
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc1
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc2
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc3
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc4
+[2023-06-21 20:05:30,452][03300] Starting process rollout_proc5
+[2023-06-21 20:05:30,453][03300] Starting process rollout_proc6
+[2023-06-21 20:05:30,453][03300] Starting process rollout_proc7
+[2023-06-21 20:05:32,460][03737] On MacOS, not setting affinity
+[2023-06-21 20:05:32,464][03739] On MacOS, not setting affinity
+[2023-06-21 20:05:32,478][03736] Starting seed is not provided
+[2023-06-21 20:05:32,478][03736] Initializing actor-critic model on device cpu
+[2023-06-21 20:05:32,478][03736] RunningMeanStd input shape: (3, 72, 128)
+[2023-06-21 20:05:32,483][03736] RunningMeanStd input shape: (1,)
+[2023-06-21 20:05:32,494][03740] On MacOS, not setting affinity
+[2023-06-21 20:05:32,494][03742] On MacOS, not setting affinity
+[2023-06-21 20:05:32,499][03736] ConvEncoder: input_channels=3
+[2023-06-21 20:05:32,560][03743] On MacOS, not setting affinity
+[2023-06-21 20:05:32,579][03744] On MacOS, not setting affinity
+[2023-06-21 20:05:32,584][03745] On MacOS, not setting affinity
+[2023-06-21 20:05:32,591][03741] On MacOS, not setting affinity
+[2023-06-21 20:05:32,609][03736] Conv encoder output size: 512
+[2023-06-21 20:05:32,609][03736] Policy head output size: 512
+[2023-06-21 20:05:32,628][03736] Created Actor Critic model with architecture:
+[2023-06-21 20:05:32,629][03736] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2023-06-21 20:05:32,635][03736] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-06-21 20:05:32,636][03736] Loading state from checkpoint /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001636_6111488.pth...
+[2023-06-21 20:05:32,674][03736] Loading model from checkpoint
+[2023-06-21 20:05:32,680][03736] Loaded experiment state at self.train_step=1636, self.env_steps=6111488
+[2023-06-21 20:05:32,681][03736] Initialized policy 0 weights for model version 1636
+[2023-06-21 20:05:32,682][03736] LearnerWorker_p0 finished initialization!
+[2023-06-21 20:05:32,685][03738] RunningMeanStd input shape: (3, 72, 128)
+[2023-06-21 20:05:32,685][03738] RunningMeanStd input shape: (1,)
+[2023-06-21 20:05:32,699][03738] ConvEncoder: input_channels=3
+[2023-06-21 20:05:32,751][03738] Conv encoder output size: 512
+[2023-06-21 20:05:32,751][03738] Policy head output size: 512
+[2023-06-21 20:05:32,760][03300] Inference worker 0-0 is ready!
+[2023-06-21 20:05:32,761][03300] All inference workers are ready! Signal rollout workers to start!
+[2023-06-21 20:05:32,797][03744] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,809][03743] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,809][03740] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,810][03745] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,815][03742] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,816][03741] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,820][03739] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:32,819][03737] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:05:34,186][03741] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,188][03737] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,188][03743] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,192][03740] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,195][03742] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,203][03739] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:34,307][03300] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 6111488. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-06-21 20:05:35,168][03740] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,177][03741] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,180][03737] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,180][03744] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:35,183][03743] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,183][03739] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,943][03744] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:35,945][03742] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:36,706][03745] Decorrelating experience for 0 frames...
+[2023-06-21 20:05:36,815][03737] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:36,815][03740] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:36,819][03739] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:37,483][03745] Decorrelating experience for 32 frames...
+[2023-06-21 20:05:37,486][03741] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:37,550][03743] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:38,238][03742] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:38,241][03744] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:39,013][03745] Decorrelating experience for 64 frames...
+[2023-06-21 20:05:39,063][03739] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:39,137][03737] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:39,169][03740] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:39,307][03300] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 6111488. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-06-21 20:05:39,810][03741] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:39,850][03743] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:40,542][03742] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:40,549][03744] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:41,291][03745] Decorrelating experience for 96 frames...
+[2023-06-21 20:05:44,306][03300] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 6111488. Throughput: 0: 3.8. Samples: 38. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-06-21 20:05:44,308][03300] Avg episode reward: [(0, '0.570')]
+[2023-06-21 20:05:47,764][03736] Stopping Batcher_0...
+[2023-06-21 20:05:47,764][03736] Saving /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001637_6114688.pth...
+[2023-06-21 20:05:47,767][03300] Component Batcher_0 stopped!
+[2023-06-21 20:05:47,764][03736] Loop batcher_evt_loop terminating...
+[2023-06-21 20:05:47,910][03738] Weights refcount: 2 0
+[2023-06-21 20:05:47,912][03738] Stopping InferenceWorker_p0-w0...
+[2023-06-21 20:05:47,912][03738] Loop inference_proc0-0_evt_loop terminating...
+[2023-06-21 20:05:47,914][03300] Component InferenceWorker_p0-w0 stopped!
+[2023-06-21 20:05:47,956][03741] Stopping RolloutWorker_w3...
+[2023-06-21 20:05:47,958][03741] Loop rollout_proc3_evt_loop terminating...
+[2023-06-21 20:05:47,974][03742] Stopping RolloutWorker_w4...
+[2023-06-21 20:05:47,975][03742] Loop rollout_proc4_evt_loop terminating...
+[2023-06-21 20:05:47,980][03736] Removing /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001612_6034688.pth
+[2023-06-21 20:05:47,985][03737] Stopping RolloutWorker_w0...
+[2023-06-21 20:05:47,985][03737] Loop rollout_proc0_evt_loop terminating...
+[2023-06-21 20:05:47,989][03745] Stopping RolloutWorker_w7...
+[2023-06-21 20:05:47,996][03745] Loop rollout_proc7_evt_loop terminating...
+[2023-06-21 20:05:48,006][03743] Stopping RolloutWorker_w5...
+[2023-06-21 20:05:48,009][03743] Loop rollout_proc5_evt_loop terminating...
+[2023-06-21 20:05:48,016][03736] Saving /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001637_6114688.pth...
+[2023-06-21 20:05:48,001][03300] Component RolloutWorker_w3 stopped!
+[2023-06-21 20:05:48,016][03740] Stopping RolloutWorker_w2...
+[2023-06-21 20:05:48,018][03740] Loop rollout_proc2_evt_loop terminating...
+[2023-06-21 20:05:48,018][03744] Stopping RolloutWorker_w6...
+[2023-06-21 20:05:48,019][03744] Loop rollout_proc6_evt_loop terminating...
+[2023-06-21 20:05:48,017][03300] Component RolloutWorker_w4 stopped!
+[2023-06-21 20:05:48,065][03739] Stopping RolloutWorker_w1...
+[2023-06-21 20:05:48,065][03739] Loop rollout_proc1_evt_loop terminating...
+[2023-06-21 20:05:48,025][03300] Component RolloutWorker_w0 stopped!
+[2023-06-21 20:05:48,076][03300] Component RolloutWorker_w7 stopped!
+[2023-06-21 20:05:48,078][03300] Component RolloutWorker_w5 stopped!
+[2023-06-21 20:05:48,079][03300] Component RolloutWorker_w2 stopped!
+[2023-06-21 20:05:48,080][03300] Component RolloutWorker_w6 stopped!
+[2023-06-21 20:05:48,080][03300] Component RolloutWorker_w1 stopped!
+[2023-06-21 20:05:48,159][03736] Stopping LearnerWorker_p0...
+[2023-06-21 20:05:48,159][03736] Loop learner_proc0_evt_loop terminating...
+[2023-06-21 20:05:48,159][03300] Component LearnerWorker_p0 stopped!
+[2023-06-21 20:05:48,161][03300] Waiting for process learner_proc0 to stop...
+[2023-06-21 20:05:48,512][03300] Waiting for process inference_proc0-0 to join...
+[2023-06-21 20:05:48,513][03300] Waiting for process rollout_proc0 to join...
+[2023-06-21 20:05:48,513][03300] Waiting for process rollout_proc1 to join...
+[2023-06-21 20:05:48,514][03300] Waiting for process rollout_proc2 to join...
+[2023-06-21 20:05:48,514][03300] Waiting for process rollout_proc3 to join...
+[2023-06-21 20:05:48,515][03300] Waiting for process rollout_proc4 to join...
+[2023-06-21 20:05:48,515][03300] Waiting for process rollout_proc5 to join...
+[2023-06-21 20:05:48,515][03300] Waiting for process rollout_proc6 to join...
+[2023-06-21 20:05:48,515][03300] Waiting for process rollout_proc7 to join...
+[2023-06-21 20:05:48,516][03300] Batcher 0 profile tree view:
+batching: 0.0072, releasing_batches: 0.0000
+[2023-06-21 20:05:48,516][03300] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0040
+  wait_policy_total: 13.0879
+update_model: 0.0109
+  weight_update: 0.0029
+one_step: 0.0054
+  handle_policy_step: 1.7860
+    deserialize: 0.0178, stack: 0.0034, obs_to_device_normalize: 0.1252, forward: 1.5687, send_messages: 0.0158
+    prepare_outputs: 0.0213
+      to_cpu: 0.0024
+[2023-06-21 20:05:48,516][03300] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 0.3879
+train: 1.2408
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0003, kl_divergence: 0.0007, after_optimizer: 0.0031
+  calculate_losses: 0.7032
+    losses_init: 0.0000, forward_head: 0.6612, bptt_initial: 0.0082, tail: 0.0032, advantages_returns: 0.0018, losses: 0.0048
+    bptt: 0.0231
+      bptt_forward_core: 0.0229
+  update: 0.5322
+    clip: 0.0019
+[2023-06-21 20:05:48,517][03300] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0006, enqueue_policy_requests: 0.0150, env_step: 6.1927, overhead: 0.0136, complete_rollouts: 0.0002
+save_policy_outputs: 0.0078
+  split_output_tensors: 0.0041
+[2023-06-21 20:05:48,517][03300] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0003, enqueue_policy_requests: 0.0084, env_step: 4.0969, overhead: 0.0086, complete_rollouts: 0.0002
+save_policy_outputs: 0.0043
+  split_output_tensors: 0.0022
+[2023-06-21 20:05:48,518][03300] Loop Runner_EvtLoop terminating...
+[2023-06-21 20:05:48,518][03300] Runner profile tree view:
+main_loop: 18.1250
+[2023-06-21 20:05:48,518][03300] Collected {0: 6114688}, FPS: 176.6
+[2023-06-21 20:07:06,012][03300] Loading existing experiment configuration from /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/config.json
+[2023-06-21 20:07:06,013][03300] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-06-21 20:07:06,014][03300] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-06-21 20:07:06,014][03300] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-06-21 20:07:06,014][03300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-06-21 20:07:06,015][03300] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-06-21 20:07:06,015][03300] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-06-21 20:07:06,015][03300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-06-21 20:07:06,016][03300] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-06-21 20:07:06,016][03300] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-06-21 20:07:06,017][03300] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-06-21 20:07:06,017][03300] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-06-21 20:07:06,017][03300] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-06-21 20:07:06,017][03300] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-06-21 20:07:06,018][03300] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-06-21 20:07:06,023][03300] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-06-21 20:07:06,023][03300] RunningMeanStd input shape: (3, 72, 128)
+[2023-06-21 20:07:06,024][03300] RunningMeanStd input shape: (1,)
+[2023-06-21 20:07:06,034][03300] ConvEncoder: input_channels=3
+[2023-06-21 20:07:06,086][03300] Conv encoder output size: 512
+[2023-06-21 20:07:06,086][03300] Policy head output size: 512
+[2023-06-21 20:07:06,092][03300] Loading state from checkpoint /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001637_6114688.pth...
+[2023-06-21 20:07:07,663][03300] Num frames 100...
+[2023-06-21 20:07:08,511][03300] Num frames 200...
+[2023-06-21 20:07:09,351][03300] Num frames 300...
+[2023-06-21 20:07:10,204][03300] Num frames 400...
+[2023-06-21 20:07:10,878][03300] Avg episode rewards: #0: 8.680, true rewards: #0: 4.680
+[2023-06-21 20:07:10,881][03300] Avg episode reward: 8.680, avg true_objective: 4.680
+[2023-06-21 20:07:11,150][03300] Num frames 500...
+[2023-06-21 20:07:12,013][03300] Num frames 600...
+[2023-06-21 20:07:12,877][03300] Num frames 700...
+[2023-06-21 20:07:13,741][03300] Num frames 800...
+[2023-06-21 20:07:14,605][03300] Num frames 900...
+[2023-06-21 20:07:15,463][03300] Num frames 1000...
+[2023-06-21 20:07:16,336][03300] Num frames 1100...
+[2023-06-21 20:07:17,178][03300] Num frames 1200...
+[2023-06-21 20:07:18,030][03300] Num frames 1300...
+[2023-06-21 20:07:18,911][03300] Num frames 1400...
+[2023-06-21 20:07:19,783][03300] Num frames 1500...
+[2023-06-21 20:07:20,668][03300] Num frames 1600...
+[2023-06-21 20:07:21,522][03300] Num frames 1700...
+[2023-06-21 20:07:22,368][03300] Num frames 1800...
+[2023-06-21 20:07:23,205][03300] Num frames 1900...
+[2023-06-21 20:07:24,079][03300] Num frames 2000...
+[2023-06-21 20:07:24,201][03300] Avg episode rewards: #0: 23.020, true rewards: #0: 10.020
+[2023-06-21 20:07:24,203][03300] Avg episode reward: 23.020, avg true_objective: 10.020
+[2023-06-21 20:07:25,021][03300] Num frames 2100...
+[2023-06-21 20:07:25,888][03300] Num frames 2200...
+[2023-06-21 20:07:26,726][03300] Num frames 2300...
+[2023-06-21 20:07:27,611][03300] Num frames 2400...
+[2023-06-21 20:07:28,457][03300] Num frames 2500...
+[2023-06-21 20:07:29,319][03300] Num frames 2600...
+[2023-06-21 20:07:30,194][03300] Num frames 2700...
+[2023-06-21 20:07:30,359][03300] Avg episode rewards: #0: 19.360, true rewards: #0: 9.027
+[2023-06-21 20:07:30,362][03300] Avg episode reward: 19.360, avg true_objective: 9.027
+[2023-06-21 20:07:31,142][03300] Num frames 2800...
+[2023-06-21 20:07:31,994][03300] Num frames 2900...
+[2023-06-21 20:07:32,874][03300] Num frames 3000...
+[2023-06-21 20:07:33,716][03300] Num frames 3100...
+[2023-06-21 20:07:34,575][03300] Num frames 3200...
+[2023-06-21 20:07:35,442][03300] Num frames 3300...
+[2023-06-21 20:07:36,286][03300] Num frames 3400...
+[2023-06-21 20:07:37,156][03300] Num frames 3500...
+[2023-06-21 20:07:37,893][03300] Avg episode rewards: #0: 18.180, true rewards: #0: 8.930
+[2023-06-21 20:07:37,896][03300] Avg episode reward: 18.180, avg true_objective: 8.930
+[2023-06-21 20:07:38,148][03300] Num frames 3600...
+[2023-06-21 20:07:39,035][03300] Num frames 3700...
+[2023-06-21 20:07:39,919][03300] Num frames 3800...
+[2023-06-21 20:07:40,790][03300] Num frames 3900...
+[2023-06-21 20:07:41,643][03300] Num frames 4000...
+[2023-06-21 20:07:42,508][03300] Num frames 4100...
+[2023-06-21 20:07:43,327][03300] Num frames 4200...
+[2023-06-21 20:07:44,046][03300] Num frames 4300...
+[2023-06-21 20:07:44,708][03300] Avg episode rewards: #0: 17.944, true rewards: #0: 8.744
+[2023-06-21 20:07:44,710][03300] Avg episode reward: 17.944, avg true_objective: 8.744
+[2023-06-21 20:07:44,942][03300] Num frames 4400...
+[2023-06-21 20:07:45,796][03300] Num frames 4500...
+[2023-06-21 20:07:46,646][03300] Num frames 4600...
+[2023-06-21 20:07:47,504][03300] Num frames 4700...
+[2023-06-21 20:07:48,368][03300] Num frames 4800...
+[2023-06-21 20:07:49,240][03300] Num frames 4900...
+[2023-06-21 20:07:50,103][03300] Num frames 5000...
+[2023-06-21 20:07:50,990][03300] Num frames 5100...
+[2023-06-21 20:07:51,873][03300] Num frames 5200...
+[2023-06-21 20:07:52,702][03300] Num frames 5300...
+[2023-06-21 20:07:53,523][03300] Num frames 5400...
+[2023-06-21 20:07:54,380][03300] Num frames 5500...
+[2023-06-21 20:07:55,259][03300] Num frames 5600...
+[2023-06-21 20:07:56,102][03300] Num frames 5700...
+[2023-06-21 20:07:56,972][03300] Num frames 5800...
+[2023-06-21 20:07:57,826][03300] Num frames 5900...
+[2023-06-21 20:07:58,679][03300] Num frames 6000...
+[2023-06-21 20:07:59,568][03300] Num frames 6100...
+[2023-06-21 20:08:00,466][03300] Num frames 6200...
+[2023-06-21 20:08:01,328][03300] Num frames 6300...
+[2023-06-21 20:08:02,202][03300] Num frames 6400...
+[2023-06-21 20:08:02,552][03300] Avg episode rewards: #0: 24.715, true rewards: #0: 10.715
+[2023-06-21 20:08:02,554][03300] Avg episode reward: 24.715, avg true_objective: 10.715
+[2023-06-21 20:08:03,175][03300] Num frames 6500...
+[2023-06-21 20:08:04,026][03300] Num frames 6600...
+[2023-06-21 20:08:04,901][03300] Num frames 6700...
+[2023-06-21 20:08:05,783][03300] Num frames 6800...
+[2023-06-21 20:08:06,639][03300] Num frames 6900...
+[2023-06-21 20:08:07,523][03300] Num frames 7000...
+[2023-06-21 20:08:08,398][03300] Num frames 7100...
+[2023-06-21 20:08:09,287][03300] Num frames 7200...
+[2023-06-21 20:08:10,069][03300] Avg episode rewards: #0: 23.967, true rewards: #0: 10.396
+[2023-06-21 20:08:10,072][03300] Avg episode reward: 23.967, avg true_objective: 10.396
+[2023-06-21 20:08:10,268][03300] Num frames 7300...
+[2023-06-21 20:08:11,157][03300] Num frames 7400...
+[2023-06-21 20:08:12,034][03300] Num frames 7500...
+[2023-06-21 20:08:12,871][03300] Num frames 7600...
+[2023-06-21 20:08:13,723][03300] Num frames 7700...
+[2023-06-21 20:08:14,579][03300] Num frames 7800...
+[2023-06-21 20:08:15,440][03300] Num frames 7900...
+[2023-06-21 20:08:16,319][03300] Num frames 8000...
+[2023-06-21 20:08:17,093][03300] Avg episode rewards: #0: 23.096, true rewards: #0: 10.096
+[2023-06-21 20:08:17,096][03300] Avg episode reward: 23.096, avg true_objective: 10.096
+[2023-06-21 20:08:17,283][03300] Num frames 8100...
+[2023-06-21 20:08:18,140][03300] Num frames 8200...
+[2023-06-21 20:08:18,980][03300] Num frames 8300...
+[2023-06-21 20:08:19,820][03300] Num frames 8400...
+[2023-06-21 20:08:20,672][03300] Num frames 8500...
+[2023-06-21 20:08:21,544][03300] Num frames 8600...
+[2023-06-21 20:08:21,820][03300] Avg episode rewards: #0: 21.468, true rewards: #0: 9.579
+[2023-06-21 20:08:21,823][03300] Avg episode reward: 21.468, avg true_objective: 9.579
+[2023-06-21 20:08:22,518][03300] Num frames 8700...
+[2023-06-21 20:08:23,385][03300] Num frames 8800...
+[2023-06-21 20:08:24,248][03300] Num frames 8900...
+[2023-06-21 20:08:24,651][03300] Avg episode rewards: #0: 19.835, true rewards: #0: 8.935
+[2023-06-21 20:08:24,654][03300] Avg episode reward: 19.835, avg true_objective: 8.935
+[2023-06-21 20:08:37,583][03300] Replay video saved to /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/replay.mp4!
+[2023-06-21 20:08:48,389][03300] Loading existing experiment configuration from /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/config.json
+[2023-06-21 20:08:48,390][03300] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-06-21 20:08:48,391][03300] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-06-21 20:08:48,391][03300] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-06-21 20:08:48,391][03300] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-06-21 20:08:48,392][03300] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-06-21 20:08:48,392][03300] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-06-21 20:08:48,393][03300] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-06-21 20:08:48,394][03300] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-06-21 20:08:48,394][03300] Adding new argument 'hf_repository'='mihirdeo16/vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-06-21 20:08:48,395][03300] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-06-21 20:08:48,395][03300] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-06-21 20:08:48,396][03300] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-06-21 20:08:48,396][03300] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-06-21 20:08:48,396][03300] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-06-21 20:08:48,402][03300] RunningMeanStd input shape: (3, 72, 128)
+[2023-06-21 20:08:48,403][03300] RunningMeanStd input shape: (1,)
+[2023-06-21 20:08:48,410][03300] ConvEncoder: input_channels=3
+[2023-06-21 20:08:48,425][03300] Conv encoder output size: 512
+[2023-06-21 20:08:48,425][03300] Policy head output size: 512
+[2023-06-21 20:08:48,431][03300] Loading state from checkpoint /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000001637_6114688.pth...
+[2023-06-21 20:08:50,025][03300] Num frames 100...
+[2023-06-21 20:08:50,876][03300] Num frames 200...
+[2023-06-21 20:08:51,777][03300] Num frames 300...
+[2023-06-21 20:08:52,671][03300] Num frames 400...
+[2023-06-21 20:08:53,543][03300] Num frames 500...
+[2023-06-21 20:08:54,430][03300] Num frames 600...
+[2023-06-21 20:08:55,320][03300] Num frames 700...
+[2023-06-21 20:08:56,026][03300] Avg episode rewards: #0: 15.680, true rewards: #0: 7.680
+[2023-06-21 20:08:56,028][03300] Avg episode reward: 15.680, avg true_objective: 7.680
+[2023-06-21 20:08:56,308][03300] Num frames 800...
+[2023-06-21 20:08:57,182][03300] Num frames 900...
+[2023-06-21 20:08:58,074][03300] Num frames 1000...
+[2023-06-21 20:08:58,962][03300] Num frames 1100...
+[2023-06-21 20:08:59,853][03300] Num frames 1200...
+[2023-06-21 20:09:00,780][03300] Num frames 1300...
+[2023-06-21 20:09:01,662][03300] Num frames 1400...
+[2023-06-21 20:09:02,547][03300] Num frames 1500...
+[2023-06-21 20:09:03,396][03300] Avg episode rewards: #0: 17.430, true rewards: #0: 7.930
+[2023-06-21 20:09:03,399][03300] Avg episode reward: 17.430, avg true_objective: 7.930
+[2023-06-21 20:09:03,516][03300] Num frames 1600...
+[2023-06-21 20:09:04,394][03300] Num frames 1700...
+[2023-06-21 20:09:05,309][03300] Num frames 1800...
+[2023-06-21 20:09:06,167][03300] Num frames 1900...
+[2023-06-21 20:09:07,043][03300] Num frames 2000...
+[2023-06-21 20:09:07,961][03300] Num frames 2100...
+[2023-06-21 20:09:08,610][03300] Avg episode rewards: #0: 14.873, true rewards: #0: 7.207
+[2023-06-21 20:09:08,612][03300] Avg episode reward: 14.873, avg true_objective: 7.207
+[2023-06-21 20:09:08,949][03300] Num frames 2200...
+[2023-06-21 20:09:09,827][03300] Num frames 2300...
+[2023-06-21 20:09:10,698][03300] Num frames 2400...
+[2023-06-21 20:09:11,591][03300] Num frames 2500...
+[2023-06-21 20:09:12,482][03300] Num frames 2600...
+[2023-06-21 20:09:13,425][03300] Num frames 2700...
+[2023-06-21 20:09:14,327][03300] Num frames 2800...
+[2023-06-21 20:09:15,210][03300] Num frames 2900...
+[2023-06-21 20:09:16,100][03300] Num frames 3000...
+[2023-06-21 20:09:16,989][03300] Num frames 3100...
+[2023-06-21 20:09:17,855][03300] Num frames 3200...
+[2023-06-21 20:09:18,714][03300] Num frames 3300...
+[2023-06-21 20:09:19,612][03300] Num frames 3400...
+[2023-06-21 20:09:20,489][03300] Num frames 3500...
+[2023-06-21 20:09:21,398][03300] Num frames 3600...
+[2023-06-21 20:09:22,288][03300] Num frames 3700...
+[2023-06-21 20:09:23,143][03300] Num frames 3800...
+[2023-06-21 20:09:24,033][03300] Num frames 3900...
+[2023-06-21 20:09:24,648][03300] Avg episode rewards: #0: 22.897, true rewards: #0: 9.897
+[2023-06-21 20:09:24,651][03300] Avg episode reward: 22.897, avg true_objective: 9.897
+[2023-06-21 20:09:25,017][03300] Num frames 4000...
+[2023-06-21 20:09:25,887][03300] Num frames 4100...
+[2023-06-21 20:09:26,806][03300] Num frames 4200...
+[2023-06-21 20:09:27,693][03300] Num frames 4300...
+[2023-06-21 20:09:28,556][03300] Num frames 4400...
+[2023-06-21 20:09:29,456][03300] Num frames 4500...
+[2023-06-21 20:09:30,389][03300] Num frames 4600...
+[2023-06-21 20:09:31,287][03300] Num frames 4700...
+[2023-06-21 20:09:32,165][03300] Num frames 4800...
+[2023-06-21 20:09:33,049][03300] Num frames 4900...
+[2023-06-21 20:09:33,922][03300] Num frames 5000...
+[2023-06-21 20:09:34,709][03300] Avg episode rewards: #0: 22.758, true rewards: #0: 10.158
+[2023-06-21 20:09:34,712][03300] Avg episode reward: 22.758, avg true_objective: 10.158
+[2023-06-21 20:09:34,890][03300] Num frames 5100...
+[2023-06-21 20:09:35,771][03300] Num frames 5200...
+[2023-06-21 20:09:36,673][03300] Num frames 5300...
+[2023-06-21 20:09:37,552][03300] Num frames 5400...
+[2023-06-21 20:09:38,434][03300] Num frames 5500...
+[2023-06-21 20:09:39,311][03300] Num frames 5600...
+[2023-06-21 20:09:40,213][03300] Num frames 5700...
+[2023-06-21 20:09:41,098][03300] Num frames 5800...
+[2023-06-21 20:09:41,978][03300] Num frames 5900...
+[2023-06-21 20:09:42,893][03300] Num frames 6000...
+[2023-06-21 20:09:43,720][03300] Num frames 6100...
+[2023-06-21 20:09:44,422][03300] Num frames 6200...
+[2023-06-21 20:09:45,214][03300] Num frames 6300...
+[2023-06-21 20:09:46,139][03300] Num frames 6400...
+[2023-06-21 20:09:46,992][03300] Num frames 6500...
+[2023-06-21 20:09:47,677][03300] Avg episode rewards: #0: 25.777, true rewards: #0: 10.943
+[2023-06-21 20:09:47,679][03300] Avg episode reward: 25.777, avg true_objective: 10.943
+[2023-06-21 20:09:47,982][03300] Num frames 6600...
+[2023-06-21 20:09:48,892][03300] Num frames 6700...
+[2023-06-21 20:09:49,800][03300] Num frames 6800...
+[2023-06-21 20:09:50,701][03300] Num frames 6900...
+[2023-06-21 20:09:51,572][03300] Num frames 7000...
+[2023-06-21 20:09:52,408][03300] Num frames 7100...
+[2023-06-21 20:09:53,196][03300] Num frames 7200...
+[2023-06-21 20:09:53,984][03300] Num frames 7300...
+[2023-06-21 20:09:54,880][03300] Num frames 7400...
+[2023-06-21 20:09:55,782][03300] Num frames 7500...
+[2023-06-21 20:09:56,675][03300] Num frames 7600...
+[2023-06-21 20:09:57,545][03300] Num frames 7700...
+[2023-06-21 20:09:58,416][03300] Num frames 7800...
+[2023-06-21 20:09:59,321][03300] Num frames 7900...
+[2023-06-21 20:10:00,190][03300] Num frames 8000...
+[2023-06-21 20:10:01,075][03300] Num frames 8100...
+[2023-06-21 20:10:01,964][03300] Num frames 8200...
+[2023-06-21 20:10:02,616][03300] Avg episode rewards: #0: 27.517, true rewards: #0: 11.803
+[2023-06-21 20:10:02,619][03300] Avg episode reward: 27.517, avg true_objective: 11.803
+[2023-06-21 20:10:02,949][03300] Num frames 8300...
+[2023-06-21 20:10:03,830][03300] Num frames 8400...
+[2023-06-21 20:10:04,681][03300] Num frames 8500...
+[2023-06-21 20:10:05,555][03300] Num frames 8600...
+[2023-06-21 20:10:06,435][03300] Num frames 8700...
+[2023-06-21 20:10:07,302][03300] Num frames 8800...
+[2023-06-21 20:10:08,156][03300] Num frames 8900...
+[2023-06-21 20:10:09,030][03300] Num frames 9000...
+[2023-06-21 20:10:09,896][03300] Num frames 9100...
+[2023-06-21 20:10:10,752][03300] Num frames 9200...
+[2023-06-21 20:10:11,621][03300] Num frames 9300...
+[2023-06-21 20:10:12,495][03300] Num frames 9400...
+[2023-06-21 20:10:13,355][03300] Num frames 9500...
+[2023-06-21 20:10:14,201][03300] Num frames 9600...
+[2023-06-21 20:10:14,883][03300] Avg episode rewards: #0: 28.331, true rewards: #0: 12.081
+[2023-06-21 20:10:14,885][03300] Avg episode reward: 28.331, avg true_objective: 12.081
+[2023-06-21 20:10:15,193][03300] Num frames 9700...
+[2023-06-21 20:10:16,066][03300] Num frames 9800...
+[2023-06-21 20:10:16,924][03300] Num frames 9900...
+[2023-06-21 20:10:17,800][03300] Avg episode rewards: #0: 25.878, true rewards: #0: 11.100
+[2023-06-21 20:10:17,803][03300] Avg episode reward: 25.878, avg true_objective: 11.100
+[2023-06-21 20:10:17,887][03300] Num frames 10000...
+[2023-06-21 20:10:18,743][03300] Num frames 10100...
+[2023-06-21 20:10:19,626][03300] Num frames 10200...
+[2023-06-21 20:10:20,496][03300] Num frames 10300...
+[2023-06-21 20:10:21,379][03300] Num frames 10400...
+[2023-06-21 20:10:22,247][03300] Num frames 10500...
+[2023-06-21 20:10:23,101][03300] Num frames 10600...
+[2023-06-21 20:10:23,993][03300] Num frames 10700...
+[2023-06-21 20:10:24,325][03300] Avg episode rewards: #0: 24.626, true rewards: #0: 10.726
+[2023-06-21 20:10:24,328][03300] Avg episode reward: 24.626, avg true_objective: 10.726
+[2023-06-21 20:10:38,574][03300] Replay video saved to /Users/md/Code/python/jubilant-memory/RL/train_dir/default_experiment/replay.mp4!