Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1725611727.4ed841473a2d

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51b33602fc2d9b7793fc2a9349e7f3a559aa224a0cfa21bf34b85c1864d333d1
+size 201167

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 7.25 +/- 2.80
+      value: 11.86 +/- 6.87
       name: mean_reward
       verified: false
 ---

checkpoint_p0/best_000001219_4993024_reward_26.655.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5a9876417ead596340c06307b52e741952dd2440efed40c0c06943e24c4e79fb
+size 34929243

checkpoint_p0/checkpoint_000001172_4800512.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:335c248786681602b347c6fa27d673a423f57e3d12e8e07313cafd8d14757367
+size 34929669

checkpoint_p0/checkpoint_000001222_5005312.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:515fd779429a9ca0c2a849321843ca16dcb6030f9fc11e272995e1ee79f95d34
+size 34929669

config.json

@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 4000000,
+  "train_for_env_steps": 5000000,
   "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 sha256:1e2c3aab26fa111584d09ecf5179644dbff431a1ad3f8e9dc3c1e6964aec9247
-size 13552315
+oid sha256:c49871602fc5a116f18f6ade3e48d8382390811cf358f940d7063b0c919ff633
+size 22845820

sf_log.txt

@@ -1058,3 +1058,847 @@ main_loop: 1081.6875
 [2024-09-06 08:29:55,437][01070] Avg episode rewards: #0: 13.847, true rewards: #0: 7.247
 [2024-09-06 08:29:55,439][01070] Avg episode reward: 13.847, avg true_objective: 7.247
 [2024-09-06 08:30:39,348][01070] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-06 08:30:46,004][01070] The model has been pushed to https://huggingface.co/Re-Re/rl_course_vizdoom_health_gathering_supreme
+[2024-09-06 08:35:27,232][01070] Environment doom_basic already registered, overwriting...
+[2024-09-06 08:35:27,234][01070] Environment doom_two_colors_easy already registered, overwriting...
+[2024-09-06 08:35:27,237][01070] Environment doom_two_colors_hard already registered, overwriting...
+[2024-09-06 08:35:27,238][01070] Environment doom_dm already registered, overwriting...
+[2024-09-06 08:35:27,240][01070] Environment doom_dwango5 already registered, overwriting...
+[2024-09-06 08:35:27,241][01070] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2024-09-06 08:35:27,242][01070] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2024-09-06 08:35:27,243][01070] Environment doom_my_way_home already registered, overwriting...
+[2024-09-06 08:35:27,244][01070] Environment doom_deadly_corridor already registered, overwriting...
+[2024-09-06 08:35:27,245][01070] Environment doom_defend_the_center already registered, overwriting...
+[2024-09-06 08:35:27,246][01070] Environment doom_defend_the_line already registered, overwriting...
+[2024-09-06 08:35:27,247][01070] Environment doom_health_gathering already registered, overwriting...
+[2024-09-06 08:35:27,248][01070] Environment doom_health_gathering_supreme already registered, overwriting...
+[2024-09-06 08:35:27,250][01070] Environment doom_battle already registered, overwriting...
+[2024-09-06 08:35:27,251][01070] Environment doom_battle2 already registered, overwriting...
+[2024-09-06 08:35:27,252][01070] Environment doom_duel_bots already registered, overwriting...
+[2024-09-06 08:35:27,253][01070] Environment doom_deathmatch_bots already registered, overwriting...
+[2024-09-06 08:35:27,254][01070] Environment doom_duel already registered, overwriting...
+[2024-09-06 08:35:27,255][01070] Environment doom_deathmatch_full already registered, overwriting...
+[2024-09-06 08:35:27,256][01070] Environment doom_benchmark already registered, overwriting...
+[2024-09-06 08:35:27,257][01070] register_encoder_factory: <function make_vizdoom_encoder at 0x78dc5537e170>
+[2024-09-06 08:35:27,282][01070] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-06 08:35:27,284][01070] Overriding arg 'train_for_env_steps' with value 5000000 passed from command line
+[2024-09-06 08:35:27,291][01070] Experiment dir /content/train_dir/default_experiment already exists!
+[2024-09-06 08:35:27,293][01070] Resuming existing experiment from /content/train_dir/default_experiment...
+[2024-09-06 08:35:27,295][01070] Weights and Biases integration disabled
+[2024-09-06 08:35:27,298][01070] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-09-06 08:35:29,357][01070] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/content/train_dir
+restart_behavior=resume
+device=gpu
+seed=None
+num_policies=1
+async_rl=True
+serial_mode=False
+batched_sampling=False
+num_batches_to_accumulate=2
+worker_num_splits=2
+policy_workers_per_policy=1
+max_policy_lag=1000
+num_workers=8
+num_envs_per_worker=4
+batch_size=1024
+num_batches_per_epoch=1
+num_epochs=1
+rollout=32
+recurrence=32
+shuffle_minibatches=False
+gamma=0.99
+reward_scale=1.0
+reward_clip=1000.0
+value_bootstrap=False
+normalize_returns=True
+exploration_loss_coeff=0.001
+value_loss_coeff=0.5
+kl_loss_coeff=0.0
+exploration_loss=symmetric_kl
+gae_lambda=0.95
+ppo_clip_ratio=0.1
+ppo_clip_value=0.2
+with_vtrace=False
+vtrace_rho=1.0
+vtrace_c=1.0
+optimizer=adam
+adam_eps=1e-06
+adam_beta1=0.9
+adam_beta2=0.999
+max_grad_norm=4.0
+learning_rate=0.0001
+lr_schedule=constant
+lr_schedule_kl_threshold=0.008
+lr_adaptive_min=1e-06
+lr_adaptive_max=0.01
+obs_subtract_mean=0.0
+obs_scale=255.0
+normalize_input=True
+normalize_input_keys=None
+decorrelate_experience_max_seconds=0
+decorrelate_envs_on_one_worker=True
+actor_worker_gpus=[]
+set_workers_cpu_affinity=True
+force_envs_single_thread=False
+default_niceness=0
+log_to_file=True
+experiment_summaries_interval=10
+flush_summaries_interval=30
+stats_avg=100
+summaries_use_frameskip=True
+heartbeat_interval=20
+heartbeat_reporting_interval=600
+train_for_env_steps=5000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2024-09-06 08:35:29,359][01070] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2024-09-06 08:35:29,362][01070] Rollout worker 0 uses device cpu
+[2024-09-06 08:35:29,364][01070] Rollout worker 1 uses device cpu
+[2024-09-06 08:35:29,365][01070] Rollout worker 2 uses device cpu
+[2024-09-06 08:35:29,366][01070] Rollout worker 3 uses device cpu
+[2024-09-06 08:35:29,368][01070] Rollout worker 4 uses device cpu
+[2024-09-06 08:35:29,369][01070] Rollout worker 5 uses device cpu
+[2024-09-06 08:35:29,370][01070] Rollout worker 6 uses device cpu
+[2024-09-06 08:35:29,372][01070] Rollout worker 7 uses device cpu
+[2024-09-06 08:35:29,446][01070] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-06 08:35:29,447][01070] InferenceWorker_p0-w0: min num requests: 2
+[2024-09-06 08:35:29,485][01070] Starting all processes...
+[2024-09-06 08:35:29,486][01070] Starting process learner_proc0
+[2024-09-06 08:35:29,535][01070] Starting all processes...
+[2024-09-06 08:35:29,540][01070] Starting process inference_proc0-0
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc0
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc1
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc2
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc3
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc4
+[2024-09-06 08:35:29,541][01070] Starting process rollout_proc5
+[2024-09-06 08:35:29,736][01070] Starting process rollout_proc7
+[2024-09-06 08:35:29,753][01070] Starting process rollout_proc6
+[2024-09-06 08:35:43,326][19093] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-06 08:35:43,327][19093] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-09-06 08:35:43,391][19093] Num visible devices: 1
+[2024-09-06 08:35:43,432][19093] Starting seed is not provided
+[2024-09-06 08:35:43,433][19093] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-06 08:35:43,434][19093] Initializing actor-critic model on device cuda:0
+[2024-09-06 08:35:43,434][19093] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-06 08:35:43,436][19093] RunningMeanStd input shape: (1,)
+[2024-09-06 08:35:43,522][19093] ConvEncoder: input_channels=3
+[2024-09-06 08:35:44,545][19093] Conv encoder output size: 512
+[2024-09-06 08:35:44,548][19093] Policy head output size: 512
+[2024-09-06 08:35:44,679][19093] Created Actor Critic model with architecture:
+[2024-09-06 08:35:44,680][19093] 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)
+  )
+)
+[2024-09-06 08:35:45,399][19110] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-06 08:35:45,404][19110] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-09-06 08:35:45,627][19116] Worker 5 uses CPU cores [1]
+[2024-09-06 08:35:45,628][19113] Worker 2 uses CPU cores [0]
+[2024-09-06 08:35:45,638][19110] Num visible devices: 1
+[2024-09-06 08:35:45,693][19114] Worker 4 uses CPU cores [0]
+[2024-09-06 08:35:45,750][19093] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-09-06 08:35:45,925][19111] Worker 1 uses CPU cores [1]
+[2024-09-06 08:35:45,964][19117] Worker 7 uses CPU cores [1]
+[2024-09-06 08:35:46,011][19118] Worker 6 uses CPU cores [0]
+[2024-09-06 08:35:46,116][19112] Worker 0 uses CPU cores [0]
+[2024-09-06 08:35:46,119][19115] Worker 3 uses CPU cores [1]
+[2024-09-06 08:35:46,846][19093] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2024-09-06 08:35:46,893][19093] Loading model from checkpoint
+[2024-09-06 08:35:46,895][19093] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2024-09-06 08:35:46,896][19093] Initialized policy 0 weights for model version 978
+[2024-09-06 08:35:46,906][19093] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-09-06 08:35:46,914][19093] LearnerWorker_p0 finished initialization!
+[2024-09-06 08:35:47,083][19110] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-06 08:35:47,085][19110] RunningMeanStd input shape: (1,)
+[2024-09-06 08:35:47,103][19110] ConvEncoder: input_channels=3
+[2024-09-06 08:35:47,256][19110] Conv encoder output size: 512
+[2024-09-06 08:35:47,257][19110] Policy head output size: 512
+[2024-09-06 08:35:47,299][01070] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 4005888. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-06 08:35:47,343][01070] Inference worker 0-0 is ready!
+[2024-09-06 08:35:47,345][01070] All inference workers are ready! Signal rollout workers to start!
+[2024-09-06 08:35:47,666][19115] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,759][19117] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,841][19111] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,847][19116] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,859][19118] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,902][19114] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,911][19113] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:47,923][19112] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-09-06 08:35:49,437][01070] Heartbeat connected on Batcher_0
+[2024-09-06 08:35:49,445][01070] Heartbeat connected on LearnerWorker_p0
+[2024-09-06 08:35:49,476][01070] Heartbeat connected on InferenceWorker_p0-w0
+[2024-09-06 08:35:49,689][19112] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:49,691][19113] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:49,916][19115] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:49,947][19117] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:50,051][19111] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:50,057][19116] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:50,424][19112] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:51,332][19117] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:51,378][19115] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:51,423][19111] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:51,456][19114] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:51,798][19113] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:52,103][19112] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:52,299][01070] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-06 08:35:52,385][19118] Decorrelating experience for 0 frames...
+[2024-09-06 08:35:52,773][19116] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:53,059][19117] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:53,088][19115] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:53,163][19111] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:53,227][19114] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:54,004][19116] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:54,080][19111] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:54,169][01070] Heartbeat connected on RolloutWorker_w1
+[2024-09-06 08:35:54,232][19113] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:54,438][19118] Decorrelating experience for 32 frames...
+[2024-09-06 08:35:54,884][19114] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:55,752][19112] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:55,972][01070] Heartbeat connected on RolloutWorker_w0
+[2024-09-06 08:35:56,002][19113] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:56,247][01070] Heartbeat connected on RolloutWorker_w2
+[2024-09-06 08:35:56,489][19118] Decorrelating experience for 64 frames...
+[2024-09-06 08:35:56,773][19114] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:57,299][01070] Heartbeat connected on RolloutWorker_w4
+[2024-09-06 08:35:57,303][01070] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 71.2. Samples: 712. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-09-06 08:35:57,307][01070] Avg episode reward: [(0, '5.702')]
+[2024-09-06 08:35:57,398][19116] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:57,706][01070] Heartbeat connected on RolloutWorker_w5
+[2024-09-06 08:35:57,841][19117] Decorrelating experience for 96 frames...
+[2024-09-06 08:35:58,244][01070] Heartbeat connected on RolloutWorker_w7
+[2024-09-06 08:36:00,233][19093] Signal inference workers to stop experience collection...
+[2024-09-06 08:36:00,248][19110] InferenceWorker_p0-w0: stopping experience collection
+[2024-09-06 08:36:00,307][19118] Decorrelating experience for 96 frames...
+[2024-09-06 08:36:00,409][01070] Heartbeat connected on RolloutWorker_w6
+[2024-09-06 08:36:00,811][19115] Decorrelating experience for 96 frames...
+[2024-09-06 08:36:00,904][01070] Heartbeat connected on RolloutWorker_w3
+[2024-09-06 08:36:02,107][19093] Signal inference workers to resume experience collection...
+[2024-09-06 08:36:02,108][19110] InferenceWorker_p0-w0: resuming experience collection
+[2024-09-06 08:36:02,300][01070] Fps is (10 sec: 409.6, 60 sec: 273.0, 300 sec: 273.0). Total num frames: 4009984. Throughput: 0: 147.9. Samples: 2218. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
+[2024-09-06 08:36:02,302][01070] Avg episode reward: [(0, '4.701')]
+[2024-09-06 08:36:07,302][01070] Fps is (10 sec: 1638.4, 60 sec: 819.0, 300 sec: 819.0). Total num frames: 4022272. Throughput: 0: 228.8. Samples: 4576. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
+[2024-09-06 08:36:07,305][01070] Avg episode reward: [(0, '6.521')]
+[2024-09-06 08:36:12,073][19110] Updated weights for policy 0, policy_version 988 (0.0020)
+[2024-09-06 08:36:12,300][01070] Fps is (10 sec: 3686.1, 60 sec: 1638.3, 300 sec: 1638.3). Total num frames: 4046848. Throughput: 0: 391.6. Samples: 9790. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:36:12,306][01070] Avg episode reward: [(0, '11.236')]
+[2024-09-06 08:36:17,299][01070] Fps is (10 sec: 4507.3, 60 sec: 2048.0, 300 sec: 2048.0). Total num frames: 4067328. Throughput: 0: 445.7. Samples: 13370. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:36:17,305][01070] Avg episode reward: [(0, '12.296')]
+[2024-09-06 08:36:22,299][01070] Fps is (10 sec: 3687.1, 60 sec: 2223.5, 300 sec: 2223.5). Total num frames: 4083712. Throughput: 0: 556.9. Samples: 19492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:36:22,301][01070] Avg episode reward: [(0, '14.420')]
+[2024-09-06 08:36:22,439][19110] Updated weights for policy 0, policy_version 998 (0.0030)
+[2024-09-06 08:36:27,299][01070] Fps is (10 sec: 3686.3, 60 sec: 2457.6, 300 sec: 2457.6). Total num frames: 4104192. Throughput: 0: 602.8. Samples: 24114. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
+[2024-09-06 08:36:27,301][01070] Avg episode reward: [(0, '16.055')]
+[2024-09-06 08:36:32,188][19110] Updated weights for policy 0, policy_version 1008 (0.0021)
+[2024-09-06 08:36:32,299][01070] Fps is (10 sec: 4505.6, 60 sec: 2730.7, 300 sec: 2730.7). Total num frames: 4128768. Throughput: 0: 615.9. Samples: 27716. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
+[2024-09-06 08:36:32,305][01070] Avg episode reward: [(0, '18.102')]
+[2024-09-06 08:36:32,309][19093] Saving new best policy, reward=18.102!
+[2024-09-06 08:36:37,300][01070] Fps is (10 sec: 4505.2, 60 sec: 2867.1, 300 sec: 2867.1). Total num frames: 4149248. Throughput: 0: 773.5. Samples: 34808. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:36:37,305][01070] Avg episode reward: [(0, '19.063')]
+[2024-09-06 08:36:37,312][19093] Saving new best policy, reward=19.063!
+[2024-09-06 08:36:42,299][01070] Fps is (10 sec: 3276.7, 60 sec: 2829.9, 300 sec: 2829.9). Total num frames: 4161536. Throughput: 0: 852.4. Samples: 39066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:36:42,303][01070] Avg episode reward: [(0, '20.446')]
+[2024-09-06 08:36:42,306][19093] Saving new best policy, reward=20.446!
+[2024-09-06 08:36:43,965][19110] Updated weights for policy 0, policy_version 1018 (0.0034)
+[2024-09-06 08:36:47,299][01070] Fps is (10 sec: 3277.1, 60 sec: 2935.5, 300 sec: 2935.5). Total num frames: 4182016. Throughput: 0: 879.8. Samples: 41808. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:36:47,305][01070] Avg episode reward: [(0, '21.840')]
+[2024-09-06 08:36:47,316][19093] Saving new best policy, reward=21.840!
+[2024-09-06 08:36:52,299][01070] Fps is (10 sec: 4505.7, 60 sec: 3345.1, 300 sec: 3087.8). Total num frames: 4206592. Throughput: 0: 982.8. Samples: 48798. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
+[2024-09-06 08:36:52,304][01070] Avg episode reward: [(0, '21.047')]
+[2024-09-06 08:36:52,709][19110] Updated weights for policy 0, policy_version 1028 (0.0017)
+[2024-09-06 08:36:57,304][01070] Fps is (10 sec: 4094.0, 60 sec: 3618.1, 300 sec: 3101.0). Total num frames: 4222976. Throughput: 0: 987.4. Samples: 54226. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:36:57,306][01070] Avg episode reward: [(0, '20.552')]
+[2024-09-06 08:37:02,299][01070] Fps is (10 sec: 2457.6, 60 sec: 3686.5, 300 sec: 3003.7). Total num frames: 4231168. Throughput: 0: 944.6. Samples: 55878. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:37:02,301][01070] Avg episode reward: [(0, '21.311')]
+[2024-09-06 08:37:07,058][19110] Updated weights for policy 0, policy_version 1038 (0.0038)
+[2024-09-06 08:37:07,299][01070] Fps is (10 sec: 2868.7, 60 sec: 3823.2, 300 sec: 3072.0). Total num frames: 4251648. Throughput: 0: 897.5. Samples: 59880. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:37:07,301][01070] Avg episode reward: [(0, '20.332')]
+[2024-09-06 08:37:12,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3754.8, 300 sec: 3132.2). Total num frames: 4272128. Throughput: 0: 950.4. Samples: 66884. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:37:12,301][01070] Avg episode reward: [(0, '19.661')]
+[2024-09-06 08:37:17,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3686.4, 300 sec: 3140.3). Total num frames: 4288512. Throughput: 0: 928.7. Samples: 69506. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:37:17,302][01070] Avg episode reward: [(0, '20.777')]
+[2024-09-06 08:37:18,168][19110] Updated weights for policy 0, policy_version 1048 (0.0027)
+[2024-09-06 08:37:22,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3754.7, 300 sec: 3190.6). Total num frames: 4308992. Throughput: 0: 873.3. Samples: 74104. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:37:22,304][01070] Avg episode reward: [(0, '21.018')]
+[2024-09-06 08:37:27,299][01070] Fps is (10 sec: 4505.6, 60 sec: 3822.9, 300 sec: 3276.8). Total num frames: 4333568. Throughput: 0: 938.8. Samples: 81312. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:37:27,300][19110] Updated weights for policy 0, policy_version 1058 (0.0031)
+[2024-09-06 08:37:27,301][01070] Avg episode reward: [(0, '21.381')]
+[2024-09-06 08:37:27,314][19093] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001058_4333568.pth...
+[2024-09-06 08:37:27,438][19093] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000975_3993600.pth
+[2024-09-06 08:37:32,300][01070] Fps is (10 sec: 4095.5, 60 sec: 3686.3, 300 sec: 3276.8). Total num frames: 4349952. Throughput: 0: 954.6. Samples: 84768. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:37:32,306][01070] Avg episode reward: [(0, '20.498')]
+[2024-09-06 08:37:37,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3618.2, 300 sec: 3276.8). Total num frames: 4366336. Throughput: 0: 899.8. Samples: 89288. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:37:37,302][01070] Avg episode reward: [(0, '20.356')]
+[2024-09-06 08:37:38,951][19110] Updated weights for policy 0, policy_version 1068 (0.0030)
+[2024-09-06 08:37:42,302][01070] Fps is (10 sec: 3685.8, 60 sec: 3754.5, 300 sec: 3312.3). Total num frames: 4386816. Throughput: 0: 918.0. Samples: 95532. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:37:42,306][01070] Avg episode reward: [(0, '18.966')]
+[2024-09-06 08:37:47,299][01070] Fps is (10 sec: 4505.6, 60 sec: 3823.0, 300 sec: 3379.2). Total num frames: 4411392. Throughput: 0: 960.9. Samples: 99118. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:37:47,303][01070] Avg episode reward: [(0, '19.345')]
+[2024-09-06 08:37:48,240][19110] Updated weights for policy 0, policy_version 1078 (0.0013)
+[2024-09-06 08:37:52,299][01070] Fps is (10 sec: 3687.5, 60 sec: 3618.1, 300 sec: 3342.3). Total num frames: 4423680. Throughput: 0: 989.1. Samples: 104388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:37:52,301][01070] Avg episode reward: [(0, '19.443')]
+[2024-09-06 08:37:57,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3755.0, 300 sec: 3402.8). Total num frames: 4448256. Throughput: 0: 957.7. Samples: 109982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:37:57,301][01070] Avg episode reward: [(0, '20.099')]
+[2024-09-06 08:37:59,151][19110] Updated weights for policy 0, policy_version 1088 (0.0024)
+[2024-09-06 08:38:02,299][01070] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3428.5). Total num frames: 4468736. Throughput: 0: 978.0. Samples: 113514. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:38:02,306][01070] Avg episode reward: [(0, '20.360')]
+[2024-09-06 08:38:07,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3423.1). Total num frames: 4485120. Throughput: 0: 1019.1. Samples: 119964. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:38:07,302][01070] Avg episode reward: [(0, '20.240')]
+[2024-09-06 08:38:10,312][19110] Updated weights for policy 0, policy_version 1098 (0.0022)
+[2024-09-06 08:38:12,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3418.0). Total num frames: 4501504. Throughput: 0: 953.8. Samples: 124232. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:38:12,304][01070] Avg episode reward: [(0, '19.557')]
+[2024-09-06 08:38:17,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3467.9). Total num frames: 4526080. Throughput: 0: 954.6. Samples: 127726. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:38:17,301][01070] Avg episode reward: [(0, '20.239')]
+[2024-09-06 08:38:19,439][19110] Updated weights for policy 0, policy_version 1108 (0.0041)
+[2024-09-06 08:38:22,301][01070] Fps is (10 sec: 4504.4, 60 sec: 3959.3, 300 sec: 3488.1). Total num frames: 4546560. Throughput: 0: 1011.7. Samples: 134818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:38:22,304][01070] Avg episode reward: [(0, '20.506')]
+[2024-09-06 08:38:27,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3481.6). Total num frames: 4562944. Throughput: 0: 977.9. Samples: 139534. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:38:27,303][01070] Avg episode reward: [(0, '20.585')]
+[2024-09-06 08:38:31,030][19110] Updated weights for policy 0, policy_version 1118 (0.0046)
+[2024-09-06 08:38:32,299][01070] Fps is (10 sec: 3687.4, 60 sec: 3891.3, 300 sec: 3500.2). Total num frames: 4583424. Throughput: 0: 953.9. Samples: 142044. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
+[2024-09-06 08:38:32,306][01070] Avg episode reward: [(0, '20.308')]
+[2024-09-06 08:38:37,299][01070] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3541.8). Total num frames: 4608000. Throughput: 0: 993.6. Samples: 149102. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:38:37,304][01070] Avg episode reward: [(0, '21.252')]
+[2024-09-06 08:38:40,626][19110] Updated weights for policy 0, policy_version 1128 (0.0030)
+[2024-09-06 08:38:42,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3959.7, 300 sec: 3534.3). Total num frames: 4624384. Throughput: 0: 994.4. Samples: 154730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:38:42,303][01070] Avg episode reward: [(0, '20.914')]
+[2024-09-06 08:38:47,299][01070] Fps is (10 sec: 3276.7, 60 sec: 3822.9, 300 sec: 3527.1). Total num frames: 4640768. Throughput: 0: 963.1. Samples: 156854. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:38:47,307][01070] Avg episode reward: [(0, '20.844')]
+[2024-09-06 08:38:51,335][19110] Updated weights for policy 0, policy_version 1138 (0.0028)
+[2024-09-06 08:38:52,299][01070] Fps is (10 sec: 4095.9, 60 sec: 4027.7, 300 sec: 3564.6). Total num frames: 4665344. Throughput: 0: 963.3. Samples: 163312. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:38:52,301][01070] Avg episode reward: [(0, '22.493')]
+[2024-09-06 08:38:52,304][19093] Saving new best policy, reward=22.493!
+[2024-09-06 08:38:57,299][01070] Fps is (10 sec: 4505.7, 60 sec: 3959.5, 300 sec: 3578.6). Total num frames: 4685824. Throughput: 0: 1017.3. Samples: 170010. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:38:57,305][01070] Avg episode reward: [(0, '21.806')]
+[2024-09-06 08:39:02,299][01070] Fps is (10 sec: 3276.9, 60 sec: 3822.9, 300 sec: 3549.9). Total num frames: 4698112. Throughput: 0: 985.0. Samples: 172050. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:39:02,300][01070] Avg episode reward: [(0, '22.885')]
+[2024-09-06 08:39:02,305][19093] Saving new best policy, reward=22.885!
+[2024-09-06 08:39:02,950][19110] Updated weights for policy 0, policy_version 1148 (0.0035)
+[2024-09-06 08:39:07,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3891.2, 300 sec: 3563.5). Total num frames: 4718592. Throughput: 0: 948.3. Samples: 177488. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:39:07,301][01070] Avg episode reward: [(0, '23.190')]
+[2024-09-06 08:39:07,318][19093] Saving new best policy, reward=23.190!
+[2024-09-06 08:39:11,864][19110] Updated weights for policy 0, policy_version 1158 (0.0024)
+[2024-09-06 08:39:12,299][01070] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3596.5). Total num frames: 4743168. Throughput: 0: 994.3. Samples: 184276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
+[2024-09-06 08:39:12,303][01070] Avg episode reward: [(0, '23.069')]
+[2024-09-06 08:39:17,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3891.2, 300 sec: 3588.9). Total num frames: 4759552. Throughput: 0: 1001.5. Samples: 187112. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
+[2024-09-06 08:39:17,301][01070] Avg episode reward: [(0, '22.125')]
+[2024-09-06 08:39:22,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3823.1, 300 sec: 3581.6). Total num frames: 4775936. Throughput: 0: 941.3. Samples: 191462. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-09-06 08:39:22,303][01070] Avg episode reward: [(0, '21.027')]
+[2024-09-06 08:39:23,456][19110] Updated weights for policy 0, policy_version 1168 (0.0022)
+[2024-09-06 08:39:27,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3611.9). Total num frames: 4800512. Throughput: 0: 973.6. Samples: 198540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:39:27,301][01070] Avg episode reward: [(0, '19.180')]
+[2024-09-06 08:39:27,314][19093] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001172_4800512.pth...
+[2024-09-06 08:39:27,463][19093] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth
+[2024-09-06 08:39:32,300][01070] Fps is (10 sec: 4504.9, 60 sec: 3959.4, 300 sec: 3622.7). Total num frames: 4820992. Throughput: 0: 1000.5. Samples: 201878. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
+[2024-09-06 08:39:32,303][01070] Avg episode reward: [(0, '20.069')]
+[2024-09-06 08:39:33,797][19110] Updated weights for policy 0, policy_version 1178 (0.0024)
+[2024-09-06 08:39:37,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3754.7, 300 sec: 3597.4). Total num frames: 4833280. Throughput: 0: 959.6. Samples: 206492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
+[2024-09-06 08:39:37,301][01070] Avg episode reward: [(0, '19.170')]
+[2024-09-06 08:39:42,299][01070] Fps is (10 sec: 3687.0, 60 sec: 3891.2, 300 sec: 3625.4). Total num frames: 4857856. Throughput: 0: 947.1. Samples: 212628. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
+[2024-09-06 08:39:42,306][01070] Avg episode reward: [(0, '20.382')]
+[2024-09-06 08:39:43,732][19110] Updated weights for policy 0, policy_version 1188 (0.0024)
+[2024-09-06 08:39:47,299][01070] Fps is (10 sec: 4505.6, 60 sec: 3959.5, 300 sec: 3635.2). Total num frames: 4878336. Throughput: 0: 980.8. Samples: 216188. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:39:47,313][01070] Avg episode reward: [(0, '21.641')]
+[2024-09-06 08:39:52,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3823.0, 300 sec: 3627.9). Total num frames: 4894720. Throughput: 0: 984.4. Samples: 221786. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:39:52,301][01070] Avg episode reward: [(0, '21.803')]
+[2024-09-06 08:39:55,248][19110] Updated weights for policy 0, policy_version 1198 (0.0031)
+[2024-09-06 08:39:57,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3822.9, 300 sec: 3637.2). Total num frames: 4915200. Throughput: 0: 951.6. Samples: 227098. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:39:57,304][01070] Avg episode reward: [(0, '22.439')]
+[2024-09-06 08:40:02,299][01070] Fps is (10 sec: 4505.6, 60 sec: 4027.7, 300 sec: 3662.3). Total num frames: 4939776. Throughput: 0: 968.4. Samples: 230692. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:40:02,305][01070] Avg episode reward: [(0, '23.387')]
+[2024-09-06 08:40:02,307][19093] Saving new best policy, reward=23.387!
+[2024-09-06 08:40:04,048][19110] Updated weights for policy 0, policy_version 1208 (0.0019)
+[2024-09-06 08:40:07,299][01070] Fps is (10 sec: 4096.0, 60 sec: 3959.5, 300 sec: 3654.9). Total num frames: 4956160. Throughput: 0: 1015.8. Samples: 237174. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:40:07,304][01070] Avg episode reward: [(0, '25.478')]
+[2024-09-06 08:40:07,312][19093] Saving new best policy, reward=25.478!
+[2024-09-06 08:40:12,299][01070] Fps is (10 sec: 3276.8, 60 sec: 3822.9, 300 sec: 3647.8). Total num frames: 4972544. Throughput: 0: 950.4. Samples: 241310. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
+[2024-09-06 08:40:12,301][01070] Avg episode reward: [(0, '26.573')]
+[2024-09-06 08:40:12,304][19093] Saving new best policy, reward=26.573!
+[2024-09-06 08:40:15,918][19110] Updated weights for policy 0, policy_version 1218 (0.0034)
+[2024-09-06 08:40:17,299][01070] Fps is (10 sec: 3686.4, 60 sec: 3891.2, 300 sec: 3656.1). Total num frames: 4993024. Throughput: 0: 947.8. Samples: 244528. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
+[2024-09-06 08:40:17,301][01070] Avg episode reward: [(0, '26.655')]
+[2024-09-06 08:40:17,310][19093] Saving new best policy, reward=26.655!
+[2024-09-06 08:40:19,413][19093] Stopping Batcher_0...
+[2024-09-06 08:40:19,413][01070] Component Batcher_0 stopped!
+[2024-09-06 08:40:19,415][19093] Loop batcher_evt_loop terminating...
+[2024-09-06 08:40:19,420][19093] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-09-06 08:40:19,470][19110] Weights refcount: 2 0
+[2024-09-06 08:40:19,478][01070] Component InferenceWorker_p0-w0 stopped!
+[2024-09-06 08:40:19,481][19110] Stopping InferenceWorker_p0-w0...
+[2024-09-06 08:40:19,481][19110] Loop inference_proc0-0_evt_loop terminating...
+[2024-09-06 08:40:19,543][19093] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001058_4333568.pth
+[2024-09-06 08:40:19,557][19093] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-09-06 08:40:19,761][01070] Component LearnerWorker_p0 stopped!
+[2024-09-06 08:40:19,761][19093] Stopping LearnerWorker_p0...
+[2024-09-06 08:40:19,766][19093] Loop learner_proc0_evt_loop terminating...
+[2024-09-06 08:40:19,774][01070] Component RolloutWorker_w3 stopped!
+[2024-09-06 08:40:19,777][19115] Stopping RolloutWorker_w3...
+[2024-09-06 08:40:19,779][19115] Loop rollout_proc3_evt_loop terminating...
+[2024-09-06 08:40:19,804][01070] Component RolloutWorker_w1 stopped!
+[2024-09-06 08:40:19,806][19111] Stopping RolloutWorker_w1...
+[2024-09-06 08:40:19,813][19111] Loop rollout_proc1_evt_loop terminating...
+[2024-09-06 08:40:19,874][01070] Component RolloutWorker_w7 stopped!
+[2024-09-06 08:40:19,880][19117] Stopping RolloutWorker_w7...
+[2024-09-06 08:40:19,888][19117] Loop rollout_proc7_evt_loop terminating...
+[2024-09-06 08:40:19,902][01070] Component RolloutWorker_w5 stopped!
+[2024-09-06 08:40:19,904][19116] Stopping RolloutWorker_w5...
+[2024-09-06 08:40:19,909][19116] Loop rollout_proc5_evt_loop terminating...
+[2024-09-06 08:40:20,003][19118] Stopping RolloutWorker_w6...
+[2024-09-06 08:40:20,003][19118] Loop rollout_proc6_evt_loop terminating...
+[2024-09-06 08:40:20,003][01070] Component RolloutWorker_w6 stopped!
+[2024-09-06 08:40:20,035][19113] Stopping RolloutWorker_w2...
+[2024-09-06 08:40:20,037][19113] Loop rollout_proc2_evt_loop terminating...
+[2024-09-06 08:40:20,035][01070] Component RolloutWorker_w2 stopped!
+[2024-09-06 08:40:20,058][19114] Stopping RolloutWorker_w4...
+[2024-09-06 08:40:20,057][01070] Component RolloutWorker_w4 stopped!
+[2024-09-06 08:40:20,062][19114] Loop rollout_proc4_evt_loop terminating...
+[2024-09-06 08:40:20,066][19112] Stopping RolloutWorker_w0...
+[2024-09-06 08:40:20,066][01070] Component RolloutWorker_w0 stopped!
+[2024-09-06 08:40:20,068][01070] Waiting for process learner_proc0 to stop...
+[2024-09-06 08:40:20,078][19112] Loop rollout_proc0_evt_loop terminating...
+[2024-09-06 08:40:21,230][01070] Waiting for process inference_proc0-0 to join...
+[2024-09-06 08:40:21,233][01070] Waiting for process rollout_proc0 to join...
+[2024-09-06 08:40:24,143][01070] Waiting for process rollout_proc1 to join...
+[2024-09-06 08:40:24,148][01070] Waiting for process rollout_proc2 to join...
+[2024-09-06 08:40:24,150][01070] Waiting for process rollout_proc3 to join...
+[2024-09-06 08:40:24,153][01070] Waiting for process rollout_proc4 to join...
+[2024-09-06 08:40:24,159][01070] Waiting for process rollout_proc5 to join...
+[2024-09-06 08:40:24,162][01070] Waiting for process rollout_proc6 to join...
+[2024-09-06 08:40:24,165][01070] Waiting for process rollout_proc7 to join...
+[2024-09-06 08:40:24,168][01070] Batcher 0 profile tree view:
+batching: 7.2186, releasing_batches: 0.0064
+[2024-09-06 08:40:24,170][01070] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0054
+  wait_policy_total: 102.6532
+update_model: 2.2548
+  weight_update: 0.0030
+one_step: 0.0026
+  handle_policy_step: 154.4121
+    deserialize: 3.6770, stack: 0.8213, obs_to_device_normalize: 31.1067, forward: 82.7946, send_messages: 7.5294
+    prepare_outputs: 21.0675
+      to_cpu: 12.5076
+[2024-09-06 08:40:24,171][01070] Learner 0 profile tree view:
+misc: 0.0012, prepare_batch: 5.2823
+train: 21.8730
+  epoch_init: 0.0014, minibatch_init: 0.0016, losses_postprocess: 0.1603, kl_divergence: 0.2048, after_optimizer: 0.9110
+  calculate_losses: 8.7013
+    losses_init: 0.0013, forward_head: 0.6601, bptt_initial: 6.1101, tail: 0.3325, advantages_returns: 0.0894, losses: 0.9715
+    bptt: 0.4678
+      bptt_forward_core: 0.4488
+  update: 11.7699
+    clip: 0.2453
+[2024-09-06 08:40:24,173][01070] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0619, enqueue_policy_requests: 23.3356, env_step: 206.1955, overhead: 3.3833, complete_rollouts: 1.8563
+save_policy_outputs: 5.2619
+  split_output_tensors: 2.1953
+[2024-09-06 08:40:24,175][01070] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0745, enqueue_policy_requests: 24.4494, env_step: 203.3563, overhead: 3.1667, complete_rollouts: 1.6788
+save_policy_outputs: 4.9515
+  split_output_tensors: 2.0046
+[2024-09-06 08:40:24,177][01070] Loop Runner_EvtLoop terminating...
+[2024-09-06 08:40:24,179][01070] Runner profile tree view:
+main_loop: 294.6944
+[2024-09-06 08:40:24,180][01070] Collected {0: 5005312}, FPS: 3391.4
+[2024-09-06 08:56:44,318][01070] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-06 08:56:44,320][01070] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-06 08:56:44,322][01070] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-06 08:56:44,324][01070] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-06 08:56:44,326][01070] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-06 08:56:44,327][01070] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-06 08:56:44,328][01070] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-06 08:56:44,329][01070] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-06 08:56:44,331][01070] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-09-06 08:56:44,332][01070] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-09-06 08:56:44,333][01070] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-06 08:56:44,334][01070] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-06 08:56:44,339][01070] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-06 08:56:44,340][01070] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-06 08:56:44,341][01070] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-06 08:56:44,368][01070] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-06 08:56:44,370][01070] RunningMeanStd input shape: (1,)
+[2024-09-06 08:56:44,390][01070] ConvEncoder: input_channels=3
+[2024-09-06 08:56:44,435][01070] Conv encoder output size: 512
+[2024-09-06 08:56:44,436][01070] Policy head output size: 512
+[2024-09-06 08:56:44,457][01070] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-09-06 08:56:44,883][01070] Num frames 100...
+[2024-09-06 08:56:45,006][01070] Num frames 200...
+[2024-09-06 08:56:45,128][01070] Num frames 300...
+[2024-09-06 08:56:45,247][01070] Num frames 400...
+[2024-09-06 08:56:45,367][01070] Num frames 500...
+[2024-09-06 08:56:45,497][01070] Num frames 600...
+[2024-09-06 08:56:45,618][01070] Num frames 700...
+[2024-09-06 08:56:45,741][01070] Num frames 800...
+[2024-09-06 08:56:45,860][01070] Num frames 900...
+[2024-09-06 08:56:45,978][01070] Num frames 1000...
+[2024-09-06 08:56:46,102][01070] Num frames 1100...
+[2024-09-06 08:56:46,224][01070] Num frames 1200...
+[2024-09-06 08:56:46,348][01070] Num frames 1300...
+[2024-09-06 08:56:46,479][01070] Num frames 1400...
+[2024-09-06 08:56:46,606][01070] Num frames 1500...
+[2024-09-06 08:56:46,726][01070] Num frames 1600...
+[2024-09-06 08:56:46,845][01070] Num frames 1700...
+[2024-09-06 08:56:46,967][01070] Num frames 1800...
+[2024-09-06 08:56:47,110][01070] Avg episode rewards: #0: 46.719, true rewards: #0: 18.720
+[2024-09-06 08:56:47,113][01070] Avg episode reward: 46.719, avg true_objective: 18.720
+[2024-09-06 08:56:47,150][01070] Num frames 1900...
+[2024-09-06 08:56:47,268][01070] Num frames 2000...
+[2024-09-06 08:56:47,388][01070] Num frames 2100...
+[2024-09-06 08:56:47,523][01070] Num frames 2200...
+[2024-09-06 08:56:47,671][01070] Num frames 2300...
+[2024-09-06 08:56:47,751][01070] Avg episode rewards: #0: 27.100, true rewards: #0: 11.600
+[2024-09-06 08:56:47,752][01070] Avg episode reward: 27.100, avg true_objective: 11.600
+[2024-09-06 08:56:47,854][01070] Num frames 2400...
+[2024-09-06 08:56:47,975][01070] Num frames 2500...
+[2024-09-06 08:56:48,094][01070] Num frames 2600...
+[2024-09-06 08:56:48,217][01070] Num frames 2700...
+[2024-09-06 08:56:48,342][01070] Num frames 2800...
+[2024-09-06 08:56:48,467][01070] Num frames 2900...
+[2024-09-06 08:56:48,602][01070] Num frames 3000...
+[2024-09-06 08:56:48,749][01070] Num frames 3100...
+[2024-09-06 08:56:48,919][01070] Num frames 3200...
+[2024-09-06 08:56:49,093][01070] Num frames 3300...
+[2024-09-06 08:56:49,273][01070] Avg episode rewards: #0: 26.253, true rewards: #0: 11.253
+[2024-09-06 08:56:49,277][01070] Avg episode reward: 26.253, avg true_objective: 11.253
+[2024-09-06 08:56:49,319][01070] Num frames 3400...
+[2024-09-06 08:56:49,496][01070] Num frames 3500...
+[2024-09-06 08:56:49,661][01070] Num frames 3600...
+[2024-09-06 08:56:49,822][01070] Num frames 3700...
+[2024-09-06 08:56:50,036][01070] Avg episode rewards: #0: 21.230, true rewards: #0: 9.480
+[2024-09-06 08:56:50,038][01070] Avg episode reward: 21.230, avg true_objective: 9.480
+[2024-09-06 08:56:50,057][01070] Num frames 3800...
+[2024-09-06 08:56:50,224][01070] Num frames 3900...
+[2024-09-06 08:56:50,397][01070] Num frames 4000...
+[2024-09-06 08:56:50,585][01070] Num frames 4100...
+[2024-09-06 08:56:50,755][01070] Num frames 4200...
+[2024-09-06 08:56:50,944][01070] Num frames 4300...
+[2024-09-06 08:56:51,125][01070] Num frames 4400...
+[2024-09-06 08:56:51,259][01070] Num frames 4500...
+[2024-09-06 08:56:51,382][01070] Num frames 4600...
+[2024-09-06 08:56:51,504][01070] Num frames 4700...
+[2024-09-06 08:56:51,623][01070] Num frames 4800...
+[2024-09-06 08:56:51,752][01070] Num frames 4900...
+[2024-09-06 08:56:51,870][01070] Num frames 5000...
+[2024-09-06 08:56:51,988][01070] Num frames 5100...
+[2024-09-06 08:56:52,111][01070] Num frames 5200...
+[2024-09-06 08:56:52,228][01070] Num frames 5300...
+[2024-09-06 08:56:52,393][01070] Avg episode rewards: #0: 24.784, true rewards: #0: 10.784
+[2024-09-06 08:56:52,394][01070] Avg episode reward: 24.784, avg true_objective: 10.784
+[2024-09-06 08:56:52,408][01070] Num frames 5400...
+[2024-09-06 08:56:52,534][01070] Num frames 5500...
+[2024-09-06 08:56:52,657][01070] Num frames 5600...
+[2024-09-06 08:56:52,788][01070] Num frames 5700...
+[2024-09-06 08:56:52,907][01070] Num frames 5800...
+[2024-09-06 08:56:53,028][01070] Num frames 5900...
+[2024-09-06 08:56:53,148][01070] Num frames 6000...
+[2024-09-06 08:56:53,268][01070] Num frames 6100...
+[2024-09-06 08:56:53,388][01070] Num frames 6200...
+[2024-09-06 08:56:53,515][01070] Num frames 6300...
+[2024-09-06 08:56:53,638][01070] Num frames 6400...
+[2024-09-06 08:56:53,779][01070] Num frames 6500...
+[2024-09-06 08:56:53,901][01070] Num frames 6600...
+[2024-09-06 08:56:54,025][01070] Num frames 6700...
+[2024-09-06 08:56:54,146][01070] Num frames 6800...
+[2024-09-06 08:56:54,268][01070] Num frames 6900...
+[2024-09-06 08:56:54,390][01070] Num frames 7000...
+[2024-09-06 08:56:54,560][01070] Avg episode rewards: #0: 28.313, true rewards: #0: 11.813
+[2024-09-06 08:56:54,562][01070] Avg episode reward: 28.313, avg true_objective: 11.813
+[2024-09-06 08:56:54,581][01070] Num frames 7100...
+[2024-09-06 08:56:54,699][01070] Num frames 7200...
+[2024-09-06 08:56:54,827][01070] Num frames 7300...
+[2024-09-06 08:56:54,945][01070] Num frames 7400...
+[2024-09-06 08:56:55,064][01070] Num frames 7500...
+[2024-09-06 08:56:55,188][01070] Num frames 7600...
+[2024-09-06 08:56:55,281][01070] Avg episode rewards: #0: 25.760, true rewards: #0: 10.903
+[2024-09-06 08:56:55,283][01070] Avg episode reward: 25.760, avg true_objective: 10.903
+[2024-09-06 08:56:55,366][01070] Num frames 7700...
+[2024-09-06 08:56:55,489][01070] Num frames 7800...
+[2024-09-06 08:56:55,612][01070] Num frames 7900...
+[2024-09-06 08:56:55,732][01070] Num frames 8000...
+[2024-09-06 08:56:55,892][01070] Avg episode rewards: #0: 23.600, true rewards: #0: 10.100
+[2024-09-06 08:56:55,894][01070] Avg episode reward: 23.600, avg true_objective: 10.100
+[2024-09-06 08:56:55,921][01070] Num frames 8100...
+[2024-09-06 08:56:56,039][01070] Num frames 8200...
+[2024-09-06 08:56:56,159][01070] Num frames 8300...
+[2024-09-06 08:56:56,280][01070] Num frames 8400...
+[2024-09-06 08:56:56,402][01070] Num frames 8500...
+[2024-09-06 08:56:56,532][01070] Num frames 8600...
+[2024-09-06 08:56:56,656][01070] Num frames 8700...
+[2024-09-06 08:56:56,782][01070] Num frames 8800...
+[2024-09-06 08:56:56,911][01070] Num frames 8900...
+[2024-09-06 08:56:57,036][01070] Num frames 9000...
+[2024-09-06 08:56:57,162][01070] Num frames 9100...
+[2024-09-06 08:56:57,286][01070] Num frames 9200...
+[2024-09-06 08:56:57,409][01070] Num frames 9300...
+[2024-09-06 08:56:57,498][01070] Avg episode rewards: #0: 24.253, true rewards: #0: 10.364
+[2024-09-06 08:56:57,500][01070] Avg episode reward: 24.253, avg true_objective: 10.364
+[2024-09-06 08:56:57,588][01070] Num frames 9400...
+[2024-09-06 08:56:57,710][01070] Num frames 9500...
+[2024-09-06 08:56:57,848][01070] Num frames 9600...
+[2024-09-06 08:56:57,973][01070] Num frames 9700...
+[2024-09-06 08:56:58,097][01070] Num frames 9800...
+[2024-09-06 08:56:58,209][01070] Avg episode rewards: #0: 22.746, true rewards: #0: 9.846
+[2024-09-06 08:56:58,211][01070] Avg episode reward: 22.746, avg true_objective: 9.846
+[2024-09-06 08:57:59,802][01070] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2024-09-06 09:00:55,778][01070] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2024-09-06 09:00:55,780][01070] Overriding arg 'num_workers' with value 1 passed from command line
+[2024-09-06 09:00:55,782][01070] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-09-06 09:00:55,784][01070] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-09-06 09:00:55,786][01070] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-09-06 09:00:55,789][01070] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-09-06 09:00:55,791][01070] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2024-09-06 09:00:55,792][01070] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-09-06 09:00:55,793][01070] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-09-06 09:00:55,794][01070] Adding new argument 'hf_repository'='Re-Re/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-09-06 09:00:55,795][01070] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-09-06 09:00:55,796][01070] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-09-06 09:00:55,797][01070] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-09-06 09:00:55,798][01070] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-09-06 09:00:55,799][01070] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-09-06 09:00:55,830][01070] RunningMeanStd input shape: (3, 72, 128)
+[2024-09-06 09:00:55,832][01070] RunningMeanStd input shape: (1,)
+[2024-09-06 09:00:55,846][01070] ConvEncoder: input_channels=3
+[2024-09-06 09:00:55,882][01070] Conv encoder output size: 512
+[2024-09-06 09:00:55,884][01070] Policy head output size: 512
+[2024-09-06 09:00:55,904][01070] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000001222_5005312.pth...
+[2024-09-06 09:00:56,320][01070] Num frames 100...
+[2024-09-06 09:00:56,441][01070] Num frames 200...
+[2024-09-06 09:00:56,597][01070] Num frames 300...
+[2024-09-06 09:00:56,715][01070] Num frames 400...
+[2024-09-06 09:00:56,840][01070] Num frames 500...
+[2024-09-06 09:00:56,960][01070] Num frames 600...
+[2024-09-06 09:00:57,080][01070] Num frames 700...
+[2024-09-06 09:00:57,182][01070] Avg episode rewards: #0: 16.380, true rewards: #0: 7.380
+[2024-09-06 09:00:57,184][01070] Avg episode reward: 16.380, avg true_objective: 7.380
+[2024-09-06 09:00:57,264][01070] Num frames 800...
+[2024-09-06 09:00:57,399][01070] Num frames 900...
+[2024-09-06 09:00:57,529][01070] Num frames 1000...
+[2024-09-06 09:00:57,650][01070] Num frames 1100...
+[2024-09-06 09:00:57,775][01070] Num frames 1200...
+[2024-09-06 09:00:57,898][01070] Num frames 1300...
+[2024-09-06 09:00:58,016][01070] Num frames 1400...
+[2024-09-06 09:00:58,136][01070] Num frames 1500...
+[2024-09-06 09:00:58,255][01070] Num frames 1600...
+[2024-09-06 09:00:58,314][01070] Avg episode rewards: #0: 18.010, true rewards: #0: 8.010
+[2024-09-06 09:00:58,316][01070] Avg episode reward: 18.010, avg true_objective: 8.010
+[2024-09-06 09:00:58,433][01070] Num frames 1700...
+[2024-09-06 09:00:58,562][01070] Num frames 1800...
+[2024-09-06 09:00:58,686][01070] Num frames 1900...
+[2024-09-06 09:00:58,804][01070] Num frames 2000...
+[2024-09-06 09:00:58,927][01070] Num frames 2100...
+[2024-09-06 09:00:59,047][01070] Num frames 2200...
+[2024-09-06 09:00:59,165][01070] Num frames 2300...
+[2024-09-06 09:00:59,285][01070] Num frames 2400...
+[2024-09-06 09:00:59,413][01070] Num frames 2500...
+[2024-09-06 09:00:59,544][01070] Num frames 2600...
+[2024-09-06 09:00:59,669][01070] Num frames 2700...
+[2024-09-06 09:00:59,789][01070] Num frames 2800...
+[2024-09-06 09:00:59,937][01070] Num frames 2900...
+[2024-09-06 09:01:00,112][01070] Num frames 3000...
+[2024-09-06 09:01:00,278][01070] Num frames 3100...
+[2024-09-06 09:01:00,453][01070] Num frames 3200...
+[2024-09-06 09:01:00,623][01070] Num frames 3300...
+[2024-09-06 09:01:00,786][01070] Num frames 3400...
+[2024-09-06 09:01:00,952][01070] Num frames 3500...
+[2024-09-06 09:01:01,119][01070] Num frames 3600...
+[2024-09-06 09:01:01,294][01070] Num frames 3700...
+[2024-09-06 09:01:01,356][01070] Avg episode rewards: #0: 30.673, true rewards: #0: 12.340
+[2024-09-06 09:01:01,357][01070] Avg episode reward: 30.673, avg true_objective: 12.340
+[2024-09-06 09:01:01,535][01070] Num frames 3800...
+[2024-09-06 09:01:01,711][01070] Num frames 3900...
+[2024-09-06 09:01:01,881][01070] Num frames 4000...
+[2024-09-06 09:01:02,049][01070] Num frames 4100...
+[2024-09-06 09:01:02,222][01070] Num frames 4200...
+[2024-09-06 09:01:02,396][01070] Num frames 4300...
+[2024-09-06 09:01:02,534][01070] Num frames 4400...
+[2024-09-06 09:01:02,655][01070] Num frames 4500...
+[2024-09-06 09:01:02,776][01070] Num frames 4600...
+[2024-09-06 09:01:02,898][01070] Num frames 4700...
+[2024-09-06 09:01:03,020][01070] Num frames 4800...
+[2024-09-06 09:01:03,140][01070] Num frames 4900...
+[2024-09-06 09:01:03,261][01070] Num frames 5000...
+[2024-09-06 09:01:03,383][01070] Num frames 5100...
+[2024-09-06 09:01:03,519][01070] Num frames 5200...
+[2024-09-06 09:01:03,641][01070] Num frames 5300...
+[2024-09-06 09:01:03,817][01070] Avg episode rewards: #0: 34.225, true rewards: #0: 13.475
+[2024-09-06 09:01:03,818][01070] Avg episode reward: 34.225, avg true_objective: 13.475
+[2024-09-06 09:01:03,835][01070] Num frames 5400...
+[2024-09-06 09:01:03,956][01070] Num frames 5500...
+[2024-09-06 09:01:04,074][01070] Num frames 5600...
+[2024-09-06 09:01:04,194][01070] Num frames 5700...
+[2024-09-06 09:01:04,314][01070] Num frames 5800...
+[2024-09-06 09:01:04,436][01070] Num frames 5900...
+[2024-09-06 09:01:04,574][01070] Num frames 6000...
+[2024-09-06 09:01:04,693][01070] Num frames 6100...
+[2024-09-06 09:01:04,810][01070] Num frames 6200...
+[2024-09-06 09:01:04,934][01070] Num frames 6300...
+[2024-09-06 09:01:05,057][01070] Num frames 6400...
+[2024-09-06 09:01:05,177][01070] Num frames 6500...
+[2024-09-06 09:01:05,296][01070] Num frames 6600...
+[2024-09-06 09:01:05,424][01070] Num frames 6700...
+[2024-09-06 09:01:05,562][01070] Num frames 6800...
+[2024-09-06 09:01:05,698][01070] Num frames 6900...
+[2024-09-06 09:01:05,816][01070] Num frames 7000...
+[2024-09-06 09:01:05,936][01070] Num frames 7100...
+[2024-09-06 09:01:06,057][01070] Num frames 7200...
+[2024-09-06 09:01:06,179][01070] Num frames 7300...
+[2024-09-06 09:01:06,303][01070] Num frames 7400...
+[2024-09-06 09:01:06,469][01070] Avg episode rewards: #0: 38.779, true rewards: #0: 14.980
+[2024-09-06 09:01:06,474][01070] Avg episode reward: 38.779, avg true_objective: 14.980
+[2024-09-06 09:01:06,493][01070] Num frames 7500...
+[2024-09-06 09:01:06,629][01070] Num frames 7600...
+[2024-09-06 09:01:06,753][01070] Num frames 7700...
+[2024-09-06 09:01:06,875][01070] Num frames 7800...
+[2024-09-06 09:01:06,995][01070] Num frames 7900...
+[2024-09-06 09:01:07,118][01070] Num frames 8000...
+[2024-09-06 09:01:07,240][01070] Num frames 8100...
+[2024-09-06 09:01:07,359][01070] Num frames 8200...
+[2024-09-06 09:01:07,476][01070] Avg episode rewards: #0: 34.920, true rewards: #0: 13.753
+[2024-09-06 09:01:07,478][01070] Avg episode reward: 34.920, avg true_objective: 13.753
+[2024-09-06 09:01:07,541][01070] Num frames 8300...
+[2024-09-06 09:01:07,670][01070] Num frames 8400...
+[2024-09-06 09:01:07,789][01070] Num frames 8500...
+[2024-09-06 09:01:07,912][01070] Num frames 8600...
+[2024-09-06 09:01:08,030][01070] Num frames 8700...
+[2024-09-06 09:01:08,150][01070] Num frames 8800...
+[2024-09-06 09:01:08,275][01070] Num frames 8900...
+[2024-09-06 09:01:08,400][01070] Avg episode rewards: #0: 31.794, true rewards: #0: 12.794
+[2024-09-06 09:01:08,402][01070] Avg episode reward: 31.794, avg true_objective: 12.794
+[2024-09-06 09:01:08,457][01070] Num frames 9000...
+[2024-09-06 09:01:08,587][01070] Num frames 9100...
+[2024-09-06 09:01:08,723][01070] Num frames 9200...
+[2024-09-06 09:01:08,851][01070] Num frames 9300...
+[2024-09-06 09:01:08,979][01070] Num frames 9400...
+[2024-09-06 09:01:09,106][01070] Num frames 9500...
+[2024-09-06 09:01:09,230][01070] Num frames 9600...
+[2024-09-06 09:01:09,356][01070] Num frames 9700...
+[2024-09-06 09:01:09,487][01070] Num frames 9800...
+[2024-09-06 09:01:09,614][01070] Num frames 9900...
+[2024-09-06 09:01:09,745][01070] Num frames 10000...
+[2024-09-06 09:01:09,870][01070] Num frames 10100...
+[2024-09-06 09:01:09,995][01070] Num frames 10200...
+[2024-09-06 09:01:10,118][01070] Num frames 10300...
+[2024-09-06 09:01:10,238][01070] Num frames 10400...
+[2024-09-06 09:01:10,360][01070] Num frames 10500...
+[2024-09-06 09:01:10,493][01070] Num frames 10600...
+[2024-09-06 09:01:10,614][01070] Num frames 10700...
+[2024-09-06 09:01:10,741][01070] Num frames 10800...
+[2024-09-06 09:01:10,866][01070] Num frames 10900...
+[2024-09-06 09:01:10,993][01070] Num frames 11000...
+[2024-09-06 09:01:11,116][01070] Avg episode rewards: #0: 34.820, true rewards: #0: 13.820
+[2024-09-06 09:01:11,118][01070] Avg episode reward: 34.820, avg true_objective: 13.820
+[2024-09-06 09:01:11,175][01070] Num frames 11100...
+[2024-09-06 09:01:11,294][01070] Num frames 11200...
+[2024-09-06 09:01:11,414][01070] Num frames 11300...
+[2024-09-06 09:01:11,549][01070] Num frames 11400...
+[2024-09-06 09:01:11,615][01070] Avg episode rewards: #0: 31.453, true rewards: #0: 12.676
+[2024-09-06 09:01:11,617][01070] Avg episode reward: 31.453, avg true_objective: 12.676
+[2024-09-06 09:01:11,740][01070] Num frames 11500...
+[2024-09-06 09:01:11,869][01070] Num frames 11600...
+[2024-09-06 09:01:11,989][01070] Num frames 11700...
+[2024-09-06 09:01:12,106][01070] Num frames 11800...
+[2024-09-06 09:01:12,231][01070] Avg episode rewards: #0: 29.156, true rewards: #0: 11.856
+[2024-09-06 09:01:12,233][01070] Avg episode reward: 29.156, avg true_objective: 11.856
+[2024-09-06 09:02:25,893][01070] Replay video saved to /content/train_dir/default_experiment/replay.mp4!