Upload . with huggingface_hub

.summary/0/events.out.tfevents.1677247527.1b4f54364242

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:599bbd1dba9c20f58c1da13b3aeda3a00067c09c9e5d65e32a95a2c3436ffa2f
+size 4801

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 9.99 +/- 3.41
+      value: 11.35 +/- 4.49
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000000980_4014080.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04a3906ab0c51e184e823418ef57c36be1f55b4c58628ed3a75985c8faa12a90
+size 34929220

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": 1000000,
   "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 sha256:2026b523afe281c85d9af34c88279becde2f93279dff4d2f7ae9af03695dce00
-size 18966078
+oid sha256:d23b878a6dcb21ff2af4992cdd9bb10523733f615ea90e9528be282cea83b2e6
+size 21786785

sf_log.txt

@@ -1098,3 +1098,703 @@ main_loop: 1068.9353
 [2023-02-24 13:57:36,392][00980] Avg episode rewards: #0: 22.988, true rewards: #0: 9.988
 [2023-02-24 13:57:36,394][00980] Avg episode reward: 22.988, avg true_objective: 9.988
 [2023-02-24 13:58:35,822][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-02-24 13:58:39,900][00980] The model has been pushed to https://huggingface.co/mnavas/rl_course_vizdoom_health_gathering_supreme
+[2023-02-24 14:05:27,094][00980] Environment doom_basic already registered, overwriting...
+[2023-02-24 14:05:27,098][00980] Environment doom_two_colors_easy already registered, overwriting...
+[2023-02-24 14:05:27,100][00980] Environment doom_two_colors_hard already registered, overwriting...
+[2023-02-24 14:05:27,101][00980] Environment doom_dm already registered, overwriting...
+[2023-02-24 14:05:27,105][00980] Environment doom_dwango5 already registered, overwriting...
+[2023-02-24 14:05:27,107][00980] Environment doom_my_way_home_flat_actions already registered, overwriting...
+[2023-02-24 14:05:27,109][00980] Environment doom_defend_the_center_flat_actions already registered, overwriting...
+[2023-02-24 14:05:27,110][00980] Environment doom_my_way_home already registered, overwriting...
+[2023-02-24 14:05:27,114][00980] Environment doom_deadly_corridor already registered, overwriting...
+[2023-02-24 14:05:27,115][00980] Environment doom_defend_the_center already registered, overwriting...
+[2023-02-24 14:05:27,119][00980] Environment doom_defend_the_line already registered, overwriting...
+[2023-02-24 14:05:27,120][00980] Environment doom_health_gathering already registered, overwriting...
+[2023-02-24 14:05:27,121][00980] Environment doom_health_gathering_supreme already registered, overwriting...
+[2023-02-24 14:05:27,122][00980] Environment doom_battle already registered, overwriting...
+[2023-02-24 14:05:27,124][00980] Environment doom_battle2 already registered, overwriting...
+[2023-02-24 14:05:27,128][00980] Environment doom_duel_bots already registered, overwriting...
+[2023-02-24 14:05:27,130][00980] Environment doom_deathmatch_bots already registered, overwriting...
+[2023-02-24 14:05:27,131][00980] Environment doom_duel already registered, overwriting...
+[2023-02-24 14:05:27,132][00980] Environment doom_deathmatch_full already registered, overwriting...
+[2023-02-24 14:05:27,133][00980] Environment doom_benchmark already registered, overwriting...
+[2023-02-24 14:05:27,135][00980] register_encoder_factory: <function make_vizdoom_encoder at 0x7ff7e26f99d0>
+[2023-02-24 14:05:27,169][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:05:27,170][00980] Overriding arg 'train_for_env_steps' with value 1000000 passed from command line
+[2023-02-24 14:05:27,179][00980] Experiment dir /content/train_dir/default_experiment already exists!
+[2023-02-24 14:05:27,185][00980] Resuming existing experiment from /content/train_dir/default_experiment...
+[2023-02-24 14:05:27,186][00980] Weights and Biases integration disabled
+[2023-02-24 14:05:27,191][00980] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2023-02-24 14:05:29,280][00980] 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=1000000
+train_for_seconds=10000000000
+save_every_sec=120
+keep_checkpoints=2
+load_checkpoint_kind=latest
+save_milestones_sec=-1
+save_best_every_sec=5
+save_best_metric=reward
+save_best_after=100000
+benchmark=False
+encoder_mlp_layers=[512, 512]
+encoder_conv_architecture=convnet_simple
+encoder_conv_mlp_layers=[512]
+use_rnn=True
+rnn_size=512
+rnn_type=gru
+rnn_num_layers=1
+decoder_mlp_layers=[]
+nonlinearity=elu
+policy_initialization=orthogonal
+policy_init_gain=1.0
+actor_critic_share_weights=True
+adaptive_stddev=True
+continuous_tanh_scale=0.0
+initial_stddev=1.0
+use_env_info_cache=False
+env_gpu_actions=False
+env_gpu_observations=True
+env_frameskip=4
+env_framestack=1
+pixel_format=CHW
+use_record_episode_statistics=False
+with_wandb=False
+wandb_user=None
+wandb_project=sample_factory
+wandb_group=None
+wandb_job_type=SF
+wandb_tags=[]
+with_pbt=False
+pbt_mix_policies_in_one_env=True
+pbt_period_env_steps=5000000
+pbt_start_mutation=20000000
+pbt_replace_fraction=0.3
+pbt_mutation_rate=0.15
+pbt_replace_reward_gap=0.1
+pbt_replace_reward_gap_absolute=1e-06
+pbt_optimize_gamma=False
+pbt_target_objective=true_objective
+pbt_perturb_min=1.1
+pbt_perturb_max=1.5
+num_agents=-1
+num_humans=0
+num_bots=-1
+start_bot_difficulty=None
+timelimit=None
+res_w=128
+res_h=72
+wide_aspect_ratio=False
+eval_env_frameskip=1
+fps=35
+command_line=--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000
+cli_args={'env': 'doom_health_gathering_supreme', 'num_workers': 8, 'num_envs_per_worker': 4, 'train_for_env_steps': 4000000}
+git_hash=unknown
+git_repo_name=not a git repository
+[2023-02-24 14:05:29,284][00980] Saving configuration to /content/train_dir/default_experiment/config.json...
+[2023-02-24 14:05:29,288][00980] Rollout worker 0 uses device cpu
+[2023-02-24 14:05:29,293][00980] Rollout worker 1 uses device cpu
+[2023-02-24 14:05:29,295][00980] Rollout worker 2 uses device cpu
+[2023-02-24 14:05:29,297][00980] Rollout worker 3 uses device cpu
+[2023-02-24 14:05:29,299][00980] Rollout worker 4 uses device cpu
+[2023-02-24 14:05:29,301][00980] Rollout worker 5 uses device cpu
+[2023-02-24 14:05:29,303][00980] Rollout worker 6 uses device cpu
+[2023-02-24 14:05:29,305][00980] Rollout worker 7 uses device cpu
+[2023-02-24 14:05:29,424][00980] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:05:29,426][00980] InferenceWorker_p0-w0: min num requests: 2
+[2023-02-24 14:05:29,459][00980] Starting all processes...
+[2023-02-24 14:05:29,461][00980] Starting process learner_proc0
+[2023-02-24 14:05:29,592][00980] Starting all processes...
+[2023-02-24 14:05:29,603][00980] Starting process inference_proc0-0
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc0
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc1
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc2
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc3
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc4
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc5
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc6
+[2023-02-24 14:05:29,604][00980] Starting process rollout_proc7
+[2023-02-24 14:05:37,475][20720] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:05:37,492][20720] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2023-02-24 14:05:37,530][20720] Num visible devices: 1
+[2023-02-24 14:05:37,562][20720] Starting seed is not provided
+[2023-02-24 14:05:37,563][20720] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:05:37,564][20720] Initializing actor-critic model on device cuda:0
+[2023-02-24 14:05:37,565][20720] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:05:37,567][20720] RunningMeanStd input shape: (1,)
+[2023-02-24 14:05:37,652][20720] ConvEncoder: input_channels=3
+[2023-02-24 14:05:38,454][20720] Conv encoder output size: 512
+[2023-02-24 14:05:38,462][20720] Policy head output size: 512
+[2023-02-24 14:05:38,547][20720] Created Actor Critic model with architecture:
+[2023-02-24 14:05:38,560][20720] ActorCriticSharedWeights(
+  (obs_normalizer): ObservationNormalizer(
+    (running_mean_std): RunningMeanStdDictInPlace(
+      (running_mean_std): ModuleDict(
+        (obs): RunningMeanStdInPlace()
+      )
+    )
+  )
+  (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
+  (encoder): VizdoomEncoder(
+    (basic_encoder): ConvEncoder(
+      (enc): RecursiveScriptModule(
+        original_name=ConvEncoderImpl
+        (conv_head): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Conv2d)
+          (1): RecursiveScriptModule(original_name=ELU)
+          (2): RecursiveScriptModule(original_name=Conv2d)
+          (3): RecursiveScriptModule(original_name=ELU)
+          (4): RecursiveScriptModule(original_name=Conv2d)
+          (5): RecursiveScriptModule(original_name=ELU)
+        )
+        (mlp_layers): RecursiveScriptModule(
+          original_name=Sequential
+          (0): RecursiveScriptModule(original_name=Linear)
+          (1): RecursiveScriptModule(original_name=ELU)
+        )
+      )
+    )
+  )
+  (core): ModelCoreRNN(
+    (core): GRU(512, 512)
+  )
+  (decoder): MlpDecoder(
+    (mlp): Identity()
+  )
+  (critic_linear): Linear(in_features=512, out_features=1, bias=True)
+  (action_parameterization): ActionParameterizationDefault(
+    (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
+  )
+)
+[2023-02-24 14:05:38,848][20735] Worker 0 uses CPU cores [0]
+[2023-02-24 14:05:38,874][20734] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:05:38,874][20734] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2023-02-24 14:05:38,948][20734] Num visible devices: 1
+[2023-02-24 14:05:39,017][20737] Worker 2 uses CPU cores [0]
+[2023-02-24 14:05:39,818][20747] Worker 4 uses CPU cores [0]
+[2023-02-24 14:05:39,866][20739] Worker 3 uses CPU cores [1]
+[2023-02-24 14:05:40,106][20741] Worker 1 uses CPU cores [1]
+[2023-02-24 14:05:40,463][20748] Worker 7 uses CPU cores [1]
+[2023-02-24 14:05:40,605][20750] Worker 5 uses CPU cores [1]
+[2023-02-24 14:05:40,683][20753] Worker 6 uses CPU cores [0]
+[2023-02-24 14:05:43,236][20720] Using optimizer <class 'torch.optim.adam.Adam'>
+[2023-02-24 14:05:43,237][20720] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
+[2023-02-24 14:05:43,279][20720] Loading model from checkpoint
+[2023-02-24 14:05:43,287][20720] Loaded experiment state at self.train_step=978, self.env_steps=4005888
+[2023-02-24 14:05:43,287][20720] Initialized policy 0 weights for model version 978
+[2023-02-24 14:05:43,293][20720] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2023-02-24 14:05:43,302][20720] LearnerWorker_p0 finished initialization!
+[2023-02-24 14:05:43,650][20734] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:05:43,652][20734] RunningMeanStd input shape: (1,)
+[2023-02-24 14:05:43,671][20734] ConvEncoder: input_channels=3
+[2023-02-24 14:05:43,805][20734] Conv encoder output size: 512
+[2023-02-24 14:05:43,805][20734] Policy head output size: 512
+[2023-02-24 14:05:46,152][00980] Inference worker 0-0 is ready!
+[2023-02-24 14:05:46,154][00980] All inference workers are ready! Signal rollout workers to start!
+[2023-02-24 14:05:46,278][20747] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,277][20735] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,274][20753] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,298][20737] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,310][20739] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,313][20748] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,317][20750] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:46,320][20741] Doom resolution: 160x120, resize resolution: (128, 72)
+[2023-02-24 14:05:47,191][00980] 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)
+[2023-02-24 14:05:47,495][20747] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,496][20735] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,497][20753] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,497][20750] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,500][20739] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,503][20741] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:47,857][20741] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:48,254][20741] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:48,444][20753] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:48,461][20735] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:48,471][20737] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:48,844][20750] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:49,216][20737] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:49,254][20748] Decorrelating experience for 0 frames...
+[2023-02-24 14:05:49,317][20753] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:49,417][00980] Heartbeat connected on Batcher_0
+[2023-02-24 14:05:49,427][00980] Heartbeat connected on LearnerWorker_p0
+[2023-02-24 14:05:49,469][00980] Heartbeat connected on InferenceWorker_p0-w0
+[2023-02-24 14:05:50,064][20735] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:50,153][20753] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:50,238][00980] Heartbeat connected on RolloutWorker_w6
+[2023-02-24 14:05:50,333][20748] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:50,358][20750] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:50,369][20741] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:50,673][00980] Heartbeat connected on RolloutWorker_w1
+[2023-02-24 14:05:51,453][20737] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:51,472][20747] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:51,931][20750] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:52,032][20748] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:52,195][00980] 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)
+[2023-02-24 14:05:52,267][00980] Heartbeat connected on RolloutWorker_w5
+[2023-02-24 14:05:53,434][20735] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:53,617][20737] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:53,926][00980] Heartbeat connected on RolloutWorker_w0
+[2023-02-24 14:05:54,196][00980] Heartbeat connected on RolloutWorker_w2
+[2023-02-24 14:05:54,491][20747] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:54,847][20748] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:55,791][00980] Heartbeat connected on RolloutWorker_w7
+[2023-02-24 14:05:57,191][00980] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 4005888. Throughput: 0: 152.4. Samples: 1524. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2023-02-24 14:05:57,201][00980] Avg episode reward: [(0, '2.762')]
+[2023-02-24 14:05:57,549][20720] Signal inference workers to stop experience collection...
+[2023-02-24 14:05:57,572][20739] Decorrelating experience for 32 frames...
+[2023-02-24 14:05:57,574][20734] InferenceWorker_p0-w0: stopping experience collection
+[2023-02-24 14:05:58,375][20747] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:58,585][00980] Heartbeat connected on RolloutWorker_w4
+[2023-02-24 14:05:58,843][20739] Decorrelating experience for 64 frames...
+[2023-02-24 14:05:59,511][20739] Decorrelating experience for 96 frames...
+[2023-02-24 14:05:59,622][00980] Heartbeat connected on RolloutWorker_w3
+[2023-02-24 14:06:00,370][20720] Signal inference workers to resume experience collection...
+[2023-02-24 14:06:00,371][20734] InferenceWorker_p0-w0: resuming experience collection
+[2023-02-24 14:06:00,372][20720] Stopping Batcher_0...
+[2023-02-24 14:06:00,373][20720] Loop batcher_evt_loop terminating...
+[2023-02-24 14:06:00,398][00980] Component Batcher_0 stopped!
+[2023-02-24 14:06:00,464][20734] Weights refcount: 2 0
+[2023-02-24 14:06:00,467][20734] Stopping InferenceWorker_p0-w0...
+[2023-02-24 14:06:00,467][00980] Component InferenceWorker_p0-w0 stopped!
+[2023-02-24 14:06:00,467][20734] Loop inference_proc0-0_evt_loop terminating...
+[2023-02-24 14:06:00,567][20747] Stopping RolloutWorker_w4...
+[2023-02-24 14:06:00,575][20747] Loop rollout_proc4_evt_loop terminating...
+[2023-02-24 14:06:00,571][00980] Component RolloutWorker_w4 stopped!
+[2023-02-24 14:06:00,580][20753] Stopping RolloutWorker_w6...
+[2023-02-24 14:06:00,581][20753] Loop rollout_proc6_evt_loop terminating...
+[2023-02-24 14:06:00,581][00980] Component RolloutWorker_w6 stopped!
+[2023-02-24 14:06:00,585][20737] Stopping RolloutWorker_w2...
+[2023-02-24 14:06:00,585][20737] Loop rollout_proc2_evt_loop terminating...
+[2023-02-24 14:06:00,588][00980] Component RolloutWorker_w2 stopped!
+[2023-02-24 14:06:00,594][20735] Stopping RolloutWorker_w0...
+[2023-02-24 14:06:00,595][00980] Component RolloutWorker_w0 stopped!
+[2023-02-24 14:06:00,594][20735] Loop rollout_proc0_evt_loop terminating...
+[2023-02-24 14:06:00,623][00980] Component RolloutWorker_w7 stopped!
+[2023-02-24 14:06:00,629][20748] Stopping RolloutWorker_w7...
+[2023-02-24 14:06:00,630][20748] Loop rollout_proc7_evt_loop terminating...
+[2023-02-24 14:06:00,659][00980] Component RolloutWorker_w1 stopped!
+[2023-02-24 14:06:00,664][00980] Component RolloutWorker_w5 stopped!
+[2023-02-24 14:06:00,668][20750] Stopping RolloutWorker_w5...
+[2023-02-24 14:06:00,669][20750] Loop rollout_proc5_evt_loop terminating...
+[2023-02-24 14:06:00,670][20741] Stopping RolloutWorker_w1...
+[2023-02-24 14:06:00,670][20741] Loop rollout_proc1_evt_loop terminating...
+[2023-02-24 14:06:00,699][00980] Component RolloutWorker_w3 stopped!
+[2023-02-24 14:06:00,710][20739] Stopping RolloutWorker_w3...
+[2023-02-24 14:06:00,710][20739] Loop rollout_proc3_evt_loop terminating...
+[2023-02-24 14:06:03,543][20720] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2023-02-24 14:06:03,663][20720] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000871_3567616.pth
+[2023-02-24 14:06:03,677][20720] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2023-02-24 14:06:03,858][20720] Stopping LearnerWorker_p0...
+[2023-02-24 14:06:03,859][20720] Loop learner_proc0_evt_loop terminating...
+[2023-02-24 14:06:03,858][00980] Component LearnerWorker_p0 stopped!
+[2023-02-24 14:06:03,869][00980] Waiting for process learner_proc0 to stop...
+[2023-02-24 14:06:04,891][00980] Waiting for process inference_proc0-0 to join...
+[2023-02-24 14:06:04,893][00980] Waiting for process rollout_proc0 to join...
+[2023-02-24 14:06:04,896][00980] Waiting for process rollout_proc1 to join...
+[2023-02-24 14:06:04,901][00980] Waiting for process rollout_proc2 to join...
+[2023-02-24 14:06:04,902][00980] Waiting for process rollout_proc3 to join...
+[2023-02-24 14:06:04,904][00980] Waiting for process rollout_proc4 to join...
+[2023-02-24 14:06:04,909][00980] Waiting for process rollout_proc5 to join...
+[2023-02-24 14:06:04,911][00980] Waiting for process rollout_proc6 to join...
+[2023-02-24 14:06:04,913][00980] Waiting for process rollout_proc7 to join...
+[2023-02-24 14:06:04,914][00980] Batcher 0 profile tree view:
+batching: 0.0456, releasing_batches: 0.0011
+[2023-02-24 14:06:04,916][00980] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0051
+  wait_policy_total: 7.3640
+update_model: 0.0356
+  weight_update: 0.0127
+one_step: 0.0326
+  handle_policy_step: 3.9057
+    deserialize: 0.0505, stack: 0.0081, obs_to_device_normalize: 0.3641, forward: 3.0388, send_messages: 0.0944
+    prepare_outputs: 0.2652
+      to_cpu: 0.1469
+[2023-02-24 14:06:04,917][00980] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 8.0217
+train: 1.7323
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0005, kl_divergence: 0.0026, after_optimizer: 0.0345
+  calculate_losses: 0.2408
+    losses_init: 0.0000, forward_head: 0.1146, bptt_initial: 0.0866, tail: 0.0014, advantages_returns: 0.0010, losses: 0.0318
+    bptt: 0.0049
+      bptt_forward_core: 0.0048
+  update: 1.4525
+    clip: 0.0120
+[2023-02-24 14:06:04,918][00980] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0005, enqueue_policy_requests: 0.7739, env_step: 2.6918, overhead: 0.0454, complete_rollouts: 0.0249
+save_policy_outputs: 0.0684
+  split_output_tensors: 0.0449
+[2023-02-24 14:06:04,920][00980] RolloutWorker_w7 profile tree view:
+wait_for_trajectories: 0.0015, enqueue_policy_requests: 0.2734, env_step: 1.2700, overhead: 0.0664, complete_rollouts: 0.0008
+save_policy_outputs: 0.0364
+  split_output_tensors: 0.0053
+[2023-02-24 14:06:04,922][00980] Loop Runner_EvtLoop terminating...
+[2023-02-24 14:06:04,924][00980] Runner profile tree view:
+main_loop: 35.4650
+[2023-02-24 14:06:04,927][00980] Collected {0: 4014080}, FPS: 231.0
+[2023-02-24 14:06:04,960][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:06:04,963][00980] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 14:06:04,964][00980] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 14:06:04,966][00980] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 14:06:04,971][00980] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:06:04,972][00980] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 14:06:04,976][00980] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:06:04,977][00980] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 14:06:04,980][00980] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2023-02-24 14:06:04,982][00980] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2023-02-24 14:06:04,984][00980] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 14:06:04,987][00980] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 14:06:04,989][00980] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 14:06:04,990][00980] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 14:06:04,991][00980] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 14:06:05,021][00980] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:06:05,024][00980] RunningMeanStd input shape: (1,)
+[2023-02-24 14:06:05,042][00980] ConvEncoder: input_channels=3
+[2023-02-24 14:06:05,093][00980] Conv encoder output size: 512
+[2023-02-24 14:06:05,095][00980] Policy head output size: 512
+[2023-02-24 14:06:05,123][00980] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2023-02-24 14:06:05,565][00980] Num frames 100...
+[2023-02-24 14:06:05,685][00980] Num frames 200...
+[2023-02-24 14:06:05,798][00980] Num frames 300...
+[2023-02-24 14:06:05,912][00980] Num frames 400...
+[2023-02-24 14:06:06,025][00980] Num frames 500...
+[2023-02-24 14:06:06,142][00980] Num frames 600...
+[2023-02-24 14:06:06,254][00980] Num frames 700...
+[2023-02-24 14:06:06,363][00980] Num frames 800...
+[2023-02-24 14:06:06,480][00980] Num frames 900...
+[2023-02-24 14:06:06,611][00980] Num frames 1000...
+[2023-02-24 14:06:06,767][00980] Avg episode rewards: #0: 22.880, true rewards: #0: 10.880
+[2023-02-24 14:06:06,770][00980] Avg episode reward: 22.880, avg true_objective: 10.880
+[2023-02-24 14:06:06,788][00980] Num frames 1100...
+[2023-02-24 14:06:06,898][00980] Num frames 1200...
+[2023-02-24 14:06:07,011][00980] Num frames 1300...
+[2023-02-24 14:06:07,122][00980] Num frames 1400...
+[2023-02-24 14:06:07,234][00980] Num frames 1500...
+[2023-02-24 14:06:07,364][00980] Num frames 1600...
+[2023-02-24 14:06:07,487][00980] Num frames 1700...
+[2023-02-24 14:06:07,603][00980] Num frames 1800...
+[2023-02-24 14:06:07,718][00980] Num frames 1900...
+[2023-02-24 14:06:07,835][00980] Num frames 2000...
+[2023-02-24 14:06:07,949][00980] Num frames 2100...
+[2023-02-24 14:06:08,032][00980] Avg episode rewards: #0: 23.120, true rewards: #0: 10.620
+[2023-02-24 14:06:08,034][00980] Avg episode reward: 23.120, avg true_objective: 10.620
+[2023-02-24 14:06:08,123][00980] Num frames 2200...
+[2023-02-24 14:06:08,238][00980] Num frames 2300...
+[2023-02-24 14:06:08,364][00980] Num frames 2400...
+[2023-02-24 14:06:08,483][00980] Num frames 2500...
+[2023-02-24 14:06:08,607][00980] Num frames 2600...
+[2023-02-24 14:06:08,738][00980] Num frames 2700...
+[2023-02-24 14:06:08,854][00980] Num frames 2800...
+[2023-02-24 14:06:08,970][00980] Num frames 2900...
+[2023-02-24 14:06:09,084][00980] Num frames 3000...
+[2023-02-24 14:06:09,201][00980] Num frames 3100...
+[2023-02-24 14:06:09,319][00980] Num frames 3200...
+[2023-02-24 14:06:09,437][00980] Num frames 3300...
+[2023-02-24 14:06:09,559][00980] Num frames 3400...
+[2023-02-24 14:06:09,674][00980] Num frames 3500...
+[2023-02-24 14:06:09,795][00980] Num frames 3600...
+[2023-02-24 14:06:09,910][00980] Num frames 3700...
+[2023-02-24 14:06:10,035][00980] Num frames 3800...
+[2023-02-24 14:06:10,160][00980] Num frames 3900...
+[2023-02-24 14:06:10,281][00980] Num frames 4000...
+[2023-02-24 14:06:10,443][00980] Avg episode rewards: #0: 31.307, true rewards: #0: 13.640
+[2023-02-24 14:06:10,444][00980] Avg episode reward: 31.307, avg true_objective: 13.640
+[2023-02-24 14:06:10,460][00980] Num frames 4100...
+[2023-02-24 14:06:10,583][00980] Num frames 4200...
+[2023-02-24 14:06:10,703][00980] Num frames 4300...
+[2023-02-24 14:06:10,816][00980] Num frames 4400...
+[2023-02-24 14:06:10,934][00980] Num frames 4500...
+[2023-02-24 14:06:11,046][00980] Num frames 4600...
+[2023-02-24 14:06:11,171][00980] Num frames 4700...
+[2023-02-24 14:06:11,286][00980] Num frames 4800...
+[2023-02-24 14:06:11,389][00980] Avg episode rewards: #0: 26.857, true rewards: #0: 12.107
+[2023-02-24 14:06:11,392][00980] Avg episode reward: 26.857, avg true_objective: 12.107
+[2023-02-24 14:06:11,458][00980] Num frames 4900...
+[2023-02-24 14:06:11,579][00980] Num frames 5000...
+[2023-02-24 14:06:11,692][00980] Num frames 5100...
+[2023-02-24 14:06:11,808][00980] Num frames 5200...
+[2023-02-24 14:06:11,922][00980] Num frames 5300...
+[2023-02-24 14:06:12,040][00980] Num frames 5400...
+[2023-02-24 14:06:12,155][00980] Num frames 5500...
+[2023-02-24 14:06:12,306][00980] Avg episode rewards: #0: 24.558, true rewards: #0: 11.158
+[2023-02-24 14:06:12,308][00980] Avg episode reward: 24.558, avg true_objective: 11.158
+[2023-02-24 14:06:12,333][00980] Num frames 5600...
+[2023-02-24 14:06:12,453][00980] Num frames 5700...
+[2023-02-24 14:06:12,571][00980] Num frames 5800...
+[2023-02-24 14:06:12,692][00980] Num frames 5900...
+[2023-02-24 14:06:12,805][00980] Num frames 6000...
+[2023-02-24 14:06:12,925][00980] Num frames 6100...
+[2023-02-24 14:06:13,040][00980] Num frames 6200...
+[2023-02-24 14:06:13,152][00980] Num frames 6300...
+[2023-02-24 14:06:13,263][00980] Num frames 6400...
+[2023-02-24 14:06:13,378][00980] Num frames 6500...
+[2023-02-24 14:06:13,492][00980] Num frames 6600...
+[2023-02-24 14:06:13,622][00980] Num frames 6700...
+[2023-02-24 14:06:13,713][00980] Avg episode rewards: #0: 25.052, true rewards: #0: 11.218
+[2023-02-24 14:06:13,718][00980] Avg episode reward: 25.052, avg true_objective: 11.218
+[2023-02-24 14:06:13,801][00980] Num frames 6800...
+[2023-02-24 14:06:13,913][00980] Num frames 6900...
+[2023-02-24 14:06:14,031][00980] Num frames 7000...
+[2023-02-24 14:06:14,144][00980] Num frames 7100...
+[2023-02-24 14:06:14,264][00980] Num frames 7200...
+[2023-02-24 14:06:14,407][00980] Num frames 7300...
+[2023-02-24 14:06:14,587][00980] Num frames 7400...
+[2023-02-24 14:06:14,653][00980] Avg episode rewards: #0: 23.147, true rewards: #0: 10.576
+[2023-02-24 14:06:14,655][00980] Avg episode reward: 23.147, avg true_objective: 10.576
+[2023-02-24 14:06:14,815][00980] Num frames 7500...
+[2023-02-24 14:06:14,976][00980] Num frames 7600...
+[2023-02-24 14:06:15,133][00980] Num frames 7700...
+[2023-02-24 14:06:15,299][00980] Num frames 7800...
+[2023-02-24 14:06:15,451][00980] Num frames 7900...
+[2023-02-24 14:06:15,614][00980] Num frames 8000...
+[2023-02-24 14:06:15,775][00980] Num frames 8100...
+[2023-02-24 14:06:15,937][00980] Num frames 8200...
+[2023-02-24 14:06:16,099][00980] Num frames 8300...
+[2023-02-24 14:06:16,250][00980] Avg episode rewards: #0: 23.198, true rewards: #0: 10.447
+[2023-02-24 14:06:16,255][00980] Avg episode reward: 23.198, avg true_objective: 10.447
+[2023-02-24 14:06:16,325][00980] Num frames 8400...
+[2023-02-24 14:06:16,489][00980] Num frames 8500...
+[2023-02-24 14:06:16,656][00980] Num frames 8600...
+[2023-02-24 14:06:16,818][00980] Num frames 8700...
+[2023-02-24 14:06:16,985][00980] Num frames 8800...
+[2023-02-24 14:06:17,151][00980] Num frames 8900...
+[2023-02-24 14:06:17,319][00980] Num frames 9000...
+[2023-02-24 14:06:17,482][00980] Num frames 9100...
+[2023-02-24 14:06:17,648][00980] Num frames 9200...
+[2023-02-24 14:06:17,812][00980] Num frames 9300...
+[2023-02-24 14:06:17,974][00980] Num frames 9400...
+[2023-02-24 14:06:18,116][00980] Num frames 9500...
+[2023-02-24 14:06:18,261][00980] Avg episode rewards: #0: 23.638, true rewards: #0: 10.638
+[2023-02-24 14:06:18,262][00980] Avg episode reward: 23.638, avg true_objective: 10.638
+[2023-02-24 14:06:18,294][00980] Num frames 9600...
+[2023-02-24 14:06:18,410][00980] Num frames 9700...
+[2023-02-24 14:06:18,527][00980] Num frames 9800...
+[2023-02-24 14:06:18,644][00980] Num frames 9900...
+[2023-02-24 14:06:18,775][00980] Num frames 10000...
+[2023-02-24 14:06:18,887][00980] Num frames 10100...
+[2023-02-24 14:06:18,997][00980] Num frames 10200...
+[2023-02-24 14:06:19,079][00980] Avg episode rewards: #0: 22.522, true rewards: #0: 10.222
+[2023-02-24 14:06:19,080][00980] Avg episode reward: 22.522, avg true_objective: 10.222
+[2023-02-24 14:07:20,449][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
+[2023-02-24 14:07:20,479][00980] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
+[2023-02-24 14:07:20,481][00980] Overriding arg 'num_workers' with value 1 passed from command line
+[2023-02-24 14:07:20,482][00980] Adding new argument 'no_render'=True that is not in the saved config file!
+[2023-02-24 14:07:20,485][00980] Adding new argument 'save_video'=True that is not in the saved config file!
+[2023-02-24 14:07:20,486][00980] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2023-02-24 14:07:20,487][00980] Adding new argument 'video_name'=None that is not in the saved config file!
+[2023-02-24 14:07:20,488][00980] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
+[2023-02-24 14:07:20,490][00980] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2023-02-24 14:07:20,491][00980] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2023-02-24 14:07:20,492][00980] Adding new argument 'hf_repository'='mnavas/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2023-02-24 14:07:20,493][00980] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2023-02-24 14:07:20,494][00980] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2023-02-24 14:07:20,495][00980] Adding new argument 'train_script'=None that is not in the saved config file!
+[2023-02-24 14:07:20,496][00980] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2023-02-24 14:07:20,498][00980] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2023-02-24 14:07:20,521][00980] RunningMeanStd input shape: (3, 72, 128)
+[2023-02-24 14:07:20,526][00980] RunningMeanStd input shape: (1,)
+[2023-02-24 14:07:20,541][00980] ConvEncoder: input_channels=3
+[2023-02-24 14:07:20,579][00980] Conv encoder output size: 512
+[2023-02-24 14:07:20,580][00980] Policy head output size: 512
+[2023-02-24 14:07:20,603][00980] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000980_4014080.pth...
+[2023-02-24 14:07:21,046][00980] Num frames 100...
+[2023-02-24 14:07:21,160][00980] Num frames 200...
+[2023-02-24 14:07:21,286][00980] Num frames 300...
+[2023-02-24 14:07:21,417][00980] Num frames 400...
+[2023-02-24 14:07:21,535][00980] Num frames 500...
+[2023-02-24 14:07:21,654][00980] Num frames 600...
+[2023-02-24 14:07:21,774][00980] Num frames 700...
+[2023-02-24 14:07:21,897][00980] Num frames 800...
+[2023-02-24 14:07:22,009][00980] Num frames 900...
+[2023-02-24 14:07:22,126][00980] Num frames 1000...
+[2023-02-24 14:07:22,242][00980] Num frames 1100...
+[2023-02-24 14:07:22,360][00980] Num frames 1200...
+[2023-02-24 14:07:22,476][00980] Num frames 1300...
+[2023-02-24 14:07:22,587][00980] Num frames 1400...
+[2023-02-24 14:07:22,688][00980] Avg episode rewards: #0: 38.400, true rewards: #0: 14.400
+[2023-02-24 14:07:22,690][00980] Avg episode reward: 38.400, avg true_objective: 14.400
+[2023-02-24 14:07:22,761][00980] Num frames 1500...
+[2023-02-24 14:07:22,884][00980] Num frames 1600...
+[2023-02-24 14:07:22,997][00980] Num frames 1700...
+[2023-02-24 14:07:23,113][00980] Num frames 1800...
+[2023-02-24 14:07:23,225][00980] Num frames 1900...
+[2023-02-24 14:07:23,350][00980] Num frames 2000...
+[2023-02-24 14:07:23,465][00980] Num frames 2100...
+[2023-02-24 14:07:23,585][00980] Num frames 2200...
+[2023-02-24 14:07:23,706][00980] Num frames 2300...
+[2023-02-24 14:07:23,820][00980] Num frames 2400...
+[2023-02-24 14:07:23,943][00980] Num frames 2500...
+[2023-02-24 14:07:24,060][00980] Num frames 2600...
+[2023-02-24 14:07:24,180][00980] Num frames 2700...
+[2023-02-24 14:07:24,295][00980] Num frames 2800...
+[2023-02-24 14:07:24,437][00980] Avg episode rewards: #0: 39.320, true rewards: #0: 14.320
+[2023-02-24 14:07:24,439][00980] Avg episode reward: 39.320, avg true_objective: 14.320
+[2023-02-24 14:07:24,483][00980] Num frames 2900...
+[2023-02-24 14:07:24,593][00980] Num frames 3000...
+[2023-02-24 14:07:24,707][00980] Num frames 3100...
+[2023-02-24 14:07:24,818][00980] Num frames 3200...
+[2023-02-24 14:07:24,931][00980] Num frames 3300...
+[2023-02-24 14:07:25,050][00980] Num frames 3400...
+[2023-02-24 14:07:25,172][00980] Num frames 3500...
+[2023-02-24 14:07:25,297][00980] Num frames 3600...
+[2023-02-24 14:07:25,451][00980] Num frames 3700...
+[2023-02-24 14:07:25,657][00980] Avg episode rewards: #0: 32.650, true rewards: #0: 12.650
+[2023-02-24 14:07:25,659][00980] Avg episode reward: 32.650, avg true_objective: 12.650
+[2023-02-24 14:07:25,673][00980] Num frames 3800...
+[2023-02-24 14:07:25,833][00980] Num frames 3900...
+[2023-02-24 14:07:25,993][00980] Num frames 4000...
+[2023-02-24 14:07:26,148][00980] Num frames 4100...
+[2023-02-24 14:07:26,308][00980] Num frames 4200...
+[2023-02-24 14:07:26,444][00980] Avg episode rewards: #0: 26.877, true rewards: #0: 10.627
+[2023-02-24 14:07:26,446][00980] Avg episode reward: 26.877, avg true_objective: 10.627
+[2023-02-24 14:07:26,529][00980] Num frames 4300...
+[2023-02-24 14:07:26,686][00980] Num frames 4400...
+[2023-02-24 14:07:26,847][00980] Num frames 4500...
+[2023-02-24 14:07:27,009][00980] Num frames 4600...
+[2023-02-24 14:07:27,168][00980] Num frames 4700...
+[2023-02-24 14:07:27,331][00980] Num frames 4800...
+[2023-02-24 14:07:27,483][00980] Avg episode rewards: #0: 24.118, true rewards: #0: 9.718
+[2023-02-24 14:07:27,485][00980] Avg episode reward: 24.118, avg true_objective: 9.718
+[2023-02-24 14:07:27,552][00980] Num frames 4900...
+[2023-02-24 14:07:27,730][00980] Num frames 5000...
+[2023-02-24 14:07:27,901][00980] Num frames 5100...
+[2023-02-24 14:07:28,066][00980] Num frames 5200...
+[2023-02-24 14:07:28,232][00980] Num frames 5300...
+[2023-02-24 14:07:28,400][00980] Num frames 5400...
+[2023-02-24 14:07:28,564][00980] Num frames 5500...
+[2023-02-24 14:07:28,733][00980] Num frames 5600...
+[2023-02-24 14:07:28,903][00980] Num frames 5700...
+[2023-02-24 14:07:29,022][00980] Num frames 5800...
+[2023-02-24 14:07:29,134][00980] Num frames 5900...
+[2023-02-24 14:07:29,251][00980] Num frames 6000...
+[2023-02-24 14:07:29,362][00980] Num frames 6100...
+[2023-02-24 14:07:29,475][00980] Num frames 6200...
+[2023-02-24 14:07:29,592][00980] Num frames 6300...
+[2023-02-24 14:07:29,711][00980] Num frames 6400...
+[2023-02-24 14:07:29,826][00980] Num frames 6500...
+[2023-02-24 14:07:29,949][00980] Num frames 6600...
+[2023-02-24 14:07:30,066][00980] Num frames 6700...
+[2023-02-24 14:07:30,189][00980] Num frames 6800...
+[2023-02-24 14:07:30,303][00980] Num frames 6900...
+[2023-02-24 14:07:30,431][00980] Avg episode rewards: #0: 30.098, true rewards: #0: 11.598
+[2023-02-24 14:07:30,433][00980] Avg episode reward: 30.098, avg true_objective: 11.598
+[2023-02-24 14:07:30,484][00980] Num frames 7000...
+[2023-02-24 14:07:30,609][00980] Num frames 7100...
+[2023-02-24 14:07:30,725][00980] Num frames 7200...
+[2023-02-24 14:07:30,843][00980] Num frames 7300...
+[2023-02-24 14:07:30,958][00980] Num frames 7400...
+[2023-02-24 14:07:31,078][00980] Num frames 7500...
+[2023-02-24 14:07:31,202][00980] Num frames 7600...
+[2023-02-24 14:07:31,320][00980] Num frames 7700...
+[2023-02-24 14:07:31,437][00980] Num frames 7800...
+[2023-02-24 14:07:31,556][00980] Num frames 7900...
+[2023-02-24 14:07:31,679][00980] Num frames 8000...
+[2023-02-24 14:07:31,799][00980] Num frames 8100...
+[2023-02-24 14:07:31,926][00980] Num frames 8200...
+[2023-02-24 14:07:32,015][00980] Avg episode rewards: #0: 29.753, true rewards: #0: 11.753
+[2023-02-24 14:07:32,016][00980] Avg episode reward: 29.753, avg true_objective: 11.753
+[2023-02-24 14:07:32,100][00980] Num frames 8300...
+[2023-02-24 14:07:32,215][00980] Num frames 8400...
+[2023-02-24 14:07:32,326][00980] Num frames 8500...
+[2023-02-24 14:07:32,439][00980] Num frames 8600...
+[2023-02-24 14:07:32,558][00980] Num frames 8700...
+[2023-02-24 14:07:32,675][00980] Num frames 8800...
+[2023-02-24 14:07:32,786][00980] Num frames 8900...
+[2023-02-24 14:07:32,900][00980] Num frames 9000...
+[2023-02-24 14:07:33,022][00980] Num frames 9100...
+[2023-02-24 14:07:33,096][00980] Avg episode rewards: #0: 28.519, true rewards: #0: 11.394
+[2023-02-24 14:07:33,097][00980] Avg episode reward: 28.519, avg true_objective: 11.394
+[2023-02-24 14:07:33,197][00980] Num frames 9200...
+[2023-02-24 14:07:33,309][00980] Num frames 9300...
+[2023-02-24 14:07:33,431][00980] Num frames 9400...
+[2023-02-24 14:07:33,547][00980] Num frames 9500...
+[2023-02-24 14:07:33,667][00980] Num frames 9600...
+[2023-02-24 14:07:33,792][00980] Num frames 9700...
+[2023-02-24 14:07:33,909][00980] Num frames 9800...
+[2023-02-24 14:07:34,026][00980] Num frames 9900...
+[2023-02-24 14:07:34,137][00980] Num frames 10000...
+[2023-02-24 14:07:34,271][00980] Avg episode rewards: #0: 27.523, true rewards: #0: 11.190
+[2023-02-24 14:07:34,273][00980] Avg episode reward: 27.523, avg true_objective: 11.190
+[2023-02-24 14:07:34,312][00980] Num frames 10100...
+[2023-02-24 14:07:34,431][00980] Num frames 10200...
+[2023-02-24 14:07:34,546][00980] Num frames 10300...
+[2023-02-24 14:07:34,672][00980] Num frames 10400...
+[2023-02-24 14:07:34,785][00980] Num frames 10500...
+[2023-02-24 14:07:34,907][00980] Num frames 10600...
+[2023-02-24 14:07:35,024][00980] Num frames 10700...
+[2023-02-24 14:07:35,142][00980] Num frames 10800...
+[2023-02-24 14:07:35,255][00980] Num frames 10900...
+[2023-02-24 14:07:35,378][00980] Num frames 11000...
+[2023-02-24 14:07:35,489][00980] Num frames 11100...
+[2023-02-24 14:07:35,614][00980] Num frames 11200...
+[2023-02-24 14:07:35,734][00980] Num frames 11300...
+[2023-02-24 14:07:35,852][00980] Avg episode rewards: #0: 27.851, true rewards: #0: 11.351
+[2023-02-24 14:07:35,853][00980] Avg episode reward: 27.851, avg true_objective: 11.351
+[2023-02-24 14:08:43,682][00980] Replay video saved to /content/train_dir/default_experiment/replay.mp4!