Upload folder using huggingface_hub

.summary/0/events.out.tfevents.1730986539.ali

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f1e11b0059b918b90d03360ce897dbcfbe4919841fc122b58ade530701936f1f
+size 3137

README.md

@@ -15,7 +15,7 @@ model-index:
       type: doom_health_gathering_supreme
     metrics:
     - type: mean_reward
-      value: 3.71 +/- 0.63
+      value: 3.81 +/- 0.46
       name: mean_reward
       verified: false
 ---

checkpoint_p0/checkpoint_000003910_16015360.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfde67df8265d9dcdfab6c6c171b5c5aeb413e650926559ad51aa292116196f0
+size 34929669

config.json

@@ -16,7 +16,7 @@
   "policy_workers_per_policy": 1,
   "max_policy_lag": 1000,
   "num_workers": 10,
-  "num_envs_per_worker": 6,
+  "num_envs_per_worker": 4,
   "batch_size": 1024,
   "num_batches_per_epoch": 1,
   "num_epochs": 1,
@@ -43,7 +43,7 @@
   "adam_beta1": 0.9,
   "adam_beta2": 0.999,
   "max_grad_norm": 4.0,
-  "learning_rate": 0.0001,
+  "learning_rate": 0.0003,
   "lr_schedule": "constant",
   "lr_schedule_kl_threshold": 0.008,
   "lr_adaptive_min": 1e-06,
@@ -65,7 +65,7 @@
   "summaries_use_frameskip": true,
   "heartbeat_interval": 20,
   "heartbeat_reporting_interval": 600,
-  "train_for_env_steps": 16000000,
+  "train_for_env_steps": 4000000,
   "train_for_seconds": 10000000000,
   "save_every_sec": 120,
   "keep_checkpoints": 2,

replay.mp4

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8d65182a01240d78094bcad1ac054bcbd3b602de2485fbaf2f3c34247352b4
-size 5783761
+oid sha256:37f9723db5bf8d58e69570838f86321d5b61c9daef0e0eed219cccfba4dcdbc0
+size 5588709

sf_log.txt

@@ -8013,3 +8013,814 @@ main_loop: 1467.0711
 [2024-11-07 15:28:22,426][04584] Avg episode rewards: #0: 3.912, true rewards: #0: 3.712
 [2024-11-07 15:28:22,431][04584] Avg episode reward: 3.912, avg true_objective: 3.712
 [2024-11-07 15:28:31,547][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
+[2024-11-07 15:28:36,824][04584] The model has been pushed to https://huggingface.co/alidenewade/rl_course_vizdoom_health_gathering_supreme
+[2024-11-07 15:35:39,627][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 15:35:39,629][04584] Overriding arg 'num_envs_per_worker' with value 4 passed from command line
+[2024-11-07 15:35:39,631][04584] Overriding arg 'learning_rate' with value 0.0003 passed from command line
+[2024-11-07 15:35:39,633][04584] Overriding arg 'train_for_env_steps' with value 4000000 passed from command line
+[2024-11-07 15:35:39,766][04584] Experiment dir /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment already exists!
+[2024-11-07 15:35:39,767][04584] Resuming existing experiment from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment...
+[2024-11-07 15:35:39,768][04584] Weights and Biases integration disabled
+[2024-11-07 15:35:39,773][04584] Environment var CUDA_VISIBLE_DEVICES is 0
+
+[2024-11-07 15:35:53,100][04584] Starting experiment with the following configuration:
+help=False
+algo=APPO
+env=doom_health_gathering_supreme
+experiment=default_experiment
+train_dir=/root/hfRL/ml/LunarLander-v2/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=10
+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=0.0003
+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=4000000
+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
+[2024-11-07 15:35:53,102][04584] Saving configuration to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json...
+[2024-11-07 15:35:53,105][04584] Rollout worker 0 uses device cpu
+[2024-11-07 15:35:53,106][04584] Rollout worker 1 uses device cpu
+[2024-11-07 15:35:53,108][04584] Rollout worker 2 uses device cpu
+[2024-11-07 15:35:53,111][04584] Rollout worker 3 uses device cpu
+[2024-11-07 15:35:53,113][04584] Rollout worker 4 uses device cpu
+[2024-11-07 15:35:53,115][04584] Rollout worker 5 uses device cpu
+[2024-11-07 15:35:53,117][04584] Rollout worker 6 uses device cpu
+[2024-11-07 15:35:53,118][04584] Rollout worker 7 uses device cpu
+[2024-11-07 15:35:53,121][04584] Rollout worker 8 uses device cpu
+[2024-11-07 15:35:53,124][04584] Rollout worker 9 uses device cpu
+[2024-11-07 15:35:53,218][04584] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 15:35:53,219][04584] InferenceWorker_p0-w0: min num requests: 3
+[2024-11-07 15:35:53,265][04584] Starting all processes...
+[2024-11-07 15:35:53,267][04584] Starting process learner_proc0
+[2024-11-07 15:35:53,321][04584] Starting all processes...
+[2024-11-07 15:35:53,334][04584] Starting process inference_proc0-0
+[2024-11-07 15:35:53,338][04584] Starting process rollout_proc0
+[2024-11-07 15:35:53,338][04584] Starting process rollout_proc1
+[2024-11-07 15:35:53,340][04584] Starting process rollout_proc2
+[2024-11-07 15:35:53,341][04584] Starting process rollout_proc3
+[2024-11-07 15:35:53,343][04584] Starting process rollout_proc4
+[2024-11-07 15:35:53,344][04584] Starting process rollout_proc5
+[2024-11-07 15:35:53,346][04584] Starting process rollout_proc6
+[2024-11-07 15:35:53,348][04584] Starting process rollout_proc7
+[2024-11-07 15:35:53,350][04584] Starting process rollout_proc8
+[2024-11-07 15:35:53,351][04584] Starting process rollout_proc9
+[2024-11-07 15:36:01,323][12380] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 15:36:01,324][12380] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
+[2024-11-07 15:36:01,855][12406] Worker 8 uses CPU cores [0, 1, 2, 3, 4, 5, 6]
+[2024-11-07 15:36:01,933][12395] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 15:36:01,934][12395] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
+[2024-11-07 15:36:02,006][12380] Num visible devices: 1
+[2024-11-07 15:36:02,044][12395] Num visible devices: 1
+[2024-11-07 15:36:02,084][12398] Worker 2 uses CPU cores [2]
+[2024-11-07 15:36:02,105][12380] Starting seed is not provided
+[2024-11-07 15:36:02,106][12380] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 15:36:02,106][12380] Initializing actor-critic model on device cuda:0
+[2024-11-07 15:36:02,107][12380] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 15:36:02,125][12380] RunningMeanStd input shape: (1,)
+[2024-11-07 15:36:02,413][12380] ConvEncoder: input_channels=3
+[2024-11-07 15:36:02,565][12407] Worker 4 uses CPU cores [4]
+[2024-11-07 15:36:02,968][12408] Worker 6 uses CPU cores [6]
+[2024-11-07 15:36:03,069][12397] Worker 0 uses CPU cores [0]
+[2024-11-07 15:36:03,316][12380] Conv encoder output size: 512
+[2024-11-07 15:36:03,322][12380] Policy head output size: 512
+[2024-11-07 15:36:03,383][12396] Worker 1 uses CPU cores [1]
+[2024-11-07 15:36:03,390][12380] Created Actor Critic model with architecture:
+[2024-11-07 15:36:03,390][12380] 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)
+  )
+)
+[2024-11-07 15:36:03,484][12409] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6]
+[2024-11-07 15:36:03,503][12399] Worker 3 uses CPU cores [3]
+[2024-11-07 15:36:03,843][12410] Worker 5 uses CPU cores [5]
+[2024-11-07 15:36:03,920][12411] Worker 9 uses CPU cores [0, 1, 2, 3, 4, 5, 6]
+[2024-11-07 15:36:04,363][12380] Using optimizer <class 'torch.optim.adam.Adam'>
+[2024-11-07 15:36:07,491][12380] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003908_16007168.pth...
+[2024-11-07 15:36:07,594][12380] Loading model from checkpoint
+[2024-11-07 15:36:07,596][12380] Loaded experiment state at self.train_step=3908, self.env_steps=16007168
+[2024-11-07 15:36:07,597][12380] Initialized policy 0 weights for model version 3908
+[2024-11-07 15:36:07,606][12380] LearnerWorker_p0 finished initialization!
+[2024-11-07 15:36:07,606][12380] Using GPUs [0] for process 0 (actually maps to GPUs [0])
+[2024-11-07 15:36:08,060][12395] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 15:36:08,061][12395] RunningMeanStd input shape: (1,)
+[2024-11-07 15:36:08,077][12395] ConvEncoder: input_channels=3
+[2024-11-07 15:36:08,262][12395] Conv encoder output size: 512
+[2024-11-07 15:36:08,262][12395] Policy head output size: 512
+[2024-11-07 15:36:08,356][04584] Inference worker 0-0 is ready!
+[2024-11-07 15:36:08,358][04584] All inference workers are ready! Signal rollout workers to start!
+[2024-11-07 15:36:08,479][12399] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,521][12407] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,526][12411] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,532][12409] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,535][12398] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,536][12396] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,545][12397] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,546][12410] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,689][12406] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:08,695][12408] Doom resolution: 160x120, resize resolution: (128, 72)
+[2024-11-07 15:36:09,198][12407] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,203][12399] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,236][12398] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,720][12411] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,748][12397] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,774][04584] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 16007168. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 15:36:09,841][12410] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:09,917][12407] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:09,948][12399] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:10,220][12396] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:10,305][12408] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:10,708][12406] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:10,813][12407] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:10,964][12399] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:11,144][12408] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:11,150][12396] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:11,225][12397] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:11,390][12411] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:11,571][12407] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:11,584][12399] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:13,567][04584] Heartbeat connected on LearnerWorker_p0
+[2024-11-07 15:36:13,569][04584] Heartbeat connected on RolloutWorker_w3
+[2024-11-07 15:36:13,575][04584] Heartbeat connected on Batcher_0
+[2024-11-07 15:36:13,580][04584] Heartbeat connected on RolloutWorker_w4
+[2024-11-07 15:36:13,730][12406] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:13,871][12410] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:13,880][12397] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:13,894][12408] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:14,131][12396] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:14,255][12411] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:14,386][12409] Decorrelating experience for 0 frames...
+[2024-11-07 15:36:14,449][12408] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:14,489][12397] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:14,512][04584] Heartbeat connected on RolloutWorker_w6
+[2024-11-07 15:36:14,595][04584] Heartbeat connected on RolloutWorker_w0
+[2024-11-07 15:36:14,604][12396] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:14,678][04584] Heartbeat connected on RolloutWorker_w1
+[2024-11-07 15:36:14,774][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 16007168. Throughput: 0: 0.0. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 15:36:14,971][12398] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:15,065][12411] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:15,200][12409] Decorrelating experience for 32 frames...
+[2024-11-07 15:36:15,266][04584] Heartbeat connected on RolloutWorker_w9
+[2024-11-07 15:36:15,504][04584] Heartbeat connected on InferenceWorker_p0-w0
+[2024-11-07 15:36:15,728][12410] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:16,300][12398] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:16,335][12409] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:17,274][12406] Decorrelating experience for 64 frames...
+[2024-11-07 15:36:17,565][12410] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:17,901][04584] Heartbeat connected on RolloutWorker_w5
+[2024-11-07 15:36:18,870][12398] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:19,062][12406] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:19,077][04584] Heartbeat connected on RolloutWorker_w2
+[2024-11-07 15:36:19,382][04584] Heartbeat connected on RolloutWorker_w8
+[2024-11-07 15:36:19,785][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 16007168. Throughput: 0: 73.1. Samples: 732. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 15:36:19,789][04584] Avg episode reward: [(0, '1.797')]
+[2024-11-07 15:36:20,780][12409] Decorrelating experience for 96 frames...
+[2024-11-07 15:36:20,905][12380] Signal inference workers to stop experience collection...
+[2024-11-07 15:36:20,925][12395] InferenceWorker_p0-w0: stopping experience collection
+[2024-11-07 15:36:21,046][04584] Heartbeat connected on RolloutWorker_w7
+[2024-11-07 15:36:24,774][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 16007168. Throughput: 0: 184.4. Samples: 2766. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 15:36:24,775][04584] Avg episode reward: [(0, '2.131')]
+[2024-11-07 15:36:29,774][04584] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 16007168. Throughput: 0: 138.3. Samples: 2766. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
+[2024-11-07 15:36:29,776][04584] Avg episode reward: [(0, '2.131')]
+[2024-11-07 15:36:31,391][12380] Signal inference workers to resume experience collection...
+[2024-11-07 15:36:31,392][12395] InferenceWorker_p0-w0: resuming experience collection
+[2024-11-07 15:36:31,396][12380] Stopping Batcher_0...
+[2024-11-07 15:36:31,396][12380] Loop batcher_evt_loop terminating...
+[2024-11-07 15:36:31,433][04584] Component Batcher_0 stopped!
+[2024-11-07 15:36:31,892][12395] Weights refcount: 2 0
+[2024-11-07 15:36:31,894][12395] Stopping InferenceWorker_p0-w0...
+[2024-11-07 15:36:31,894][12395] Loop inference_proc0-0_evt_loop terminating...
+[2024-11-07 15:36:31,894][04584] Component InferenceWorker_p0-w0 stopped!
+[2024-11-07 15:36:32,099][12380] Saving /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003910_16015360.pth...
+[2024-11-07 15:36:32,269][12411] Stopping RolloutWorker_w9...
+[2024-11-07 15:36:32,270][12411] Loop rollout_proc9_evt_loop terminating...
+[2024-11-07 15:36:32,269][04584] Component RolloutWorker_w9 stopped!
+[2024-11-07 15:36:32,294][12408] Stopping RolloutWorker_w6...
+[2024-11-07 15:36:32,295][12408] Loop rollout_proc6_evt_loop terminating...
+[2024-11-07 15:36:32,296][12396] Stopping RolloutWorker_w1...
+[2024-11-07 15:36:32,297][12396] Loop rollout_proc1_evt_loop terminating...
+[2024-11-07 15:36:32,284][04584] Component RolloutWorker_w8 stopped!
+[2024-11-07 15:36:32,468][12406] Stopping RolloutWorker_w8...
+[2024-11-07 15:36:32,469][12406] Loop rollout_proc8_evt_loop terminating...
+[2024-11-07 15:36:32,467][04584] Component RolloutWorker_w6 stopped!
+[2024-11-07 15:36:32,470][04584] Component RolloutWorker_w1 stopped!
+[2024-11-07 15:36:32,489][04584] Component RolloutWorker_w5 stopped!
+[2024-11-07 15:36:32,490][12399] Stopping RolloutWorker_w3...
+[2024-11-07 15:36:32,490][04584] Component RolloutWorker_w3 stopped!
+[2024-11-07 15:36:32,492][12410] Stopping RolloutWorker_w5...
+[2024-11-07 15:36:32,492][12399] Loop rollout_proc3_evt_loop terminating...
+[2024-11-07 15:36:32,493][12410] Loop rollout_proc5_evt_loop terminating...
+[2024-11-07 15:36:32,644][12409] Stopping RolloutWorker_w7...
+[2024-11-07 15:36:32,645][12409] Loop rollout_proc7_evt_loop terminating...
+[2024-11-07 15:36:32,645][04584] Component RolloutWorker_w7 stopped!
+[2024-11-07 15:36:32,716][12397] Stopping RolloutWorker_w0...
+[2024-11-07 15:36:32,717][04584] Component RolloutWorker_w0 stopped!
+[2024-11-07 15:36:32,735][12397] Loop rollout_proc0_evt_loop terminating...
+[2024-11-07 15:36:32,920][12398] Stopping RolloutWorker_w2...
+[2024-11-07 15:36:32,920][12398] Loop rollout_proc2_evt_loop terminating...
+[2024-11-07 15:36:32,920][04584] Component RolloutWorker_w2 stopped!
+[2024-11-07 15:36:33,007][04584] Component RolloutWorker_w4 stopped!
+[2024-11-07 15:36:33,009][12407] Stopping RolloutWorker_w4...
+[2024-11-07 15:36:33,011][12407] Loop rollout_proc4_evt_loop terminating...
+[2024-11-07 15:36:33,392][12380] Removing /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003865_15831040.pth
+[2024-11-07 15:36:33,454][12380] Saving /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003910_16015360.pth...
+[2024-11-07 15:36:34,291][04584] Component LearnerWorker_p0 stopped!
+[2024-11-07 15:36:34,290][12380] Stopping LearnerWorker_p0...
+[2024-11-07 15:36:34,300][12380] Loop learner_proc0_evt_loop terminating...
+[2024-11-07 15:36:34,300][04584] Waiting for process learner_proc0 to stop...
+[2024-11-07 15:36:36,214][04584] Waiting for process inference_proc0-0 to join...
+[2024-11-07 15:36:36,215][04584] Waiting for process rollout_proc0 to join...
+[2024-11-07 15:36:36,216][04584] Waiting for process rollout_proc1 to join...
+[2024-11-07 15:36:36,218][04584] Waiting for process rollout_proc2 to join...
+[2024-11-07 15:36:36,220][04584] Waiting for process rollout_proc3 to join...
+[2024-11-07 15:36:36,224][04584] Waiting for process rollout_proc4 to join...
+[2024-11-07 15:36:36,225][04584] Waiting for process rollout_proc5 to join...
+[2024-11-07 15:36:36,228][04584] Waiting for process rollout_proc6 to join...
+[2024-11-07 15:36:36,229][04584] Waiting for process rollout_proc7 to join...
+[2024-11-07 15:36:36,231][04584] Waiting for process rollout_proc8 to join...
+[2024-11-07 15:36:36,244][04584] Waiting for process rollout_proc9 to join...
+[2024-11-07 15:36:36,246][04584] Batcher 0 profile tree view:
+batching: 0.1186, releasing_batches: 0.0010
+[2024-11-07 15:36:36,249][04584] InferenceWorker_p0-w0 profile tree view:
+wait_policy: 0.0051
+  wait_policy_total: 3.3668
+update_model: 0.4621
+  weight_update: 0.4034
+one_step: 0.0533
+  handle_policy_step: 8.7830
+    deserialize: 0.1270, stack: 0.0172, obs_to_device_normalize: 3.1395, forward: 4.5298, send_messages: 0.1979
+    prepare_outputs: 0.5682
+      to_cpu: 0.4418
+[2024-11-07 15:36:36,251][04584] Learner 0 profile tree view:
+misc: 0.0000, prepare_batch: 3.5253
+train: 9.8063
+  epoch_init: 0.0000, minibatch_init: 0.0000, losses_postprocess: 0.0012, kl_divergence: 0.1010, after_optimizer: 1.5531
+  calculate_losses: 1.1109
+    losses_init: 0.0000, forward_head: 0.5490, bptt_initial: 0.2427, tail: 0.0206, advantages_returns: 0.0022, losses: 0.2701
+    bptt: 0.0253
+      bptt_forward_core: 0.0251
+  update: 7.0378
+    clip: 0.2975
+[2024-11-07 15:36:36,255][04584] RolloutWorker_w0 profile tree view:
+wait_for_trajectories: 0.0012, enqueue_policy_requests: 0.1829, env_step: 1.6410, overhead: 0.1598, complete_rollouts: 0.0046
+save_policy_outputs: 0.0904
+  split_output_tensors: 0.0334
+[2024-11-07 15:36:36,260][04584] RolloutWorker_w9 profile tree view:
+wait_for_trajectories: 0.0012, enqueue_policy_requests: 0.3210, env_step: 2.2709, overhead: 0.0749, complete_rollouts: 0.0414
+save_policy_outputs: 0.0948
+  split_output_tensors: 0.0223
+[2024-11-07 15:36:36,263][04584] Loop Runner_EvtLoop terminating...
+[2024-11-07 15:36:36,268][04584] Runner profile tree view:
+main_loop: 43.0008
+[2024-11-07 15:36:36,270][04584] Collected {0: 16015360}, FPS: 190.5
+[2024-11-07 15:37:41,648][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 15:37:41,650][04584] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-07 15:37:41,652][04584] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-07 15:37:41,654][04584] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-07 15:37:41,656][04584] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-07 15:37:41,657][04584] Adding new argument 'max_num_frames'=50000 that is not in the saved config file!
+[2024-11-07 15:37:41,659][04584] Adding new argument 'max_num_episodes'=50 that is not in the saved config file!
+[2024-11-07 15:37:41,661][04584] Adding new argument 'push_to_hub'=False that is not in the saved config file!
+[2024-11-07 15:37:41,662][04584] Adding new argument 'hf_repository'=None that is not in the saved config file!
+[2024-11-07 15:37:41,663][04584] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-07 15:37:41,665][04584] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-07 15:37:41,666][04584] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-07 15:37:41,668][04584] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-07 15:37:41,671][04584] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-07 15:37:41,960][04584] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 15:37:41,972][04584] RunningMeanStd input shape: (1,)
+[2024-11-07 15:37:42,066][04584] ConvEncoder: input_channels=3
+[2024-11-07 15:37:42,267][04584] Conv encoder output size: 512
+[2024-11-07 15:37:42,271][04584] Policy head output size: 512
+[2024-11-07 15:37:42,469][04584] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003910_16015360.pth...
+[2024-11-07 15:37:43,334][04584] Num frames 100...
+[2024-11-07 15:37:43,616][04584] Num frames 200...
+[2024-11-07 15:37:43,874][04584] Num frames 300...
+[2024-11-07 15:37:44,131][04584] Num frames 400...
+[2024-11-07 15:37:44,308][04584] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
+[2024-11-07 15:37:44,314][04584] Avg episode reward: 5.480, avg true_objective: 4.480
+[2024-11-07 15:37:44,458][04584] Num frames 500...
+[2024-11-07 15:37:44,722][04584] Num frames 600...
+[2024-11-07 15:37:44,966][04584] Num frames 700...
+[2024-11-07 15:37:45,212][04584] Num frames 800...
+[2024-11-07 15:37:45,399][04584] Num frames 900...
+[2024-11-07 15:37:45,576][04584] Avg episode rewards: #0: 6.300, true rewards: #0: 4.800
+[2024-11-07 15:37:45,579][04584] Avg episode reward: 6.300, avg true_objective: 4.800
+[2024-11-07 15:37:45,668][04584] Num frames 1000...
+[2024-11-07 15:37:45,866][04584] Num frames 1100...
+[2024-11-07 15:37:46,070][04584] Num frames 1200...
+[2024-11-07 15:37:46,219][04584] Avg episode rewards: #0: 5.493, true rewards: #0: 4.160
+[2024-11-07 15:37:46,222][04584] Avg episode reward: 5.493, avg true_objective: 4.160
+[2024-11-07 15:37:46,327][04584] Num frames 1300...
+[2024-11-07 15:37:46,558][04584] Num frames 1400...
+[2024-11-07 15:37:46,796][04584] Num frames 1500...
+[2024-11-07 15:37:47,024][04584] Num frames 1600...
+[2024-11-07 15:37:47,319][04584] Avg episode rewards: #0: 5.490, true rewards: #0: 4.240
+[2024-11-07 15:37:47,320][04584] Avg episode reward: 5.490, avg true_objective: 4.240
+[2024-11-07 15:37:47,332][04584] Num frames 1700...
+[2024-11-07 15:37:47,581][04584] Num frames 1800...
+[2024-11-07 15:37:47,849][04584] Num frames 1900...
+[2024-11-07 15:37:48,088][04584] Num frames 2000...
+[2024-11-07 15:37:48,351][04584] Num frames 2100...
+[2024-11-07 15:37:48,524][04584] Avg episode rewards: #0: 5.488, true rewards: #0: 4.288
+[2024-11-07 15:37:48,526][04584] Avg episode reward: 5.488, avg true_objective: 4.288
+[2024-11-07 15:37:48,684][04584] Num frames 2200...
+[2024-11-07 15:37:48,922][04584] Num frames 2300...
+[2024-11-07 15:37:49,182][04584] Num frames 2400...
+[2024-11-07 15:37:49,236][04584] Avg episode rewards: #0: 5.000, true rewards: #0: 4.000
+[2024-11-07 15:37:49,239][04584] Avg episode reward: 5.000, avg true_objective: 4.000
+[2024-11-07 15:37:49,535][04584] Num frames 2500...
+[2024-11-07 15:37:49,918][04584] Num frames 2600...
+[2024-11-07 15:37:50,190][04584] Num frames 2700...
+[2024-11-07 15:37:50,445][04584] Avg episode rewards: #0: 4.834, true rewards: #0: 3.977
+[2024-11-07 15:37:50,448][04584] Avg episode reward: 4.834, avg true_objective: 3.977
+[2024-11-07 15:37:50,499][04584] Num frames 2800...
+[2024-11-07 15:37:50,761][04584] Num frames 2900...
+[2024-11-07 15:37:51,078][04584] Num frames 3000...
+[2024-11-07 15:37:51,427][04584] Num frames 3100...
+[2024-11-07 15:37:51,661][04584] Num frames 3200...
+[2024-11-07 15:37:51,786][04584] Avg episode rewards: #0: 4.915, true rewards: #0: 4.040
+[2024-11-07 15:37:51,792][04584] Avg episode reward: 4.915, avg true_objective: 4.040
+[2024-11-07 15:37:51,964][04584] Num frames 3300...
+[2024-11-07 15:37:52,359][04584] Num frames 3400...
+[2024-11-07 15:37:52,697][04584] Num frames 3500...
+[2024-11-07 15:37:52,980][04584] Avg episode rewards: #0: 4.777, true rewards: #0: 3.999
+[2024-11-07 15:37:52,985][04584] Avg episode reward: 4.777, avg true_objective: 3.999
+[2024-11-07 15:37:53,003][04584] Num frames 3600...
+[2024-11-07 15:37:53,277][04584] Num frames 3700...
+[2024-11-07 15:37:53,537][04584] Num frames 3800...
+[2024-11-07 15:37:55,495][04584] Num frames 3900...
+[2024-11-07 15:37:55,889][04584] Num frames 4000...
+[2024-11-07 15:37:56,113][04584] Avg episode rewards: #0: 4.847, true rewards: #0: 4.047
+[2024-11-07 15:37:56,114][04584] Avg episode reward: 4.847, avg true_objective: 4.047
+[2024-11-07 15:37:56,302][04584] Num frames 4100...
+[2024-11-07 15:37:56,492][04584] Num frames 4200...
+[2024-11-07 15:37:56,686][04584] Num frames 4300...
+[2024-11-07 15:37:56,874][04584] Num frames 4400...
+[2024-11-07 15:37:56,989][04584] Avg episode rewards: #0: 4.755, true rewards: #0: 4.028
+[2024-11-07 15:37:56,995][04584] Avg episode reward: 4.755, avg true_objective: 4.028
+[2024-11-07 15:37:57,143][04584] Num frames 4500...
+[2024-11-07 15:37:57,319][04584] Num frames 4600...
+[2024-11-07 15:37:57,495][04584] Num frames 4700...
+[2024-11-07 15:37:57,661][04584] Num frames 4800...
+[2024-11-07 15:37:57,745][04584] Avg episode rewards: #0: 4.679, true rewards: #0: 4.012
+[2024-11-07 15:37:57,749][04584] Avg episode reward: 4.679, avg true_objective: 4.012
+[2024-11-07 15:37:57,913][04584] Num frames 4900...
+[2024-11-07 15:37:58,074][04584] Num frames 5000...
+[2024-11-07 15:37:58,242][04584] Num frames 5100...
+[2024-11-07 15:37:58,405][04584] Num frames 5200...
+[2024-11-07 15:37:58,518][04584] Avg episode rewards: #0: 4.639, true rewards: #0: 4.024
+[2024-11-07 15:37:58,524][04584] Avg episode reward: 4.639, avg true_objective: 4.024
+[2024-11-07 15:37:58,671][04584] Num frames 5300...
+[2024-11-07 15:37:59,095][04584] Num frames 5400...
+[2024-11-07 15:37:59,551][04584] Num frames 5500...
+[2024-11-07 15:37:59,996][04584] Num frames 5600...
+[2024-11-07 15:38:00,123][04584] Avg episode rewards: #0: 4.582, true rewards: #0: 4.011
+[2024-11-07 15:38:00,127][04584] Avg episode reward: 4.582, avg true_objective: 4.011
+[2024-11-07 15:38:00,379][04584] Num frames 5700...
+[2024-11-07 15:38:00,650][04584] Num frames 5800...
+[2024-11-07 15:38:00,927][04584] Num frames 5900...
+[2024-11-07 15:38:01,238][04584] Avg episode rewards: #0: 4.533, true rewards: #0: 3.999
+[2024-11-07 15:38:01,240][04584] Avg episode reward: 4.533, avg true_objective: 3.999
+[2024-11-07 15:38:01,243][04584] Num frames 6000...
+[2024-11-07 15:38:01,558][04584] Num frames 6100...
+[2024-11-07 15:38:01,882][04584] Num frames 6200...
+[2024-11-07 15:38:02,265][04584] Num frames 6300...
+[2024-11-07 15:38:02,603][04584] Avg episode rewards: #0: 4.489, true rewards: #0: 3.989
+[2024-11-07 15:38:02,607][04584] Avg episode reward: 4.489, avg true_objective: 3.989
+[2024-11-07 15:38:02,683][04584] Num frames 6400...
+[2024-11-07 15:38:03,119][04584] Num frames 6500...
+[2024-11-07 15:38:03,370][04584] Num frames 6600...
+[2024-11-07 15:38:03,681][04584] Num frames 6700...
+[2024-11-07 15:38:03,940][04584] Avg episode rewards: #0: 4.451, true rewards: #0: 3.981
+[2024-11-07 15:38:03,946][04584] Avg episode reward: 4.451, avg true_objective: 3.981
+[2024-11-07 15:38:04,043][04584] Num frames 6800...
+[2024-11-07 15:38:04,300][04584] Num frames 6900...
+[2024-11-07 15:38:04,526][04584] Num frames 7000...
+[2024-11-07 15:38:04,767][04584] Num frames 7100...
+[2024-11-07 15:38:05,021][04584] Num frames 7200...
+[2024-11-07 15:38:05,132][04584] Avg episode rewards: #0: 4.508, true rewards: #0: 4.008
+[2024-11-07 15:38:05,136][04584] Avg episode reward: 4.508, avg true_objective: 4.008
+[2024-11-07 15:38:05,405][04584] Num frames 7300...
+[2024-11-07 15:38:05,721][04584] Num frames 7400...
+[2024-11-07 15:38:06,063][04584] Num frames 7500...
+[2024-11-07 15:38:06,318][04584] Num frames 7600...
+[2024-11-07 15:38:06,580][04584] Num frames 7700...
+[2024-11-07 15:38:06,845][04584] Num frames 7800...
+[2024-11-07 15:38:06,965][04584] Avg episode rewards: #0: 4.749, true rewards: #0: 4.117
+[2024-11-07 15:38:06,971][04584] Avg episode reward: 4.749, avg true_objective: 4.117
+[2024-11-07 15:38:07,186][04584] Num frames 7900...
+[2024-11-07 15:38:07,437][04584] Num frames 8000...
+[2024-11-07 15:38:07,692][04584] Num frames 8100...
+[2024-11-07 15:38:07,937][04584] Num frames 8200...
+[2024-11-07 15:38:08,025][04584] Avg episode rewards: #0: 4.704, true rewards: #0: 4.103
+[2024-11-07 15:38:08,029][04584] Avg episode reward: 4.704, avg true_objective: 4.103
+[2024-11-07 15:38:08,317][04584] Num frames 8300...
+[2024-11-07 15:38:08,566][04584] Num frames 8400...
+[2024-11-07 15:38:08,837][04584] Num frames 8500...
+[2024-11-07 15:38:09,107][04584] Num frames 8600...
+[2024-11-07 15:38:09,307][04584] Avg episode rewards: #0: 4.740, true rewards: #0: 4.121
+[2024-11-07 15:38:09,308][04584] Avg episode reward: 4.740, avg true_objective: 4.121
+[2024-11-07 15:38:09,453][04584] Num frames 8700...
+[2024-11-07 15:38:09,686][04584] Num frames 8800...
+[2024-11-07 15:38:09,939][04584] Num frames 8900...
+[2024-11-07 15:38:10,177][04584] Num frames 9000...
+[2024-11-07 15:38:10,338][04584] Avg episode rewards: #0: 4.700, true rewards: #0: 4.109
+[2024-11-07 15:38:10,342][04584] Avg episode reward: 4.700, avg true_objective: 4.109
+[2024-11-07 15:38:10,508][04584] Num frames 9100...
+[2024-11-07 15:38:10,747][04584] Num frames 9200...
+[2024-11-07 15:38:11,002][04584] Num frames 9300...
+[2024-11-07 15:38:11,253][04584] Num frames 9400...
+[2024-11-07 15:38:11,371][04584] Avg episode rewards: #0: 4.662, true rewards: #0: 4.097
+[2024-11-07 15:38:11,373][04584] Avg episode reward: 4.662, avg true_objective: 4.097
+[2024-11-07 15:38:11,558][04584] Num frames 9500...
+[2024-11-07 15:38:11,797][04584] Num frames 9600...
+[2024-11-07 15:38:12,042][04584] Num frames 9700...
+[2024-11-07 15:38:12,321][04584] Num frames 9800...
+[2024-11-07 15:38:12,400][04584] Avg episode rewards: #0: 4.628, true rewards: #0: 4.086
+[2024-11-07 15:38:12,405][04584] Avg episode reward: 4.628, avg true_objective: 4.086
+[2024-11-07 15:38:12,627][04584] Num frames 9900...
+[2024-11-07 15:38:12,861][04584] Num frames 10000...
+[2024-11-07 15:38:13,121][04584] Num frames 10100...
+[2024-11-07 15:38:13,439][04584] Avg episode rewards: #0: 4.596, true rewards: #0: 4.076
+[2024-11-07 15:38:13,441][04584] Avg episode reward: 4.596, avg true_objective: 4.076
+[2024-11-07 15:38:13,474][04584] Num frames 10200...
+[2024-11-07 15:38:13,711][04584] Num frames 10300...
+[2024-11-07 15:38:13,959][04584] Num frames 10400...
+[2024-11-07 15:38:14,240][04584] Num frames 10500...
+[2024-11-07 15:38:14,512][04584] Avg episode rewards: #0: 4.567, true rewards: #0: 4.067
+[2024-11-07 15:38:14,518][04584] Avg episode reward: 4.567, avg true_objective: 4.067
+[2024-11-07 15:38:14,597][04584] Num frames 10600...
+[2024-11-07 15:38:14,856][04584] Num frames 10700...
+[2024-11-07 15:38:15,109][04584] Num frames 10800...
+[2024-11-07 15:38:15,380][04584] Num frames 10900...
+[2024-11-07 15:38:15,591][04584] Avg episode rewards: #0: 4.540, true rewards: #0: 4.059
+[2024-11-07 15:38:15,597][04584] Avg episode reward: 4.540, avg true_objective: 4.059
+[2024-11-07 15:38:15,718][04584] Num frames 11000...
+[2024-11-07 15:38:15,972][04584] Num frames 11100...
+[2024-11-07 15:38:16,222][04584] Num frames 11200...
+[2024-11-07 15:38:16,517][04584] Num frames 11300...
+[2024-11-07 15:38:16,679][04584] Avg episode rewards: #0: 4.515, true rewards: #0: 4.051
+[2024-11-07 15:38:16,682][04584] Avg episode reward: 4.515, avg true_objective: 4.051
+[2024-11-07 15:38:16,832][04584] Num frames 11400...
+[2024-11-07 15:38:17,074][04584] Num frames 11500...
+[2024-11-07 15:38:17,327][04584] Num frames 11600...
+[2024-11-07 15:38:17,592][04584] Num frames 11700...
+[2024-11-07 15:38:17,715][04584] Avg episode rewards: #0: 4.492, true rewards: #0: 4.044
+[2024-11-07 15:38:17,716][04584] Avg episode reward: 4.492, avg true_objective: 4.044
+[2024-11-07 15:38:17,918][04584] Num frames 11800...
+[2024-11-07 15:38:18,163][04584] Num frames 11900...
+[2024-11-07 15:38:18,415][04584] Num frames 12000...
+[2024-11-07 15:38:18,667][04584] Num frames 12100...
+[2024-11-07 15:38:18,899][04584] Avg episode rewards: #0: 4.525, true rewards: #0: 4.058
+[2024-11-07 15:38:18,901][04584] Avg episode reward: 4.525, avg true_objective: 4.058
+[2024-11-07 15:38:18,974][04584] Num frames 12200...
+[2024-11-07 15:38:19,220][04584] Num frames 12300...
+[2024-11-07 15:38:19,443][04584] Num frames 12400...
+[2024-11-07 15:38:19,702][04584] Num frames 12500...
+[2024-11-07 15:38:19,901][04584] Avg episode rewards: #0: 4.503, true rewards: #0: 4.051
+[2024-11-07 15:38:19,907][04584] Avg episode reward: 4.503, avg true_objective: 4.051
+[2024-11-07 15:38:20,027][04584] Num frames 12600...
+[2024-11-07 15:38:20,278][04584] Num frames 12700...
+[2024-11-07 15:38:20,526][04584] Num frames 12800...
+[2024-11-07 15:38:20,752][04584] Num frames 12900...
+[2024-11-07 15:38:20,839][04584] Avg episode rewards: #0: 4.503, true rewards: #0: 4.035
+[2024-11-07 15:38:20,846][04584] Avg episode reward: 4.503, avg true_objective: 4.035
+[2024-11-07 15:38:21,054][04584] Num frames 13000...
+[2024-11-07 15:38:21,288][04584] Num frames 13100...
+[2024-11-07 15:38:21,597][04584] Num frames 13200...
+[2024-11-07 15:38:21,876][04584] Avg episode rewards: #0: 4.483, true rewards: #0: 4.029
+[2024-11-07 15:38:21,880][04584] Avg episode reward: 4.483, avg true_objective: 4.029
+[2024-11-07 15:38:21,916][04584] Num frames 13300...
+[2024-11-07 15:38:22,192][04584] Num frames 13400...
+[2024-11-07 15:38:22,459][04584] Num frames 13500...
+[2024-11-07 15:38:22,719][04584] Num frames 13600...
+[2024-11-07 15:38:22,781][04584] Avg episode rewards: #0: 4.442, true rewards: #0: 4.001
+[2024-11-07 15:38:22,788][04584] Avg episode reward: 4.442, avg true_objective: 4.001
+[2024-11-07 15:38:23,111][04584] Num frames 13700...
+[2024-11-07 15:38:23,346][04584] Num frames 13800...
+[2024-11-07 15:38:23,604][04584] Num frames 13900...
+[2024-11-07 15:38:23,879][04584] Num frames 14000...
+[2024-11-07 15:38:23,997][04584] Avg episode rewards: #0: 4.434, true rewards: #0: 4.005
+[2024-11-07 15:38:24,001][04584] Avg episode reward: 4.434, avg true_objective: 4.005
+[2024-11-07 15:38:24,227][04584] Num frames 14100...
+[2024-11-07 15:38:24,495][04584] Num frames 14200...
+[2024-11-07 15:38:24,742][04584] Num frames 14300...
+[2024-11-07 15:38:25,027][04584] Num frames 14400...
+[2024-11-07 15:38:25,091][04584] Avg episode rewards: #0: 4.417, true rewards: #0: 4.001
+[2024-11-07 15:38:25,094][04584] Avg episode reward: 4.417, avg true_objective: 4.001
+[2024-11-07 15:38:25,343][04584] Num frames 14500...
+[2024-11-07 15:38:25,587][04584] Num frames 14600...
+[2024-11-07 15:38:25,844][04584] Num frames 14700...
+[2024-11-07 15:38:26,130][04584] Avg episode rewards: #0: 4.402, true rewards: #0: 3.996
+[2024-11-07 15:38:26,132][04584] Avg episode reward: 4.402, avg true_objective: 3.996
+[2024-11-07 15:38:26,174][04584] Num frames 14800...
+[2024-11-07 15:38:26,405][04584] Num frames 14900...
+[2024-11-07 15:38:26,648][04584] Num frames 15000...
+[2024-11-07 15:38:26,901][04584] Num frames 15100...
+[2024-11-07 15:38:27,138][04584] Avg episode rewards: #0: 4.387, true rewards: #0: 3.992
+[2024-11-07 15:38:27,141][04584] Avg episode reward: 4.387, avg true_objective: 3.992
+[2024-11-07 15:38:27,236][04584] Num frames 15200...
+[2024-11-07 15:38:27,478][04584] Num frames 15300...
+[2024-11-07 15:38:29,403][04584] Num frames 15400...
+[2024-11-07 15:38:29,697][04584] Num frames 15500...
+[2024-11-07 15:38:29,972][04584] Num frames 15600...
+[2024-11-07 15:38:30,085][04584] Avg episode rewards: #0: 4.415, true rewards: #0: 4.005
+[2024-11-07 15:38:30,089][04584] Avg episode reward: 4.415, avg true_objective: 4.005
+[2024-11-07 15:38:30,347][04584] Num frames 15700...
+[2024-11-07 15:38:30,657][04584] Num frames 15800...
+[2024-11-07 15:38:30,952][04584] Num frames 15900...
+[2024-11-07 15:38:31,268][04584] Num frames 16000...
+[2024-11-07 15:38:31,337][04584] Avg episode rewards: #0: 4.401, true rewards: #0: 4.000
+[2024-11-07 15:38:31,342][04584] Avg episode reward: 4.401, avg true_objective: 4.000
+[2024-11-07 15:38:31,684][04584] Num frames 16100...
+[2024-11-07 15:38:32,012][04584] Num frames 16200...
+[2024-11-07 15:38:32,319][04584] Num frames 16300...
+[2024-11-07 15:38:32,645][04584] Avg episode rewards: #0: 4.387, true rewards: #0: 3.997
+[2024-11-07 15:38:32,646][04584] Avg episode reward: 4.387, avg true_objective: 3.997
+[2024-11-07 15:38:32,697][04584] Num frames 16400...
+[2024-11-07 15:38:33,003][04584] Num frames 16500...
+[2024-11-07 15:38:33,307][04584] Num frames 16600...
+[2024-11-07 15:38:33,484][04584] Avg episode rewards: #0: 4.343, true rewards: #0: 3.962
+[2024-11-07 15:38:33,488][04584] Avg episode reward: 4.343, avg true_objective: 3.962
+[2024-11-07 15:38:33,668][04584] Num frames 16700...
+[2024-11-07 15:38:34,047][04584] Num frames 16800...
+[2024-11-07 15:38:34,523][04584] Num frames 16900...
+[2024-11-07 15:38:34,994][04584] Num frames 17000...
+[2024-11-07 15:38:35,794][04584] Avg episode rewards: #0: 4.370, true rewards: #0: 3.974
+[2024-11-07 15:38:35,798][04584] Avg episode reward: 4.370, avg true_objective: 3.974
+[2024-11-07 15:38:35,859][04584] Num frames 17100...
+[2024-11-07 15:38:36,262][04584] Num frames 17200...
+[2024-11-07 15:38:36,655][04584] Num frames 17300...
+[2024-11-07 15:38:37,022][04584] Num frames 17400...
+[2024-11-07 15:38:37,312][04584] Avg episode rewards: #0: 4.358, true rewards: #0: 3.971
+[2024-11-07 15:38:37,315][04584] Avg episode reward: 4.358, avg true_objective: 3.971
+[2024-11-07 15:38:37,421][04584] Num frames 17500...
+[2024-11-07 15:38:37,774][04584] Num frames 17600...
+[2024-11-07 15:38:38,184][04584] Num frames 17700...
+[2024-11-07 15:38:38,526][04584] Num frames 17800...
+[2024-11-07 15:38:38,811][04584] Avg episode rewards: #0: 4.346, true rewards: #0: 3.968
+[2024-11-07 15:38:38,813][04584] Avg episode reward: 4.346, avg true_objective: 3.968
+[2024-11-07 15:38:39,007][04584] Num frames 17900...
+[2024-11-07 15:38:39,335][04584] Num frames 18000...
+[2024-11-07 15:38:39,650][04584] Num frames 18100...
+[2024-11-07 15:38:39,961][04584] Num frames 18200...
+[2024-11-07 15:38:40,263][04584] Avg episode rewards: #0: 4.342, true rewards: #0: 3.973
+[2024-11-07 15:38:40,266][04584] Avg episode reward: 4.342, avg true_objective: 3.973
+[2024-11-07 15:38:40,341][04584] Num frames 18300...
+[2024-11-07 15:38:40,634][04584] Num frames 18400...
+[2024-11-07 15:38:40,919][04584] Num frames 18500...
+[2024-11-07 15:38:41,232][04584] Num frames 18600...
+[2024-11-07 15:38:41,471][04584] Avg episode rewards: #0: 4.331, true rewards: #0: 3.970
+[2024-11-07 15:38:41,474][04584] Avg episode reward: 4.331, avg true_objective: 3.970
+[2024-11-07 15:38:41,617][04584] Num frames 18700...
+[2024-11-07 15:38:42,015][04584] Num frames 18800...
+[2024-11-07 15:38:42,322][04584] Num frames 18900...
+[2024-11-07 15:38:42,631][04584] Num frames 19000...
+[2024-11-07 15:38:42,886][04584] Num frames 19100...
+[2024-11-07 15:38:42,995][04584] Avg episode rewards: #0: 4.355, true rewards: #0: 3.980
+[2024-11-07 15:38:42,997][04584] Avg episode reward: 4.355, avg true_objective: 3.980
+[2024-11-07 15:38:43,228][04584] Num frames 19200...
+[2024-11-07 15:38:43,472][04584] Num frames 19300...
+[2024-11-07 15:38:43,715][04584] Num frames 19400...
+[2024-11-07 15:38:44,003][04584] Avg episode rewards: #0: 4.345, true rewards: #0: 3.978
+[2024-11-07 15:38:44,006][04584] Avg episode reward: 4.345, avg true_objective: 3.978
+[2024-11-07 15:38:44,051][04584] Num frames 19500...
+[2024-11-07 15:38:44,300][04584] Num frames 19600...
+[2024-11-07 15:38:44,563][04584] Num frames 19700...
+[2024-11-07 15:38:44,799][04584] Num frames 19800...
+[2024-11-07 15:38:45,032][04584] Avg episode rewards: #0: 4.335, true rewards: #0: 3.975
+[2024-11-07 15:38:45,034][04584] Avg episode reward: 4.335, avg true_objective: 3.975
+[2024-11-07 15:39:53,318][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!
+[2024-11-07 15:40:57,409][04584] Loading existing experiment configuration from /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/config.json
+[2024-11-07 15:40:57,411][04584] Overriding arg 'num_workers' with value 4 passed from command line
+[2024-11-07 15:40:57,412][04584] Adding new argument 'no_render'=True that is not in the saved config file!
+[2024-11-07 15:40:57,414][04584] Adding new argument 'save_video'=True that is not in the saved config file!
+[2024-11-07 15:40:57,416][04584] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
+[2024-11-07 15:40:57,417][04584] Adding new argument 'video_name'=None that is not in the saved config file!
+[2024-11-07 15:40:57,418][04584] Adding new argument 'max_num_frames'=50000 that is not in the saved config file!
+[2024-11-07 15:40:57,421][04584] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
+[2024-11-07 15:40:57,423][04584] Adding new argument 'push_to_hub'=True that is not in the saved config file!
+[2024-11-07 15:40:57,424][04584] Adding new argument 'hf_repository'='alidenewade/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
+[2024-11-07 15:40:57,425][04584] Adding new argument 'policy_index'=0 that is not in the saved config file!
+[2024-11-07 15:40:57,427][04584] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
+[2024-11-07 15:40:57,431][04584] Adding new argument 'train_script'=None that is not in the saved config file!
+[2024-11-07 15:40:57,433][04584] Adding new argument 'enjoy_script'=None that is not in the saved config file!
+[2024-11-07 15:40:57,436][04584] Using frameskip 1 and render_action_repeat=4 for evaluation
+[2024-11-07 15:40:57,474][04584] RunningMeanStd input shape: (3, 72, 128)
+[2024-11-07 15:40:57,476][04584] RunningMeanStd input shape: (1,)
+[2024-11-07 15:40:57,512][04584] ConvEncoder: input_channels=3
+[2024-11-07 15:40:57,565][04584] Conv encoder output size: 512
+[2024-11-07 15:40:57,567][04584] Policy head output size: 512
+[2024-11-07 15:40:57,598][04584] Loading state from checkpoint /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/checkpoint_p0/checkpoint_000003910_16015360.pth...
+[2024-11-07 15:40:58,332][04584] Num frames 100...
+[2024-11-07 15:40:58,540][04584] Num frames 200...
+[2024-11-07 15:40:58,710][04584] Avg episode rewards: #0: 2.560, true rewards: #0: 2.560
+[2024-11-07 15:40:58,711][04584] Avg episode reward: 2.560, avg true_objective: 2.560
+[2024-11-07 15:40:58,803][04584] Num frames 300...
+[2024-11-07 15:40:58,973][04584] Num frames 400...
+[2024-11-07 15:40:59,162][04584] Num frames 500...
+[2024-11-07 15:40:59,354][04584] Num frames 600...
+[2024-11-07 15:40:59,547][04584] Avg episode rewards: #0: 3.860, true rewards: #0: 3.360
+[2024-11-07 15:40:59,550][04584] Avg episode reward: 3.860, avg true_objective: 3.360
+[2024-11-07 15:40:59,619][04584] Num frames 700...
+[2024-11-07 15:40:59,833][04584] Num frames 800...
+[2024-11-07 15:41:00,011][04584] Num frames 900...
+[2024-11-07 15:41:00,183][04584] Num frames 1000...
+[2024-11-07 15:41:00,331][04584] Avg episode rewards: #0: 3.853, true rewards: #0: 3.520
+[2024-11-07 15:41:00,333][04584] Avg episode reward: 3.853, avg true_objective: 3.520
+[2024-11-07 15:41:00,444][04584] Num frames 1100...
+[2024-11-07 15:41:00,779][04584] Num frames 1200...
+[2024-11-07 15:41:01,066][04584] Num frames 1300...
+[2024-11-07 15:41:01,488][04584] Num frames 1400...
+[2024-11-07 15:41:01,736][04584] Avg episode rewards: #0: 3.850, true rewards: #0: 3.600
+[2024-11-07 15:41:01,738][04584] Avg episode reward: 3.850, avg true_objective: 3.600
+[2024-11-07 15:41:01,904][04584] Num frames 1500...
+[2024-11-07 15:41:02,150][04584] Num frames 1600...
+[2024-11-07 15:41:02,426][04584] Num frames 1700...
+[2024-11-07 15:41:02,629][04584] Num frames 1800...
+[2024-11-07 15:41:02,733][04584] Avg episode rewards: #0: 3.848, true rewards: #0: 3.648
+[2024-11-07 15:41:02,736][04584] Avg episode reward: 3.848, avg true_objective: 3.648
+[2024-11-07 15:41:03,184][04584] Num frames 1900...
+[2024-11-07 15:41:03,620][04584] Num frames 2000...
+[2024-11-07 15:41:03,844][04584] Num frames 2100...
+[2024-11-07 15:41:04,080][04584] Num frames 2200...
+[2024-11-07 15:41:04,173][04584] Avg episode rewards: #0: 3.847, true rewards: #0: 3.680
+[2024-11-07 15:41:04,174][04584] Avg episode reward: 3.847, avg true_objective: 3.680
+[2024-11-07 15:41:04,417][04584] Num frames 2300...
+[2024-11-07 15:41:04,822][04584] Num frames 2400...
+[2024-11-07 15:41:05,110][04584] Num frames 2500...
+[2024-11-07 15:41:05,409][04584] Num frames 2600...
+[2024-11-07 15:41:05,670][04584] Avg episode rewards: #0: 4.080, true rewards: #0: 3.794
+[2024-11-07 15:41:05,674][04584] Avg episode reward: 4.080, avg true_objective: 3.794
+[2024-11-07 15:41:05,824][04584] Num frames 2700...
+[2024-11-07 15:41:06,090][04584] Num frames 2800...
+[2024-11-07 15:41:06,377][04584] Num frames 2900...
+[2024-11-07 15:41:06,676][04584] Num frames 3000...
+[2024-11-07 15:41:06,844][04584] Avg episode rewards: #0: 4.050, true rewards: #0: 3.800
+[2024-11-07 15:41:06,846][04584] Avg episode reward: 4.050, avg true_objective: 3.800
+[2024-11-07 15:41:07,023][04584] Num frames 3100...
+[2024-11-07 15:41:07,265][04584] Num frames 3200...
+[2024-11-07 15:41:07,535][04584] Num frames 3300...
+[2024-11-07 15:41:07,812][04584] Num frames 3400...
+[2024-11-07 15:41:07,932][04584] Avg episode rewards: #0: 4.027, true rewards: #0: 3.804
+[2024-11-07 15:41:07,935][04584] Avg episode reward: 4.027, avg true_objective: 3.804
+[2024-11-07 15:41:08,163][04584] Num frames 3500...
+[2024-11-07 15:41:08,509][04584] Num frames 3600...
+[2024-11-07 15:41:08,879][04584] Num frames 3700...
+[2024-11-07 15:41:09,205][04584] Num frames 3800...
+[2024-11-07 15:41:09,303][04584] Avg episode rewards: #0: 4.008, true rewards: #0: 3.808
+[2024-11-07 15:41:09,305][04584] Avg episode reward: 4.008, avg true_objective: 3.808
+[2024-11-07 15:41:24,061][04584] Replay video saved to /root/hfRL/ml/LunarLander-v2/train_dir/default_experiment/replay.mp4!