Hugging Face's logo

magnustragardh
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results (legacy)
Model card Files
xet
 Metrics Community
magnustragardh commited on
Commit
6d5ff06
·
1 Parent(s): f4d4e4e

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1690746938.ptah +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000835_3420160_reward_25.153.pth +3 -0
  5. checkpoint_p0/checkpoint_000000946_3874816.pth +3 -0
  6. checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
  7. config.json +142 -0
  8. replay.mp4 +3 -0
  9. sf_log.txt +904 -0
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1690746938.ptah ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ca264f44d7226cb18027e9f1819b65def2d91d7d7b4a8913addead49ba5e8813
3
+ size 435825
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 11.50 +/- 5.76
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r magnustragardh/rl_course_vizdoom_health_gathering_supreme
34
+ ```
35
+
36
+
37
+ ## Using the model
38
+
39
+ To run the model after download, use the `enjoy` script corresponding to this environment:
40
+ ```
41
+ python -m <path.to.enjoy.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme
42
+ ```
43
+
44
+
45
+ You can also upload models to the Hugging Face Hub using the same script with the `--push_to_hub` flag.
46
+ See https://www.samplefactory.dev/10-huggingface/huggingface/ for more details
47
+
48
+ ## Training with this model
49
+
50
+ To continue training with this model, use the `train` script corresponding to this environment:
51
+ ```
52
+ python -m <path.to.train.module> --algo=APPO --env=doom_health_gathering_supreme --train_dir=./train_dir --experiment=rl_course_vizdoom_health_gathering_supreme --restart_behavior=resume --train_for_env_steps=10000000000
53
+ ```
54
+
55
+ Note, you may have to adjust `--train_for_env_steps` to a suitably high number as the experiment will resume at the number of steps it concluded at.
56
+
checkpoint_p0/best_000000835_3420160_reward_25.153.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fc5da6b186b5a609e2aadac4c3c36cdccce14189a7073f5b2251d5b8f6c4330
3
+ size 34928614
checkpoint_p0/checkpoint_000000946_3874816.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c76c04560987a2e8793866ca8f22b3748cb4bda7b1d920f17a3904a1e8be95a
3
+ size 34929028
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2e733420a3d7aec0a73508e4ed9ba9c5fa37c0d0e969a357a7c89f32edcd439
3
+ size 34929028
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/home/magnus/src/huggingface-reinforcement-learning-course/train_dir",
7
+ "restart_behavior": "resume",
8
+ "device": "gpu",
9
+ "seed": null,
10
+ "num_policies": 1,
11
+ "async_rl": true,
12
+ "serial_mode": false,
13
+ "batched_sampling": false,
14
+ "num_batches_to_accumulate": 2,
15
+ "worker_num_splits": 2,
16
+ "policy_workers_per_policy": 1,
17
+ "max_policy_lag": 1000,
18
+ "num_workers": 8,
19
+ "num_envs_per_worker": 4,
20
+ "batch_size": 1024,
21
+ "num_batches_per_epoch": 1,
22
+ "num_epochs": 1,
23
+ "rollout": 32,
24
+ "recurrence": 32,
25
+ "shuffle_minibatches": false,
26
+ "gamma": 0.99,
27
+ "reward_scale": 1.0,
28
+ "reward_clip": 1000.0,
29
+ "value_bootstrap": false,
30
+ "normalize_returns": true,
31
+ "exploration_loss_coeff": 0.001,
32
+ "value_loss_coeff": 0.5,
33
+ "kl_loss_coeff": 0.0,
34
+ "exploration_loss": "symmetric_kl",
35
+ "gae_lambda": 0.95,
36
+ "ppo_clip_ratio": 0.1,
37
+ "ppo_clip_value": 0.2,
38
+ "with_vtrace": false,
39
+ "vtrace_rho": 1.0,
40
+ "vtrace_c": 1.0,
41
+ "optimizer": "adam",
42
+ "adam_eps": 1e-06,
43
+ "adam_beta1": 0.9,
44
+ "adam_beta2": 0.999,
45
+ "max_grad_norm": 4.0,
46
+ "learning_rate": 0.0001,
47
+ "lr_schedule": "constant",
48
+ "lr_schedule_kl_threshold": 0.008,
49
+ "lr_adaptive_min": 1e-06,
50
+ "lr_adaptive_max": 0.01,
51
+ "obs_subtract_mean": 0.0,
52
+ "obs_scale": 255.0,
53
+ "normalize_input": true,
54
+ "normalize_input_keys": null,
55
+ "decorrelate_experience_max_seconds": 0,
56
+ "decorrelate_envs_on_one_worker": true,
57
+ "actor_worker_gpus": [],
58
+ "set_workers_cpu_affinity": true,
59
+ "force_envs_single_thread": false,
60
+ "default_niceness": 0,
61
+ "log_to_file": true,
62
+ "experiment_summaries_interval": 10,
63
+ "flush_summaries_interval": 30,
64
+ "stats_avg": 100,
65
+ "summaries_use_frameskip": true,
66
+ "heartbeat_interval": 20,
67
+ "heartbeat_reporting_interval": 600,
68
+ "train_for_env_steps": 4000000,
69
+ "train_for_seconds": 10000000000,
70
+ "save_every_sec": 120,
71
+ "keep_checkpoints": 2,
72
+ "load_checkpoint_kind": "latest",
73
+ "save_milestones_sec": -1,
74
+ "save_best_every_sec": 5,
75
+ "save_best_metric": "reward",
76
+ "save_best_after": 100000,
77
+ "benchmark": false,
78
+ "encoder_mlp_layers": [
79
+ 512,
80
+ 512
81
+ ],
82
+ "encoder_conv_architecture": "convnet_simple",
83
+ "encoder_conv_mlp_layers": [
84
+ 512
85
+ ],
86
+ "use_rnn": true,
87
+ "rnn_size": 512,
88
+ "rnn_type": "gru",
89
+ "rnn_num_layers": 1,
90
+ "decoder_mlp_layers": [],
91
+ "nonlinearity": "elu",
92
+ "policy_initialization": "orthogonal",
93
+ "policy_init_gain": 1.0,
94
+ "actor_critic_share_weights": true,
95
+ "adaptive_stddev": true,
96
+ "continuous_tanh_scale": 0.0,
97
+ "initial_stddev": 1.0,
98
+ "use_env_info_cache": false,
99
+ "env_gpu_actions": false,
100
+ "env_gpu_observations": true,
101
+ "env_frameskip": 4,
102
+ "env_framestack": 1,
103
+ "pixel_format": "CHW",
104
+ "use_record_episode_statistics": false,
105
+ "with_wandb": false,
106
+ "wandb_user": null,
107
+ "wandb_project": "sample_factory",
108
+ "wandb_group": null,
109
+ "wandb_job_type": "SF",
110
+ "wandb_tags": [],
111
+ "with_pbt": false,
112
+ "pbt_mix_policies_in_one_env": true,
113
+ "pbt_period_env_steps": 5000000,
114
+ "pbt_start_mutation": 20000000,
115
+ "pbt_replace_fraction": 0.3,
116
+ "pbt_mutation_rate": 0.15,
117
+ "pbt_replace_reward_gap": 0.1,
118
+ "pbt_replace_reward_gap_absolute": 1e-06,
119
+ "pbt_optimize_gamma": false,
120
+ "pbt_target_objective": "true_objective",
121
+ "pbt_perturb_min": 1.1,
122
+ "pbt_perturb_max": 1.5,
123
+ "num_agents": -1,
124
+ "num_humans": 0,
125
+ "num_bots": -1,
126
+ "start_bot_difficulty": null,
127
+ "timelimit": null,
128
+ "res_w": 128,
129
+ "res_h": 72,
130
+ "wide_aspect_ratio": false,
131
+ "eval_env_frameskip": 1,
132
+ "fps": 35,
133
+ "command_line": "--env=doom_health_gathering_supreme --num_workers=8 --num_envs_per_worker=4 --train_for_env_steps=4000000",
134
+ "cli_args": {
135
+ "env": "doom_health_gathering_supreme",
136
+ "num_workers": 8,
137
+ "num_envs_per_worker": 4,
138
+ "train_for_env_steps": 4000000
139
+ },
140
+ "git_hash": "unknown",
141
+ "git_repo_name": "not a git repository"
142
+ }
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:46802e0f7d8ed5f3bc9dd6f94482397a9c1cf24b3ced211b746d26e719a6f028
3
+ size 22110584
sf_log.txt ADDED
@@ -0,0 +1,904 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2023-07-30 21:55:41,672][26583] Saving configuration to /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/config.json...
2
+ [2023-07-30 21:55:41,674][26583] Rollout worker 0 uses device cpu
3
+ [2023-07-30 21:55:41,675][26583] Rollout worker 1 uses device cpu
4
+ [2023-07-30 21:55:41,676][26583] Rollout worker 2 uses device cpu
5
+ [2023-07-30 21:55:41,677][26583] Rollout worker 3 uses device cpu
6
+ [2023-07-30 21:55:41,678][26583] Rollout worker 4 uses device cpu
7
+ [2023-07-30 21:55:41,679][26583] Rollout worker 5 uses device cpu
8
+ [2023-07-30 21:55:41,680][26583] Rollout worker 6 uses device cpu
9
+ [2023-07-30 21:55:41,681][26583] Rollout worker 7 uses device cpu
10
+ [2023-07-30 21:55:41,759][26583] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2023-07-30 21:55:41,760][26583] InferenceWorker_p0-w0: min num requests: 2
12
+ [2023-07-30 21:55:41,781][26583] Starting all processes...
13
+ [2023-07-30 21:55:41,781][26583] Starting process learner_proc0
14
+ [2023-07-30 21:55:41,831][26583] Starting all processes...
15
+ [2023-07-30 21:55:41,845][26583] Starting process inference_proc0-0
16
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc0
17
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc1
18
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc2
19
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc3
20
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc4
21
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc5
22
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc6
23
+ [2023-07-30 21:55:41,846][26583] Starting process rollout_proc7
24
+ [2023-07-30 21:55:44,376][30444] Worker 6 uses CPU cores [6]
25
+ [2023-07-30 21:55:44,377][30439] Worker 3 uses CPU cores [3]
26
+ [2023-07-30 21:55:44,378][30442] Worker 5 uses CPU cores [5]
27
+ [2023-07-30 21:55:44,383][30441] Worker 4 uses CPU cores [4]
28
+ [2023-07-30 21:55:44,410][30435] Worker 0 uses CPU cores [0]
29
+ [2023-07-30 21:55:44,412][30403] Using GPUs [0] for process 0 (actually maps to GPUs [0])
30
+ [2023-07-30 21:55:44,412][30403] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
31
+ [2023-07-30 21:55:44,420][30434] Using GPUs [0] for process 0 (actually maps to GPUs [0])
32
+ [2023-07-30 21:55:44,420][30434] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
33
+ [2023-07-30 21:55:44,452][30434] Num visible devices: 1
34
+ [2023-07-30 21:55:44,454][30403] Num visible devices: 1
35
+ [2023-07-30 21:55:44,482][30403] Starting seed is not provided
36
+ [2023-07-30 21:55:44,483][30403] Using GPUs [0] for process 0 (actually maps to GPUs [0])
37
+ [2023-07-30 21:55:44,483][30403] Initializing actor-critic model on device cuda:0
38
+ [2023-07-30 21:55:44,483][30403] RunningMeanStd input shape: (3, 72, 128)
39
+ [2023-07-30 21:55:44,487][30403] RunningMeanStd input shape: (1,)
40
+ [2023-07-30 21:55:44,491][30437] Worker 2 uses CPU cores [2]
41
+ [2023-07-30 21:55:44,497][30403] ConvEncoder: input_channels=3
42
+ [2023-07-30 21:55:44,632][30443] Worker 7 uses CPU cores [7]
43
+ [2023-07-30 21:55:44,658][30438] Worker 1 uses CPU cores [1]
44
+ [2023-07-30 21:55:44,690][30403] Conv encoder output size: 512
45
+ [2023-07-30 21:55:44,690][30403] Policy head output size: 512
46
+ [2023-07-30 21:55:44,714][30403] Created Actor Critic model with architecture:
47
+ [2023-07-30 21:55:44,714][30403] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2023-07-30 21:55:44,957][30403] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2023-07-30 21:55:44,958][30403] No checkpoints found
90
+ [2023-07-30 21:55:44,958][30403] Did not load from checkpoint, starting from scratch!
91
+ [2023-07-30 21:55:44,958][30403] Initialized policy 0 weights for model version 0
92
+ [2023-07-30 21:55:44,962][30403] LearnerWorker_p0 finished initialization!
93
+ [2023-07-30 21:55:44,962][30403] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2023-07-30 21:55:45,047][30434] RunningMeanStd input shape: (3, 72, 128)
95
+ [2023-07-30 21:55:45,047][30434] RunningMeanStd input shape: (1,)
96
+ [2023-07-30 21:55:45,057][30434] ConvEncoder: input_channels=3
97
+ [2023-07-30 21:55:45,132][30434] Conv encoder output size: 512
98
+ [2023-07-30 21:55:45,133][30434] Policy head output size: 512
99
+ [2023-07-30 21:55:45,184][26583] Inference worker 0-0 is ready!
100
+ [2023-07-30 21:55:45,184][26583] All inference workers are ready! Signal rollout workers to start!
101
+ [2023-07-30 21:55:45,232][30441] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2023-07-30 21:55:45,232][30435] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2023-07-30 21:55:45,238][30444] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2023-07-30 21:55:45,239][30443] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2023-07-30 21:55:45,241][30438] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2023-07-30 21:55:45,255][30439] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2023-07-30 21:55:45,255][30437] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2023-07-30 21:55:45,266][30442] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2023-07-30 21:55:45,459][30442] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
110
+ [2023-07-30 21:55:45,460][30442] EvtLoop [rollout_proc5_evt_loop, process=rollout_proc5] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
111
+ Traceback (most recent call last):
112
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init
113
+ self.game.init()
114
+ vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly.
115
+
116
+ During handling of the above exception, another exception occurred:
117
+
118
+ Traceback (most recent call last):
119
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
120
+ slot_callable(*args)
121
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
122
+ env_runner.init(self.timing)
123
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
124
+ self._reset()
125
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset
126
+ observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0
127
+ ^^^^^^^^^^^^^^^^^^
128
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/gymnasium/core.py", line 453, in reset
129
+ return self.env.reset(seed=seed, options=options)
130
+ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
131
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
132
+ obs, info = self.env.reset(**kwargs)
133
+ ^^^^^^^^^^^^^^^^^^^^^^^^
134
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
135
+ obs, info = self.env.reset(**kwargs)
136
+ ^^^^^^^^^^^^^^^^^^^^^^^^
137
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
138
+ return self.env.reset(**kwargs)
139
+ ^^^^^^^^^^^^^^^^^^^^^^^^
140
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/gymnasium/core.py", line 501, in reset
141
+ obs, info = self.env.reset(seed=seed, options=options)
142
+ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
143
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sample_factory/envs/env_wrappers.py", line 82, in reset
144
+ obs, info = self.env.reset(**kwargs)
145
+ ^^^^^^^^^^^^^^^^^^^^^^^^
146
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/gymnasium/core.py", line 453, in reset
147
+ return self.env.reset(seed=seed, options=options)
148
+ ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
149
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
150
+ return self.env.reset(**kwargs)
151
+ ^^^^^^^^^^^^^^^^^^^^^^^^
152
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
153
+ self._ensure_initialized()
154
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
155
+ self.initialize()
156
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
157
+ self._game_init()
158
+ File "/home/magnus/.local/venv/python3.11/lib/python3.11/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
159
+ raise EnvCriticalError()
160
+ sample_factory.envs.env_utils.EnvCriticalError
161
+ [2023-07-30 21:55:45,465][30442] Unhandled exception in evt loop rollout_proc5_evt_loop
162
+ [2023-07-30 21:55:45,689][30435] Decorrelating experience for 0 frames...
163
+ [2023-07-30 21:55:45,689][30438] Decorrelating experience for 0 frames...
164
+ [2023-07-30 21:55:45,689][30439] Decorrelating experience for 0 frames...
165
+ [2023-07-30 21:55:45,689][30443] Decorrelating experience for 0 frames...
166
+ [2023-07-30 21:55:45,696][30444] Decorrelating experience for 0 frames...
167
+ [2023-07-30 21:55:45,899][30443] Decorrelating experience for 32 frames...
168
+ [2023-07-30 21:55:45,904][30435] Decorrelating experience for 32 frames...
169
+ [2023-07-30 21:55:45,911][30438] Decorrelating experience for 32 frames...
170
+ [2023-07-30 21:55:45,918][30439] Decorrelating experience for 32 frames...
171
+ [2023-07-30 21:55:45,934][30437] Decorrelating experience for 0 frames...
172
+ [2023-07-30 21:55:46,156][30441] Decorrelating experience for 0 frames...
173
+ [2023-07-30 21:55:46,156][30437] Decorrelating experience for 32 frames...
174
+ [2023-07-30 21:55:46,250][30435] Decorrelating experience for 64 frames...
175
+ [2023-07-30 21:55:46,254][30443] Decorrelating experience for 64 frames...
176
+ [2023-07-30 21:55:46,255][30439] Decorrelating experience for 64 frames...
177
+ [2023-07-30 21:55:46,350][30438] Decorrelating experience for 64 frames...
178
+ [2023-07-30 21:55:46,414][30437] Decorrelating experience for 64 frames...
179
+ [2023-07-30 21:55:46,445][30441] Decorrelating experience for 32 frames...
180
+ [2023-07-30 21:55:46,542][30444] Decorrelating experience for 32 frames...
181
+ [2023-07-30 21:55:46,559][30438] Decorrelating experience for 96 frames...
182
+ [2023-07-30 21:55:46,667][30439] Decorrelating experience for 96 frames...
183
+ [2023-07-30 21:55:46,779][30435] Decorrelating experience for 96 frames...
184
+ [2023-07-30 21:55:46,797][30444] Decorrelating experience for 64 frames...
185
+ [2023-07-30 21:55:46,878][30443] Decorrelating experience for 96 frames...
186
+ [2023-07-30 21:55:47,007][30444] Decorrelating experience for 96 frames...
187
+ [2023-07-30 21:55:47,097][30437] Decorrelating experience for 96 frames...
188
+ [2023-07-30 21:55:47,311][30441] Decorrelating experience for 64 frames...
189
+ [2023-07-30 21:55:47,517][30441] Decorrelating experience for 96 frames...
190
+ [2023-07-30 21:55:48,337][30403] Signal inference workers to stop experience collection...
191
+ [2023-07-30 21:55:48,342][30434] InferenceWorker_p0-w0: stopping experience collection
192
+ [2023-07-30 21:55:48,342][26583] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 2316. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
193
+ [2023-07-30 21:55:48,345][26583] Avg episode reward: [(0, '2.603')]
194
+ [2023-07-30 21:55:53,342][26583] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 79.2. Samples: 2712. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
195
+ [2023-07-30 21:55:53,351][26583] Avg episode reward: [(0, '2.603')]
196
+ [2023-07-30 21:55:57,154][30403] Signal inference workers to resume experience collection...
197
+ [2023-07-30 21:55:57,156][30434] InferenceWorker_p0-w0: resuming experience collection
198
+ [2023-07-30 21:55:58,342][26583] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 8192. Throughput: 0: 43.0. Samples: 2746. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
199
+ [2023-07-30 21:55:58,343][26583] Avg episode reward: [(0, '3.233')]
200
+ [2023-07-30 21:56:00,994][30434] Updated weights for policy 0, policy_version 10 (0.0013)
201
+ [2023-07-30 21:56:01,757][26583] Heartbeat connected on Batcher_0
202
+ [2023-07-30 21:56:01,764][26583] Heartbeat connected on InferenceWorker_p0-w0
203
+ [2023-07-30 21:56:01,770][26583] Heartbeat connected on LearnerWorker_p0
204
+ [2023-07-30 21:56:01,771][26583] Heartbeat connected on RolloutWorker_w2
205
+ [2023-07-30 21:56:01,775][26583] Heartbeat connected on RolloutWorker_w1
206
+ [2023-07-30 21:56:01,777][26583] Heartbeat connected on RolloutWorker_w3
207
+ [2023-07-30 21:56:01,779][26583] Heartbeat connected on RolloutWorker_w7
208
+ [2023-07-30 21:56:01,782][26583] Heartbeat connected on RolloutWorker_w6
209
+ [2023-07-30 21:56:01,786][26583] Heartbeat connected on RolloutWorker_w0
210
+ [2023-07-30 21:56:01,791][26583] Heartbeat connected on RolloutWorker_w4
211
+ [2023-07-30 21:56:03,342][26583] Fps is (10 sec: 6553.7, 60 sec: 4369.1, 300 sec: 4369.1). Total num frames: 65536. Throughput: 0: 975.2. Samples: 16944. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
212
+ [2023-07-30 21:56:03,343][26583] Avg episode reward: [(0, '4.284')]
213
+ [2023-07-30 21:56:04,737][30434] Updated weights for policy 0, policy_version 20 (0.0006)
214
+ [2023-07-30 21:56:08,342][26583] Fps is (10 sec: 11059.4, 60 sec: 5939.2, 300 sec: 5939.2). Total num frames: 118784. Throughput: 0: 1148.2. Samples: 25280. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
215
+ [2023-07-30 21:56:08,343][26583] Avg episode reward: [(0, '4.428')]
216
+ [2023-07-30 21:56:08,530][30403] Saving new best policy, reward=4.428!
217
+ [2023-07-30 21:56:08,531][30434] Updated weights for policy 0, policy_version 30 (0.0006)
218
+ [2023-07-30 21:56:12,442][30434] Updated weights for policy 0, policy_version 40 (0.0007)
219
+ [2023-07-30 21:56:13,342][26583] Fps is (10 sec: 10649.3, 60 sec: 6881.2, 300 sec: 6881.2). Total num frames: 172032. Throughput: 0: 1557.4. Samples: 41252. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
220
+ [2023-07-30 21:56:13,344][26583] Avg episode reward: [(0, '4.537')]
221
+ [2023-07-30 21:56:13,346][30403] Saving new best policy, reward=4.537!
222
+ [2023-07-30 21:56:16,393][30434] Updated weights for policy 0, policy_version 50 (0.0007)
223
+ [2023-07-30 21:56:18,342][26583] Fps is (10 sec: 10649.5, 60 sec: 7509.3, 300 sec: 7509.3). Total num frames: 225280. Throughput: 0: 1818.9. Samples: 56882. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
224
+ [2023-07-30 21:56:18,343][26583] Avg episode reward: [(0, '4.453')]
225
+ [2023-07-30 21:56:20,232][30434] Updated weights for policy 0, policy_version 60 (0.0007)
226
+ [2023-07-30 21:56:23,342][26583] Fps is (10 sec: 10240.2, 60 sec: 7840.9, 300 sec: 7840.9). Total num frames: 274432. Throughput: 0: 1788.3. Samples: 64906. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
227
+ [2023-07-30 21:56:23,343][26583] Avg episode reward: [(0, '4.392')]
228
+ [2023-07-30 21:56:24,233][30434] Updated weights for policy 0, policy_version 70 (0.0006)
229
+ [2023-07-30 21:56:28,182][30434] Updated weights for policy 0, policy_version 80 (0.0006)
230
+ [2023-07-30 21:56:28,342][26583] Fps is (10 sec: 10240.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 327680. Throughput: 0: 1952.3. Samples: 80408. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
231
+ [2023-07-30 21:56:28,344][26583] Avg episode reward: [(0, '4.330')]
232
+ [2023-07-30 21:56:33,107][30434] Updated weights for policy 0, policy_version 90 (0.0014)
233
+ [2023-07-30 21:56:33,342][26583] Fps is (10 sec: 9420.6, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 368640. Throughput: 0: 2017.1. Samples: 93084. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
234
+ [2023-07-30 21:56:33,344][26583] Avg episode reward: [(0, '4.669')]
235
+ [2023-07-30 21:56:33,345][30403] Saving new best policy, reward=4.669!
236
+ [2023-07-30 21:56:38,342][26583] Fps is (10 sec: 7782.3, 60 sec: 8110.1, 300 sec: 8110.1). Total num frames: 405504. Throughput: 0: 2134.0. Samples: 98744. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
237
+ [2023-07-30 21:56:38,343][26583] Avg episode reward: [(0, '4.369')]
238
+ [2023-07-30 21:56:38,423][30434] Updated weights for policy 0, policy_version 100 (0.0014)
239
+ [2023-07-30 21:56:43,342][26583] Fps is (10 sec: 7782.4, 60 sec: 8117.5, 300 sec: 8117.5). Total num frames: 446464. Throughput: 0: 2390.3. Samples: 110310. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
240
+ [2023-07-30 21:56:43,343][26583] Avg episode reward: [(0, '4.646')]
241
+ [2023-07-30 21:56:43,615][30434] Updated weights for policy 0, policy_version 110 (0.0013)
242
+ [2023-07-30 21:56:48,342][26583] Fps is (10 sec: 8191.9, 60 sec: 8123.7, 300 sec: 8123.7). Total num frames: 487424. Throughput: 0: 2363.5. Samples: 123304. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
243
+ [2023-07-30 21:56:48,344][26583] Avg episode reward: [(0, '4.407')]
244
+ [2023-07-30 21:56:48,397][30434] Updated weights for policy 0, policy_version 120 (0.0013)
245
+ [2023-07-30 21:56:53,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8806.4, 300 sec: 8129.0). Total num frames: 528384. Throughput: 0: 2312.9. Samples: 129360. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
246
+ [2023-07-30 21:56:53,343][26583] Avg episode reward: [(0, '4.498')]
247
+ [2023-07-30 21:56:53,373][30434] Updated weights for policy 0, policy_version 130 (0.0013)
248
+ [2023-07-30 21:56:58,113][30434] Updated weights for policy 0, policy_version 140 (0.0014)
249
+ [2023-07-30 21:56:58,342][26583] Fps is (10 sec: 8601.5, 60 sec: 9420.8, 300 sec: 8192.0). Total num frames: 573440. Throughput: 0: 2238.5. Samples: 141984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
250
+ [2023-07-30 21:56:58,345][26583] Avg episode reward: [(0, '4.593')]
251
+ [2023-07-30 21:57:03,342][26583] Fps is (10 sec: 8192.0, 60 sec: 9079.4, 300 sec: 8137.4). Total num frames: 610304. Throughput: 0: 2140.0. Samples: 153182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
252
+ [2023-07-30 21:57:03,343][26583] Avg episode reward: [(0, '4.483')]
253
+ [2023-07-30 21:57:03,778][30434] Updated weights for policy 0, policy_version 150 (0.0015)
254
+ [2023-07-30 21:57:08,342][26583] Fps is (10 sec: 7372.9, 60 sec: 8806.4, 300 sec: 8089.6). Total num frames: 647168. Throughput: 0: 2091.6. Samples: 159030. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
255
+ [2023-07-30 21:57:08,343][26583] Avg episode reward: [(0, '4.429')]
256
+ [2023-07-30 21:57:08,921][30434] Updated weights for policy 0, policy_version 160 (0.0014)
257
+ [2023-07-30 21:57:13,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8669.9, 300 sec: 8143.8). Total num frames: 692224. Throughput: 0: 2028.5. Samples: 171692. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
258
+ [2023-07-30 21:57:13,343][26583] Avg episode reward: [(0, '4.433')]
259
+ [2023-07-30 21:57:13,603][30434] Updated weights for policy 0, policy_version 170 (0.0013)
260
+ [2023-07-30 21:57:18,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8146.5). Total num frames: 733184. Throughput: 0: 2036.4. Samples: 184722. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
261
+ [2023-07-30 21:57:18,343][26583] Avg episode reward: [(0, '4.585')]
262
+ [2023-07-30 21:57:18,400][30434] Updated weights for policy 0, policy_version 180 (0.0013)
263
+ [2023-07-30 21:57:23,249][30434] Updated weights for policy 0, policy_version 190 (0.0014)
264
+ [2023-07-30 21:57:23,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8192.0). Total num frames: 778240. Throughput: 0: 2049.7. Samples: 190980. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
265
+ [2023-07-30 21:57:23,344][26583] Avg episode reward: [(0, '4.433')]
266
+ [2023-07-30 21:57:28,262][30434] Updated weights for policy 0, policy_version 200 (0.0015)
267
+ [2023-07-30 21:57:28,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 819200. Throughput: 0: 2069.0. Samples: 203416. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
268
+ [2023-07-30 21:57:28,343][26583] Avg episode reward: [(0, '4.535')]
269
+ [2023-07-30 21:57:33,138][30434] Updated weights for policy 0, policy_version 210 (0.0012)
270
+ [2023-07-30 21:57:33,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 860160. Throughput: 0: 2059.3. Samples: 215972. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
271
+ [2023-07-30 21:57:33,344][26583] Avg episode reward: [(0, '4.492')]
272
+ [2023-07-30 21:57:37,832][30434] Updated weights for policy 0, policy_version 220 (0.0013)
273
+ [2023-07-30 21:57:38,343][26583] Fps is (10 sec: 8600.8, 60 sec: 8328.4, 300 sec: 8229.2). Total num frames: 905216. Throughput: 0: 2074.7. Samples: 222722. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
274
+ [2023-07-30 21:57:38,344][26583] Avg episode reward: [(0, '4.588')]
275
+ [2023-07-30 21:57:38,350][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000221_905216.pth...
276
+ [2023-07-30 21:57:42,640][30434] Updated weights for policy 0, policy_version 230 (0.0013)
277
+ [2023-07-30 21:57:43,342][26583] Fps is (10 sec: 8601.5, 60 sec: 8328.5, 300 sec: 8227.6). Total num frames: 946176. Throughput: 0: 2072.4. Samples: 235242. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
278
+ [2023-07-30 21:57:43,344][26583] Avg episode reward: [(0, '4.537')]
279
+ [2023-07-30 21:57:47,512][30434] Updated weights for policy 0, policy_version 240 (0.0013)
280
+ [2023-07-30 21:57:48,342][26583] Fps is (10 sec: 8192.7, 60 sec: 8328.5, 300 sec: 8226.1). Total num frames: 987136. Throughput: 0: 2111.3. Samples: 248192. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
281
+ [2023-07-30 21:57:48,343][26583] Avg episode reward: [(0, '5.086')]
282
+ [2023-07-30 21:57:48,408][30403] Saving new best policy, reward=5.086!
283
+ [2023-07-30 21:57:52,125][30434] Updated weights for policy 0, policy_version 250 (0.0013)
284
+ [2023-07-30 21:57:53,342][26583] Fps is (10 sec: 8601.8, 60 sec: 8396.8, 300 sec: 8257.5). Total num frames: 1032192. Throughput: 0: 2122.9. Samples: 254560. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
285
+ [2023-07-30 21:57:53,343][26583] Avg episode reward: [(0, '4.973')]
286
+ [2023-07-30 21:57:56,866][30434] Updated weights for policy 0, policy_version 260 (0.0012)
287
+ [2023-07-30 21:57:58,342][26583] Fps is (10 sec: 9011.2, 60 sec: 8396.8, 300 sec: 8286.5). Total num frames: 1077248. Throughput: 0: 2135.0. Samples: 267766. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
288
+ [2023-07-30 21:57:58,344][26583] Avg episode reward: [(0, '5.061')]
289
+ [2023-07-30 21:58:01,829][30434] Updated weights for policy 0, policy_version 270 (0.0013)
290
+ [2023-07-30 21:58:03,342][26583] Fps is (10 sec: 8601.5, 60 sec: 8465.1, 300 sec: 8283.0). Total num frames: 1118208. Throughput: 0: 2121.0. Samples: 280168. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
291
+ [2023-07-30 21:58:03,344][26583] Avg episode reward: [(0, '5.590')]
292
+ [2023-07-30 21:58:03,345][30403] Saving new best policy, reward=5.590!
293
+ [2023-07-30 21:58:06,701][30434] Updated weights for policy 0, policy_version 280 (0.0015)
294
+ [2023-07-30 21:58:08,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8533.3, 300 sec: 8279.8). Total num frames: 1159168. Throughput: 0: 2118.5. Samples: 286312. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
295
+ [2023-07-30 21:58:08,344][26583] Avg episode reward: [(0, '5.949')]
296
+ [2023-07-30 21:58:08,352][30403] Saving new best policy, reward=5.949!
297
+ [2023-07-30 21:58:11,531][30434] Updated weights for policy 0, policy_version 290 (0.0013)
298
+ [2023-07-30 21:58:13,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8276.7). Total num frames: 1200128. Throughput: 0: 2128.5. Samples: 299198. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
299
+ [2023-07-30 21:58:13,344][26583] Avg episode reward: [(0, '5.925')]
300
+ [2023-07-30 21:58:16,169][30434] Updated weights for policy 0, policy_version 300 (0.0013)
301
+ [2023-07-30 21:58:18,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8301.2). Total num frames: 1245184. Throughput: 0: 2145.9. Samples: 312538. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
302
+ [2023-07-30 21:58:18,344][26583] Avg episode reward: [(0, '6.779')]
303
+ [2023-07-30 21:58:18,476][30403] Saving new best policy, reward=6.779!
304
+ [2023-07-30 21:58:20,995][30434] Updated weights for policy 0, policy_version 310 (0.0013)
305
+ [2023-07-30 21:58:23,342][26583] Fps is (10 sec: 9011.2, 60 sec: 8533.3, 300 sec: 8324.1). Total num frames: 1290240. Throughput: 0: 2134.7. Samples: 318780. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
306
+ [2023-07-30 21:58:23,343][26583] Avg episode reward: [(0, '6.417')]
307
+ [2023-07-30 21:58:25,737][30434] Updated weights for policy 0, policy_version 320 (0.0013)
308
+ [2023-07-30 21:58:28,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8533.3, 300 sec: 8320.0). Total num frames: 1331200. Throughput: 0: 2139.1. Samples: 331500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
309
+ [2023-07-30 21:58:28,343][26583] Avg episode reward: [(0, '6.890')]
310
+ [2023-07-30 21:58:28,350][30403] Saving new best policy, reward=6.890!
311
+ [2023-07-30 21:58:30,888][30434] Updated weights for policy 0, policy_version 330 (0.0013)
312
+ [2023-07-30 21:58:33,342][26583] Fps is (10 sec: 8191.9, 60 sec: 8533.3, 300 sec: 8316.1). Total num frames: 1372160. Throughput: 0: 2122.0. Samples: 343682. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
313
+ [2023-07-30 21:58:33,344][26583] Avg episode reward: [(0, '7.279')]
314
+ [2023-07-30 21:58:33,346][30403] Saving new best policy, reward=7.279!
315
+ [2023-07-30 21:58:35,791][30434] Updated weights for policy 0, policy_version 340 (0.0013)
316
+ [2023-07-30 21:58:38,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8465.2, 300 sec: 8312.5). Total num frames: 1413120. Throughput: 0: 2120.1. Samples: 349964. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
317
+ [2023-07-30 21:58:38,343][26583] Avg episode reward: [(0, '6.870')]
318
+ [2023-07-30 21:58:40,463][30434] Updated weights for policy 0, policy_version 350 (0.0014)
319
+ [2023-07-30 21:58:43,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8309.0). Total num frames: 1454080. Throughput: 0: 2107.3. Samples: 362594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
320
+ [2023-07-30 21:58:43,343][26583] Avg episode reward: [(0, '7.057')]
321
+ [2023-07-30 21:58:45,489][30434] Updated weights for policy 0, policy_version 360 (0.0014)
322
+ [2023-07-30 21:58:48,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8305.8). Total num frames: 1495040. Throughput: 0: 2103.6. Samples: 374828. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
323
+ [2023-07-30 21:58:48,343][26583] Avg episode reward: [(0, '6.917')]
324
+ [2023-07-30 21:58:50,366][30434] Updated weights for policy 0, policy_version 370 (0.0013)
325
+ [2023-07-30 21:58:53,342][26583] Fps is (10 sec: 8601.4, 60 sec: 8465.0, 300 sec: 8324.8). Total num frames: 1540096. Throughput: 0: 2118.0. Samples: 381624. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
326
+ [2023-07-30 21:58:53,345][26583] Avg episode reward: [(0, '7.737')]
327
+ [2023-07-30 21:58:53,348][30403] Saving new best policy, reward=7.737!
328
+ [2023-07-30 21:58:55,122][30434] Updated weights for policy 0, policy_version 380 (0.0013)
329
+ [2023-07-30 21:58:58,342][26583] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 8321.3). Total num frames: 1581056. Throughput: 0: 2117.8. Samples: 394498. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
330
+ [2023-07-30 21:58:58,344][26583] Avg episode reward: [(0, '8.603')]
331
+ [2023-07-30 21:58:58,359][30403] Saving new best policy, reward=8.603!
332
+ [2023-07-30 21:59:00,179][30434] Updated weights for policy 0, policy_version 390 (0.0013)
333
+ [2023-07-30 21:59:03,342][26583] Fps is (10 sec: 7782.6, 60 sec: 8328.5, 300 sec: 8297.0). Total num frames: 1617920. Throughput: 0: 2074.6. Samples: 405896. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
334
+ [2023-07-30 21:59:03,344][26583] Avg episode reward: [(0, '10.367')]
335
+ [2023-07-30 21:59:03,382][30403] Saving new best policy, reward=10.367!
336
+ [2023-07-30 21:59:05,461][30434] Updated weights for policy 0, policy_version 400 (0.0013)
337
+ [2023-07-30 21:59:08,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8396.8, 300 sec: 8314.9). Total num frames: 1662976. Throughput: 0: 2075.5. Samples: 412178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
338
+ [2023-07-30 21:59:08,343][26583] Avg episode reward: [(0, '10.512')]
339
+ [2023-07-30 21:59:08,350][30403] Saving new best policy, reward=10.512!
340
+ [2023-07-30 21:59:10,731][30434] Updated weights for policy 0, policy_version 410 (0.0014)
341
+ [2023-07-30 21:59:13,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8328.5, 300 sec: 8291.9). Total num frames: 1699840. Throughput: 0: 2040.4. Samples: 423316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
342
+ [2023-07-30 21:59:13,343][26583] Avg episode reward: [(0, '10.663')]
343
+ [2023-07-30 21:59:13,345][30403] Saving new best policy, reward=10.663!
344
+ [2023-07-30 21:59:16,025][30434] Updated weights for policy 0, policy_version 420 (0.0015)
345
+ [2023-07-30 21:59:18,342][26583] Fps is (10 sec: 7372.8, 60 sec: 8192.0, 300 sec: 8270.0). Total num frames: 1736704. Throughput: 0: 2035.4. Samples: 435274. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
346
+ [2023-07-30 21:59:18,343][26583] Avg episode reward: [(0, '12.375')]
347
+ [2023-07-30 21:59:18,513][30403] Saving new best policy, reward=12.375!
348
+ [2023-07-30 21:59:20,936][30434] Updated weights for policy 0, policy_version 430 (0.0014)
349
+ [2023-07-30 21:59:23,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8287.3). Total num frames: 1781760. Throughput: 0: 2040.4. Samples: 441780. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
350
+ [2023-07-30 21:59:23,343][26583] Avg episode reward: [(0, '12.711')]
351
+ [2023-07-30 21:59:23,345][30403] Saving new best policy, reward=12.711!
352
+ [2023-07-30 21:59:25,812][30434] Updated weights for policy 0, policy_version 440 (0.0013)
353
+ [2023-07-30 21:59:28,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8285.1). Total num frames: 1822720. Throughput: 0: 2036.2. Samples: 454222. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
354
+ [2023-07-30 21:59:28,345][26583] Avg episode reward: [(0, '12.625')]
355
+ [2023-07-30 21:59:30,578][30434] Updated weights for policy 0, policy_version 450 (0.0014)
356
+ [2023-07-30 21:59:33,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8301.2). Total num frames: 1867776. Throughput: 0: 2059.1. Samples: 467488. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
357
+ [2023-07-30 21:59:33,343][26583] Avg episode reward: [(0, '12.390')]
358
+ [2023-07-30 21:59:35,226][30434] Updated weights for policy 0, policy_version 460 (0.0012)
359
+ [2023-07-30 21:59:38,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8281.0). Total num frames: 1904640. Throughput: 0: 2040.9. Samples: 473462. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
360
+ [2023-07-30 21:59:38,344][26583] Avg episode reward: [(0, '11.377')]
361
+ [2023-07-30 21:59:38,363][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000466_1908736.pth...
362
+ [2023-07-30 21:59:40,198][30434] Updated weights for policy 0, policy_version 470 (0.0013)
363
+ [2023-07-30 21:59:43,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8296.6). Total num frames: 1949696. Throughput: 0: 2037.8. Samples: 486200. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
364
+ [2023-07-30 21:59:43,344][26583] Avg episode reward: [(0, '11.310')]
365
+ [2023-07-30 21:59:45,111][30434] Updated weights for policy 0, policy_version 480 (0.0013)
366
+ [2023-07-30 21:59:48,343][26583] Fps is (10 sec: 9010.0, 60 sec: 8328.3, 300 sec: 8311.4). Total num frames: 1994752. Throughput: 0: 2075.3. Samples: 499286. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
367
+ [2023-07-30 21:59:48,345][26583] Avg episode reward: [(0, '11.651')]
368
+ [2023-07-30 21:59:49,776][30434] Updated weights for policy 0, policy_version 490 (0.0013)
369
+ [2023-07-30 21:59:53,343][26583] Fps is (10 sec: 8601.1, 60 sec: 8260.2, 300 sec: 8309.0). Total num frames: 2035712. Throughput: 0: 2075.1. Samples: 505560. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
370
+ [2023-07-30 21:59:53,344][26583] Avg episode reward: [(0, '11.646')]
371
+ [2023-07-30 21:59:54,788][30434] Updated weights for policy 0, policy_version 500 (0.0014)
372
+ [2023-07-30 21:59:58,342][26583] Fps is (10 sec: 8193.0, 60 sec: 8260.3, 300 sec: 8306.7). Total num frames: 2076672. Throughput: 0: 2102.1. Samples: 517912. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
373
+ [2023-07-30 21:59:58,344][26583] Avg episode reward: [(0, '11.284')]
374
+ [2023-07-30 21:59:59,877][30434] Updated weights for policy 0, policy_version 510 (0.0020)
375
+ [2023-07-30 22:00:03,342][26583] Fps is (10 sec: 7782.5, 60 sec: 8260.2, 300 sec: 8288.4). Total num frames: 2113536. Throughput: 0: 2095.8. Samples: 529586. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
376
+ [2023-07-30 22:00:03,344][26583] Avg episode reward: [(0, '13.889')]
377
+ [2023-07-30 22:00:03,462][30403] Saving new best policy, reward=13.889!
378
+ [2023-07-30 22:00:05,109][30434] Updated weights for policy 0, policy_version 520 (0.0013)
379
+ [2023-07-30 22:00:08,342][26583] Fps is (10 sec: 7782.3, 60 sec: 8192.0, 300 sec: 8286.5). Total num frames: 2154496. Throughput: 0: 2084.5. Samples: 535582. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
380
+ [2023-07-30 22:00:08,346][26583] Avg episode reward: [(0, '13.681')]
381
+ [2023-07-30 22:00:10,317][30434] Updated weights for policy 0, policy_version 530 (0.0013)
382
+ [2023-07-30 22:00:13,342][26583] Fps is (10 sec: 7782.6, 60 sec: 8192.0, 300 sec: 8269.3). Total num frames: 2191360. Throughput: 0: 2055.0. Samples: 546696. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
383
+ [2023-07-30 22:00:13,344][26583] Avg episode reward: [(0, '12.054')]
384
+ [2023-07-30 22:00:16,372][30434] Updated weights for policy 0, policy_version 540 (0.0016)
385
+ [2023-07-30 22:00:18,342][26583] Fps is (10 sec: 6963.4, 60 sec: 8123.7, 300 sec: 8237.5). Total num frames: 2224128. Throughput: 0: 1988.3. Samples: 556962. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
386
+ [2023-07-30 22:00:18,344][26583] Avg episode reward: [(0, '12.806')]
387
+ [2023-07-30 22:00:22,159][30434] Updated weights for policy 0, policy_version 550 (0.0014)
388
+ [2023-07-30 22:00:23,342][26583] Fps is (10 sec: 6963.2, 60 sec: 7987.2, 300 sec: 8221.8). Total num frames: 2260992. Throughput: 0: 1975.1. Samples: 562340. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
389
+ [2023-07-30 22:00:23,344][26583] Avg episode reward: [(0, '14.083')]
390
+ [2023-07-30 22:00:23,347][30403] Saving new best policy, reward=14.083!
391
+ [2023-07-30 22:00:27,613][30434] Updated weights for policy 0, policy_version 560 (0.0014)
392
+ [2023-07-30 22:00:28,342][26583] Fps is (10 sec: 7372.8, 60 sec: 7918.9, 300 sec: 8206.6). Total num frames: 2297856. Throughput: 0: 1934.9. Samples: 573270. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
393
+ [2023-07-30 22:00:28,344][26583] Avg episode reward: [(0, '13.523')]
394
+ [2023-07-30 22:00:32,509][30434] Updated weights for policy 0, policy_version 570 (0.0015)
395
+ [2023-07-30 22:00:33,342][26583] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 8206.4). Total num frames: 2338816. Throughput: 0: 1923.3. Samples: 585830. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
396
+ [2023-07-30 22:00:33,344][26583] Avg episode reward: [(0, '13.131')]
397
+ [2023-07-30 22:00:37,363][30434] Updated weights for policy 0, policy_version 580 (0.0017)
398
+ [2023-07-30 22:00:38,342][26583] Fps is (10 sec: 8601.6, 60 sec: 7987.2, 300 sec: 8220.2). Total num frames: 2383872. Throughput: 0: 1926.9. Samples: 592270. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
399
+ [2023-07-30 22:00:38,344][26583] Avg episode reward: [(0, '15.660')]
400
+ [2023-07-30 22:00:38,351][30403] Saving new best policy, reward=15.660!
401
+ [2023-07-30 22:00:42,233][30434] Updated weights for policy 0, policy_version 590 (0.0012)
402
+ [2023-07-30 22:00:43,342][26583] Fps is (10 sec: 8601.5, 60 sec: 7918.9, 300 sec: 8219.8). Total num frames: 2424832. Throughput: 0: 1929.9. Samples: 604756. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
403
+ [2023-07-30 22:00:43,344][26583] Avg episode reward: [(0, '17.529')]
404
+ [2023-07-30 22:00:43,346][30403] Saving new best policy, reward=17.529!
405
+ [2023-07-30 22:00:47,415][30434] Updated weights for policy 0, policy_version 600 (0.0013)
406
+ [2023-07-30 22:00:48,342][26583] Fps is (10 sec: 7782.3, 60 sec: 7782.6, 300 sec: 8344.7). Total num frames: 2461696. Throughput: 0: 1934.0. Samples: 616616. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
407
+ [2023-07-30 22:00:48,344][26583] Avg episode reward: [(0, '16.239')]
408
+ [2023-07-30 22:00:52,539][30434] Updated weights for policy 0, policy_version 610 (0.0017)
409
+ [2023-07-30 22:00:53,342][26583] Fps is (10 sec: 7782.4, 60 sec: 7782.5, 300 sec: 8455.8). Total num frames: 2502656. Throughput: 0: 1929.8. Samples: 622424. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
410
+ [2023-07-30 22:00:53,344][26583] Avg episode reward: [(0, '17.078')]
411
+ [2023-07-30 22:00:57,596][30434] Updated weights for policy 0, policy_version 620 (0.0015)
412
+ [2023-07-30 22:00:58,342][26583] Fps is (10 sec: 8192.1, 60 sec: 7782.4, 300 sec: 8400.3). Total num frames: 2543616. Throughput: 0: 1955.6. Samples: 634698. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
413
+ [2023-07-30 22:00:58,343][26583] Avg episode reward: [(0, '19.059')]
414
+ [2023-07-30 22:00:58,349][30403] Saving new best policy, reward=19.059!
415
+ [2023-07-30 22:01:02,383][30434] Updated weights for policy 0, policy_version 630 (0.0013)
416
+ [2023-07-30 22:01:03,342][26583] Fps is (10 sec: 8601.7, 60 sec: 7919.0, 300 sec: 8372.5). Total num frames: 2588672. Throughput: 0: 2016.3. Samples: 647696. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
417
+ [2023-07-30 22:01:03,343][26583] Avg episode reward: [(0, '19.691')]
418
+ [2023-07-30 22:01:03,346][30403] Saving new best policy, reward=19.691!
419
+ [2023-07-30 22:01:07,070][30434] Updated weights for policy 0, policy_version 640 (0.0013)
420
+ [2023-07-30 22:01:08,342][26583] Fps is (10 sec: 8601.6, 60 sec: 7919.0, 300 sec: 8330.9). Total num frames: 2629632. Throughput: 0: 2039.3. Samples: 654110. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
421
+ [2023-07-30 22:01:08,343][26583] Avg episode reward: [(0, '19.344')]
422
+ [2023-07-30 22:01:11,832][30434] Updated weights for policy 0, policy_version 650 (0.0013)
423
+ [2023-07-30 22:01:13,342][26583] Fps is (10 sec: 8601.5, 60 sec: 8055.5, 300 sec: 8303.1). Total num frames: 2674688. Throughput: 0: 2088.5. Samples: 667254. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
424
+ [2023-07-30 22:01:13,344][26583] Avg episode reward: [(0, '19.095')]
425
+ [2023-07-30 22:01:16,544][30434] Updated weights for policy 0, policy_version 660 (0.0013)
426
+ [2023-07-30 22:01:18,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8275.3). Total num frames: 2715648. Throughput: 0: 2101.7. Samples: 680406. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
427
+ [2023-07-30 22:01:18,343][26583] Avg episode reward: [(0, '19.372')]
428
+ [2023-07-30 22:01:21,187][30434] Updated weights for policy 0, policy_version 670 (0.0013)
429
+ [2023-07-30 22:01:23,342][26583] Fps is (10 sec: 8601.7, 60 sec: 8328.6, 300 sec: 8247.5). Total num frames: 2760704. Throughput: 0: 2102.9. Samples: 686900. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
430
+ [2023-07-30 22:01:23,343][26583] Avg episode reward: [(0, '18.327')]
431
+ [2023-07-30 22:01:25,846][30434] Updated weights for policy 0, policy_version 680 (0.0013)
432
+ [2023-07-30 22:01:28,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8396.8, 300 sec: 8247.5). Total num frames: 2801664. Throughput: 0: 2115.5. Samples: 699954. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
433
+ [2023-07-30 22:01:28,343][26583] Avg episode reward: [(0, '18.028')]
434
+ [2023-07-30 22:01:30,919][30434] Updated weights for policy 0, policy_version 690 (0.0013)
435
+ [2023-07-30 22:01:33,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8465.1, 300 sec: 8275.3). Total num frames: 2846720. Throughput: 0: 2127.9. Samples: 712372. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
436
+ [2023-07-30 22:01:33,343][26583] Avg episode reward: [(0, '16.941')]
437
+ [2023-07-30 22:01:35,670][30434] Updated weights for policy 0, policy_version 700 (0.0013)
438
+ [2023-07-30 22:01:38,342][26583] Fps is (10 sec: 8601.5, 60 sec: 8396.8, 300 sec: 8275.3). Total num frames: 2887680. Throughput: 0: 2134.3. Samples: 718466. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
439
+ [2023-07-30 22:01:38,343][26583] Avg episode reward: [(0, '19.004')]
440
+ [2023-07-30 22:01:38,502][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000706_2891776.pth...
441
+ [2023-07-30 22:01:38,610][30403] Removing /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000221_905216.pth
442
+ [2023-07-30 22:01:40,593][30434] Updated weights for policy 0, policy_version 710 (0.0013)
443
+ [2023-07-30 22:01:43,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8396.8, 300 sec: 8275.3). Total num frames: 2928640. Throughput: 0: 2151.1. Samples: 731496. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
444
+ [2023-07-30 22:01:43,343][26583] Avg episode reward: [(0, '20.682')]
445
+ [2023-07-30 22:01:43,462][30403] Saving new best policy, reward=20.682!
446
+ [2023-07-30 22:01:45,500][30434] Updated weights for policy 0, policy_version 720 (0.0015)
447
+ [2023-07-30 22:01:48,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8465.1, 300 sec: 8275.3). Total num frames: 2969600. Throughput: 0: 2137.0. Samples: 743862. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
448
+ [2023-07-30 22:01:48,343][26583] Avg episode reward: [(0, '21.288')]
449
+ [2023-07-30 22:01:48,390][30403] Saving new best policy, reward=21.288!
450
+ [2023-07-30 22:01:50,481][30434] Updated weights for policy 0, policy_version 730 (0.0013)
451
+ [2023-07-30 22:01:53,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8533.4, 300 sec: 8275.3). Total num frames: 3014656. Throughput: 0: 2130.5. Samples: 749982. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
452
+ [2023-07-30 22:01:53,343][26583] Avg episode reward: [(0, '19.356')]
453
+ [2023-07-30 22:01:55,167][30434] Updated weights for policy 0, policy_version 740 (0.0013)
454
+ [2023-07-30 22:01:58,342][26583] Fps is (10 sec: 8601.4, 60 sec: 8533.3, 300 sec: 8289.2). Total num frames: 3055616. Throughput: 0: 2125.3. Samples: 762892. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
455
+ [2023-07-30 22:01:58,344][26583] Avg episode reward: [(0, '16.883')]
456
+ [2023-07-30 22:02:00,208][30434] Updated weights for policy 0, policy_version 750 (0.0013)
457
+ [2023-07-30 22:02:03,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8465.1, 300 sec: 8303.1). Total num frames: 3096576. Throughput: 0: 2103.6. Samples: 775068. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
458
+ [2023-07-30 22:02:03,343][26583] Avg episode reward: [(0, '19.054')]
459
+ [2023-07-30 22:02:04,962][30434] Updated weights for policy 0, policy_version 760 (0.0013)
460
+ [2023-07-30 22:02:08,344][26583] Fps is (10 sec: 8190.5, 60 sec: 8464.8, 300 sec: 8289.1). Total num frames: 3137536. Throughput: 0: 2105.6. Samples: 781658. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
461
+ [2023-07-30 22:02:08,346][26583] Avg episode reward: [(0, '20.371')]
462
+ [2023-07-30 22:02:10,042][30434] Updated weights for policy 0, policy_version 770 (0.0013)
463
+ [2023-07-30 22:02:13,342][26583] Fps is (10 sec: 8191.7, 60 sec: 8396.8, 300 sec: 8289.2). Total num frames: 3178496. Throughput: 0: 2078.6. Samples: 793492. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
464
+ [2023-07-30 22:02:13,344][26583] Avg episode reward: [(0, '21.359')]
465
+ [2023-07-30 22:02:13,346][30403] Saving new best policy, reward=21.359!
466
+ [2023-07-30 22:02:15,435][30434] Updated weights for policy 0, policy_version 780 (0.0014)
467
+ [2023-07-30 22:02:18,342][26583] Fps is (10 sec: 7784.0, 60 sec: 8328.5, 300 sec: 8261.4). Total num frames: 3215360. Throughput: 0: 2058.9. Samples: 805024. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
468
+ [2023-07-30 22:02:18,344][26583] Avg episode reward: [(0, '21.280')]
469
+ [2023-07-30 22:02:20,617][30434] Updated weights for policy 0, policy_version 790 (0.0013)
470
+ [2023-07-30 22:02:23,342][26583] Fps is (10 sec: 7782.4, 60 sec: 8260.2, 300 sec: 8261.4). Total num frames: 3256320. Throughput: 0: 2051.8. Samples: 810796. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
471
+ [2023-07-30 22:02:23,344][26583] Avg episode reward: [(0, '21.538')]
472
+ [2023-07-30 22:02:23,346][30403] Saving new best policy, reward=21.538!
473
+ [2023-07-30 22:02:25,527][30434] Updated weights for policy 0, policy_version 800 (0.0013)
474
+ [2023-07-30 22:02:28,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8260.3, 300 sec: 8261.4). Total num frames: 3297280. Throughput: 0: 2044.1. Samples: 823482. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
475
+ [2023-07-30 22:02:28,343][26583] Avg episode reward: [(0, '20.435')]
476
+ [2023-07-30 22:02:30,558][30434] Updated weights for policy 0, policy_version 810 (0.0014)
477
+ [2023-07-30 22:02:33,342][26583] Fps is (10 sec: 8192.3, 60 sec: 8192.0, 300 sec: 8247.6). Total num frames: 3338240. Throughput: 0: 2030.1. Samples: 835216. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
478
+ [2023-07-30 22:02:33,344][26583] Avg episode reward: [(0, '22.275')]
479
+ [2023-07-30 22:02:33,345][30403] Saving new best policy, reward=22.275!
480
+ [2023-07-30 22:02:35,807][30434] Updated weights for policy 0, policy_version 820 (0.0014)
481
+ [2023-07-30 22:02:38,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8247.5). Total num frames: 3379200. Throughput: 0: 2029.3. Samples: 841302. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
482
+ [2023-07-30 22:02:38,344][26583] Avg episode reward: [(0, '24.539')]
483
+ [2023-07-30 22:02:38,350][30403] Saving new best policy, reward=24.539!
484
+ [2023-07-30 22:02:40,621][30434] Updated weights for policy 0, policy_version 830 (0.0013)
485
+ [2023-07-30 22:02:43,342][26583] Fps is (10 sec: 8191.6, 60 sec: 8191.9, 300 sec: 8247.5). Total num frames: 3420160. Throughput: 0: 2020.3. Samples: 853806. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
486
+ [2023-07-30 22:02:43,347][26583] Avg episode reward: [(0, '25.153')]
487
+ [2023-07-30 22:02:43,349][30403] Saving new best policy, reward=25.153!
488
+ [2023-07-30 22:02:45,497][30434] Updated weights for policy 0, policy_version 840 (0.0013)
489
+ [2023-07-30 22:02:48,342][26583] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8247.5). Total num frames: 3465216. Throughput: 0: 2035.4. Samples: 866660. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
490
+ [2023-07-30 22:02:48,343][26583] Avg episode reward: [(0, '21.855')]
491
+ [2023-07-30 22:02:50,394][30434] Updated weights for policy 0, policy_version 850 (0.0013)
492
+ [2023-07-30 22:02:53,342][26583] Fps is (10 sec: 8601.9, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3506176. Throughput: 0: 2029.3. Samples: 872972. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
493
+ [2023-07-30 22:02:53,344][26583] Avg episode reward: [(0, '20.560')]
494
+ [2023-07-30 22:02:55,181][30434] Updated weights for policy 0, policy_version 860 (0.0013)
495
+ [2023-07-30 22:02:58,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3547136. Throughput: 0: 2049.3. Samples: 885708. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
496
+ [2023-07-30 22:02:58,343][26583] Avg episode reward: [(0, '20.219')]
497
+ [2023-07-30 22:03:00,046][30434] Updated weights for policy 0, policy_version 870 (0.0015)
498
+ [2023-07-30 22:03:03,342][26583] Fps is (10 sec: 8191.8, 60 sec: 8192.0, 300 sec: 8233.6). Total num frames: 3588096. Throughput: 0: 2064.6. Samples: 897930. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
499
+ [2023-07-30 22:03:03,344][26583] Avg episode reward: [(0, '20.055')]
500
+ [2023-07-30 22:03:05,098][30434] Updated weights for policy 0, policy_version 880 (0.0013)
501
+ [2023-07-30 22:03:08,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.3, 300 sec: 8233.7). Total num frames: 3629056. Throughput: 0: 2073.8. Samples: 904118. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
502
+ [2023-07-30 22:03:08,344][26583] Avg episode reward: [(0, '20.730')]
503
+ [2023-07-30 22:03:10,017][30434] Updated weights for policy 0, policy_version 890 (0.0013)
504
+ [2023-07-30 22:03:13,342][26583] Fps is (10 sec: 8192.2, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 3670016. Throughput: 0: 2067.2. Samples: 916504. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
505
+ [2023-07-30 22:03:13,344][26583] Avg episode reward: [(0, '19.995')]
506
+ [2023-07-30 22:03:15,073][30434] Updated weights for policy 0, policy_version 900 (0.0013)
507
+ [2023-07-30 22:03:18,342][26583] Fps is (10 sec: 8191.6, 60 sec: 8260.2, 300 sec: 8205.9). Total num frames: 3710976. Throughput: 0: 2078.9. Samples: 928768. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
508
+ [2023-07-30 22:03:18,344][26583] Avg episode reward: [(0, '21.314')]
509
+ [2023-07-30 22:03:20,056][30434] Updated weights for policy 0, policy_version 910 (0.0013)
510
+ [2023-07-30 22:03:23,342][26583] Fps is (10 sec: 8191.9, 60 sec: 8260.3, 300 sec: 8205.9). Total num frames: 3751936. Throughput: 0: 2084.7. Samples: 935114. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
511
+ [2023-07-30 22:03:23,343][26583] Avg episode reward: [(0, '24.316')]
512
+ [2023-07-30 22:03:25,038][30434] Updated weights for policy 0, policy_version 920 (0.0017)
513
+ [2023-07-30 22:03:28,342][26583] Fps is (10 sec: 8192.3, 60 sec: 8260.3, 300 sec: 8205.9). Total num frames: 3792896. Throughput: 0: 2079.1. Samples: 947366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
514
+ [2023-07-30 22:03:28,343][26583] Avg episode reward: [(0, '23.519')]
515
+ [2023-07-30 22:03:29,999][30434] Updated weights for policy 0, policy_version 930 (0.0013)
516
+ [2023-07-30 22:03:33,342][26583] Fps is (10 sec: 8192.1, 60 sec: 8260.3, 300 sec: 8205.9). Total num frames: 3833856. Throughput: 0: 2070.0. Samples: 959808. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
517
+ [2023-07-30 22:03:33,343][26583] Avg episode reward: [(0, '21.054')]
518
+ [2023-07-30 22:03:35,049][30434] Updated weights for policy 0, policy_version 940 (0.0013)
519
+ [2023-07-30 22:03:38,342][26583] Fps is (10 sec: 8191.9, 60 sec: 8260.2, 300 sec: 8205.9). Total num frames: 3874816. Throughput: 0: 2062.4. Samples: 965782. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
520
+ [2023-07-30 22:03:38,344][26583] Avg episode reward: [(0, '22.256')]
521
+ [2023-07-30 22:03:38,363][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000946_3874816.pth...
522
+ [2023-07-30 22:03:38,478][30403] Removing /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000466_1908736.pth
523
+ [2023-07-30 22:03:40,049][30434] Updated weights for policy 0, policy_version 950 (0.0013)
524
+ [2023-07-30 22:03:43,342][26583] Fps is (10 sec: 8191.9, 60 sec: 8260.3, 300 sec: 8205.9). Total num frames: 3915776. Throughput: 0: 2048.4. Samples: 977886. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
525
+ [2023-07-30 22:03:43,344][26583] Avg episode reward: [(0, '22.156')]
526
+ [2023-07-30 22:03:45,071][30434] Updated weights for policy 0, policy_version 960 (0.0014)
527
+ [2023-07-30 22:03:48,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 3956736. Throughput: 0: 2061.4. Samples: 990694. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
528
+ [2023-07-30 22:03:48,344][26583] Avg episode reward: [(0, '21.617')]
529
+ [2023-07-30 22:03:49,946][30434] Updated weights for policy 0, policy_version 970 (0.0013)
530
+ [2023-07-30 22:03:53,342][26583] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 3997696. Throughput: 0: 2057.6. Samples: 996708. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
531
+ [2023-07-30 22:03:53,344][26583] Avg episode reward: [(0, '21.716')]
532
+ [2023-07-30 22:03:53,922][30403] Stopping Batcher_0...
533
+ [2023-07-30 22:03:53,923][30403] Loop batcher_evt_loop terminating...
534
+ [2023-07-30 22:03:53,925][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
535
+ [2023-07-30 22:03:53,942][30441] Stopping RolloutWorker_w4...
536
+ [2023-07-30 22:03:53,943][30441] Loop rollout_proc4_evt_loop terminating...
537
+ [2023-07-30 22:03:53,946][30444] Stopping RolloutWorker_w6...
538
+ [2023-07-30 22:03:53,947][30444] Loop rollout_proc6_evt_loop terminating...
539
+ [2023-07-30 22:03:53,928][26583] Component Batcher_0 stopped!
540
+ [2023-07-30 22:03:53,952][30438] Stopping RolloutWorker_w1...
541
+ [2023-07-30 22:03:53,951][26583] Component RolloutWorker_w5 process died already! Don't wait for it.
542
+ [2023-07-30 22:03:53,954][26583] Component RolloutWorker_w4 stopped!
543
+ [2023-07-30 22:03:53,953][30438] Loop rollout_proc1_evt_loop terminating...
544
+ [2023-07-30 22:03:53,959][30437] Stopping RolloutWorker_w2...
545
+ [2023-07-30 22:03:53,960][30437] Loop rollout_proc2_evt_loop terminating...
546
+ [2023-07-30 22:03:53,960][30435] Stopping RolloutWorker_w0...
547
+ [2023-07-30 22:03:53,960][30435] Loop rollout_proc0_evt_loop terminating...
548
+ [2023-07-30 22:03:53,955][26583] Component RolloutWorker_w6 stopped!
549
+ [2023-07-30 22:03:53,962][26583] Component RolloutWorker_w1 stopped!
550
+ [2023-07-30 22:03:53,964][26583] Component RolloutWorker_w2 stopped!
551
+ [2023-07-30 22:03:53,965][26583] Component RolloutWorker_w0 stopped!
552
+ [2023-07-30 22:03:54,007][30443] Stopping RolloutWorker_w7...
553
+ [2023-07-30 22:03:54,008][30443] Loop rollout_proc7_evt_loop terminating...
554
+ [2023-07-30 22:03:54,007][26583] Component RolloutWorker_w7 stopped!
555
+ [2023-07-30 22:03:54,028][30434] Weights refcount: 2 0
556
+ [2023-07-30 22:03:54,038][30403] Removing /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000706_2891776.pth
557
+ [2023-07-30 22:03:54,045][30434] Stopping InferenceWorker_p0-w0...
558
+ [2023-07-30 22:03:54,046][30434] Loop inference_proc0-0_evt_loop terminating...
559
+ [2023-07-30 22:03:54,047][30403] Saving /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
560
+ [2023-07-30 22:03:54,046][26583] Component InferenceWorker_p0-w0 stopped!
561
+ [2023-07-30 22:03:54,048][26583] Component RolloutWorker_w3 stopped!
562
+ [2023-07-30 22:03:54,047][30439] Stopping RolloutWorker_w3...
563
+ [2023-07-30 22:03:54,067][30439] Loop rollout_proc3_evt_loop terminating...
564
+ [2023-07-30 22:03:54,188][26583] Component LearnerWorker_p0 stopped!
565
+ [2023-07-30 22:03:54,190][26583] Waiting for process learner_proc0 to stop...
566
+ [2023-07-30 22:03:54,188][30403] Stopping LearnerWorker_p0...
567
+ [2023-07-30 22:03:54,194][30403] Loop learner_proc0_evt_loop terminating...
568
+ [2023-07-30 22:03:56,031][26583] Waiting for process inference_proc0-0 to join...
569
+ [2023-07-30 22:03:56,033][26583] Waiting for process rollout_proc0 to join...
570
+ [2023-07-30 22:03:56,034][26583] Waiting for process rollout_proc1 to join...
571
+ [2023-07-30 22:03:56,034][26583] Waiting for process rollout_proc2 to join...
572
+ [2023-07-30 22:03:56,036][26583] Waiting for process rollout_proc3 to join...
573
+ [2023-07-30 22:03:56,037][26583] Waiting for process rollout_proc4 to join...
574
+ [2023-07-30 22:03:56,038][26583] Waiting for process rollout_proc5 to join...
575
+ [2023-07-30 22:03:56,038][26583] Waiting for process rollout_proc6 to join...
576
+ [2023-07-30 22:03:56,039][26583] Waiting for process rollout_proc7 to join...
577
+ [2023-07-30 22:03:56,040][26583] Batcher 0 profile tree view:
578
+ batching: 30.6361, releasing_batches: 0.0313
579
+ [2023-07-30 22:03:56,041][26583] InferenceWorker_p0-w0 profile tree view:
580
+ wait_policy: 0.0001
581
+ wait_policy_total: 5.9584
582
+ update_model: 6.1880
583
+ weight_update: 0.0013
584
+ one_step: 0.0044
585
+ handle_policy_step: 451.3703
586
+ deserialize: 12.3897, stack: 1.9836, obs_to_device_normalize: 104.3261, forward: 233.5697, send_messages: 20.0537
587
+ prepare_outputs: 65.5532
588
+ to_cpu: 45.7944
589
+ [2023-07-30 22:03:56,042][26583] Learner 0 profile tree view:
590
+ misc: 0.0048, prepare_batch: 45.2123
591
+ train: 151.8237
592
+ epoch_init: 0.0058, minibatch_init: 0.0093, losses_postprocess: 0.3465, kl_divergence: 0.5140, after_optimizer: 6.6997
593
+ calculate_losses: 46.0883
594
+ losses_init: 0.0042, forward_head: 1.7090, bptt_initial: 34.5737, tail: 0.9082, advantages_returns: 0.2350, losses: 6.6376
595
+ bptt: 1.7625
596
+ bptt_forward_core: 1.6864
597
+ update: 97.6623
598
+ clip: 83.0312
599
+ [2023-07-30 22:03:56,043][26583] RolloutWorker_w0 profile tree view:
600
+ wait_for_trajectories: 0.2418, enqueue_policy_requests: 15.3283, env_step: 200.3237, overhead: 19.9119, complete_rollouts: 1.0946
601
+ save_policy_outputs: 14.7657
602
+ split_output_tensors: 7.4017
603
+ [2023-07-30 22:03:56,044][26583] RolloutWorker_w7 profile tree view:
604
+ wait_for_trajectories: 0.2626, enqueue_policy_requests: 16.3642, env_step: 208.3844, overhead: 21.9437, complete_rollouts: 0.9140
605
+ save_policy_outputs: 15.4870
606
+ split_output_tensors: 7.8016
607
+ [2023-07-30 22:03:56,045][26583] Loop Runner_EvtLoop terminating...
608
+ [2023-07-30 22:03:56,046][26583] Runner profile tree view:
609
+ main_loop: 494.2660
610
+ [2023-07-30 22:03:56,047][26583] Collected {0: 4005888}, FPS: 8104.7
611
+ [2023-07-30 22:04:33,102][26583] Loading existing experiment configuration from /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/config.json
612
+ [2023-07-30 22:04:33,103][26583] Overriding arg 'num_workers' with value 1 passed from command line
613
+ [2023-07-30 22:04:33,103][26583] Adding new argument 'no_render'=True that is not in the saved config file!
614
+ [2023-07-30 22:04:33,104][26583] Adding new argument 'save_video'=True that is not in the saved config file!
615
+ [2023-07-30 22:04:33,104][26583] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
616
+ [2023-07-30 22:04:33,104][26583] Adding new argument 'video_name'=None that is not in the saved config file!
617
+ [2023-07-30 22:04:33,105][26583] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
618
+ [2023-07-30 22:04:33,105][26583] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
619
+ [2023-07-30 22:04:33,105][26583] Adding new argument 'push_to_hub'=False that is not in the saved config file!
620
+ [2023-07-30 22:04:33,106][26583] Adding new argument 'hf_repository'=None that is not in the saved config file!
621
+ [2023-07-30 22:04:33,107][26583] Adding new argument 'policy_index'=0 that is not in the saved config file!
622
+ [2023-07-30 22:04:33,107][26583] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
623
+ [2023-07-30 22:04:33,109][26583] Adding new argument 'train_script'=None that is not in the saved config file!
624
+ [2023-07-30 22:04:33,109][26583] Adding new argument 'enjoy_script'=None that is not in the saved config file!
625
+ [2023-07-30 22:04:33,110][26583] Using frameskip 1 and render_action_repeat=4 for evaluation
626
+ [2023-07-30 22:04:33,136][26583] Doom resolution: 160x120, resize resolution: (128, 72)
627
+ [2023-07-30 22:04:33,140][26583] RunningMeanStd input shape: (3, 72, 128)
628
+ [2023-07-30 22:04:33,142][26583] RunningMeanStd input shape: (1,)
629
+ [2023-07-30 22:04:33,153][26583] ConvEncoder: input_channels=3
630
+ [2023-07-30 22:04:33,308][26583] Conv encoder output size: 512
631
+ [2023-07-30 22:04:33,309][26583] Policy head output size: 512
632
+ [2023-07-30 22:04:33,491][26583] Loading state from checkpoint /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
633
+ [2023-07-30 22:04:34,515][26583] Num frames 100...
634
+ [2023-07-30 22:04:34,720][26583] Num frames 200...
635
+ [2023-07-30 22:04:34,879][26583] Num frames 300...
636
+ [2023-07-30 22:04:35,089][26583] Num frames 400...
637
+ [2023-07-30 22:04:35,293][26583] Num frames 500...
638
+ [2023-07-30 22:04:35,500][26583] Num frames 600...
639
+ [2023-07-30 22:04:35,668][26583] Num frames 700...
640
+ [2023-07-30 22:04:35,828][26583] Num frames 800...
641
+ [2023-07-30 22:04:35,991][26583] Num frames 900...
642
+ [2023-07-30 22:04:36,171][26583] Num frames 1000...
643
+ [2023-07-30 22:04:36,346][26583] Num frames 1100...
644
+ [2023-07-30 22:04:36,554][26583] Num frames 1200...
645
+ [2023-07-30 22:04:36,758][26583] Num frames 1300...
646
+ [2023-07-30 22:04:36,941][26583] Num frames 1400...
647
+ [2023-07-30 22:04:37,085][26583] Avg episode rewards: #0: 35.400, true rewards: #0: 14.400
648
+ [2023-07-30 22:04:37,087][26583] Avg episode reward: 35.400, avg true_objective: 14.400
649
+ [2023-07-30 22:04:37,212][26583] Num frames 1500...
650
+ [2023-07-30 22:04:37,357][26583] Num frames 1600...
651
+ [2023-07-30 22:04:37,572][26583] Num frames 1700...
652
+ [2023-07-30 22:04:37,737][26583] Num frames 1800...
653
+ [2023-07-30 22:04:37,899][26583] Num frames 1900...
654
+ [2023-07-30 22:04:38,085][26583] Num frames 2000...
655
+ [2023-07-30 22:04:38,262][26583] Num frames 2100...
656
+ [2023-07-30 22:04:38,428][26583] Num frames 2200...
657
+ [2023-07-30 22:04:38,628][26583] Num frames 2300...
658
+ [2023-07-30 22:04:38,837][26583] Num frames 2400...
659
+ [2023-07-30 22:04:39,009][26583] Num frames 2500...
660
+ [2023-07-30 22:04:39,228][26583] Num frames 2600...
661
+ [2023-07-30 22:04:39,392][26583] Num frames 2700...
662
+ [2023-07-30 22:04:39,576][26583] Num frames 2800...
663
+ [2023-07-30 22:04:39,665][26583] Avg episode rewards: #0: 33.580, true rewards: #0: 14.080
664
+ [2023-07-30 22:04:39,667][26583] Avg episode reward: 33.580, avg true_objective: 14.080
665
+ [2023-07-30 22:04:39,850][26583] Num frames 2900...
666
+ [2023-07-30 22:04:40,058][26583] Num frames 3000...
667
+ [2023-07-30 22:04:40,240][26583] Num frames 3100...
668
+ [2023-07-30 22:04:40,469][26583] Num frames 3200...
669
+ [2023-07-30 22:04:40,522][26583] Avg episode rewards: #0: 23.667, true rewards: #0: 10.667
670
+ [2023-07-30 22:04:40,523][26583] Avg episode reward: 23.667, avg true_objective: 10.667
671
+ [2023-07-30 22:04:40,709][26583] Num frames 3300...
672
+ [2023-07-30 22:04:40,854][26583] Num frames 3400...
673
+ [2023-07-30 22:04:41,043][26583] Num frames 3500...
674
+ [2023-07-30 22:04:41,229][26583] Num frames 3600...
675
+ [2023-07-30 22:04:41,426][26583] Num frames 3700...
676
+ [2023-07-30 22:04:41,619][26583] Avg episode rewards: #0: 20.190, true rewards: #0: 9.440
677
+ [2023-07-30 22:04:41,621][26583] Avg episode reward: 20.190, avg true_objective: 9.440
678
+ [2023-07-30 22:04:41,672][26583] Num frames 3800...
679
+ [2023-07-30 22:04:41,872][26583] Num frames 3900...
680
+ [2023-07-30 22:04:42,075][26583] Num frames 4000...
681
+ [2023-07-30 22:04:42,265][26583] Num frames 4100...
682
+ [2023-07-30 22:04:42,456][26583] Num frames 4200...
683
+ [2023-07-30 22:04:42,651][26583] Num frames 4300...
684
+ [2023-07-30 22:04:42,828][26583] Num frames 4400...
685
+ [2023-07-30 22:04:42,993][26583] Num frames 4500...
686
+ [2023-07-30 22:04:43,153][26583] Num frames 4600...
687
+ [2023-07-30 22:04:43,318][26583] Num frames 4700...
688
+ [2023-07-30 22:04:43,474][26583] Num frames 4800...
689
+ [2023-07-30 22:04:43,704][26583] Num frames 4900...
690
+ [2023-07-30 22:04:43,940][26583] Num frames 5000...
691
+ [2023-07-30 22:04:44,137][26583] Num frames 5100...
692
+ [2023-07-30 22:04:44,334][26583] Num frames 5200...
693
+ [2023-07-30 22:04:44,545][26583] Num frames 5300...
694
+ [2023-07-30 22:04:44,775][26583] Num frames 5400...
695
+ [2023-07-30 22:04:44,850][26583] Avg episode rewards: #0: 24.216, true rewards: #0: 10.816
696
+ [2023-07-30 22:04:44,852][26583] Avg episode reward: 24.216, avg true_objective: 10.816
697
+ [2023-07-30 22:04:45,058][26583] Num frames 5500...
698
+ [2023-07-30 22:04:45,245][26583] Num frames 5600...
699
+ [2023-07-30 22:04:45,397][26583] Num frames 5700...
700
+ [2023-07-30 22:04:45,566][26583] Num frames 5800...
701
+ [2023-07-30 22:04:45,772][26583] Num frames 5900...
702
+ [2023-07-30 22:04:45,954][26583] Num frames 6000...
703
+ [2023-07-30 22:04:46,123][26583] Num frames 6100...
704
+ [2023-07-30 22:04:46,345][26583] Num frames 6200...
705
+ [2023-07-30 22:04:46,507][26583] Num frames 6300...
706
+ [2023-07-30 22:04:46,677][26583] Num frames 6400...
707
+ [2023-07-30 22:04:46,855][26583] Num frames 6500...
708
+ [2023-07-30 22:04:46,942][26583] Avg episode rewards: #0: 25.197, true rewards: #0: 10.863
709
+ [2023-07-30 22:04:46,943][26583] Avg episode reward: 25.197, avg true_objective: 10.863
710
+ [2023-07-30 22:04:47,118][26583] Num frames 6600...
711
+ [2023-07-30 22:04:47,259][26583] Num frames 6700...
712
+ [2023-07-30 22:04:47,407][26583] Num frames 6800...
713
+ [2023-07-30 22:04:47,590][26583] Num frames 6900...
714
+ [2023-07-30 22:04:47,785][26583] Num frames 7000...
715
+ [2023-07-30 22:04:47,945][26583] Avg episode rewards: #0: 22.660, true rewards: #0: 10.089
716
+ [2023-07-30 22:04:47,946][26583] Avg episode reward: 22.660, avg true_objective: 10.089
717
+ [2023-07-30 22:04:48,023][26583] Num frames 7100...
718
+ [2023-07-30 22:04:48,229][26583] Num frames 7200...
719
+ [2023-07-30 22:04:48,372][26583] Num frames 7300...
720
+ [2023-07-30 22:04:48,573][26583] Num frames 7400...
721
+ [2023-07-30 22:04:48,778][26583] Num frames 7500...
722
+ [2023-07-30 22:04:48,907][26583] Num frames 7600...
723
+ [2023-07-30 22:04:49,069][26583] Avg episode rewards: #0: 21.213, true rewards: #0: 9.587
724
+ [2023-07-30 22:04:49,070][26583] Avg episode reward: 21.213, avg true_objective: 9.587
725
+ [2023-07-30 22:04:49,138][26583] Num frames 7700...
726
+ [2023-07-30 22:04:49,288][26583] Num frames 7800...
727
+ [2023-07-30 22:04:49,489][26583] Num frames 7900...
728
+ [2023-07-30 22:04:49,644][26583] Num frames 8000...
729
+ [2023-07-30 22:04:49,866][26583] Num frames 8100...
730
+ [2023-07-30 22:04:50,027][26583] Num frames 8200...
731
+ [2023-07-30 22:04:50,183][26583] Avg episode rewards: #0: 19.829, true rewards: #0: 9.162
732
+ [2023-07-30 22:04:50,184][26583] Avg episode reward: 19.829, avg true_objective: 9.162
733
+ [2023-07-30 22:04:50,302][26583] Num frames 8300...
734
+ [2023-07-30 22:04:50,504][26583] Num frames 8400...
735
+ [2023-07-30 22:04:50,734][26583] Num frames 8500...
736
+ [2023-07-30 22:04:50,899][26583] Num frames 8600...
737
+ [2023-07-30 22:04:51,107][26583] Num frames 8700...
738
+ [2023-07-30 22:04:51,275][26583] Num frames 8800...
739
+ [2023-07-30 22:04:51,473][26583] Num frames 8900...
740
+ [2023-07-30 22:04:51,668][26583] Num frames 9000...
741
+ [2023-07-30 22:04:51,833][26583] Num frames 9100...
742
+ [2023-07-30 22:04:52,003][26583] Num frames 9200...
743
+ [2023-07-30 22:04:52,155][26583] Num frames 9300...
744
+ [2023-07-30 22:04:52,305][26583] Num frames 9400...
745
+ [2023-07-30 22:04:52,475][26583] Avg episode rewards: #0: 20.863, true rewards: #0: 9.463
746
+ [2023-07-30 22:04:52,476][26583] Avg episode reward: 20.863, avg true_objective: 9.463
747
+ [2023-07-30 22:05:21,771][26583] Replay video saved to /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/replay.mp4!
748
+ [2023-07-30 22:07:34,467][26583] Loading existing experiment configuration from /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/config.json
749
+ [2023-07-30 22:07:34,468][26583] Overriding arg 'num_workers' with value 1 passed from command line
750
+ [2023-07-30 22:07:34,468][26583] Adding new argument 'no_render'=True that is not in the saved config file!
751
+ [2023-07-30 22:07:34,469][26583] Adding new argument 'save_video'=True that is not in the saved config file!
752
+ [2023-07-30 22:07:34,469][26583] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
753
+ [2023-07-30 22:07:34,469][26583] Adding new argument 'video_name'=None that is not in the saved config file!
754
+ [2023-07-30 22:07:34,470][26583] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
755
+ [2023-07-30 22:07:34,470][26583] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
756
+ [2023-07-30 22:07:34,470][26583] Adding new argument 'push_to_hub'=True that is not in the saved config file!
757
+ [2023-07-30 22:07:34,471][26583] Adding new argument 'hf_repository'='magnustragardh/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
758
+ [2023-07-30 22:07:34,471][26583] Adding new argument 'policy_index'=0 that is not in the saved config file!
759
+ [2023-07-30 22:07:34,472][26583] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
760
+ [2023-07-30 22:07:34,473][26583] Adding new argument 'train_script'=None that is not in the saved config file!
761
+ [2023-07-30 22:07:34,473][26583] Adding new argument 'enjoy_script'=None that is not in the saved config file!
762
+ [2023-07-30 22:07:34,473][26583] Using frameskip 1 and render_action_repeat=4 for evaluation
763
+ [2023-07-30 22:07:34,491][26583] RunningMeanStd input shape: (3, 72, 128)
764
+ [2023-07-30 22:07:34,492][26583] RunningMeanStd input shape: (1,)
765
+ [2023-07-30 22:07:34,500][26583] ConvEncoder: input_channels=3
766
+ [2023-07-30 22:07:34,598][26583] Conv encoder output size: 512
767
+ [2023-07-30 22:07:34,602][26583] Policy head output size: 512
768
+ [2023-07-30 22:07:34,629][26583] Loading state from checkpoint /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
769
+ [2023-07-30 22:07:35,019][26583] Num frames 100...
770
+ [2023-07-30 22:07:35,210][26583] Num frames 200...
771
+ [2023-07-30 22:07:35,332][26583] Num frames 300...
772
+ [2023-07-30 22:07:35,454][26583] Num frames 400...
773
+ [2023-07-30 22:07:35,602][26583] Num frames 500...
774
+ [2023-07-30 22:07:35,808][26583] Num frames 600...
775
+ [2023-07-30 22:07:35,965][26583] Num frames 700...
776
+ [2023-07-30 22:07:36,160][26583] Num frames 800...
777
+ [2023-07-30 22:07:36,289][26583] Num frames 900...
778
+ [2023-07-30 22:07:36,427][26583] Num frames 1000...
779
+ [2023-07-30 22:07:36,558][26583] Num frames 1100...
780
+ [2023-07-30 22:07:36,691][26583] Num frames 1200...
781
+ [2023-07-30 22:07:36,807][26583] Num frames 1300...
782
+ [2023-07-30 22:07:36,927][26583] Num frames 1400...
783
+ [2023-07-30 22:07:37,045][26583] Num frames 1500...
784
+ [2023-07-30 22:07:37,165][26583] Num frames 1600...
785
+ [2023-07-30 22:07:37,284][26583] Num frames 1700...
786
+ [2023-07-30 22:07:37,411][26583] Num frames 1800...
787
+ [2023-07-30 22:07:37,522][26583] Num frames 1900...
788
+ [2023-07-30 22:07:37,650][26583] Num frames 2000...
789
+ [2023-07-30 22:07:37,760][26583] Avg episode rewards: #0: 53.479, true rewards: #0: 20.480
790
+ [2023-07-30 22:07:37,762][26583] Avg episode reward: 53.479, avg true_objective: 20.480
791
+ [2023-07-30 22:07:37,840][26583] Num frames 2100...
792
+ [2023-07-30 22:07:37,990][26583] Num frames 2200...
793
+ [2023-07-30 22:07:38,104][26583] Num frames 2300...
794
+ [2023-07-30 22:07:38,310][26583] Num frames 2400...
795
+ [2023-07-30 22:07:38,421][26583] Num frames 2500...
796
+ [2023-07-30 22:07:38,572][26583] Num frames 2600...
797
+ [2023-07-30 22:07:38,734][26583] Avg episode rewards: #0: 33.449, true rewards: #0: 13.450
798
+ [2023-07-30 22:07:38,735][26583] Avg episode reward: 33.449, avg true_objective: 13.450
799
+ [2023-07-30 22:07:38,758][26583] Num frames 2700...
800
+ [2023-07-30 22:07:38,980][26583] Num frames 2800...
801
+ [2023-07-30 22:07:39,179][26583] Num frames 2900...
802
+ [2023-07-30 22:07:39,296][26583] Num frames 3000...
803
+ [2023-07-30 22:07:39,463][26583] Num frames 3100...
804
+ [2023-07-30 22:07:39,676][26583] Num frames 3200...
805
+ [2023-07-30 22:07:39,854][26583] Num frames 3300...
806
+ [2023-07-30 22:07:40,018][26583] Num frames 3400...
807
+ [2023-07-30 22:07:40,131][26583] Num frames 3500...
808
+ [2023-07-30 22:07:40,304][26583] Num frames 3600...
809
+ [2023-07-30 22:07:40,509][26583] Num frames 3700...
810
+ [2023-07-30 22:07:40,627][26583] Num frames 3800...
811
+ [2023-07-30 22:07:40,793][26583] Num frames 3900...
812
+ [2023-07-30 22:07:40,915][26583] Num frames 4000...
813
+ [2023-07-30 22:07:41,068][26583] Avg episode rewards: #0: 31.220, true rewards: #0: 13.553
814
+ [2023-07-30 22:07:41,069][26583] Avg episode reward: 31.220, avg true_objective: 13.553
815
+ [2023-07-30 22:07:41,120][26583] Num frames 4100...
816
+ [2023-07-30 22:07:41,269][26583] Num frames 4200...
817
+ [2023-07-30 22:07:41,409][26583] Num frames 4300...
818
+ [2023-07-30 22:07:41,531][26583] Num frames 4400...
819
+ [2023-07-30 22:07:41,661][26583] Num frames 4500...
820
+ [2023-07-30 22:07:41,827][26583] Num frames 4600...
821
+ [2023-07-30 22:07:41,998][26583] Num frames 4700...
822
+ [2023-07-30 22:07:42,116][26583] Num frames 4800...
823
+ [2023-07-30 22:07:42,283][26583] Num frames 4900...
824
+ [2023-07-30 22:07:42,452][26583] Num frames 5000...
825
+ [2023-07-30 22:07:42,597][26583] Num frames 5100...
826
+ [2023-07-30 22:07:42,800][26583] Num frames 5200...
827
+ [2023-07-30 22:07:43,026][26583] Num frames 5300...
828
+ [2023-07-30 22:07:43,213][26583] Num frames 5400...
829
+ [2023-07-30 22:07:43,379][26583] Num frames 5500...
830
+ [2023-07-30 22:07:43,516][26583] Num frames 5600...
831
+ [2023-07-30 22:07:43,649][26583] Num frames 5700...
832
+ [2023-07-30 22:07:43,835][26583] Avg episode rewards: #0: 34.987, true rewards: #0: 14.487
833
+ [2023-07-30 22:07:43,837][26583] Avg episode reward: 34.987, avg true_objective: 14.487
834
+ [2023-07-30 22:07:43,848][26583] Num frames 5800...
835
+ [2023-07-30 22:07:43,963][26583] Num frames 5900...
836
+ [2023-07-30 22:07:44,077][26583] Num frames 6000...
837
+ [2023-07-30 22:07:44,198][26583] Num frames 6100...
838
+ [2023-07-30 22:07:44,327][26583] Num frames 6200...
839
+ [2023-07-30 22:07:44,452][26583] Num frames 6300...
840
+ [2023-07-30 22:07:44,574][26583] Num frames 6400...
841
+ [2023-07-30 22:07:44,689][26583] Avg episode rewards: #0: 30.708, true rewards: #0: 12.908
842
+ [2023-07-30 22:07:44,690][26583] Avg episode reward: 30.708, avg true_objective: 12.908
843
+ [2023-07-30 22:07:44,785][26583] Num frames 6500...
844
+ [2023-07-30 22:07:44,924][26583] Num frames 6600...
845
+ [2023-07-30 22:07:45,039][26583] Num frames 6700...
846
+ [2023-07-30 22:07:45,156][26583] Num frames 6800...
847
+ [2023-07-30 22:07:45,284][26583] Num frames 6900...
848
+ [2023-07-30 22:07:45,472][26583] Avg episode rewards: #0: 27.273, true rewards: #0: 11.607
849
+ [2023-07-30 22:07:45,473][26583] Avg episode reward: 27.273, avg true_objective: 11.607
850
+ [2023-07-30 22:07:45,549][26583] Num frames 7000...
851
+ [2023-07-30 22:07:45,674][26583] Num frames 7100...
852
+ [2023-07-30 22:07:45,817][26583] Num frames 7200...
853
+ [2023-07-30 22:07:45,961][26583] Num frames 7300...
854
+ [2023-07-30 22:07:46,137][26583] Num frames 7400...
855
+ [2023-07-30 22:07:46,280][26583] Num frames 7500...
856
+ [2023-07-30 22:07:46,439][26583] Num frames 7600...
857
+ [2023-07-30 22:07:46,645][26583] Avg episode rewards: #0: 25.851, true rewards: #0: 10.994
858
+ [2023-07-30 22:07:46,647][26583] Avg episode reward: 25.851, avg true_objective: 10.994
859
+ [2023-07-30 22:07:46,658][26583] Num frames 7700...
860
+ [2023-07-30 22:07:46,813][26583] Num frames 7800...
861
+ [2023-07-30 22:07:46,940][26583] Num frames 7900...
862
+ [2023-07-30 22:07:47,111][26583] Num frames 8000...
863
+ [2023-07-30 22:07:47,218][26583] Num frames 8100...
864
+ [2023-07-30 22:07:47,328][26583] Num frames 8200...
865
+ [2023-07-30 22:07:47,427][26583] Avg episode rewards: #0: 23.917, true rewards: #0: 10.292
866
+ [2023-07-30 22:07:47,429][26583] Avg episode reward: 23.917, avg true_objective: 10.292
867
+ [2023-07-30 22:07:47,546][26583] Num frames 8300...
868
+ [2023-07-30 22:07:47,728][26583] Num frames 8400...
869
+ [2023-07-30 22:07:47,892][26583] Num frames 8500...
870
+ [2023-07-30 22:07:48,010][26583] Num frames 8600...
871
+ [2023-07-30 22:07:48,126][26583] Num frames 8700...
872
+ [2023-07-30 22:07:48,266][26583] Num frames 8800...
873
+ [2023-07-30 22:07:48,444][26583] Num frames 8900...
874
+ [2023-07-30 22:07:48,579][26583] Num frames 9000...
875
+ [2023-07-30 22:07:48,771][26583] Num frames 9100...
876
+ [2023-07-30 22:07:48,900][26583] Num frames 9200...
877
+ [2023-07-30 22:07:49,034][26583] Num frames 9300...
878
+ [2023-07-30 22:07:49,179][26583] Num frames 9400...
879
+ [2023-07-30 22:07:49,293][26583] Num frames 9500...
880
+ [2023-07-30 22:07:49,410][26583] Avg episode rewards: #0: 24.495, true rewards: #0: 10.607
881
+ [2023-07-30 22:07:49,411][26583] Avg episode reward: 24.495, avg true_objective: 10.607
882
+ [2023-07-30 22:07:49,494][26583] Num frames 9600...
883
+ [2023-07-30 22:07:49,624][26583] Num frames 9700...
884
+ [2023-07-30 22:07:49,786][26583] Num frames 9800...
885
+ [2023-07-30 22:07:49,941][26583] Num frames 9900...
886
+ [2023-07-30 22:07:50,131][26583] Num frames 10000...
887
+ [2023-07-30 22:07:50,267][26583] Num frames 10100...
888
+ [2023-07-30 22:07:50,413][26583] Num frames 10200...
889
+ [2023-07-30 22:07:50,541][26583] Num frames 10300...
890
+ [2023-07-30 22:07:50,717][26583] Num frames 10400...
891
+ [2023-07-30 22:07:50,891][26583] Num frames 10500...
892
+ [2023-07-30 22:07:51,000][26583] Num frames 10600...
893
+ [2023-07-30 22:07:51,187][26583] Num frames 10700...
894
+ [2023-07-30 22:07:51,321][26583] Num frames 10800...
895
+ [2023-07-30 22:07:51,537][26583] Num frames 10900...
896
+ [2023-07-30 22:07:51,717][26583] Num frames 11000...
897
+ [2023-07-30 22:07:51,894][26583] Num frames 11100...
898
+ [2023-07-30 22:07:52,006][26583] Num frames 11200...
899
+ [2023-07-30 22:07:52,124][26583] Num frames 11300...
900
+ [2023-07-30 22:07:52,265][26583] Num frames 11400...
901
+ [2023-07-30 22:07:52,459][26583] Avg episode rewards: #0: 27.098, true rewards: #0: 11.498
902
+ [2023-07-30 22:07:52,461][26583] Avg episode reward: 27.098, avg true_objective: 11.498
903
+ [2023-07-30 22:07:52,465][26583] Num frames 11500...
904
+ [2023-07-30 22:08:15,079][26583] Replay video saved to /home/magnus/src/huggingface-reinforcement-learning-course/train_dir/default_experiment/replay.mp4!