Hugging Face's logo

MalyO2
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files
xet
Metrics Community
MalyO2 commited on
Commit
14b4e13
·
verified ·
1 Parent(s): c691e11

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1728497575.b5245ca6beae +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000923_3780608_reward_26.745.pth +3 -0
  5. checkpoint_p0/checkpoint_000000913_3739648.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 +856 -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.1728497575.b5245ca6beae ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d04bcba498700f754f830373a92ec2581507af16c2c9625dac0c8b664013a0a6
3
+ size 462554
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: 9.69 +/- 5.23
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 MalyO2/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_000000923_3780608_reward_26.745.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6392d3972b424c2f68d8fcda528b002b4ec7874cdcda735910e2a5deb003b72d
3
+ size 34929051
checkpoint_p0/checkpoint_000000913_3739648.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:861dd7e3f86e4dd5a5dad02d70c8607a0eaef7616ad03ece4560b18ba1769a20
3
+ size 34929477
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:336ec0a08c3e5d33bd34e9ea7d14762f3b91e980b0c7d06fedf76df45dcde180
3
+ size 34929541
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": "/kaggle/working/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:d1fad9eea012f5cb044a37654742a8a5f859a3b6d5cb43b2dcc8468443cae6a7
3
+ size 18672988
sf_log.txt ADDED
@@ -0,0 +1,856 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-10-09 18:13:00,272][00030] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json...
2
+ [2024-10-09 18:13:00,275][00030] Rollout worker 0 uses device cpu
3
+ [2024-10-09 18:13:00,276][00030] Rollout worker 1 uses device cpu
4
+ [2024-10-09 18:13:00,277][00030] Rollout worker 2 uses device cpu
5
+ [2024-10-09 18:13:00,277][00030] Rollout worker 3 uses device cpu
6
+ [2024-10-09 18:13:00,278][00030] Rollout worker 4 uses device cpu
7
+ [2024-10-09 18:13:00,279][00030] Rollout worker 5 uses device cpu
8
+ [2024-10-09 18:13:00,280][00030] Rollout worker 6 uses device cpu
9
+ [2024-10-09 18:13:00,280][00030] Rollout worker 7 uses device cpu
10
+ [2024-10-09 18:13:00,387][00030] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-10-09 18:13:00,388][00030] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-10-09 18:13:00,428][00030] Starting all processes...
13
+ [2024-10-09 18:13:00,429][00030] Starting process learner_proc0
14
+ [2024-10-09 18:13:01,013][00030] Starting all processes...
15
+ [2024-10-09 18:13:01,021][00030] Starting process inference_proc0-0
16
+ [2024-10-09 18:13:01,022][00030] Starting process rollout_proc0
17
+ [2024-10-09 18:13:01,022][00030] Starting process rollout_proc1
18
+ [2024-10-09 18:13:01,023][00030] Starting process rollout_proc2
19
+ [2024-10-09 18:13:01,024][00030] Starting process rollout_proc3
20
+ [2024-10-09 18:13:01,025][00030] Starting process rollout_proc4
21
+ [2024-10-09 18:13:01,027][00030] Starting process rollout_proc5
22
+ [2024-10-09 18:13:01,028][00030] Starting process rollout_proc6
23
+ [2024-10-09 18:13:01,028][00030] Starting process rollout_proc7
24
+ [2024-10-09 18:13:09,245][01812] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2024-10-09 18:13:09,245][01812] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
26
+ [2024-10-09 18:13:09,299][01812] Num visible devices: 1
27
+ [2024-10-09 18:13:09,356][01812] Starting seed is not provided
28
+ [2024-10-09 18:13:09,356][01812] Using GPUs [0] for process 0 (actually maps to GPUs [0])
29
+ [2024-10-09 18:13:09,357][01812] Initializing actor-critic model on device cuda:0
30
+ [2024-10-09 18:13:09,357][01812] RunningMeanStd input shape: (3, 72, 128)
31
+ [2024-10-09 18:13:09,361][01812] RunningMeanStd input shape: (1,)
32
+ [2024-10-09 18:13:09,419][01812] ConvEncoder: input_channels=3
33
+ [2024-10-09 18:13:09,439][01833] Worker 7 uses CPU cores [3]
34
+ [2024-10-09 18:13:09,609][01825] Using GPUs [0] for process 0 (actually maps to GPUs [0])
35
+ [2024-10-09 18:13:09,610][01825] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
36
+ [2024-10-09 18:13:09,663][01825] Num visible devices: 1
37
+ [2024-10-09 18:13:09,773][01827] Worker 4 uses CPU cores [0]
38
+ [2024-10-09 18:13:09,796][01829] Worker 1 uses CPU cores [1]
39
+ [2024-10-09 18:13:09,836][01828] Worker 3 uses CPU cores [3]
40
+ [2024-10-09 18:13:09,887][01812] Conv encoder output size: 512
41
+ [2024-10-09 18:13:09,887][01812] Policy head output size: 512
42
+ [2024-10-09 18:13:09,890][01832] Worker 6 uses CPU cores [2]
43
+ [2024-10-09 18:13:09,902][01831] Worker 5 uses CPU cores [1]
44
+ [2024-10-09 18:13:09,907][01830] Worker 0 uses CPU cores [0]
45
+ [2024-10-09 18:13:09,908][01826] Worker 2 uses CPU cores [2]
46
+ [2024-10-09 18:13:09,943][01812] Created Actor Critic model with architecture:
47
+ [2024-10-09 18:13:09,943][01812] 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
+ [2024-10-09 18:13:10,225][01812] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-10-09 18:13:11,075][01812] No checkpoints found
90
+ [2024-10-09 18:13:11,075][01812] Did not load from checkpoint, starting from scratch!
91
+ [2024-10-09 18:13:11,077][01812] Initialized policy 0 weights for model version 0
92
+ [2024-10-09 18:13:11,083][01812] LearnerWorker_p0 finished initialization!
93
+ [2024-10-09 18:13:11,084][01812] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-10-09 18:13:11,175][01825] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-10-09 18:13:11,176][01825] RunningMeanStd input shape: (1,)
96
+ [2024-10-09 18:13:11,192][01825] ConvEncoder: input_channels=3
97
+ [2024-10-09 18:13:11,315][01825] Conv encoder output size: 512
98
+ [2024-10-09 18:13:11,315][01825] Policy head output size: 512
99
+ [2024-10-09 18:13:11,355][00030] Inference worker 0-0 is ready!
100
+ [2024-10-09 18:13:11,356][00030] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-10-09 18:13:11,462][01829] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-10-09 18:13:11,459][01832] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-10-09 18:13:11,461][01831] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-10-09 18:13:11,462][01833] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-10-09 18:13:11,462][01826] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-10-09 18:13:11,463][01827] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-10-09 18:13:11,463][01830] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-10-09 18:13:11,465][01828] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-10-09 18:13:12,144][01830] Decorrelating experience for 0 frames...
110
+ [2024-10-09 18:13:12,144][01826] Decorrelating experience for 0 frames...
111
+ [2024-10-09 18:13:12,460][01826] Decorrelating experience for 32 frames...
112
+ [2024-10-09 18:13:12,540][01828] Decorrelating experience for 0 frames...
113
+ [2024-10-09 18:13:12,542][01829] Decorrelating experience for 0 frames...
114
+ [2024-10-09 18:13:12,544][01833] Decorrelating experience for 0 frames...
115
+ [2024-10-09 18:13:12,550][01831] Decorrelating experience for 0 frames...
116
+ [2024-10-09 18:13:13,176][01832] Decorrelating experience for 0 frames...
117
+ [2024-10-09 18:13:13,178][01826] Decorrelating experience for 64 frames...
118
+ [2024-10-09 18:13:13,446][01833] Decorrelating experience for 32 frames...
119
+ [2024-10-09 18:13:13,503][01831] Decorrelating experience for 32 frames...
120
+ [2024-10-09 18:13:13,506][01829] Decorrelating experience for 32 frames...
121
+ [2024-10-09 18:13:13,577][01828] Decorrelating experience for 32 frames...
122
+ [2024-10-09 18:13:13,714][01832] Decorrelating experience for 32 frames...
123
+ [2024-10-09 18:13:13,714][01830] Decorrelating experience for 32 frames...
124
+ [2024-10-09 18:13:14,150][01826] Decorrelating experience for 96 frames...
125
+ [2024-10-09 18:13:14,213][01833] Decorrelating experience for 64 frames...
126
+ [2024-10-09 18:13:14,707][01831] Decorrelating experience for 64 frames...
127
+ [2024-10-09 18:13:14,725][01829] Decorrelating experience for 64 frames...
128
+ [2024-10-09 18:13:14,846][01833] Decorrelating experience for 96 frames...
129
+ [2024-10-09 18:13:15,262][00030] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 0. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
130
+ [2024-10-09 18:13:15,329][01832] Decorrelating experience for 64 frames...
131
+ [2024-10-09 18:13:15,419][01831] Decorrelating experience for 96 frames...
132
+ [2024-10-09 18:13:16,632][01832] Decorrelating experience for 96 frames...
133
+ [2024-10-09 18:13:16,672][01829] Decorrelating experience for 96 frames...
134
+ [2024-10-09 18:13:16,739][01828] Decorrelating experience for 64 frames...
135
+ [2024-10-09 18:13:17,406][01830] Decorrelating experience for 64 frames...
136
+ [2024-10-09 18:13:17,989][01830] Decorrelating experience for 96 frames...
137
+ [2024-10-09 18:13:18,007][01828] Decorrelating experience for 96 frames...
138
+ [2024-10-09 18:13:18,202][01812] Signal inference workers to stop experience collection...
139
+ [2024-10-09 18:13:18,208][01825] InferenceWorker_p0-w0: stopping experience collection
140
+ [2024-10-09 18:13:20,003][01812] Signal inference workers to resume experience collection...
141
+ [2024-10-09 18:13:20,003][01825] InferenceWorker_p0-w0: resuming experience collection
142
+ [2024-10-09 18:13:20,262][00030] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 4096. Throughput: 0: 319.6. Samples: 1598. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
143
+ [2024-10-09 18:13:20,264][00030] Avg episode reward: [(0, '3.229')]
144
+ [2024-10-09 18:13:20,378][00030] Heartbeat connected on Batcher_0
145
+ [2024-10-09 18:13:20,382][00030] Heartbeat connected on LearnerWorker_p0
146
+ [2024-10-09 18:13:20,391][00030] Heartbeat connected on InferenceWorker_p0-w0
147
+ [2024-10-09 18:13:20,402][00030] Heartbeat connected on RolloutWorker_w0
148
+ [2024-10-09 18:13:20,410][00030] Heartbeat connected on RolloutWorker_w1
149
+ [2024-10-09 18:13:20,411][00030] Heartbeat connected on RolloutWorker_w2
150
+ [2024-10-09 18:13:20,422][00030] Heartbeat connected on RolloutWorker_w5
151
+ [2024-10-09 18:13:20,431][00030] Heartbeat connected on RolloutWorker_w3
152
+ [2024-10-09 18:13:20,437][00030] Heartbeat connected on RolloutWorker_w6
153
+ [2024-10-09 18:13:20,444][00030] Heartbeat connected on RolloutWorker_w7
154
+ [2024-10-09 18:13:24,448][01825] Updated weights for policy 0, policy_version 10 (0.0117)
155
+ [2024-10-09 18:13:25,262][00030] Fps is (10 sec: 4505.6, 60 sec: 4505.6, 300 sec: 4505.6). Total num frames: 45056. Throughput: 0: 856.4. Samples: 8564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
156
+ [2024-10-09 18:13:25,265][00030] Avg episode reward: [(0, '4.134')]
157
+ [2024-10-09 18:13:29,626][01825] Updated weights for policy 0, policy_version 20 (0.0019)
158
+ [2024-10-09 18:13:30,262][00030] Fps is (10 sec: 8192.0, 60 sec: 5734.4, 300 sec: 5734.4). Total num frames: 86016. Throughput: 0: 1369.5. Samples: 20542. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
159
+ [2024-10-09 18:13:30,264][00030] Avg episode reward: [(0, '4.582')]
160
+ [2024-10-09 18:13:34,490][01825] Updated weights for policy 0, policy_version 30 (0.0021)
161
+ [2024-10-09 18:13:35,262][00030] Fps is (10 sec: 8192.0, 60 sec: 6348.8, 300 sec: 6348.8). Total num frames: 126976. Throughput: 0: 1337.5. Samples: 26750. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
162
+ [2024-10-09 18:13:35,264][00030] Avg episode reward: [(0, '4.277')]
163
+ [2024-10-09 18:13:35,274][01812] Saving new best policy, reward=4.277!
164
+ [2024-10-09 18:13:39,457][01825] Updated weights for policy 0, policy_version 40 (0.0020)
165
+ [2024-10-09 18:13:40,262][00030] Fps is (10 sec: 8191.9, 60 sec: 6717.4, 300 sec: 6717.4). Total num frames: 167936. Throughput: 0: 1569.0. Samples: 39224. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
166
+ [2024-10-09 18:13:40,264][00030] Avg episode reward: [(0, '4.422')]
167
+ [2024-10-09 18:13:40,266][01812] Saving new best policy, reward=4.422!
168
+ [2024-10-09 18:13:44,298][01825] Updated weights for policy 0, policy_version 50 (0.0021)
169
+ [2024-10-09 18:13:45,262][00030] Fps is (10 sec: 8192.0, 60 sec: 6963.2, 300 sec: 6963.2). Total num frames: 208896. Throughput: 0: 1723.9. Samples: 51716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
170
+ [2024-10-09 18:13:45,264][00030] Avg episode reward: [(0, '4.600')]
171
+ [2024-10-09 18:13:45,273][01812] Saving new best policy, reward=4.600!
172
+ [2024-10-09 18:13:49,929][01825] Updated weights for policy 0, policy_version 60 (0.0024)
173
+ [2024-10-09 18:13:50,262][00030] Fps is (10 sec: 7782.3, 60 sec: 7021.7, 300 sec: 7021.7). Total num frames: 245760. Throughput: 0: 1650.1. Samples: 57754. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
174
+ [2024-10-09 18:13:50,264][00030] Avg episode reward: [(0, '4.415')]
175
+ [2024-10-09 18:13:54,668][01825] Updated weights for policy 0, policy_version 70 (0.0021)
176
+ [2024-10-09 18:13:55,262][00030] Fps is (10 sec: 7782.4, 60 sec: 7168.0, 300 sec: 7168.0). Total num frames: 286720. Throughput: 0: 1731.1. Samples: 69242. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
177
+ [2024-10-09 18:13:55,264][00030] Avg episode reward: [(0, '4.380')]
178
+ [2024-10-09 18:13:59,562][01825] Updated weights for policy 0, policy_version 80 (0.0016)
179
+ [2024-10-09 18:14:00,262][00030] Fps is (10 sec: 8601.8, 60 sec: 7372.8, 300 sec: 7372.8). Total num frames: 331776. Throughput: 0: 1819.1. Samples: 81860. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
180
+ [2024-10-09 18:14:00,265][00030] Avg episode reward: [(0, '4.453')]
181
+ [2024-10-09 18:14:04,470][01825] Updated weights for policy 0, policy_version 90 (0.0016)
182
+ [2024-10-09 18:14:05,262][00030] Fps is (10 sec: 8601.5, 60 sec: 7454.7, 300 sec: 7454.7). Total num frames: 372736. Throughput: 0: 1923.3. Samples: 88146. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
183
+ [2024-10-09 18:14:05,264][00030] Avg episode reward: [(0, '4.462')]
184
+ [2024-10-09 18:14:09,383][01825] Updated weights for policy 0, policy_version 100 (0.0020)
185
+ [2024-10-09 18:14:10,262][00030] Fps is (10 sec: 8192.0, 60 sec: 7521.7, 300 sec: 7521.7). Total num frames: 413696. Throughput: 0: 2049.0. Samples: 100770. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
186
+ [2024-10-09 18:14:10,264][00030] Avg episode reward: [(0, '4.371')]
187
+ [2024-10-09 18:14:14,259][01825] Updated weights for policy 0, policy_version 110 (0.0019)
188
+ [2024-10-09 18:14:15,262][00030] Fps is (10 sec: 8192.0, 60 sec: 7577.6, 300 sec: 7577.6). Total num frames: 454656. Throughput: 0: 2060.7. Samples: 113274. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
189
+ [2024-10-09 18:14:15,264][00030] Avg episode reward: [(0, '4.545')]
190
+ [2024-10-09 18:14:19,295][01825] Updated weights for policy 0, policy_version 120 (0.0016)
191
+ [2024-10-09 18:14:20,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 7687.9). Total num frames: 499712. Throughput: 0: 2058.6. Samples: 119386. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
192
+ [2024-10-09 18:14:20,268][00030] Avg episode reward: [(0, '4.494')]
193
+ [2024-10-09 18:14:24,696][01825] Updated weights for policy 0, policy_version 130 (0.0016)
194
+ [2024-10-09 18:14:25,262][00030] Fps is (10 sec: 7782.5, 60 sec: 8123.7, 300 sec: 7606.9). Total num frames: 532480. Throughput: 0: 2031.7. Samples: 130652. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
195
+ [2024-10-09 18:14:25,264][00030] Avg episode reward: [(0, '4.438')]
196
+ [2024-10-09 18:14:29,668][01825] Updated weights for policy 0, policy_version 140 (0.0019)
197
+ [2024-10-09 18:14:30,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7700.5). Total num frames: 577536. Throughput: 0: 2031.8. Samples: 143146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
198
+ [2024-10-09 18:14:30,263][00030] Avg episode reward: [(0, '4.458')]
199
+ [2024-10-09 18:14:34,575][01825] Updated weights for policy 0, policy_version 150 (0.0017)
200
+ [2024-10-09 18:14:35,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7731.2). Total num frames: 618496. Throughput: 0: 2038.8. Samples: 149500. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
201
+ [2024-10-09 18:14:35,264][00030] Avg episode reward: [(0, '4.471')]
202
+ [2024-10-09 18:14:39,550][01825] Updated weights for policy 0, policy_version 160 (0.0017)
203
+ [2024-10-09 18:14:40,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7758.3). Total num frames: 659456. Throughput: 0: 2059.8. Samples: 161934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
204
+ [2024-10-09 18:14:40,264][00030] Avg episode reward: [(0, '4.569')]
205
+ [2024-10-09 18:14:44,401][01825] Updated weights for policy 0, policy_version 170 (0.0028)
206
+ [2024-10-09 18:14:45,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7782.4). Total num frames: 700416. Throughput: 0: 2059.3. Samples: 174528. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
207
+ [2024-10-09 18:14:45,264][00030] Avg episode reward: [(0, '4.834')]
208
+ [2024-10-09 18:14:45,270][01812] Saving new best policy, reward=4.834!
209
+ [2024-10-09 18:14:49,367][01825] Updated weights for policy 0, policy_version 180 (0.0020)
210
+ [2024-10-09 18:14:50,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7804.0). Total num frames: 741376. Throughput: 0: 2054.3. Samples: 180590. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
211
+ [2024-10-09 18:14:50,264][00030] Avg episode reward: [(0, '4.542')]
212
+ [2024-10-09 18:14:54,716][01825] Updated weights for policy 0, policy_version 190 (0.0025)
213
+ [2024-10-09 18:14:55,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7782.4). Total num frames: 778240. Throughput: 0: 2046.8. Samples: 192876. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
214
+ [2024-10-09 18:14:55,264][00030] Avg episode reward: [(0, '4.494')]
215
+ [2024-10-09 18:14:55,272][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000190_778240.pth...
216
+ [2024-10-09 18:14:59,808][01825] Updated weights for policy 0, policy_version 200 (0.0018)
217
+ [2024-10-09 18:15:00,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8123.7, 300 sec: 7801.9). Total num frames: 819200. Throughput: 0: 2024.1. Samples: 204360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
218
+ [2024-10-09 18:15:00,264][00030] Avg episode reward: [(0, '4.636')]
219
+ [2024-10-09 18:15:04,746][01825] Updated weights for policy 0, policy_version 210 (0.0019)
220
+ [2024-10-09 18:15:05,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 7819.6). Total num frames: 860160. Throughput: 0: 2025.2. Samples: 210518. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
221
+ [2024-10-09 18:15:05,265][00030] Avg episode reward: [(0, '4.737')]
222
+ [2024-10-09 18:15:09,630][01825] Updated weights for policy 0, policy_version 220 (0.0024)
223
+ [2024-10-09 18:15:10,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7871.4). Total num frames: 905216. Throughput: 0: 2055.5. Samples: 223148. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
224
+ [2024-10-09 18:15:10,264][00030] Avg episode reward: [(0, '4.489')]
225
+ [2024-10-09 18:15:14,481][01825] Updated weights for policy 0, policy_version 230 (0.0020)
226
+ [2024-10-09 18:15:15,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7884.8). Total num frames: 946176. Throughput: 0: 2059.2. Samples: 235808. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
227
+ [2024-10-09 18:15:15,264][00030] Avg episode reward: [(0, '4.624')]
228
+ [2024-10-09 18:15:19,499][01825] Updated weights for policy 0, policy_version 240 (0.0019)
229
+ [2024-10-09 18:15:20,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 7897.1). Total num frames: 987136. Throughput: 0: 2051.6. Samples: 241822. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
230
+ [2024-10-09 18:15:20,264][00030] Avg episode reward: [(0, '4.678')]
231
+ [2024-10-09 18:15:24,358][01825] Updated weights for policy 0, policy_version 250 (0.0022)
232
+ [2024-10-09 18:15:25,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7908.4). Total num frames: 1028096. Throughput: 0: 2055.6. Samples: 254436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
233
+ [2024-10-09 18:15:25,264][00030] Avg episode reward: [(0, '4.655')]
234
+ [2024-10-09 18:15:29,911][01825] Updated weights for policy 0, policy_version 260 (0.0016)
235
+ [2024-10-09 18:15:30,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8123.7, 300 sec: 7888.6). Total num frames: 1064960. Throughput: 0: 2023.8. Samples: 265600. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
236
+ [2024-10-09 18:15:30,264][00030] Avg episode reward: [(0, '4.731')]
237
+ [2024-10-09 18:15:34,906][01825] Updated weights for policy 0, policy_version 270 (0.0019)
238
+ [2024-10-09 18:15:35,262][00030] Fps is (10 sec: 7782.3, 60 sec: 8123.7, 300 sec: 7899.4). Total num frames: 1105920. Throughput: 0: 2028.0. Samples: 271850. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
239
+ [2024-10-09 18:15:35,267][00030] Avg episode reward: [(0, '4.968')]
240
+ [2024-10-09 18:15:35,275][01812] Saving new best policy, reward=4.968!
241
+ [2024-10-09 18:15:39,641][01825] Updated weights for policy 0, policy_version 280 (0.0018)
242
+ [2024-10-09 18:15:40,264][00030] Fps is (10 sec: 8600.2, 60 sec: 8191.8, 300 sec: 7937.7). Total num frames: 1150976. Throughput: 0: 2032.0. Samples: 284318. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
243
+ [2024-10-09 18:15:40,268][00030] Avg episode reward: [(0, '5.260')]
244
+ [2024-10-09 18:15:40,270][01812] Saving new best policy, reward=5.260!
245
+ [2024-10-09 18:15:44,577][01825] Updated weights for policy 0, policy_version 290 (0.0016)
246
+ [2024-10-09 18:15:45,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7946.2). Total num frames: 1191936. Throughput: 0: 2059.6. Samples: 297042. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
247
+ [2024-10-09 18:15:45,264][00030] Avg episode reward: [(0, '5.617')]
248
+ [2024-10-09 18:15:45,272][01812] Saving new best policy, reward=5.617!
249
+ [2024-10-09 18:15:49,467][01825] Updated weights for policy 0, policy_version 300 (0.0022)
250
+ [2024-10-09 18:15:50,262][00030] Fps is (10 sec: 8193.4, 60 sec: 8192.0, 300 sec: 7954.2). Total num frames: 1232896. Throughput: 0: 2057.1. Samples: 303088. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
251
+ [2024-10-09 18:15:50,264][00030] Avg episode reward: [(0, '4.989')]
252
+ [2024-10-09 18:15:54,372][01825] Updated weights for policy 0, policy_version 310 (0.0016)
253
+ [2024-10-09 18:15:55,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 7961.6). Total num frames: 1273856. Throughput: 0: 2059.2. Samples: 315810. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
254
+ [2024-10-09 18:15:55,264][00030] Avg episode reward: [(0, '5.235')]
255
+ [2024-10-09 18:15:59,856][01825] Updated weights for policy 0, policy_version 320 (0.0024)
256
+ [2024-10-09 18:16:00,262][00030] Fps is (10 sec: 7782.3, 60 sec: 8192.0, 300 sec: 7943.8). Total num frames: 1310720. Throughput: 0: 2038.4. Samples: 327538. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
257
+ [2024-10-09 18:16:00,264][00030] Avg episode reward: [(0, '5.297')]
258
+ [2024-10-09 18:16:04,883][01825] Updated weights for policy 0, policy_version 330 (0.0021)
259
+ [2024-10-09 18:16:05,262][00030] Fps is (10 sec: 7782.5, 60 sec: 8192.0, 300 sec: 7951.1). Total num frames: 1351680. Throughput: 0: 2033.2. Samples: 333318. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
260
+ [2024-10-09 18:16:05,265][00030] Avg episode reward: [(0, '5.426')]
261
+ [2024-10-09 18:16:09,675][01825] Updated weights for policy 0, policy_version 340 (0.0016)
262
+ [2024-10-09 18:16:10,262][00030] Fps is (10 sec: 8601.7, 60 sec: 8192.0, 300 sec: 7981.3). Total num frames: 1396736. Throughput: 0: 2030.2. Samples: 345794. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
263
+ [2024-10-09 18:16:10,266][00030] Avg episode reward: [(0, '5.827')]
264
+ [2024-10-09 18:16:10,269][01812] Saving new best policy, reward=5.827!
265
+ [2024-10-09 18:16:14,539][01825] Updated weights for policy 0, policy_version 350 (0.0016)
266
+ [2024-10-09 18:16:15,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 7987.2). Total num frames: 1437696. Throughput: 0: 2064.4. Samples: 358496. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
267
+ [2024-10-09 18:16:15,264][00030] Avg episode reward: [(0, '6.395')]
268
+ [2024-10-09 18:16:15,272][01812] Saving new best policy, reward=6.395!
269
+ [2024-10-09 18:16:19,460][01825] Updated weights for policy 0, policy_version 360 (0.0019)
270
+ [2024-10-09 18:16:20,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7992.7). Total num frames: 1478656. Throughput: 0: 2062.3. Samples: 364652. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
271
+ [2024-10-09 18:16:20,264][00030] Avg episode reward: [(0, '6.413')]
272
+ [2024-10-09 18:16:20,265][01812] Saving new best policy, reward=6.413!
273
+ [2024-10-09 18:16:24,331][01825] Updated weights for policy 0, policy_version 370 (0.0016)
274
+ [2024-10-09 18:16:25,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 7998.0). Total num frames: 1519616. Throughput: 0: 2066.6. Samples: 377312. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
275
+ [2024-10-09 18:16:25,264][00030] Avg episode reward: [(0, '6.739')]
276
+ [2024-10-09 18:16:25,272][01812] Saving new best policy, reward=6.739!
277
+ [2024-10-09 18:16:29,200][01825] Updated weights for policy 0, policy_version 380 (0.0018)
278
+ [2024-10-09 18:16:30,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8024.0). Total num frames: 1564672. Throughput: 0: 2063.2. Samples: 389888. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
279
+ [2024-10-09 18:16:30,264][00030] Avg episode reward: [(0, '6.711')]
280
+ [2024-10-09 18:16:34,768][01825] Updated weights for policy 0, policy_version 390 (0.0020)
281
+ [2024-10-09 18:16:35,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 7987.2). Total num frames: 1597440. Throughput: 0: 2049.6. Samples: 395318. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
282
+ [2024-10-09 18:16:35,266][00030] Avg episode reward: [(0, '6.806')]
283
+ [2024-10-09 18:16:35,291][01812] Saving new best policy, reward=6.806!
284
+ [2024-10-09 18:16:39,650][01825] Updated weights for policy 0, policy_version 400 (0.0027)
285
+ [2024-10-09 18:16:40,262][00030] Fps is (10 sec: 7782.3, 60 sec: 8192.2, 300 sec: 8012.2). Total num frames: 1642496. Throughput: 0: 2034.9. Samples: 407380. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
286
+ [2024-10-09 18:16:40,264][00030] Avg episode reward: [(0, '6.465')]
287
+ [2024-10-09 18:16:44,591][01825] Updated weights for policy 0, policy_version 410 (0.0016)
288
+ [2024-10-09 18:16:45,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8016.5). Total num frames: 1683456. Throughput: 0: 2055.5. Samples: 420036. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
289
+ [2024-10-09 18:16:45,264][00030] Avg episode reward: [(0, '7.251')]
290
+ [2024-10-09 18:16:45,271][01812] Saving new best policy, reward=7.251!
291
+ [2024-10-09 18:16:49,468][01825] Updated weights for policy 0, policy_version 420 (0.0018)
292
+ [2024-10-09 18:16:50,262][00030] Fps is (10 sec: 8192.1, 60 sec: 8192.0, 300 sec: 8020.5). Total num frames: 1724416. Throughput: 0: 2064.4. Samples: 426216. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
293
+ [2024-10-09 18:16:50,264][00030] Avg episode reward: [(0, '7.413')]
294
+ [2024-10-09 18:16:50,266][01812] Saving new best policy, reward=7.413!
295
+ [2024-10-09 18:16:54,346][01825] Updated weights for policy 0, policy_version 430 (0.0019)
296
+ [2024-10-09 18:16:55,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8192.0, 300 sec: 8024.4). Total num frames: 1765376. Throughput: 0: 2068.6. Samples: 438880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
297
+ [2024-10-09 18:16:55,267][00030] Avg episode reward: [(0, '8.437')]
298
+ [2024-10-09 18:16:55,319][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000432_1769472.pth...
299
+ [2024-10-09 18:16:55,424][01812] Saving new best policy, reward=8.437!
300
+ [2024-10-09 18:16:59,269][01825] Updated weights for policy 0, policy_version 440 (0.0021)
301
+ [2024-10-09 18:17:00,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8328.6, 300 sec: 8046.4). Total num frames: 1810432. Throughput: 0: 2064.0. Samples: 451376. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
302
+ [2024-10-09 18:17:00,264][00030] Avg episode reward: [(0, '8.584')]
303
+ [2024-10-09 18:17:00,268][01812] Saving new best policy, reward=8.584!
304
+ [2024-10-09 18:17:04,263][01825] Updated weights for policy 0, policy_version 450 (0.0027)
305
+ [2024-10-09 18:17:05,262][00030] Fps is (10 sec: 8191.8, 60 sec: 8260.2, 300 sec: 8031.7). Total num frames: 1847296. Throughput: 0: 2066.6. Samples: 457650. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
306
+ [2024-10-09 18:17:05,266][00030] Avg episode reward: [(0, '7.755')]
307
+ [2024-10-09 18:17:09,597][01825] Updated weights for policy 0, policy_version 460 (0.0019)
308
+ [2024-10-09 18:17:10,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8035.1). Total num frames: 1888256. Throughput: 0: 2037.7. Samples: 469008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
309
+ [2024-10-09 18:17:10,264][00030] Avg episode reward: [(0, '8.058')]
310
+ [2024-10-09 18:17:14,415][01825] Updated weights for policy 0, policy_version 470 (0.0017)
311
+ [2024-10-09 18:17:15,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8191.9, 300 sec: 8038.4). Total num frames: 1929216. Throughput: 0: 2043.1. Samples: 481828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
312
+ [2024-10-09 18:17:15,267][00030] Avg episode reward: [(0, '9.013')]
313
+ [2024-10-09 18:17:15,275][01812] Saving new best policy, reward=9.013!
314
+ [2024-10-09 18:17:19,351][01825] Updated weights for policy 0, policy_version 480 (0.0020)
315
+ [2024-10-09 18:17:20,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8058.3). Total num frames: 1974272. Throughput: 0: 2057.6. Samples: 487910. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
316
+ [2024-10-09 18:17:20,264][00030] Avg episode reward: [(0, '10.857')]
317
+ [2024-10-09 18:17:20,266][01812] Saving new best policy, reward=10.857!
318
+ [2024-10-09 18:17:24,222][01825] Updated weights for policy 0, policy_version 490 (0.0019)
319
+ [2024-10-09 18:17:25,262][00030] Fps is (10 sec: 8602.0, 60 sec: 8260.3, 300 sec: 8060.9). Total num frames: 2015232. Throughput: 0: 2069.6. Samples: 500514. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
320
+ [2024-10-09 18:17:25,264][00030] Avg episode reward: [(0, '11.131')]
321
+ [2024-10-09 18:17:25,271][01812] Saving new best policy, reward=11.131!
322
+ [2024-10-09 18:17:29,197][01825] Updated weights for policy 0, policy_version 500 (0.0017)
323
+ [2024-10-09 18:17:30,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8192.0, 300 sec: 8063.5). Total num frames: 2056192. Throughput: 0: 2065.6. Samples: 512988. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
324
+ [2024-10-09 18:17:30,264][00030] Avg episode reward: [(0, '12.048')]
325
+ [2024-10-09 18:17:30,265][01812] Saving new best policy, reward=12.048!
326
+ [2024-10-09 18:17:34,025][01825] Updated weights for policy 0, policy_version 510 (0.0023)
327
+ [2024-10-09 18:17:35,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8328.5, 300 sec: 8066.0). Total num frames: 2097152. Throughput: 0: 2066.4. Samples: 519202. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
328
+ [2024-10-09 18:17:35,264][00030] Avg episode reward: [(0, '12.824')]
329
+ [2024-10-09 18:17:35,275][01812] Saving new best policy, reward=12.824!
330
+ [2024-10-09 18:17:39,499][01825] Updated weights for policy 0, policy_version 520 (0.0024)
331
+ [2024-10-09 18:17:40,262][00030] Fps is (10 sec: 7782.5, 60 sec: 8192.0, 300 sec: 8052.9). Total num frames: 2134016. Throughput: 0: 2038.8. Samples: 530626. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
332
+ [2024-10-09 18:17:40,264][00030] Avg episode reward: [(0, '13.791')]
333
+ [2024-10-09 18:17:40,268][01812] Saving new best policy, reward=13.791!
334
+ [2024-10-09 18:17:44,283][01825] Updated weights for policy 0, policy_version 530 (0.0018)
335
+ [2024-10-09 18:17:45,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8055.5). Total num frames: 2174976. Throughput: 0: 2041.1. Samples: 543224. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
336
+ [2024-10-09 18:17:45,264][00030] Avg episode reward: [(0, '13.643')]
337
+ [2024-10-09 18:17:49,247][01825] Updated weights for policy 0, policy_version 540 (0.0017)
338
+ [2024-10-09 18:17:50,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8058.0). Total num frames: 2215936. Throughput: 0: 2040.6. Samples: 549474. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
339
+ [2024-10-09 18:17:50,266][00030] Avg episode reward: [(0, '14.494')]
340
+ [2024-10-09 18:17:50,275][01812] Saving new best policy, reward=14.494!
341
+ [2024-10-09 18:17:54,082][01825] Updated weights for policy 0, policy_version 550 (0.0024)
342
+ [2024-10-09 18:17:55,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8060.3). Total num frames: 2256896. Throughput: 0: 2067.7. Samples: 562054. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
343
+ [2024-10-09 18:17:55,268][00030] Avg episode reward: [(0, '13.346')]
344
+ [2024-10-09 18:17:58,953][01825] Updated weights for policy 0, policy_version 560 (0.0020)
345
+ [2024-10-09 18:18:00,262][00030] Fps is (10 sec: 8601.5, 60 sec: 8192.0, 300 sec: 8077.0). Total num frames: 2301952. Throughput: 0: 2063.6. Samples: 574688. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
346
+ [2024-10-09 18:18:00,264][00030] Avg episode reward: [(0, '13.990')]
347
+ [2024-10-09 18:18:03,859][01825] Updated weights for policy 0, policy_version 570 (0.0016)
348
+ [2024-10-09 18:18:05,262][00030] Fps is (10 sec: 8601.5, 60 sec: 8260.3, 300 sec: 8079.0). Total num frames: 2342912. Throughput: 0: 2069.5. Samples: 581038. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
349
+ [2024-10-09 18:18:05,265][00030] Avg episode reward: [(0, '15.549')]
350
+ [2024-10-09 18:18:05,273][01812] Saving new best policy, reward=15.549!
351
+ [2024-10-09 18:18:08,800][01825] Updated weights for policy 0, policy_version 580 (0.0016)
352
+ [2024-10-09 18:18:10,262][00030] Fps is (10 sec: 8192.1, 60 sec: 8260.3, 300 sec: 8080.9). Total num frames: 2383872. Throughput: 0: 2066.6. Samples: 593510. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
353
+ [2024-10-09 18:18:10,266][00030] Avg episode reward: [(0, '18.591')]
354
+ [2024-10-09 18:18:10,268][01812] Saving new best policy, reward=18.591!
355
+ [2024-10-09 18:18:14,238][01825] Updated weights for policy 0, policy_version 590 (0.0017)
356
+ [2024-10-09 18:18:15,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.1, 300 sec: 8192.0). Total num frames: 2420736. Throughput: 0: 2041.8. Samples: 604870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
357
+ [2024-10-09 18:18:15,264][00030] Avg episode reward: [(0, '17.334')]
358
+ [2024-10-09 18:18:19,239][01825] Updated weights for policy 0, policy_version 600 (0.0023)
359
+ [2024-10-09 18:18:20,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2465792. Throughput: 0: 2039.3. Samples: 610970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
360
+ [2024-10-09 18:18:20,264][00030] Avg episode reward: [(0, '15.347')]
361
+ [2024-10-09 18:18:24,130][01825] Updated weights for policy 0, policy_version 610 (0.0016)
362
+ [2024-10-09 18:18:25,262][00030] Fps is (10 sec: 8601.4, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2506752. Throughput: 0: 2065.3. Samples: 623564. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
363
+ [2024-10-09 18:18:25,264][00030] Avg episode reward: [(0, '15.667')]
364
+ [2024-10-09 18:18:29,023][01825] Updated weights for policy 0, policy_version 620 (0.0020)
365
+ [2024-10-09 18:18:30,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2547712. Throughput: 0: 2062.1. Samples: 636018. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
366
+ [2024-10-09 18:18:30,264][00030] Avg episode reward: [(0, '17.863')]
367
+ [2024-10-09 18:18:33,947][01825] Updated weights for policy 0, policy_version 630 (0.0019)
368
+ [2024-10-09 18:18:35,262][00030] Fps is (10 sec: 8192.1, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2588672. Throughput: 0: 2064.6. Samples: 642380. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
369
+ [2024-10-09 18:18:35,264][00030] Avg episode reward: [(0, '18.695')]
370
+ [2024-10-09 18:18:35,276][01812] Saving new best policy, reward=18.695!
371
+ [2024-10-09 18:18:38,879][01825] Updated weights for policy 0, policy_version 640 (0.0022)
372
+ [2024-10-09 18:18:40,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8328.5, 300 sec: 8219.8). Total num frames: 2633728. Throughput: 0: 2063.2. Samples: 654898. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
373
+ [2024-10-09 18:18:40,266][00030] Avg episode reward: [(0, '17.631')]
374
+ [2024-10-09 18:18:44,272][01825] Updated weights for policy 0, policy_version 650 (0.0024)
375
+ [2024-10-09 18:18:45,262][00030] Fps is (10 sec: 7782.3, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2666496. Throughput: 0: 2034.3. Samples: 666230. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
376
+ [2024-10-09 18:18:45,264][00030] Avg episode reward: [(0, '18.206')]
377
+ [2024-10-09 18:18:49,147][01825] Updated weights for policy 0, policy_version 660 (0.0017)
378
+ [2024-10-09 18:18:50,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 2711552. Throughput: 0: 2031.1. Samples: 672436. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
379
+ [2024-10-09 18:18:50,266][00030] Avg episode reward: [(0, '19.325')]
380
+ [2024-10-09 18:18:50,268][01812] Saving new best policy, reward=19.325!
381
+ [2024-10-09 18:18:54,116][01825] Updated weights for policy 0, policy_version 670 (0.0018)
382
+ [2024-10-09 18:18:55,262][00030] Fps is (10 sec: 8601.8, 60 sec: 8260.3, 300 sec: 8205.9). Total num frames: 2752512. Throughput: 0: 2033.4. Samples: 685012. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
383
+ [2024-10-09 18:18:55,264][00030] Avg episode reward: [(0, '20.108')]
384
+ [2024-10-09 18:18:55,274][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000672_2752512.pth...
385
+ [2024-10-09 18:18:55,360][01812] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000190_778240.pth
386
+ [2024-10-09 18:18:55,371][01812] Saving new best policy, reward=20.108!
387
+ [2024-10-09 18:18:59,090][01825] Updated weights for policy 0, policy_version 680 (0.0019)
388
+ [2024-10-09 18:19:00,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2793472. Throughput: 0: 2057.8. Samples: 697472. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
389
+ [2024-10-09 18:19:00,267][00030] Avg episode reward: [(0, '20.841')]
390
+ [2024-10-09 18:19:00,269][01812] Saving new best policy, reward=20.841!
391
+ [2024-10-09 18:19:03,929][01825] Updated weights for policy 0, policy_version 690 (0.0024)
392
+ [2024-10-09 18:19:05,262][00030] Fps is (10 sec: 8191.8, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2834432. Throughput: 0: 2063.0. Samples: 703806. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
393
+ [2024-10-09 18:19:05,264][00030] Avg episode reward: [(0, '20.247')]
394
+ [2024-10-09 18:19:08,809][01825] Updated weights for policy 0, policy_version 700 (0.0016)
395
+ [2024-10-09 18:19:10,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 2879488. Throughput: 0: 2066.7. Samples: 716566. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
396
+ [2024-10-09 18:19:10,264][00030] Avg episode reward: [(0, '16.643')]
397
+ [2024-10-09 18:19:13,533][01825] Updated weights for policy 0, policy_version 710 (0.0020)
398
+ [2024-10-09 18:19:15,273][00030] Fps is (10 sec: 8592.5, 60 sec: 8327.0, 300 sec: 8205.6). Total num frames: 2920448. Throughput: 0: 2073.5. Samples: 729348. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
399
+ [2024-10-09 18:19:15,278][00030] Avg episode reward: [(0, '17.261')]
400
+ [2024-10-09 18:19:19,039][01825] Updated weights for policy 0, policy_version 720 (0.0018)
401
+ [2024-10-09 18:19:20,262][00030] Fps is (10 sec: 7782.2, 60 sec: 8191.9, 300 sec: 8219.8). Total num frames: 2957312. Throughput: 0: 2042.8. Samples: 734308. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
402
+ [2024-10-09 18:19:20,264][00030] Avg episode reward: [(0, '19.252')]
403
+ [2024-10-09 18:19:23,868][01825] Updated weights for policy 0, policy_version 730 (0.0021)
404
+ [2024-10-09 18:19:25,262][00030] Fps is (10 sec: 7790.8, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 2998272. Throughput: 0: 2047.4. Samples: 747030. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
405
+ [2024-10-09 18:19:25,264][00030] Avg episode reward: [(0, '21.401')]
406
+ [2024-10-09 18:19:25,272][01812] Saving new best policy, reward=21.401!
407
+ [2024-10-09 18:19:28,773][01825] Updated weights for policy 0, policy_version 740 (0.0019)
408
+ [2024-10-09 18:19:30,262][00030] Fps is (10 sec: 8601.9, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 3043328. Throughput: 0: 2070.7. Samples: 759412. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
409
+ [2024-10-09 18:19:30,264][00030] Avg episode reward: [(0, '22.437')]
410
+ [2024-10-09 18:19:30,268][01812] Saving new best policy, reward=22.437!
411
+ [2024-10-09 18:19:33,755][01825] Updated weights for policy 0, policy_version 750 (0.0020)
412
+ [2024-10-09 18:19:35,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8205.9). Total num frames: 3080192. Throughput: 0: 2069.0. Samples: 765540. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
413
+ [2024-10-09 18:19:35,264][00030] Avg episode reward: [(0, '18.207')]
414
+ [2024-10-09 18:19:38,679][01825] Updated weights for policy 0, policy_version 760 (0.0016)
415
+ [2024-10-09 18:19:40,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8123.7, 300 sec: 8205.9). Total num frames: 3121152. Throughput: 0: 2066.0. Samples: 777982. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
416
+ [2024-10-09 18:19:40,264][00030] Avg episode reward: [(0, '19.387')]
417
+ [2024-10-09 18:19:43,599][01825] Updated weights for policy 0, policy_version 770 (0.0017)
418
+ [2024-10-09 18:19:45,262][00030] Fps is (10 sec: 8601.7, 60 sec: 8328.6, 300 sec: 8219.8). Total num frames: 3166208. Throughput: 0: 2070.5. Samples: 790646. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
419
+ [2024-10-09 18:19:45,263][00030] Avg episode reward: [(0, '22.432')]
420
+ [2024-10-09 18:19:48,934][01825] Updated weights for policy 0, policy_version 780 (0.0020)
421
+ [2024-10-09 18:19:50,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 3203072. Throughput: 0: 2064.2. Samples: 796696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
422
+ [2024-10-09 18:19:50,266][00030] Avg episode reward: [(0, '22.368')]
423
+ [2024-10-09 18:19:53,893][01825] Updated weights for policy 0, policy_version 790 (0.0019)
424
+ [2024-10-09 18:19:55,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 3244032. Throughput: 0: 2040.1. Samples: 808372. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
425
+ [2024-10-09 18:19:55,264][00030] Avg episode reward: [(0, '21.580')]
426
+ [2024-10-09 18:19:58,709][01825] Updated weights for policy 0, policy_version 800 (0.0021)
427
+ [2024-10-09 18:20:00,262][00030] Fps is (10 sec: 8601.3, 60 sec: 8260.2, 300 sec: 8233.6). Total num frames: 3289088. Throughput: 0: 2039.1. Samples: 821084. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
428
+ [2024-10-09 18:20:00,264][00030] Avg episode reward: [(0, '21.612')]
429
+ [2024-10-09 18:20:03,603][01825] Updated weights for policy 0, policy_version 810 (0.0022)
430
+ [2024-10-09 18:20:05,262][00030] Fps is (10 sec: 8601.5, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 3330048. Throughput: 0: 2068.9. Samples: 827408. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
431
+ [2024-10-09 18:20:05,264][00030] Avg episode reward: [(0, '21.123')]
432
+ [2024-10-09 18:20:08,470][01825] Updated weights for policy 0, policy_version 820 (0.0015)
433
+ [2024-10-09 18:20:10,262][00030] Fps is (10 sec: 8192.1, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 3371008. Throughput: 0: 2067.3. Samples: 840060. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
434
+ [2024-10-09 18:20:10,264][00030] Avg episode reward: [(0, '22.082')]
435
+ [2024-10-09 18:20:13,247][01825] Updated weights for policy 0, policy_version 830 (0.0022)
436
+ [2024-10-09 18:20:15,262][00030] Fps is (10 sec: 8601.7, 60 sec: 8261.8, 300 sec: 8233.7). Total num frames: 3416064. Throughput: 0: 2072.1. Samples: 852658. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
437
+ [2024-10-09 18:20:15,267][00030] Avg episode reward: [(0, '22.373')]
438
+ [2024-10-09 18:20:18,173][01825] Updated weights for policy 0, policy_version 840 (0.0019)
439
+ [2024-10-09 18:20:20,262][00030] Fps is (10 sec: 8601.8, 60 sec: 8328.6, 300 sec: 8233.7). Total num frames: 3457024. Throughput: 0: 2072.7. Samples: 858812. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
440
+ [2024-10-09 18:20:20,264][00030] Avg episode reward: [(0, '23.595')]
441
+ [2024-10-09 18:20:20,268][01812] Saving new best policy, reward=23.595!
442
+ [2024-10-09 18:20:23,580][01825] Updated weights for policy 0, policy_version 850 (0.0015)
443
+ [2024-10-09 18:20:25,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8260.3, 300 sec: 8233.7). Total num frames: 3493888. Throughput: 0: 2050.8. Samples: 870266. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
444
+ [2024-10-09 18:20:25,264][00030] Avg episode reward: [(0, '25.079')]
445
+ [2024-10-09 18:20:25,272][01812] Saving new best policy, reward=25.079!
446
+ [2024-10-09 18:20:28,546][01825] Updated weights for policy 0, policy_version 860 (0.0022)
447
+ [2024-10-09 18:20:30,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3534848. Throughput: 0: 2047.4. Samples: 882780. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
448
+ [2024-10-09 18:20:30,265][00030] Avg episode reward: [(0, '24.937')]
449
+ [2024-10-09 18:20:33,362][01825] Updated weights for policy 0, policy_version 870 (0.0025)
450
+ [2024-10-09 18:20:35,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 3575808. Throughput: 0: 2056.3. Samples: 889228. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
451
+ [2024-10-09 18:20:35,264][00030] Avg episode reward: [(0, '24.485')]
452
+ [2024-10-09 18:20:38,256][01825] Updated weights for policy 0, policy_version 880 (0.0020)
453
+ [2024-10-09 18:20:40,262][00030] Fps is (10 sec: 8191.9, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 3616768. Throughput: 0: 2075.6. Samples: 901774. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
454
+ [2024-10-09 18:20:40,264][00030] Avg episode reward: [(0, '24.276')]
455
+ [2024-10-09 18:20:43,173][01825] Updated weights for policy 0, policy_version 890 (0.0024)
456
+ [2024-10-09 18:20:45,262][00030] Fps is (10 sec: 8601.6, 60 sec: 8260.3, 300 sec: 8233.7). Total num frames: 3661824. Throughput: 0: 2075.1. Samples: 914462. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
457
+ [2024-10-09 18:20:45,264][00030] Avg episode reward: [(0, '25.563')]
458
+ [2024-10-09 18:20:45,274][01812] Saving new best policy, reward=25.563!
459
+ [2024-10-09 18:20:48,165][01825] Updated weights for policy 0, policy_version 900 (0.0016)
460
+ [2024-10-09 18:20:50,262][00030] Fps is (10 sec: 8601.8, 60 sec: 8328.5, 300 sec: 8233.7). Total num frames: 3702784. Throughput: 0: 2067.3. Samples: 920434. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
461
+ [2024-10-09 18:20:50,264][00030] Avg episode reward: [(0, '25.378')]
462
+ [2024-10-09 18:20:53,131][01825] Updated weights for policy 0, policy_version 910 (0.0016)
463
+ [2024-10-09 18:20:55,262][00030] Fps is (10 sec: 7782.3, 60 sec: 8260.2, 300 sec: 8233.7). Total num frames: 3739648. Throughput: 0: 2058.8. Samples: 932704. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
464
+ [2024-10-09 18:20:55,264][00030] Avg episode reward: [(0, '25.640')]
465
+ [2024-10-09 18:20:55,276][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000913_3739648.pth...
466
+ [2024-10-09 18:20:55,388][01812] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000432_1769472.pth
467
+ [2024-10-09 18:20:55,397][01812] Saving new best policy, reward=25.640!
468
+ [2024-10-09 18:20:58,553][01825] Updated weights for policy 0, policy_version 920 (0.0020)
469
+ [2024-10-09 18:21:00,262][00030] Fps is (10 sec: 7782.4, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3780608. Throughput: 0: 2038.4. Samples: 944388. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
470
+ [2024-10-09 18:21:00,264][00030] Avg episode reward: [(0, '26.745')]
471
+ [2024-10-09 18:21:00,266][01812] Saving new best policy, reward=26.745!
472
+ [2024-10-09 18:21:03,336][01825] Updated weights for policy 0, policy_version 930 (0.0016)
473
+ [2024-10-09 18:21:05,262][00030] Fps is (10 sec: 8191.8, 60 sec: 8192.0, 300 sec: 8219.8). Total num frames: 3821568. Throughput: 0: 2042.6. Samples: 950728. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
474
+ [2024-10-09 18:21:05,264][00030] Avg episode reward: [(0, '22.445')]
475
+ [2024-10-09 18:21:08,301][01825] Updated weights for policy 0, policy_version 940 (0.0028)
476
+ [2024-10-09 18:21:10,262][00030] Fps is (10 sec: 8601.3, 60 sec: 8260.2, 300 sec: 8233.6). Total num frames: 3866624. Throughput: 0: 2066.4. Samples: 963254. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
477
+ [2024-10-09 18:21:10,264][00030] Avg episode reward: [(0, '21.426')]
478
+ [2024-10-09 18:21:13,086][01825] Updated weights for policy 0, policy_version 950 (0.0020)
479
+ [2024-10-09 18:21:15,262][00030] Fps is (10 sec: 8601.9, 60 sec: 8192.0, 300 sec: 8233.7). Total num frames: 3907584. Throughput: 0: 2073.2. Samples: 976074. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
480
+ [2024-10-09 18:21:15,264][00030] Avg episode reward: [(0, '21.892')]
481
+ [2024-10-09 18:21:18,028][01825] Updated weights for policy 0, policy_version 960 (0.0029)
482
+ [2024-10-09 18:21:20,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8233.6). Total num frames: 3948544. Throughput: 0: 2068.4. Samples: 982306. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
483
+ [2024-10-09 18:21:20,264][00030] Avg episode reward: [(0, '21.588')]
484
+ [2024-10-09 18:21:22,912][01825] Updated weights for policy 0, policy_version 970 (0.0018)
485
+ [2024-10-09 18:21:25,262][00030] Fps is (10 sec: 8192.0, 60 sec: 8260.3, 300 sec: 8219.8). Total num frames: 3989504. Throughput: 0: 2069.7. Samples: 994912. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
486
+ [2024-10-09 18:21:25,264][00030] Avg episode reward: [(0, '21.715')]
487
+ [2024-10-09 18:21:27,330][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
488
+ [2024-10-09 18:21:27,337][01812] Stopping Batcher_0...
489
+ [2024-10-09 18:21:27,337][01812] Loop batcher_evt_loop terminating...
490
+ [2024-10-09 18:21:27,338][00030] Component Batcher_0 stopped!
491
+ [2024-10-09 18:21:27,340][00030] Component RolloutWorker_w4 process died already! Don't wait for it.
492
+ [2024-10-09 18:21:27,368][01825] Weights refcount: 2 0
493
+ [2024-10-09 18:21:27,370][01825] Stopping InferenceWorker_p0-w0...
494
+ [2024-10-09 18:21:27,370][01825] Loop inference_proc0-0_evt_loop terminating...
495
+ [2024-10-09 18:21:27,371][00030] Component InferenceWorker_p0-w0 stopped!
496
+ [2024-10-09 18:21:27,438][01812] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000672_2752512.pth
497
+ [2024-10-09 18:21:27,438][00030] Component RolloutWorker_w5 stopped!
498
+ [2024-10-09 18:21:27,443][01831] Stopping RolloutWorker_w5...
499
+ [2024-10-09 18:21:27,446][00030] Component RolloutWorker_w1 stopped!
500
+ [2024-10-09 18:21:27,448][01812] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
501
+ [2024-10-09 18:21:27,446][01829] Stopping RolloutWorker_w1...
502
+ [2024-10-09 18:21:27,444][01831] Loop rollout_proc5_evt_loop terminating...
503
+ [2024-10-09 18:21:27,450][01829] Loop rollout_proc1_evt_loop terminating...
504
+ [2024-10-09 18:21:27,555][01826] Stopping RolloutWorker_w2...
505
+ [2024-10-09 18:21:27,556][01826] Loop rollout_proc2_evt_loop terminating...
506
+ [2024-10-09 18:21:27,557][01832] Stopping RolloutWorker_w6...
507
+ [2024-10-09 18:21:27,558][01832] Loop rollout_proc6_evt_loop terminating...
508
+ [2024-10-09 18:21:27,559][00030] Component RolloutWorker_w2 stopped!
509
+ [2024-10-09 18:21:27,563][00030] Component RolloutWorker_w6 stopped!
510
+ [2024-10-09 18:21:27,578][01812] Stopping LearnerWorker_p0...
511
+ [2024-10-09 18:21:27,578][00030] Component LearnerWorker_p0 stopped!
512
+ [2024-10-09 18:21:27,580][01812] Loop learner_proc0_evt_loop terminating...
513
+ [2024-10-09 18:21:27,710][00030] Component RolloutWorker_w0 stopped!
514
+ [2024-10-09 18:21:27,712][01830] Stopping RolloutWorker_w0...
515
+ [2024-10-09 18:21:27,718][01833] Stopping RolloutWorker_w7...
516
+ [2024-10-09 18:21:27,713][01830] Loop rollout_proc0_evt_loop terminating...
517
+ [2024-10-09 18:21:27,719][00030] Component RolloutWorker_w7 stopped!
518
+ [2024-10-09 18:21:27,720][01833] Loop rollout_proc7_evt_loop terminating...
519
+ [2024-10-09 18:21:27,731][00030] Component RolloutWorker_w3 stopped!
520
+ [2024-10-09 18:21:27,732][00030] Waiting for process learner_proc0 to stop...
521
+ [2024-10-09 18:21:27,730][01828] Stopping RolloutWorker_w3...
522
+ [2024-10-09 18:21:27,734][01828] Loop rollout_proc3_evt_loop terminating...
523
+ [2024-10-09 18:21:28,787][00030] Waiting for process inference_proc0-0 to join...
524
+ [2024-10-09 18:21:28,789][00030] Waiting for process rollout_proc0 to join...
525
+ [2024-10-09 18:21:29,097][00030] Waiting for process rollout_proc1 to join...
526
+ [2024-10-09 18:21:29,101][00030] Waiting for process rollout_proc2 to join...
527
+ [2024-10-09 18:21:29,228][00030] Waiting for process rollout_proc3 to join...
528
+ [2024-10-09 18:21:29,230][00030] Waiting for process rollout_proc4 to join...
529
+ [2024-10-09 18:21:29,231][00030] Waiting for process rollout_proc5 to join...
530
+ [2024-10-09 18:21:29,232][00030] Waiting for process rollout_proc6 to join...
531
+ [2024-10-09 18:21:29,234][00030] Waiting for process rollout_proc7 to join...
532
+ [2024-10-09 18:21:29,235][00030] Batcher 0 profile tree view:
533
+ batching: 21.1720, releasing_batches: 0.0282
534
+ [2024-10-09 18:21:29,236][00030] InferenceWorker_p0-w0 profile tree view:
535
+ wait_policy: 0.0001
536
+ wait_policy_total: 31.9920
537
+ update_model: 7.1724
538
+ weight_update: 0.0018
539
+ one_step: 0.0032
540
+ handle_policy_step: 428.6168
541
+ deserialize: 13.7148, stack: 2.8770, obs_to_device_normalize: 98.3347, forward: 220.0858, send_messages: 22.3031
542
+ prepare_outputs: 48.6425
543
+ to_cpu: 27.4382
544
+ [2024-10-09 18:21:29,237][00030] Learner 0 profile tree view:
545
+ misc: 0.0055, prepare_batch: 7.8052
546
+ train: 36.2766
547
+ epoch_init: 0.0069, minibatch_init: 0.0068, losses_postprocess: 0.3675, kl_divergence: 0.4555, after_optimizer: 13.1285
548
+ calculate_losses: 11.9069
549
+ losses_init: 0.0046, forward_head: 0.7718, bptt_initial: 7.0356, tail: 0.8140, advantages_returns: 0.1901, losses: 1.4712
550
+ bptt: 1.3921
551
+ bptt_forward_core: 1.3153
552
+ update: 9.9407
553
+ clip: 0.8936
554
+ [2024-10-09 18:21:29,238][00030] RolloutWorker_w0 profile tree view:
555
+ wait_for_trajectories: 0.2099, enqueue_policy_requests: 9.7928, env_step: 329.9937, overhead: 6.8166, complete_rollouts: 2.1093
556
+ save_policy_outputs: 13.0185
557
+ split_output_tensors: 4.7072
558
+ [2024-10-09 18:21:29,240][00030] RolloutWorker_w7 profile tree view:
559
+ wait_for_trajectories: 0.2545, enqueue_policy_requests: 12.6464, env_step: 330.8292, overhead: 9.0653, complete_rollouts: 2.7812
560
+ save_policy_outputs: 17.9088
561
+ split_output_tensors: 6.4777
562
+ [2024-10-09 18:21:29,241][00030] Loop Runner_EvtLoop terminating...
563
+ [2024-10-09 18:21:29,242][00030] Runner profile tree view:
564
+ main_loop: 508.8147
565
+ [2024-10-09 18:21:29,243][00030] Collected {0: 4005888}, FPS: 7873.0
566
+ [2024-10-09 18:21:29,564][00030] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
567
+ [2024-10-09 18:21:29,565][00030] Overriding arg 'num_workers' with value 1 passed from command line
568
+ [2024-10-09 18:21:29,566][00030] Adding new argument 'no_render'=True that is not in the saved config file!
569
+ [2024-10-09 18:21:29,567][00030] Adding new argument 'save_video'=True that is not in the saved config file!
570
+ [2024-10-09 18:21:29,569][00030] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
571
+ [2024-10-09 18:21:29,570][00030] Adding new argument 'video_name'=None that is not in the saved config file!
572
+ [2024-10-09 18:21:29,571][00030] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
573
+ [2024-10-09 18:21:29,572][00030] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
574
+ [2024-10-09 18:21:29,573][00030] Adding new argument 'push_to_hub'=False that is not in the saved config file!
575
+ [2024-10-09 18:21:29,574][00030] Adding new argument 'hf_repository'=None that is not in the saved config file!
576
+ [2024-10-09 18:21:29,575][00030] Adding new argument 'policy_index'=0 that is not in the saved config file!
577
+ [2024-10-09 18:21:29,576][00030] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
578
+ [2024-10-09 18:21:29,577][00030] Adding new argument 'train_script'=None that is not in the saved config file!
579
+ [2024-10-09 18:21:29,578][00030] Adding new argument 'enjoy_script'=None that is not in the saved config file!
580
+ [2024-10-09 18:21:29,579][00030] Using frameskip 1 and render_action_repeat=4 for evaluation
581
+ [2024-10-09 18:21:29,606][00030] Doom resolution: 160x120, resize resolution: (128, 72)
582
+ [2024-10-09 18:21:29,609][00030] RunningMeanStd input shape: (3, 72, 128)
583
+ [2024-10-09 18:21:29,610][00030] RunningMeanStd input shape: (1,)
584
+ [2024-10-09 18:21:29,628][00030] ConvEncoder: input_channels=3
585
+ [2024-10-09 18:21:29,762][00030] Conv encoder output size: 512
586
+ [2024-10-09 18:21:29,763][00030] Policy head output size: 512
587
+ [2024-10-09 18:21:29,921][00030] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
588
+ [2024-10-09 18:21:30,744][00030] Num frames 100...
589
+ [2024-10-09 18:21:30,890][00030] Num frames 200...
590
+ [2024-10-09 18:21:31,028][00030] Num frames 300...
591
+ [2024-10-09 18:21:31,167][00030] Num frames 400...
592
+ [2024-10-09 18:21:31,305][00030] Num frames 500...
593
+ [2024-10-09 18:21:31,443][00030] Num frames 600...
594
+ [2024-10-09 18:21:31,587][00030] Num frames 700...
595
+ [2024-10-09 18:21:31,730][00030] Num frames 800...
596
+ [2024-10-09 18:21:31,870][00030] Num frames 900...
597
+ [2024-10-09 18:21:32,010][00030] Num frames 1000...
598
+ [2024-10-09 18:21:32,160][00030] Num frames 1100...
599
+ [2024-10-09 18:21:32,308][00030] Num frames 1200...
600
+ [2024-10-09 18:21:32,452][00030] Num frames 1300...
601
+ [2024-10-09 18:21:32,597][00030] Num frames 1400...
602
+ [2024-10-09 18:21:32,740][00030] Num frames 1500...
603
+ [2024-10-09 18:21:32,883][00030] Num frames 1600...
604
+ [2024-10-09 18:21:32,981][00030] Avg episode rewards: #0: 42.319, true rewards: #0: 16.320
605
+ [2024-10-09 18:21:32,982][00030] Avg episode reward: 42.319, avg true_objective: 16.320
606
+ [2024-10-09 18:21:33,080][00030] Num frames 1700...
607
+ [2024-10-09 18:21:33,222][00030] Num frames 1800...
608
+ [2024-10-09 18:21:33,365][00030] Num frames 1900...
609
+ [2024-10-09 18:21:33,537][00030] Avg episode rewards: #0: 24.420, true rewards: #0: 9.920
610
+ [2024-10-09 18:21:33,539][00030] Avg episode reward: 24.420, avg true_objective: 9.920
611
+ [2024-10-09 18:21:33,564][00030] Num frames 2000...
612
+ [2024-10-09 18:21:33,703][00030] Num frames 2100...
613
+ [2024-10-09 18:21:33,841][00030] Num frames 2200...
614
+ [2024-10-09 18:21:33,983][00030] Num frames 2300...
615
+ [2024-10-09 18:21:34,126][00030] Num frames 2400...
616
+ [2024-10-09 18:21:34,273][00030] Num frames 2500...
617
+ [2024-10-09 18:21:34,413][00030] Num frames 2600...
618
+ [2024-10-09 18:21:34,553][00030] Num frames 2700...
619
+ [2024-10-09 18:21:34,682][00030] Avg episode rewards: #0: 21.507, true rewards: #0: 9.173
620
+ [2024-10-09 18:21:34,683][00030] Avg episode reward: 21.507, avg true_objective: 9.173
621
+ [2024-10-09 18:21:34,750][00030] Num frames 2800...
622
+ [2024-10-09 18:21:34,909][00030] Num frames 2900...
623
+ [2024-10-09 18:21:35,070][00030] Num frames 3000...
624
+ [2024-10-09 18:21:35,217][00030] Num frames 3100...
625
+ [2024-10-09 18:21:35,356][00030] Num frames 3200...
626
+ [2024-10-09 18:21:35,494][00030] Num frames 3300...
627
+ [2024-10-09 18:21:35,634][00030] Num frames 3400...
628
+ [2024-10-09 18:21:35,723][00030] Avg episode rewards: #0: 19.060, true rewards: #0: 8.560
629
+ [2024-10-09 18:21:35,724][00030] Avg episode reward: 19.060, avg true_objective: 8.560
630
+ [2024-10-09 18:21:35,832][00030] Num frames 3500...
631
+ [2024-10-09 18:21:35,977][00030] Num frames 3600...
632
+ [2024-10-09 18:21:36,123][00030] Num frames 3700...
633
+ [2024-10-09 18:21:36,260][00030] Num frames 3800...
634
+ [2024-10-09 18:21:36,395][00030] Num frames 3900...
635
+ [2024-10-09 18:21:36,532][00030] Num frames 4000...
636
+ [2024-10-09 18:21:36,669][00030] Num frames 4100...
637
+ [2024-10-09 18:21:36,812][00030] Avg episode rewards: #0: 17.920, true rewards: #0: 8.320
638
+ [2024-10-09 18:21:36,814][00030] Avg episode reward: 17.920, avg true_objective: 8.320
639
+ [2024-10-09 18:21:36,875][00030] Num frames 4200...
640
+ [2024-10-09 18:21:37,015][00030] Num frames 4300...
641
+ [2024-10-09 18:21:37,152][00030] Num frames 4400...
642
+ [2024-10-09 18:21:37,289][00030] Num frames 4500...
643
+ [2024-10-09 18:21:37,424][00030] Num frames 4600...
644
+ [2024-10-09 18:21:37,564][00030] Num frames 4700...
645
+ [2024-10-09 18:21:37,707][00030] Num frames 4800...
646
+ [2024-10-09 18:21:37,844][00030] Num frames 4900...
647
+ [2024-10-09 18:21:37,981][00030] Num frames 5000...
648
+ [2024-10-09 18:21:38,118][00030] Num frames 5100...
649
+ [2024-10-09 18:21:38,257][00030] Num frames 5200...
650
+ [2024-10-09 18:21:38,396][00030] Num frames 5300...
651
+ [2024-10-09 18:21:38,539][00030] Num frames 5400...
652
+ [2024-10-09 18:21:38,678][00030] Num frames 5500...
653
+ [2024-10-09 18:21:38,816][00030] Num frames 5600...
654
+ [2024-10-09 18:21:38,955][00030] Num frames 5700...
655
+ [2024-10-09 18:21:39,092][00030] Num frames 5800...
656
+ [2024-10-09 18:21:39,228][00030] Num frames 5900...
657
+ [2024-10-09 18:21:39,372][00030] Num frames 6000...
658
+ [2024-10-09 18:21:39,515][00030] Num frames 6100...
659
+ [2024-10-09 18:21:39,658][00030] Num frames 6200...
660
+ [2024-10-09 18:21:39,799][00030] Avg episode rewards: #0: 24.766, true rewards: #0: 10.433
661
+ [2024-10-09 18:21:39,800][00030] Avg episode reward: 24.766, avg true_objective: 10.433
662
+ [2024-10-09 18:21:39,855][00030] Num frames 6300...
663
+ [2024-10-09 18:21:39,992][00030] Num frames 6400...
664
+ [2024-10-09 18:21:40,127][00030] Num frames 6500...
665
+ [2024-10-09 18:21:40,268][00030] Num frames 6600...
666
+ [2024-10-09 18:21:40,406][00030] Num frames 6700...
667
+ [2024-10-09 18:21:40,546][00030] Num frames 6800...
668
+ [2024-10-09 18:21:40,684][00030] Num frames 6900...
669
+ [2024-10-09 18:21:40,820][00030] Num frames 7000...
670
+ [2024-10-09 18:21:40,962][00030] Num frames 7100...
671
+ [2024-10-09 18:21:41,109][00030] Num frames 7200...
672
+ [2024-10-09 18:21:41,252][00030] Num frames 7300...
673
+ [2024-10-09 18:21:41,393][00030] Num frames 7400...
674
+ [2024-10-09 18:21:41,538][00030] Num frames 7500...
675
+ [2024-10-09 18:21:41,684][00030] Num frames 7600...
676
+ [2024-10-09 18:21:41,832][00030] Num frames 7700...
677
+ [2024-10-09 18:21:42,024][00030] Avg episode rewards: #0: 25.851, true rewards: #0: 11.137
678
+ [2024-10-09 18:21:42,025][00030] Avg episode reward: 25.851, avg true_objective: 11.137
679
+ [2024-10-09 18:21:42,034][00030] Num frames 7800...
680
+ [2024-10-09 18:21:42,178][00030] Num frames 7900...
681
+ [2024-10-09 18:21:42,322][00030] Num frames 8000...
682
+ [2024-10-09 18:21:42,467][00030] Num frames 8100...
683
+ [2024-10-09 18:21:42,606][00030] Num frames 8200...
684
+ [2024-10-09 18:21:42,750][00030] Num frames 8300...
685
+ [2024-10-09 18:21:42,892][00030] Num frames 8400...
686
+ [2024-10-09 18:21:43,031][00030] Num frames 8500...
687
+ [2024-10-09 18:21:43,170][00030] Num frames 8600...
688
+ [2024-10-09 18:21:43,262][00030] Avg episode rewards: #0: 25.032, true rewards: #0: 10.782
689
+ [2024-10-09 18:21:43,263][00030] Avg episode reward: 25.032, avg true_objective: 10.782
690
+ [2024-10-09 18:21:43,365][00030] Num frames 8700...
691
+ [2024-10-09 18:21:43,507][00030] Num frames 8800...
692
+ [2024-10-09 18:21:43,652][00030] Num frames 8900...
693
+ [2024-10-09 18:21:43,798][00030] Num frames 9000...
694
+ [2024-10-09 18:21:43,940][00030] Num frames 9100...
695
+ [2024-10-09 18:21:44,077][00030] Num frames 9200...
696
+ [2024-10-09 18:21:44,216][00030] Num frames 9300...
697
+ [2024-10-09 18:21:44,355][00030] Num frames 9400...
698
+ [2024-10-09 18:21:44,505][00030] Num frames 9500...
699
+ [2024-10-09 18:21:44,656][00030] Num frames 9600...
700
+ [2024-10-09 18:21:44,793][00030] Num frames 9700...
701
+ [2024-10-09 18:21:44,934][00030] Num frames 9800...
702
+ [2024-10-09 18:21:45,090][00030] Num frames 9900...
703
+ [2024-10-09 18:21:45,228][00030] Num frames 10000...
704
+ [2024-10-09 18:21:45,370][00030] Num frames 10100...
705
+ [2024-10-09 18:21:45,510][00030] Num frames 10200...
706
+ [2024-10-09 18:21:45,646][00030] Avg episode rewards: #0: 26.620, true rewards: #0: 11.398
707
+ [2024-10-09 18:21:45,648][00030] Avg episode reward: 26.620, avg true_objective: 11.398
708
+ [2024-10-09 18:21:45,708][00030] Num frames 10300...
709
+ [2024-10-09 18:21:45,844][00030] Num frames 10400...
710
+ [2024-10-09 18:21:45,979][00030] Num frames 10500...
711
+ [2024-10-09 18:21:46,116][00030] Num frames 10600...
712
+ [2024-10-09 18:21:46,259][00030] Num frames 10700...
713
+ [2024-10-09 18:21:46,397][00030] Num frames 10800...
714
+ [2024-10-09 18:21:46,542][00030] Num frames 10900...
715
+ [2024-10-09 18:21:46,686][00030] Num frames 11000...
716
+ [2024-10-09 18:21:46,869][00030] Avg episode rewards: #0: 25.790, true rewards: #0: 11.090
717
+ [2024-10-09 18:21:46,871][00030] Avg episode reward: 25.790, avg true_objective: 11.090
718
+ [2024-10-09 18:22:24,948][00030] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
719
+ [2024-10-09 18:26:14,805][00030] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
720
+ [2024-10-09 18:26:14,806][00030] Overriding arg 'num_workers' with value 1 passed from command line
721
+ [2024-10-09 18:26:14,807][00030] Adding new argument 'no_render'=True that is not in the saved config file!
722
+ [2024-10-09 18:26:14,808][00030] Adding new argument 'save_video'=True that is not in the saved config file!
723
+ [2024-10-09 18:26:14,809][00030] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
724
+ [2024-10-09 18:26:14,810][00030] Adding new argument 'video_name'=None that is not in the saved config file!
725
+ [2024-10-09 18:26:14,812][00030] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
726
+ [2024-10-09 18:26:14,812][00030] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
727
+ [2024-10-09 18:26:14,813][00030] Adding new argument 'push_to_hub'=True that is not in the saved config file!
728
+ [2024-10-09 18:26:14,815][00030] Adding new argument 'hf_repository'='MalyO2/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
729
+ [2024-10-09 18:26:14,816][00030] Adding new argument 'policy_index'=0 that is not in the saved config file!
730
+ [2024-10-09 18:26:14,817][00030] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
731
+ [2024-10-09 18:26:14,818][00030] Adding new argument 'train_script'=None that is not in the saved config file!
732
+ [2024-10-09 18:26:14,819][00030] Adding new argument 'enjoy_script'=None that is not in the saved config file!
733
+ [2024-10-09 18:26:14,820][00030] Using frameskip 1 and render_action_repeat=4 for evaluation
734
+ [2024-10-09 18:26:14,851][00030] RunningMeanStd input shape: (3, 72, 128)
735
+ [2024-10-09 18:26:14,853][00030] RunningMeanStd input shape: (1,)
736
+ [2024-10-09 18:26:14,871][00030] ConvEncoder: input_channels=3
737
+ [2024-10-09 18:26:14,921][00030] Conv encoder output size: 512
738
+ [2024-10-09 18:26:14,922][00030] Policy head output size: 512
739
+ [2024-10-09 18:26:14,947][00030] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
740
+ [2024-10-09 18:26:15,496][00030] Num frames 100...
741
+ [2024-10-09 18:26:15,636][00030] Num frames 200...
742
+ [2024-10-09 18:26:15,775][00030] Num frames 300...
743
+ [2024-10-09 18:26:15,912][00030] Num frames 400...
744
+ [2024-10-09 18:26:16,053][00030] Num frames 500...
745
+ [2024-10-09 18:26:16,194][00030] Num frames 600...
746
+ [2024-10-09 18:26:16,330][00030] Num frames 700...
747
+ [2024-10-09 18:26:16,390][00030] Avg episode rewards: #0: 11.040, true rewards: #0: 7.040
748
+ [2024-10-09 18:26:16,391][00030] Avg episode reward: 11.040, avg true_objective: 7.040
749
+ [2024-10-09 18:26:16,523][00030] Num frames 800...
750
+ [2024-10-09 18:26:16,665][00030] Num frames 900...
751
+ [2024-10-09 18:26:16,802][00030] Num frames 1000...
752
+ [2024-10-09 18:26:16,993][00030] Avg episode rewards: #0: 8.940, true rewards: #0: 5.440
753
+ [2024-10-09 18:26:16,994][00030] Avg episode reward: 8.940, avg true_objective: 5.440
754
+ [2024-10-09 18:26:17,013][00030] Num frames 1100...
755
+ [2024-10-09 18:26:17,148][00030] Num frames 1200...
756
+ [2024-10-09 18:26:17,288][00030] Num frames 1300...
757
+ [2024-10-09 18:26:17,428][00030] Num frames 1400...
758
+ [2024-10-09 18:26:17,567][00030] Num frames 1500...
759
+ [2024-10-09 18:26:17,708][00030] Num frames 1600...
760
+ [2024-10-09 18:26:17,850][00030] Num frames 1700...
761
+ [2024-10-09 18:26:17,987][00030] Num frames 1800...
762
+ [2024-10-09 18:26:18,124][00030] Num frames 1900...
763
+ [2024-10-09 18:26:18,263][00030] Num frames 2000...
764
+ [2024-10-09 18:26:18,405][00030] Num frames 2100...
765
+ [2024-10-09 18:26:18,550][00030] Num frames 2200...
766
+ [2024-10-09 18:26:18,698][00030] Num frames 2300...
767
+ [2024-10-09 18:26:18,841][00030] Num frames 2400...
768
+ [2024-10-09 18:26:18,986][00030] Num frames 2500...
769
+ [2024-10-09 18:26:19,129][00030] Num frames 2600...
770
+ [2024-10-09 18:26:19,271][00030] Num frames 2700...
771
+ [2024-10-09 18:26:19,418][00030] Num frames 2800...
772
+ [2024-10-09 18:26:19,563][00030] Num frames 2900...
773
+ [2024-10-09 18:26:19,703][00030] Num frames 3000...
774
+ [2024-10-09 18:26:19,842][00030] Num frames 3100...
775
+ [2024-10-09 18:26:20,023][00030] Avg episode rewards: #0: 24.960, true rewards: #0: 10.627
776
+ [2024-10-09 18:26:20,024][00030] Avg episode reward: 24.960, avg true_objective: 10.627
777
+ [2024-10-09 18:26:20,044][00030] Num frames 3200...
778
+ [2024-10-09 18:26:20,183][00030] Num frames 3300...
779
+ [2024-10-09 18:26:20,321][00030] Num frames 3400...
780
+ [2024-10-09 18:26:20,460][00030] Num frames 3500...
781
+ [2024-10-09 18:26:20,605][00030] Num frames 3600...
782
+ [2024-10-09 18:26:20,711][00030] Avg episode rewards: #0: 20.090, true rewards: #0: 9.090
783
+ [2024-10-09 18:26:20,712][00030] Avg episode reward: 20.090, avg true_objective: 9.090
784
+ [2024-10-09 18:26:20,799][00030] Num frames 3700...
785
+ [2024-10-09 18:26:20,941][00030] Num frames 3800...
786
+ [2024-10-09 18:26:21,082][00030] Num frames 3900...
787
+ [2024-10-09 18:26:21,221][00030] Num frames 4000...
788
+ [2024-10-09 18:26:21,359][00030] Num frames 4100...
789
+ [2024-10-09 18:26:21,506][00030] Num frames 4200...
790
+ [2024-10-09 18:26:21,647][00030] Num frames 4300...
791
+ [2024-10-09 18:26:21,796][00030] Num frames 4400...
792
+ [2024-10-09 18:26:21,944][00030] Num frames 4500...
793
+ [2024-10-09 18:26:22,095][00030] Num frames 4600...
794
+ [2024-10-09 18:26:22,238][00030] Avg episode rewards: #0: 21.120, true rewards: #0: 9.320
795
+ [2024-10-09 18:26:22,240][00030] Avg episode reward: 21.120, avg true_objective: 9.320
796
+ [2024-10-09 18:26:22,300][00030] Num frames 4700...
797
+ [2024-10-09 18:26:22,442][00030] Num frames 4800...
798
+ [2024-10-09 18:26:22,589][00030] Num frames 4900...
799
+ [2024-10-09 18:26:22,736][00030] Num frames 5000...
800
+ [2024-10-09 18:26:22,889][00030] Num frames 5100...
801
+ [2024-10-09 18:26:23,041][00030] Num frames 5200...
802
+ [2024-10-09 18:26:23,186][00030] Num frames 5300...
803
+ [2024-10-09 18:26:23,327][00030] Num frames 5400...
804
+ [2024-10-09 18:26:23,466][00030] Num frames 5500...
805
+ [2024-10-09 18:26:23,606][00030] Num frames 5600...
806
+ [2024-10-09 18:26:23,750][00030] Num frames 5700...
807
+ [2024-10-09 18:26:23,893][00030] Num frames 5800...
808
+ [2024-10-09 18:26:24,036][00030] Num frames 5900...
809
+ [2024-10-09 18:26:24,181][00030] Num frames 6000...
810
+ [2024-10-09 18:26:24,324][00030] Num frames 6100...
811
+ [2024-10-09 18:26:24,469][00030] Avg episode rewards: #0: 23.273, true rewards: #0: 10.273
812
+ [2024-10-09 18:26:24,471][00030] Avg episode reward: 23.273, avg true_objective: 10.273
813
+ [2024-10-09 18:26:24,526][00030] Num frames 6200...
814
+ [2024-10-09 18:26:24,672][00030] Num frames 6300...
815
+ [2024-10-09 18:26:24,812][00030] Num frames 6400...
816
+ [2024-10-09 18:26:24,974][00030] Num frames 6500...
817
+ [2024-10-09 18:26:25,131][00030] Num frames 6600...
818
+ [2024-10-09 18:26:25,280][00030] Num frames 6700...
819
+ [2024-10-09 18:26:25,425][00030] Num frames 6800...
820
+ [2024-10-09 18:26:25,571][00030] Num frames 6900...
821
+ [2024-10-09 18:26:25,708][00030] Num frames 7000...
822
+ [2024-10-09 18:26:25,849][00030] Num frames 7100...
823
+ [2024-10-09 18:26:25,996][00030] Num frames 7200...
824
+ [2024-10-09 18:26:26,141][00030] Num frames 7300...
825
+ [2024-10-09 18:26:26,289][00030] Num frames 7400...
826
+ [2024-10-09 18:26:26,363][00030] Avg episode rewards: #0: 24.160, true rewards: #0: 10.589
827
+ [2024-10-09 18:26:26,364][00030] Avg episode reward: 24.160, avg true_objective: 10.589
828
+ [2024-10-09 18:26:26,489][00030] Num frames 7500...
829
+ [2024-10-09 18:26:26,634][00030] Num frames 7600...
830
+ [2024-10-09 18:26:26,776][00030] Num frames 7700...
831
+ [2024-10-09 18:26:26,923][00030] Num frames 7800...
832
+ [2024-10-09 18:26:27,064][00030] Avg episode rewards: #0: 21.825, true rewards: #0: 9.825
833
+ [2024-10-09 18:26:27,065][00030] Avg episode reward: 21.825, avg true_objective: 9.825
834
+ [2024-10-09 18:26:27,128][00030] Num frames 7900...
835
+ [2024-10-09 18:26:27,272][00030] Num frames 8000...
836
+ [2024-10-09 18:26:27,410][00030] Num frames 8100...
837
+ [2024-10-09 18:26:27,551][00030] Num frames 8200...
838
+ [2024-10-09 18:26:27,689][00030] Num frames 8300...
839
+ [2024-10-09 18:26:27,829][00030] Num frames 8400...
840
+ [2024-10-09 18:26:27,975][00030] Num frames 8500...
841
+ [2024-10-09 18:26:28,066][00030] Avg episode rewards: #0: 20.914, true rewards: #0: 9.470
842
+ [2024-10-09 18:26:28,068][00030] Avg episode reward: 20.914, avg true_objective: 9.470
843
+ [2024-10-09 18:26:28,176][00030] Num frames 8600...
844
+ [2024-10-09 18:26:28,317][00030] Num frames 8700...
845
+ [2024-10-09 18:26:28,455][00030] Num frames 8800...
846
+ [2024-10-09 18:26:28,595][00030] Num frames 8900...
847
+ [2024-10-09 18:26:28,737][00030] Num frames 9000...
848
+ [2024-10-09 18:26:28,883][00030] Num frames 9100...
849
+ [2024-10-09 18:26:29,026][00030] Num frames 9200...
850
+ [2024-10-09 18:26:29,166][00030] Num frames 9300...
851
+ [2024-10-09 18:26:29,305][00030] Num frames 9400...
852
+ [2024-10-09 18:26:29,447][00030] Num frames 9500...
853
+ [2024-10-09 18:26:29,592][00030] Num frames 9600...
854
+ [2024-10-09 18:26:29,786][00030] Avg episode rewards: #0: 21.893, true rewards: #0: 9.693
855
+ [2024-10-09 18:26:29,787][00030] Avg episode reward: 21.893, avg true_objective: 9.693
856
+ [2024-10-09 18:27:03,077][00030] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!