Hugging Face's logo

jaymanvirk
/
ppo_sample_factory_doom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
jaymanvirk commited on
Commit
444e5c9
•
1 Parent(s): 1f751bb

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1715925830.29e5e4c8c05f +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000977_4001792_reward_26.560.pth +3 -0
  5. checkpoint_p0/checkpoint_000000879_3600384.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 +870 -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.1715925830.29e5e4c8c05f ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d5a4bbab650e7493be8d38ab50ccc51e1e44a898f72b5e9ede70545bc2abe8c
3
+ size 472903
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: 8.36 +/- 4.79
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 jaymanvirk/ppo_sample_factory_doom_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=ppo_sample_factory_doom_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=ppo_sample_factory_doom_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_000000977_4001792_reward_26.560.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2be8ffe2e525b8801e1d3e8d044457f290d222477ba326964512782b5347938
3
+ size 34929051
checkpoint_p0/checkpoint_000000879_3600384.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5c6d2b959f33dafe92331e50842f52b7b370df3b0e0ccdddb5d760ebfe3d1c43
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:ab8d153277fc0035347bc05b18fa6f49391f445404ed649821d601f9bf260a51
3
+ size 34929477
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:aefb90d9d9fc0a9d21e8d66140b485b21cd5696a30c9d972a2b2c01f8c381788
3
+ size 16378745
sf_log.txt ADDED
@@ -0,0 +1,870 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-05-17 06:03:56,183][00035] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json...
2
+ [2024-05-17 06:03:56,186][00035] Rollout worker 0 uses device cpu
3
+ [2024-05-17 06:03:56,186][00035] Rollout worker 1 uses device cpu
4
+ [2024-05-17 06:03:56,187][00035] Rollout worker 2 uses device cpu
5
+ [2024-05-17 06:03:56,188][00035] Rollout worker 3 uses device cpu
6
+ [2024-05-17 06:03:56,189][00035] Rollout worker 4 uses device cpu
7
+ [2024-05-17 06:03:56,190][00035] Rollout worker 5 uses device cpu
8
+ [2024-05-17 06:03:56,191][00035] Rollout worker 6 uses device cpu
9
+ [2024-05-17 06:03:56,192][00035] Rollout worker 7 uses device cpu
10
+ [2024-05-17 06:03:56,298][00035] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-05-17 06:03:56,300][00035] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-05-17 06:03:56,336][00035] Starting all processes...
13
+ [2024-05-17 06:03:56,337][00035] Starting process learner_proc0
14
+ [2024-05-17 06:03:56,443][00035] Starting all processes...
15
+ [2024-05-17 06:03:56,451][00035] Starting process inference_proc0-0
16
+ [2024-05-17 06:03:56,451][00035] Starting process rollout_proc0
17
+ [2024-05-17 06:03:56,452][00035] Starting process rollout_proc1
18
+ [2024-05-17 06:03:56,453][00035] Starting process rollout_proc2
19
+ [2024-05-17 06:03:56,453][00035] Starting process rollout_proc3
20
+ [2024-05-17 06:03:56,453][00035] Starting process rollout_proc4
21
+ [2024-05-17 06:03:56,453][00035] Starting process rollout_proc5
22
+ [2024-05-17 06:03:56,455][00035] Starting process rollout_proc6
23
+ [2024-05-17 06:03:56,455][00035] Starting process rollout_proc7
24
+ [2024-05-17 06:04:04,774][00159] Worker 5 uses CPU cores [1]
25
+ [2024-05-17 06:04:04,952][00156] Worker 2 uses CPU cores [2]
26
+ [2024-05-17 06:04:05,033][00154] Worker 1 uses CPU cores [1]
27
+ [2024-05-17 06:04:05,183][00153] Using GPUs [0] for process 0 (actually maps to GPUs [0])
28
+ [2024-05-17 06:04:05,183][00153] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
29
+ [2024-05-17 06:04:05,208][00140] Using GPUs [0] for process 0 (actually maps to GPUs [0])
30
+ [2024-05-17 06:04:05,208][00140] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
31
+ [2024-05-17 06:04:05,236][00153] Num visible devices: 1
32
+ [2024-05-17 06:04:05,254][00140] Num visible devices: 1
33
+ [2024-05-17 06:04:05,285][00140] Starting seed is not provided
34
+ [2024-05-17 06:04:05,286][00140] Using GPUs [0] for process 0 (actually maps to GPUs [0])
35
+ [2024-05-17 06:04:05,286][00140] Initializing actor-critic model on device cuda:0
36
+ [2024-05-17 06:04:05,286][00140] RunningMeanStd input shape: (3, 72, 128)
37
+ [2024-05-17 06:04:05,290][00140] RunningMeanStd input shape: (1,)
38
+ [2024-05-17 06:04:05,313][00158] Worker 4 uses CPU cores [0]
39
+ [2024-05-17 06:04:05,329][00140] ConvEncoder: input_channels=3
40
+ [2024-05-17 06:04:05,485][00161] Worker 7 uses CPU cores [3]
41
+ [2024-05-17 06:04:05,549][00160] Worker 6 uses CPU cores [2]
42
+ [2024-05-17 06:04:05,588][00157] Worker 3 uses CPU cores [3]
43
+ [2024-05-17 06:04:05,588][00155] Worker 0 uses CPU cores [0]
44
+ [2024-05-17 06:04:05,650][00140] Conv encoder output size: 512
45
+ [2024-05-17 06:04:05,651][00140] Policy head output size: 512
46
+ [2024-05-17 06:04:05,704][00140] Created Actor Critic model with architecture:
47
+ [2024-05-17 06:04:05,704][00140] 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
+ [2024-05-17 06:04:05,984][00140] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-05-17 06:04:08,182][00140] No checkpoints found
90
+ [2024-05-17 06:04:08,182][00140] Did not load from checkpoint, starting from scratch!
91
+ [2024-05-17 06:04:08,182][00140] Initialized policy 0 weights for model version 0
92
+ [2024-05-17 06:04:08,185][00140] LearnerWorker_p0 finished initialization!
93
+ [2024-05-17 06:04:08,185][00140] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-05-17 06:04:08,281][00153] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-05-17 06:04:08,282][00153] RunningMeanStd input shape: (1,)
96
+ [2024-05-17 06:04:08,298][00153] ConvEncoder: input_channels=3
97
+ [2024-05-17 06:04:08,420][00153] Conv encoder output size: 512
98
+ [2024-05-17 06:04:08,420][00153] Policy head output size: 512
99
+ [2024-05-17 06:04:08,478][00035] Inference worker 0-0 is ready!
100
+ [2024-05-17 06:04:08,479][00035] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-05-17 06:04:08,587][00154] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-05-17 06:04:08,590][00160] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-05-17 06:04:08,589][00159] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-05-17 06:04:08,590][00156] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-05-17 06:04:08,592][00157] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-05-17 06:04:08,594][00158] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-05-17 06:04:08,592][00161] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-05-17 06:04:08,595][00155] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-05-17 06:04:09,079][00160] Decorrelating experience for 0 frames...
110
+ [2024-05-17 06:04:09,553][00160] Decorrelating experience for 32 frames...
111
+ [2024-05-17 06:04:09,615][00155] Decorrelating experience for 0 frames...
112
+ [2024-05-17 06:04:09,668][00159] Decorrelating experience for 0 frames...
113
+ [2024-05-17 06:04:09,671][00154] Decorrelating experience for 0 frames...
114
+ [2024-05-17 06:04:09,675][00157] Decorrelating experience for 0 frames...
115
+ [2024-05-17 06:04:09,678][00161] Decorrelating experience for 0 frames...
116
+ [2024-05-17 06:04:10,152][00161] Decorrelating experience for 32 frames...
117
+ [2024-05-17 06:04:10,177][00155] Decorrelating experience for 32 frames...
118
+ [2024-05-17 06:04:10,211][00156] Decorrelating experience for 0 frames...
119
+ [2024-05-17 06:04:10,686][00159] Decorrelating experience for 32 frames...
120
+ [2024-05-17 06:04:10,688][00154] Decorrelating experience for 32 frames...
121
+ [2024-05-17 06:04:10,847][00157] Decorrelating experience for 32 frames...
122
+ [2024-05-17 06:04:10,851][00035] 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)
123
+ [2024-05-17 06:04:10,917][00155] Decorrelating experience for 64 frames...
124
+ [2024-05-17 06:04:11,230][00160] Decorrelating experience for 64 frames...
125
+ [2024-05-17 06:04:11,299][00156] Decorrelating experience for 32 frames...
126
+ [2024-05-17 06:04:11,437][00158] Decorrelating experience for 0 frames...
127
+ [2024-05-17 06:04:11,566][00161] Decorrelating experience for 64 frames...
128
+ [2024-05-17 06:04:12,041][00159] Decorrelating experience for 64 frames...
129
+ [2024-05-17 06:04:12,044][00154] Decorrelating experience for 64 frames...
130
+ [2024-05-17 06:04:12,089][00160] Decorrelating experience for 96 frames...
131
+ [2024-05-17 06:04:12,305][00156] Decorrelating experience for 64 frames...
132
+ [2024-05-17 06:04:12,526][00158] Decorrelating experience for 32 frames...
133
+ [2024-05-17 06:04:12,609][00157] Decorrelating experience for 64 frames...
134
+ [2024-05-17 06:04:12,652][00159] Decorrelating experience for 96 frames...
135
+ [2024-05-17 06:04:12,689][00161] Decorrelating experience for 96 frames...
136
+ [2024-05-17 06:04:12,992][00155] Decorrelating experience for 96 frames...
137
+ [2024-05-17 06:04:13,153][00157] Decorrelating experience for 96 frames...
138
+ [2024-05-17 06:04:13,431][00158] Decorrelating experience for 64 frames...
139
+ [2024-05-17 06:04:14,536][00156] Decorrelating experience for 96 frames...
140
+ [2024-05-17 06:04:14,610][00158] Decorrelating experience for 96 frames...
141
+ [2024-05-17 06:04:15,524][00140] Signal inference workers to stop experience collection...
142
+ [2024-05-17 06:04:15,542][00153] InferenceWorker_p0-w0: stopping experience collection
143
+ [2024-05-17 06:04:15,738][00154] Decorrelating experience for 96 frames...
144
+ [2024-05-17 06:04:15,851][00035] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 265.2. Samples: 1326. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
145
+ [2024-05-17 06:04:15,852][00035] Avg episode reward: [(0, '2.625')]
146
+ [2024-05-17 06:04:16,289][00035] Heartbeat connected on Batcher_0
147
+ [2024-05-17 06:04:16,299][00035] Heartbeat connected on InferenceWorker_p0-w0
148
+ [2024-05-17 06:04:16,306][00035] Heartbeat connected on RolloutWorker_w0
149
+ [2024-05-17 06:04:16,315][00035] Heartbeat connected on RolloutWorker_w1
150
+ [2024-05-17 06:04:16,316][00035] Heartbeat connected on RolloutWorker_w2
151
+ [2024-05-17 06:04:16,319][00035] Heartbeat connected on RolloutWorker_w3
152
+ [2024-05-17 06:04:16,324][00035] Heartbeat connected on RolloutWorker_w4
153
+ [2024-05-17 06:04:16,331][00035] Heartbeat connected on RolloutWorker_w6
154
+ [2024-05-17 06:04:16,333][00035] Heartbeat connected on RolloutWorker_w5
155
+ [2024-05-17 06:04:16,337][00035] Heartbeat connected on RolloutWorker_w7
156
+ [2024-05-17 06:04:18,078][00140] Signal inference workers to resume experience collection...
157
+ [2024-05-17 06:04:18,079][00153] InferenceWorker_p0-w0: resuming experience collection
158
+ [2024-05-17 06:04:19,086][00035] Heartbeat connected on LearnerWorker_p0
159
+ [2024-05-17 06:04:20,855][00035] Fps is (10 sec: 2047.1, 60 sec: 2047.1, 300 sec: 2047.1). Total num frames: 20480. Throughput: 0: 560.2. Samples: 5604. Policy #0 lag: (min: 0.0, avg: 0.5, max: 3.0)
160
+ [2024-05-17 06:04:20,857][00035] Avg episode reward: [(0, '3.529')]
161
+ [2024-05-17 06:04:23,434][00153] Updated weights for policy 0, policy_version 10 (0.0020)
162
+ [2024-05-17 06:04:25,850][00035] Fps is (10 sec: 5734.5, 60 sec: 3823.0, 300 sec: 3823.0). Total num frames: 57344. Throughput: 0: 739.6. Samples: 11094. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
163
+ [2024-05-17 06:04:25,852][00035] Avg episode reward: [(0, '4.245')]
164
+ [2024-05-17 06:04:28,564][00153] Updated weights for policy 0, policy_version 20 (0.0020)
165
+ [2024-05-17 06:04:30,851][00035] Fps is (10 sec: 7785.9, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 98304. Throughput: 0: 1156.4. Samples: 23128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
166
+ [2024-05-17 06:04:30,856][00035] Avg episode reward: [(0, '4.448')]
167
+ [2024-05-17 06:04:33,559][00153] Updated weights for policy 0, policy_version 30 (0.0023)
168
+ [2024-05-17 06:04:35,851][00035] Fps is (10 sec: 8191.8, 60 sec: 5570.6, 300 sec: 5570.6). Total num frames: 139264. Throughput: 0: 1409.4. Samples: 35234. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
169
+ [2024-05-17 06:04:35,855][00035] Avg episode reward: [(0, '4.527')]
170
+ [2024-05-17 06:04:35,857][00140] Saving new best policy, reward=4.527!
171
+ [2024-05-17 06:04:38,684][00153] Updated weights for policy 0, policy_version 40 (0.0029)
172
+ [2024-05-17 06:04:40,851][00035] Fps is (10 sec: 8192.0, 60 sec: 6007.5, 300 sec: 6007.5). Total num frames: 180224. Throughput: 0: 1374.9. Samples: 41246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
173
+ [2024-05-17 06:04:40,855][00035] Avg episode reward: [(0, '4.464')]
174
+ [2024-05-17 06:04:43,788][00153] Updated weights for policy 0, policy_version 50 (0.0016)
175
+ [2024-05-17 06:04:45,851][00035] Fps is (10 sec: 7782.3, 60 sec: 6202.5, 300 sec: 6202.5). Total num frames: 217088. Throughput: 0: 1519.6. Samples: 53186. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
176
+ [2024-05-17 06:04:45,852][00035] Avg episode reward: [(0, '4.516')]
177
+ [2024-05-17 06:04:48,801][00153] Updated weights for policy 0, policy_version 60 (0.0030)
178
+ [2024-05-17 06:04:50,850][00035] Fps is (10 sec: 8192.1, 60 sec: 6553.6, 300 sec: 6553.6). Total num frames: 262144. Throughput: 0: 1638.8. Samples: 65550. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
179
+ [2024-05-17 06:04:50,853][00035] Avg episode reward: [(0, '4.474')]
180
+ [2024-05-17 06:04:54,386][00153] Updated weights for policy 0, policy_version 70 (0.0018)
181
+ [2024-05-17 06:04:55,850][00035] Fps is (10 sec: 8192.3, 60 sec: 6644.7, 300 sec: 6644.7). Total num frames: 299008. Throughput: 0: 1571.0. Samples: 70694. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
182
+ [2024-05-17 06:04:55,852][00035] Avg episode reward: [(0, '4.485')]
183
+ [2024-05-17 06:04:59,338][00153] Updated weights for policy 0, policy_version 80 (0.0020)
184
+ [2024-05-17 06:05:00,851][00035] Fps is (10 sec: 7782.3, 60 sec: 6799.4, 300 sec: 6799.4). Total num frames: 339968. Throughput: 0: 1812.0. Samples: 82868. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
185
+ [2024-05-17 06:05:00,854][00035] Avg episode reward: [(0, '4.475')]
186
+ [2024-05-17 06:05:04,730][00153] Updated weights for policy 0, policy_version 90 (0.0017)
187
+ [2024-05-17 06:05:05,850][00035] Fps is (10 sec: 7782.4, 60 sec: 6851.5, 300 sec: 6851.5). Total num frames: 376832. Throughput: 0: 1970.4. Samples: 94264. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
188
+ [2024-05-17 06:05:05,852][00035] Avg episode reward: [(0, '4.327')]
189
+ [2024-05-17 06:05:09,931][00153] Updated weights for policy 0, policy_version 100 (0.0028)
190
+ [2024-05-17 06:05:10,851][00035] Fps is (10 sec: 7372.8, 60 sec: 6894.9, 300 sec: 6894.9). Total num frames: 413696. Throughput: 0: 1981.1. Samples: 100244. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
191
+ [2024-05-17 06:05:10,852][00035] Avg episode reward: [(0, '4.639')]
192
+ [2024-05-17 06:05:10,857][00140] Saving new best policy, reward=4.639!
193
+ [2024-05-17 06:05:14,987][00153] Updated weights for policy 0, policy_version 110 (0.0030)
194
+ [2024-05-17 06:05:15,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7577.6, 300 sec: 6994.7). Total num frames: 454656. Throughput: 0: 1983.3. Samples: 112376. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
195
+ [2024-05-17 06:05:15,852][00035] Avg episode reward: [(0, '4.814')]
196
+ [2024-05-17 06:05:15,854][00140] Saving new best policy, reward=4.814!
197
+ [2024-05-17 06:05:19,984][00153] Updated weights for policy 0, policy_version 120 (0.0015)
198
+ [2024-05-17 06:05:20,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7919.5, 300 sec: 7080.2). Total num frames: 495616. Throughput: 0: 1987.3. Samples: 124662. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
199
+ [2024-05-17 06:05:20,852][00035] Avg episode reward: [(0, '4.671')]
200
+ [2024-05-17 06:05:25,573][00153] Updated weights for policy 0, policy_version 130 (0.0020)
201
+ [2024-05-17 06:05:25,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7099.8). Total num frames: 532480. Throughput: 0: 1987.4. Samples: 130678. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
202
+ [2024-05-17 06:05:25,852][00035] Avg episode reward: [(0, '4.572')]
203
+ [2024-05-17 06:05:30,548][00153] Updated weights for policy 0, policy_version 140 (0.0021)
204
+ [2024-05-17 06:05:30,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7919.0, 300 sec: 7168.0). Total num frames: 573440. Throughput: 0: 1974.5. Samples: 142036. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
205
+ [2024-05-17 06:05:30,852][00035] Avg episode reward: [(0, '4.491')]
206
+ [2024-05-17 06:05:35,434][00153] Updated weights for policy 0, policy_version 150 (0.0024)
207
+ [2024-05-17 06:05:35,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7919.0, 300 sec: 7228.2). Total num frames: 614400. Throughput: 0: 1970.9. Samples: 154240. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
208
+ [2024-05-17 06:05:35,852][00035] Avg episode reward: [(0, '4.522')]
209
+ [2024-05-17 06:05:40,641][00153] Updated weights for policy 0, policy_version 160 (0.0015)
210
+ [2024-05-17 06:05:40,851][00035] Fps is (10 sec: 8191.9, 60 sec: 7918.9, 300 sec: 7281.8). Total num frames: 655360. Throughput: 0: 1991.2. Samples: 160298. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
211
+ [2024-05-17 06:05:40,852][00035] Avg episode reward: [(0, '4.503')]
212
+ [2024-05-17 06:05:45,664][00153] Updated weights for policy 0, policy_version 170 (0.0026)
213
+ [2024-05-17 06:05:45,850][00035] Fps is (10 sec: 8192.1, 60 sec: 7987.2, 300 sec: 7329.7). Total num frames: 696320. Throughput: 0: 1988.8. Samples: 172362. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
214
+ [2024-05-17 06:05:45,852][00035] Avg episode reward: [(0, '4.364')]
215
+ [2024-05-17 06:05:50,850][00035] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 7331.9). Total num frames: 733184. Throughput: 0: 2000.5. Samples: 184286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
216
+ [2024-05-17 06:05:50,853][00035] Avg episode reward: [(0, '4.568')]
217
+ [2024-05-17 06:05:50,872][00153] Updated weights for policy 0, policy_version 180 (0.0025)
218
+ [2024-05-17 06:05:50,875][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth...
219
+ [2024-05-17 06:05:55,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7372.8). Total num frames: 774144. Throughput: 0: 2000.4. Samples: 190260. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
220
+ [2024-05-17 06:05:55,855][00035] Avg episode reward: [(0, '4.728')]
221
+ [2024-05-17 06:05:56,027][00153] Updated weights for policy 0, policy_version 190 (0.0021)
222
+ [2024-05-17 06:06:00,851][00035] Fps is (10 sec: 7782.1, 60 sec: 7850.6, 300 sec: 7372.8). Total num frames: 811008. Throughput: 0: 1980.3. Samples: 201492. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
223
+ [2024-05-17 06:06:00,855][00035] Avg episode reward: [(0, '4.760')]
224
+ [2024-05-17 06:06:01,400][00153] Updated weights for policy 0, policy_version 200 (0.0024)
225
+ [2024-05-17 06:06:05,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7408.4). Total num frames: 851968. Throughput: 0: 1978.8. Samples: 213710. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
226
+ [2024-05-17 06:06:05,856][00035] Avg episode reward: [(0, '4.779')]
227
+ [2024-05-17 06:06:06,466][00153] Updated weights for policy 0, policy_version 210 (0.0026)
228
+ [2024-05-17 06:06:10,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7441.1). Total num frames: 892928. Throughput: 0: 1979.9. Samples: 219772. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
229
+ [2024-05-17 06:06:10,854][00035] Avg episode reward: [(0, '4.816')]
230
+ [2024-05-17 06:06:10,861][00140] Saving new best policy, reward=4.816!
231
+ [2024-05-17 06:06:11,545][00153] Updated weights for policy 0, policy_version 220 (0.0020)
232
+ [2024-05-17 06:06:15,851][00035] Fps is (10 sec: 8191.9, 60 sec: 7987.2, 300 sec: 7471.1). Total num frames: 933888. Throughput: 0: 1999.3. Samples: 232006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
233
+ [2024-05-17 06:06:15,854][00035] Avg episode reward: [(0, '4.674')]
234
+ [2024-05-17 06:06:16,542][00153] Updated weights for policy 0, policy_version 230 (0.0015)
235
+ [2024-05-17 06:06:20,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7498.8). Total num frames: 974848. Throughput: 0: 2001.4. Samples: 244304. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
236
+ [2024-05-17 06:06:20,852][00035] Avg episode reward: [(0, '4.882')]
237
+ [2024-05-17 06:06:20,859][00140] Saving new best policy, reward=4.882!
238
+ [2024-05-17 06:06:21,581][00153] Updated weights for policy 0, policy_version 240 (0.0019)
239
+ [2024-05-17 06:06:25,850][00035] Fps is (10 sec: 8192.2, 60 sec: 8055.5, 300 sec: 7524.5). Total num frames: 1015808. Throughput: 0: 2001.9. Samples: 250384. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
240
+ [2024-05-17 06:06:25,852][00035] Avg episode reward: [(0, '4.818')]
241
+ [2024-05-17 06:06:26,536][00153] Updated weights for policy 0, policy_version 250 (0.0016)
242
+ [2024-05-17 06:06:30,851][00035] Fps is (10 sec: 7782.6, 60 sec: 7987.2, 300 sec: 7519.1). Total num frames: 1052672. Throughput: 0: 1984.1. Samples: 261648. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
243
+ [2024-05-17 06:06:30,854][00035] Avg episode reward: [(0, '5.022')]
244
+ [2024-05-17 06:06:30,860][00140] Saving new best policy, reward=5.022!
245
+ [2024-05-17 06:06:32,110][00153] Updated weights for policy 0, policy_version 260 (0.0023)
246
+ [2024-05-17 06:06:35,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7542.3). Total num frames: 1093632. Throughput: 0: 1990.3. Samples: 273848. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
247
+ [2024-05-17 06:06:35,852][00035] Avg episode reward: [(0, '4.902')]
248
+ [2024-05-17 06:06:37,124][00153] Updated weights for policy 0, policy_version 270 (0.0022)
249
+ [2024-05-17 06:06:40,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7564.0). Total num frames: 1134592. Throughput: 0: 1991.7. Samples: 279888. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
250
+ [2024-05-17 06:06:40,855][00035] Avg episode reward: [(0, '5.238')]
251
+ [2024-05-17 06:06:40,863][00140] Saving new best policy, reward=5.238!
252
+ [2024-05-17 06:06:42,305][00153] Updated weights for policy 0, policy_version 280 (0.0029)
253
+ [2024-05-17 06:06:45,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7557.8). Total num frames: 1171456. Throughput: 0: 2005.7. Samples: 291746. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
254
+ [2024-05-17 06:06:45,855][00035] Avg episode reward: [(0, '5.224')]
255
+ [2024-05-17 06:06:47,400][00153] Updated weights for policy 0, policy_version 290 (0.0025)
256
+ [2024-05-17 06:06:50,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7577.6). Total num frames: 1212416. Throughput: 0: 2004.6. Samples: 303916. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
257
+ [2024-05-17 06:06:50,852][00035] Avg episode reward: [(0, '5.396')]
258
+ [2024-05-17 06:06:50,861][00140] Saving new best policy, reward=5.396!
259
+ [2024-05-17 06:06:52,517][00153] Updated weights for policy 0, policy_version 300 (0.0021)
260
+ [2024-05-17 06:06:55,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7596.2). Total num frames: 1253376. Throughput: 0: 2004.5. Samples: 309972. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
261
+ [2024-05-17 06:06:55,852][00035] Avg episode reward: [(0, '5.484')]
262
+ [2024-05-17 06:06:55,854][00140] Saving new best policy, reward=5.484!
263
+ [2024-05-17 06:06:57,490][00153] Updated weights for policy 0, policy_version 310 (0.0021)
264
+ [2024-05-17 06:07:00,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7613.7). Total num frames: 1294336. Throughput: 0: 2003.6. Samples: 322168. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
265
+ [2024-05-17 06:07:00,855][00035] Avg episode reward: [(0, '6.088')]
266
+ [2024-05-17 06:07:00,864][00140] Saving new best policy, reward=6.088!
267
+ [2024-05-17 06:07:02,998][00153] Updated weights for policy 0, policy_version 320 (0.0021)
268
+ [2024-05-17 06:07:05,851][00035] Fps is (10 sec: 7782.2, 60 sec: 7987.2, 300 sec: 7606.9). Total num frames: 1331200. Throughput: 0: 1979.1. Samples: 333364. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
269
+ [2024-05-17 06:07:05,853][00035] Avg episode reward: [(0, '6.205')]
270
+ [2024-05-17 06:07:05,854][00140] Saving new best policy, reward=6.205!
271
+ [2024-05-17 06:07:08,088][00153] Updated weights for policy 0, policy_version 330 (0.0025)
272
+ [2024-05-17 06:07:10,850][00035] Fps is (10 sec: 7782.5, 60 sec: 7987.2, 300 sec: 7623.1). Total num frames: 1372160. Throughput: 0: 1980.3. Samples: 339496. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
273
+ [2024-05-17 06:07:10,852][00035] Avg episode reward: [(0, '5.807')]
274
+ [2024-05-17 06:07:13,157][00153] Updated weights for policy 0, policy_version 340 (0.0018)
275
+ [2024-05-17 06:07:15,850][00035] Fps is (10 sec: 8192.3, 60 sec: 7987.2, 300 sec: 7638.5). Total num frames: 1413120. Throughput: 0: 1999.5. Samples: 351624. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
276
+ [2024-05-17 06:07:15,852][00035] Avg episode reward: [(0, '5.878')]
277
+ [2024-05-17 06:07:18,178][00153] Updated weights for policy 0, policy_version 350 (0.0018)
278
+ [2024-05-17 06:07:20,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7653.1). Total num frames: 1454080. Throughput: 0: 2002.7. Samples: 363968. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
279
+ [2024-05-17 06:07:20,852][00035] Avg episode reward: [(0, '5.326')]
280
+ [2024-05-17 06:07:23,183][00153] Updated weights for policy 0, policy_version 360 (0.0023)
281
+ [2024-05-17 06:07:25,851][00035] Fps is (10 sec: 8191.9, 60 sec: 7987.2, 300 sec: 7666.9). Total num frames: 1495040. Throughput: 0: 2004.6. Samples: 370094. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
282
+ [2024-05-17 06:07:25,855][00035] Avg episode reward: [(0, '6.135')]
283
+ [2024-05-17 06:07:28,150][00153] Updated weights for policy 0, policy_version 370 (0.0019)
284
+ [2024-05-17 06:07:30,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7680.0). Total num frames: 1536000. Throughput: 0: 2013.4. Samples: 382348. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
285
+ [2024-05-17 06:07:30,852][00035] Avg episode reward: [(0, '5.980')]
286
+ [2024-05-17 06:07:33,478][00153] Updated weights for policy 0, policy_version 380 (0.0016)
287
+ [2024-05-17 06:07:35,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7672.5). Total num frames: 1572864. Throughput: 0: 1995.8. Samples: 393726. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
288
+ [2024-05-17 06:07:35,852][00035] Avg episode reward: [(0, '6.054')]
289
+ [2024-05-17 06:07:38,603][00153] Updated weights for policy 0, policy_version 390 (0.0024)
290
+ [2024-05-17 06:07:40,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7684.9). Total num frames: 1613824. Throughput: 0: 1999.4. Samples: 399946. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
291
+ [2024-05-17 06:07:40,852][00035] Avg episode reward: [(0, '6.208')]
292
+ [2024-05-17 06:07:40,859][00140] Saving new best policy, reward=6.208!
293
+ [2024-05-17 06:07:43,637][00153] Updated weights for policy 0, policy_version 400 (0.0017)
294
+ [2024-05-17 06:07:45,850][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7696.7). Total num frames: 1654784. Throughput: 0: 1994.8. Samples: 411934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
295
+ [2024-05-17 06:07:45,852][00035] Avg episode reward: [(0, '6.015')]
296
+ [2024-05-17 06:07:48,673][00153] Updated weights for policy 0, policy_version 410 (0.0015)
297
+ [2024-05-17 06:07:50,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7707.9). Total num frames: 1695744. Throughput: 0: 2014.3. Samples: 424008. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
298
+ [2024-05-17 06:07:50,853][00035] Avg episode reward: [(0, '6.166')]
299
+ [2024-05-17 06:07:50,861][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000414_1695744.pth...
300
+ [2024-05-17 06:07:53,781][00153] Updated weights for policy 0, policy_version 420 (0.0031)
301
+ [2024-05-17 06:07:55,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7718.7). Total num frames: 1736704. Throughput: 0: 2010.5. Samples: 429970. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
302
+ [2024-05-17 06:07:55,853][00035] Avg episode reward: [(0, '6.566')]
303
+ [2024-05-17 06:07:55,855][00140] Saving new best policy, reward=6.566!
304
+ [2024-05-17 06:07:58,790][00153] Updated weights for policy 0, policy_version 430 (0.0020)
305
+ [2024-05-17 06:08:00,850][00035] Fps is (10 sec: 8192.1, 60 sec: 8055.5, 300 sec: 7729.0). Total num frames: 1777664. Throughput: 0: 2012.6. Samples: 442190. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
306
+ [2024-05-17 06:08:00,855][00035] Avg episode reward: [(0, '5.995')]
307
+ [2024-05-17 06:08:04,232][00153] Updated weights for policy 0, policy_version 440 (0.0016)
308
+ [2024-05-17 06:08:05,851][00035] Fps is (10 sec: 7372.8, 60 sec: 7987.2, 300 sec: 7704.0). Total num frames: 1810432. Throughput: 0: 1984.3. Samples: 453262. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
309
+ [2024-05-17 06:08:05,852][00035] Avg episode reward: [(0, '6.847')]
310
+ [2024-05-17 06:08:05,855][00140] Saving new best policy, reward=6.847!
311
+ [2024-05-17 06:08:09,487][00153] Updated weights for policy 0, policy_version 450 (0.0024)
312
+ [2024-05-17 06:08:10,851][00035] Fps is (10 sec: 7372.8, 60 sec: 7987.2, 300 sec: 7714.1). Total num frames: 1851392. Throughput: 0: 1983.3. Samples: 459342. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
313
+ [2024-05-17 06:08:10,854][00035] Avg episode reward: [(0, '8.208')]
314
+ [2024-05-17 06:08:10,862][00140] Saving new best policy, reward=8.208!
315
+ [2024-05-17 06:08:14,614][00153] Updated weights for policy 0, policy_version 460 (0.0019)
316
+ [2024-05-17 06:08:15,851][00035] Fps is (10 sec: 8191.8, 60 sec: 7987.1, 300 sec: 7723.9). Total num frames: 1892352. Throughput: 0: 1977.6. Samples: 471342. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
317
+ [2024-05-17 06:08:15,853][00035] Avg episode reward: [(0, '9.213')]
318
+ [2024-05-17 06:08:15,855][00140] Saving new best policy, reward=9.213!
319
+ [2024-05-17 06:08:19,738][00153] Updated weights for policy 0, policy_version 470 (0.0016)
320
+ [2024-05-17 06:08:20,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7733.3). Total num frames: 1933312. Throughput: 0: 1994.0. Samples: 483454. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
321
+ [2024-05-17 06:08:20,852][00035] Avg episode reward: [(0, '7.943')]
322
+ [2024-05-17 06:08:24,826][00153] Updated weights for policy 0, policy_version 480 (0.0020)
323
+ [2024-05-17 06:08:25,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7918.9, 300 sec: 7726.2). Total num frames: 1970176. Throughput: 0: 1989.4. Samples: 489470. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
324
+ [2024-05-17 06:08:25,856][00035] Avg episode reward: [(0, '9.662')]
325
+ [2024-05-17 06:08:25,858][00140] Saving new best policy, reward=9.662!
326
+ [2024-05-17 06:08:30,004][00153] Updated weights for policy 0, policy_version 490 (0.0023)
327
+ [2024-05-17 06:08:30,851][00035] Fps is (10 sec: 7782.5, 60 sec: 7918.9, 300 sec: 7735.1). Total num frames: 2011136. Throughput: 0: 1988.8. Samples: 501430. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
328
+ [2024-05-17 06:08:30,855][00035] Avg episode reward: [(0, '11.998')]
329
+ [2024-05-17 06:08:30,862][00140] Saving new best policy, reward=11.998!
330
+ [2024-05-17 06:08:35,065][00153] Updated weights for policy 0, policy_version 500 (0.0024)
331
+ [2024-05-17 06:08:35,851][00035] Fps is (10 sec: 8192.3, 60 sec: 7987.2, 300 sec: 7743.8). Total num frames: 2052096. Throughput: 0: 1987.5. Samples: 513444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
332
+ [2024-05-17 06:08:35,856][00035] Avg episode reward: [(0, '12.595')]
333
+ [2024-05-17 06:08:35,858][00140] Saving new best policy, reward=12.595!
334
+ [2024-05-17 06:08:40,547][00153] Updated weights for policy 0, policy_version 510 (0.0016)
335
+ [2024-05-17 06:08:40,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7918.9, 300 sec: 7736.9). Total num frames: 2088960. Throughput: 0: 1971.6. Samples: 518690. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
336
+ [2024-05-17 06:08:40,852][00035] Avg episode reward: [(0, '12.461')]
337
+ [2024-05-17 06:08:45,794][00153] Updated weights for policy 0, policy_version 520 (0.0021)
338
+ [2024-05-17 06:08:45,850][00035] Fps is (10 sec: 7782.5, 60 sec: 7918.9, 300 sec: 7745.2). Total num frames: 2129920. Throughput: 0: 1965.2. Samples: 530622. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
339
+ [2024-05-17 06:08:45,852][00035] Avg episode reward: [(0, '12.327')]
340
+ [2024-05-17 06:08:50,726][00153] Updated weights for policy 0, policy_version 530 (0.0018)
341
+ [2024-05-17 06:08:50,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7753.1). Total num frames: 2170880. Throughput: 0: 1992.0. Samples: 542904. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
342
+ [2024-05-17 06:08:50,852][00035] Avg episode reward: [(0, '11.491')]
343
+ [2024-05-17 06:08:55,765][00153] Updated weights for policy 0, policy_version 540 (0.0020)
344
+ [2024-05-17 06:08:55,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7760.8). Total num frames: 2211840. Throughput: 0: 1992.1. Samples: 548986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
345
+ [2024-05-17 06:08:55,852][00035] Avg episode reward: [(0, '11.941')]
346
+ [2024-05-17 06:09:00,794][00153] Updated weights for policy 0, policy_version 550 (0.0020)
347
+ [2024-05-17 06:09:00,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7768.3). Total num frames: 2252800. Throughput: 0: 1995.0. Samples: 561116. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
348
+ [2024-05-17 06:09:00,855][00035] Avg episode reward: [(0, '13.207')]
349
+ [2024-05-17 06:09:00,861][00140] Saving new best policy, reward=13.207!
350
+ [2024-05-17 06:09:05,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7761.6). Total num frames: 2289664. Throughput: 0: 1994.4. Samples: 573204. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
351
+ [2024-05-17 06:09:05,853][00035] Avg episode reward: [(0, '14.667')]
352
+ [2024-05-17 06:09:05,854][00140] Saving new best policy, reward=14.667!
353
+ [2024-05-17 06:09:06,050][00153] Updated weights for policy 0, policy_version 560 (0.0016)
354
+ [2024-05-17 06:09:10,851][00035] Fps is (10 sec: 7372.7, 60 sec: 7918.9, 300 sec: 7886.5). Total num frames: 2326528. Throughput: 0: 1981.6. Samples: 578642. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
355
+ [2024-05-17 06:09:10,856][00035] Avg episode reward: [(0, '14.416')]
356
+ [2024-05-17 06:09:11,584][00153] Updated weights for policy 0, policy_version 570 (0.0025)
357
+ [2024-05-17 06:09:15,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7919.0, 300 sec: 7956.1). Total num frames: 2367488. Throughput: 0: 1969.5. Samples: 590056. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
358
+ [2024-05-17 06:09:15,852][00035] Avg episode reward: [(0, '14.208')]
359
+ [2024-05-17 06:09:16,827][00153] Updated weights for policy 0, policy_version 580 (0.0017)
360
+ [2024-05-17 06:09:20,851][00035] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 7956.0). Total num frames: 2404352. Throughput: 0: 1967.8. Samples: 601994. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
361
+ [2024-05-17 06:09:20,854][00035] Avg episode reward: [(0, '12.438')]
362
+ [2024-05-17 06:09:21,889][00153] Updated weights for policy 0, policy_version 590 (0.0021)
363
+ [2024-05-17 06:09:25,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7919.0, 300 sec: 7956.0). Total num frames: 2445312. Throughput: 0: 1982.7. Samples: 607912. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
364
+ [2024-05-17 06:09:25,853][00035] Avg episode reward: [(0, '14.737')]
365
+ [2024-05-17 06:09:25,856][00140] Saving new best policy, reward=14.737!
366
+ [2024-05-17 06:09:27,102][00153] Updated weights for policy 0, policy_version 600 (0.0015)
367
+ [2024-05-17 06:09:30,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7956.0). Total num frames: 2486272. Throughput: 0: 1981.7. Samples: 619798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
368
+ [2024-05-17 06:09:30,853][00035] Avg episode reward: [(0, '16.054')]
369
+ [2024-05-17 06:09:30,860][00140] Saving new best policy, reward=16.054!
370
+ [2024-05-17 06:09:32,252][00153] Updated weights for policy 0, policy_version 610 (0.0015)
371
+ [2024-05-17 06:09:35,850][00035] Fps is (10 sec: 7782.5, 60 sec: 7850.7, 300 sec: 7942.1). Total num frames: 2523136. Throughput: 0: 1972.6. Samples: 631670. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
372
+ [2024-05-17 06:09:35,852][00035] Avg episode reward: [(0, '15.161')]
373
+ [2024-05-17 06:09:37,470][00153] Updated weights for policy 0, policy_version 620 (0.0023)
374
+ [2024-05-17 06:09:40,851][00035] Fps is (10 sec: 7782.0, 60 sec: 7918.9, 300 sec: 7956.0). Total num frames: 2564096. Throughput: 0: 1971.2. Samples: 637692. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
375
+ [2024-05-17 06:09:40,853][00035] Avg episode reward: [(0, '18.281')]
376
+ [2024-05-17 06:09:40,861][00140] Saving new best policy, reward=18.281!
377
+ [2024-05-17 06:09:43,009][00153] Updated weights for policy 0, policy_version 630 (0.0017)
378
+ [2024-05-17 06:09:45,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7850.7, 300 sec: 7928.2). Total num frames: 2600960. Throughput: 0: 1945.8. Samples: 648676. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
379
+ [2024-05-17 06:09:45,855][00035] Avg episode reward: [(0, '19.968')]
380
+ [2024-05-17 06:09:45,857][00140] Saving new best policy, reward=19.968!
381
+ [2024-05-17 06:09:48,191][00153] Updated weights for policy 0, policy_version 640 (0.0018)
382
+ [2024-05-17 06:09:50,850][00035] Fps is (10 sec: 7782.8, 60 sec: 7850.7, 300 sec: 7942.1). Total num frames: 2641920. Throughput: 0: 1942.1. Samples: 660598. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
383
+ [2024-05-17 06:09:50,855][00035] Avg episode reward: [(0, '17.637')]
384
+ [2024-05-17 06:09:50,862][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000645_2641920.pth...
385
+ [2024-05-17 06:09:50,956][00140] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000180_737280.pth
386
+ [2024-05-17 06:09:53,357][00153] Updated weights for policy 0, policy_version 650 (0.0015)
387
+ [2024-05-17 06:09:55,850][00035] Fps is (10 sec: 7782.5, 60 sec: 7782.4, 300 sec: 7928.2). Total num frames: 2678784. Throughput: 0: 1954.6. Samples: 666598. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
388
+ [2024-05-17 06:09:55,855][00035] Avg episode reward: [(0, '18.721')]
389
+ [2024-05-17 06:09:58,443][00153] Updated weights for policy 0, policy_version 660 (0.0018)
390
+ [2024-05-17 06:10:00,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7782.4, 300 sec: 7942.1). Total num frames: 2719744. Throughput: 0: 1968.9. Samples: 678658. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
391
+ [2024-05-17 06:10:00,855][00035] Avg episode reward: [(0, '22.213')]
392
+ [2024-05-17 06:10:00,862][00140] Saving new best policy, reward=22.213!
393
+ [2024-05-17 06:10:03,499][00153] Updated weights for policy 0, policy_version 670 (0.0026)
394
+ [2024-05-17 06:10:05,851][00035] Fps is (10 sec: 8191.8, 60 sec: 7850.6, 300 sec: 7956.0). Total num frames: 2760704. Throughput: 0: 1972.7. Samples: 690768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
395
+ [2024-05-17 06:10:05,853][00035] Avg episode reward: [(0, '24.976')]
396
+ [2024-05-17 06:10:05,854][00140] Saving new best policy, reward=24.976!
397
+ [2024-05-17 06:10:08,653][00153] Updated weights for policy 0, policy_version 680 (0.0016)
398
+ [2024-05-17 06:10:10,851][00035] Fps is (10 sec: 8191.9, 60 sec: 7918.9, 300 sec: 7956.0). Total num frames: 2801664. Throughput: 0: 1975.4. Samples: 696804. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
399
+ [2024-05-17 06:10:10,852][00035] Avg episode reward: [(0, '25.233')]
400
+ [2024-05-17 06:10:10,859][00140] Saving new best policy, reward=25.233!
401
+ [2024-05-17 06:10:14,295][00153] Updated weights for policy 0, policy_version 690 (0.0016)
402
+ [2024-05-17 06:10:15,850][00035] Fps is (10 sec: 7782.6, 60 sec: 7850.7, 300 sec: 7942.1). Total num frames: 2838528. Throughput: 0: 1953.1. Samples: 707688. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
403
+ [2024-05-17 06:10:15,852][00035] Avg episode reward: [(0, '24.850')]
404
+ [2024-05-17 06:10:19,274][00153] Updated weights for policy 0, policy_version 700 (0.0017)
405
+ [2024-05-17 06:10:20,851][00035] Fps is (10 sec: 7782.6, 60 sec: 7918.9, 300 sec: 7956.0). Total num frames: 2879488. Throughput: 0: 1959.9. Samples: 719866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
406
+ [2024-05-17 06:10:20,853][00035] Avg episode reward: [(0, '22.118')]
407
+ [2024-05-17 06:10:24,348][00153] Updated weights for policy 0, policy_version 710 (0.0015)
408
+ [2024-05-17 06:10:25,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 7942.1). Total num frames: 2916352. Throughput: 0: 1961.8. Samples: 725970. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
409
+ [2024-05-17 06:10:25,852][00035] Avg episode reward: [(0, '21.601')]
410
+ [2024-05-17 06:10:29,485][00153] Updated weights for policy 0, policy_version 720 (0.0020)
411
+ [2024-05-17 06:10:30,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7850.7, 300 sec: 7942.1). Total num frames: 2957312. Throughput: 0: 1985.6. Samples: 738028. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
412
+ [2024-05-17 06:10:30,852][00035] Avg episode reward: [(0, '20.622')]
413
+ [2024-05-17 06:10:34,488][00153] Updated weights for policy 0, policy_version 730 (0.0019)
414
+ [2024-05-17 06:10:35,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7918.9, 300 sec: 7942.1). Total num frames: 2998272. Throughput: 0: 1992.2. Samples: 750246. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
415
+ [2024-05-17 06:10:35,852][00035] Avg episode reward: [(0, '20.143')]
416
+ [2024-05-17 06:10:39,467][00153] Updated weights for policy 0, policy_version 740 (0.0031)
417
+ [2024-05-17 06:10:40,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7919.0, 300 sec: 7942.1). Total num frames: 3039232. Throughput: 0: 1996.4. Samples: 756436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
418
+ [2024-05-17 06:10:40,852][00035] Avg episode reward: [(0, '19.925')]
419
+ [2024-05-17 06:10:44,958][00153] Updated weights for policy 0, policy_version 750 (0.0017)
420
+ [2024-05-17 06:10:45,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7918.9, 300 sec: 7942.1). Total num frames: 3076096. Throughput: 0: 1983.9. Samples: 767934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
421
+ [2024-05-17 06:10:45,852][00035] Avg episode reward: [(0, '21.490')]
422
+ [2024-05-17 06:10:50,100][00153] Updated weights for policy 0, policy_version 760 (0.0017)
423
+ [2024-05-17 06:10:50,851][00035] Fps is (10 sec: 7782.5, 60 sec: 7918.9, 300 sec: 7942.1). Total num frames: 3117056. Throughput: 0: 1978.3. Samples: 779792. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
424
+ [2024-05-17 06:10:50,855][00035] Avg episode reward: [(0, '23.507')]
425
+ [2024-05-17 06:10:55,134][00153] Updated weights for policy 0, policy_version 770 (0.0016)
426
+ [2024-05-17 06:10:55,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3158016. Throughput: 0: 1981.3. Samples: 785964. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
427
+ [2024-05-17 06:10:55,852][00035] Avg episode reward: [(0, '22.066')]
428
+ [2024-05-17 06:11:00,044][00153] Updated weights for policy 0, policy_version 780 (0.0021)
429
+ [2024-05-17 06:11:00,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3198976. Throughput: 0: 2013.1. Samples: 798276. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
430
+ [2024-05-17 06:11:00,854][00035] Avg episode reward: [(0, '19.856')]
431
+ [2024-05-17 06:11:05,132][00153] Updated weights for policy 0, policy_version 790 (0.0024)
432
+ [2024-05-17 06:11:05,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3239936. Throughput: 0: 2012.8. Samples: 810440. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
433
+ [2024-05-17 06:11:05,852][00035] Avg episode reward: [(0, '22.541')]
434
+ [2024-05-17 06:11:10,118][00153] Updated weights for policy 0, policy_version 800 (0.0016)
435
+ [2024-05-17 06:11:10,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3280896. Throughput: 0: 2012.9. Samples: 816550. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
436
+ [2024-05-17 06:11:10,853][00035] Avg episode reward: [(0, '23.306')]
437
+ [2024-05-17 06:11:15,180][00153] Updated weights for policy 0, policy_version 810 (0.0018)
438
+ [2024-05-17 06:11:15,858][00035] Fps is (10 sec: 8186.0, 60 sec: 8054.5, 300 sec: 7955.8). Total num frames: 3321856. Throughput: 0: 2015.5. Samples: 828742. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
439
+ [2024-05-17 06:11:15,860][00035] Avg episode reward: [(0, '24.237')]
440
+ [2024-05-17 06:11:20,557][00153] Updated weights for policy 0, policy_version 820 (0.0023)
441
+ [2024-05-17 06:11:20,851][00035] Fps is (10 sec: 7782.3, 60 sec: 7987.2, 300 sec: 7942.1). Total num frames: 3358720. Throughput: 0: 1997.5. Samples: 840132. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
442
+ [2024-05-17 06:11:20,855][00035] Avg episode reward: [(0, '24.361')]
443
+ [2024-05-17 06:11:25,588][00153] Updated weights for policy 0, policy_version 830 (0.0023)
444
+ [2024-05-17 06:11:25,851][00035] Fps is (10 sec: 7788.1, 60 sec: 8055.5, 300 sec: 7956.0). Total num frames: 3399680. Throughput: 0: 1995.8. Samples: 846246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
445
+ [2024-05-17 06:11:25,855][00035] Avg episode reward: [(0, '24.772')]
446
+ [2024-05-17 06:11:30,557][00153] Updated weights for policy 0, policy_version 840 (0.0024)
447
+ [2024-05-17 06:11:30,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7956.0). Total num frames: 3440640. Throughput: 0: 2012.1. Samples: 858478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
448
+ [2024-05-17 06:11:30,852][00035] Avg episode reward: [(0, '23.976')]
449
+ [2024-05-17 06:11:35,540][00153] Updated weights for policy 0, policy_version 850 (0.0025)
450
+ [2024-05-17 06:11:35,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8055.5, 300 sec: 7956.0). Total num frames: 3481600. Throughput: 0: 2022.4. Samples: 870798. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
451
+ [2024-05-17 06:11:35,853][00035] Avg episode reward: [(0, '23.335')]
452
+ [2024-05-17 06:11:40,612][00153] Updated weights for policy 0, policy_version 860 (0.0027)
453
+ [2024-05-17 06:11:40,850][00035] Fps is (10 sec: 8192.1, 60 sec: 8055.5, 300 sec: 7969.8). Total num frames: 3522560. Throughput: 0: 2021.9. Samples: 876950. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
454
+ [2024-05-17 06:11:40,852][00035] Avg episode reward: [(0, '22.927')]
455
+ [2024-05-17 06:11:45,781][00153] Updated weights for policy 0, policy_version 870 (0.0021)
456
+ [2024-05-17 06:11:45,851][00035] Fps is (10 sec: 8192.0, 60 sec: 8123.7, 300 sec: 7969.8). Total num frames: 3563520. Throughput: 0: 2015.7. Samples: 888984. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
457
+ [2024-05-17 06:11:45,852][00035] Avg episode reward: [(0, '22.753')]
458
+ [2024-05-17 06:11:50,851][00035] Fps is (10 sec: 7782.4, 60 sec: 8055.5, 300 sec: 7956.0). Total num frames: 3600384. Throughput: 0: 1993.2. Samples: 900132. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
459
+ [2024-05-17 06:11:50,853][00035] Avg episode reward: [(0, '23.432')]
460
+ [2024-05-17 06:11:50,862][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000879_3600384.pth...
461
+ [2024-05-17 06:11:50,969][00140] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000414_1695744.pth
462
+ [2024-05-17 06:11:51,369][00153] Updated weights for policy 0, policy_version 880 (0.0021)
463
+ [2024-05-17 06:11:55,850][00035] Fps is (10 sec: 7372.8, 60 sec: 7987.2, 300 sec: 7942.1). Total num frames: 3637248. Throughput: 0: 1990.6. Samples: 906126. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
464
+ [2024-05-17 06:11:55,853][00035] Avg episode reward: [(0, '23.944')]
465
+ [2024-05-17 06:11:56,382][00153] Updated weights for policy 0, policy_version 890 (0.0033)
466
+ [2024-05-17 06:12:00,851][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3678208. Throughput: 0: 1991.5. Samples: 918346. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
467
+ [2024-05-17 06:12:00,852][00035] Avg episode reward: [(0, '24.289')]
468
+ [2024-05-17 06:12:01,394][00153] Updated weights for policy 0, policy_version 900 (0.0019)
469
+ [2024-05-17 06:12:05,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3719168. Throughput: 0: 2009.5. Samples: 930558. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
470
+ [2024-05-17 06:12:05,852][00035] Avg episode reward: [(0, '23.688')]
471
+ [2024-05-17 06:12:06,374][00153] Updated weights for policy 0, policy_version 910 (0.0026)
472
+ [2024-05-17 06:12:10,851][00035] Fps is (10 sec: 8601.6, 60 sec: 8055.5, 300 sec: 7969.8). Total num frames: 3764224. Throughput: 0: 2012.7. Samples: 936818. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
473
+ [2024-05-17 06:12:10,852][00035] Avg episode reward: [(0, '23.088')]
474
+ [2024-05-17 06:12:11,271][00153] Updated weights for policy 0, policy_version 920 (0.0016)
475
+ [2024-05-17 06:12:15,850][00035] Fps is (10 sec: 8192.0, 60 sec: 7988.2, 300 sec: 7956.0). Total num frames: 3801088. Throughput: 0: 2012.3. Samples: 949032. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
476
+ [2024-05-17 06:12:15,853][00035] Avg episode reward: [(0, '23.329')]
477
+ [2024-05-17 06:12:16,465][00153] Updated weights for policy 0, policy_version 930 (0.0021)
478
+ [2024-05-17 06:12:20,850][00035] Fps is (10 sec: 7782.5, 60 sec: 8055.5, 300 sec: 7956.0). Total num frames: 3842048. Throughput: 0: 1997.0. Samples: 960664. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
479
+ [2024-05-17 06:12:20,854][00035] Avg episode reward: [(0, '23.216')]
480
+ [2024-05-17 06:12:21,933][00153] Updated weights for policy 0, policy_version 940 (0.0024)
481
+ [2024-05-17 06:12:25,850][00035] Fps is (10 sec: 7782.4, 60 sec: 7987.2, 300 sec: 7942.1). Total num frames: 3878912. Throughput: 0: 1985.9. Samples: 966316. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
482
+ [2024-05-17 06:12:25,852][00035] Avg episode reward: [(0, '25.377')]
483
+ [2024-05-17 06:12:25,855][00140] Saving new best policy, reward=25.377!
484
+ [2024-05-17 06:12:27,072][00153] Updated weights for policy 0, policy_version 950 (0.0026)
485
+ [2024-05-17 06:12:30,851][00035] Fps is (10 sec: 7782.1, 60 sec: 7987.2, 300 sec: 7955.9). Total num frames: 3919872. Throughput: 0: 1986.8. Samples: 978390. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
486
+ [2024-05-17 06:12:30,855][00035] Avg episode reward: [(0, '26.015')]
487
+ [2024-05-17 06:12:30,864][00140] Saving new best policy, reward=26.015!
488
+ [2024-05-17 06:12:32,041][00153] Updated weights for policy 0, policy_version 960 (0.0023)
489
+ [2024-05-17 06:12:35,851][00035] Fps is (10 sec: 8192.0, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 3960832. Throughput: 0: 2010.6. Samples: 990608. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
490
+ [2024-05-17 06:12:35,852][00035] Avg episode reward: [(0, '25.582')]
491
+ [2024-05-17 06:12:37,150][00153] Updated weights for policy 0, policy_version 970 (0.0020)
492
+ [2024-05-17 06:12:40,851][00035] Fps is (10 sec: 8192.3, 60 sec: 7987.2, 300 sec: 7956.0). Total num frames: 4001792. Throughput: 0: 2014.0. Samples: 996754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
493
+ [2024-05-17 06:12:40,852][00035] Avg episode reward: [(0, '26.560')]
494
+ [2024-05-17 06:12:40,860][00140] Saving new best policy, reward=26.560!
495
+ [2024-05-17 06:12:41,146][00140] Stopping Batcher_0...
496
+ [2024-05-17 06:12:41,146][00140] Loop batcher_evt_loop terminating...
497
+ [2024-05-17 06:12:41,149][00035] Component Batcher_0 stopped!
498
+ [2024-05-17 06:12:41,155][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
499
+ [2024-05-17 06:12:41,165][00035] Component RolloutWorker_w4 stopped!
500
+ [2024-05-17 06:12:41,167][00157] Stopping RolloutWorker_w3...
501
+ [2024-05-17 06:12:41,167][00035] Component RolloutWorker_w3 stopped!
502
+ [2024-05-17 06:12:41,172][00155] Stopping RolloutWorker_w0...
503
+ [2024-05-17 06:12:41,173][00155] Loop rollout_proc0_evt_loop terminating...
504
+ [2024-05-17 06:12:41,172][00035] Component RolloutWorker_w0 stopped!
505
+ [2024-05-17 06:12:41,174][00160] Stopping RolloutWorker_w6...
506
+ [2024-05-17 06:12:41,164][00158] Stopping RolloutWorker_w4...
507
+ [2024-05-17 06:12:41,172][00156] Stopping RolloutWorker_w2...
508
+ [2024-05-17 06:12:41,174][00035] Component RolloutWorker_w2 stopped!
509
+ [2024-05-17 06:12:41,177][00158] Loop rollout_proc4_evt_loop terminating...
510
+ [2024-05-17 06:12:41,177][00035] Component RolloutWorker_w6 stopped!
511
+ [2024-05-17 06:12:41,178][00160] Loop rollout_proc6_evt_loop terminating...
512
+ [2024-05-17 06:12:41,177][00156] Loop rollout_proc2_evt_loop terminating...
513
+ [2024-05-17 06:12:41,168][00157] Loop rollout_proc3_evt_loop terminating...
514
+ [2024-05-17 06:12:41,183][00035] Component RolloutWorker_w7 stopped!
515
+ [2024-05-17 06:12:41,184][00035] Component RolloutWorker_w5 stopped!
516
+ [2024-05-17 06:12:41,183][00161] Stopping RolloutWorker_w7...
517
+ [2024-05-17 06:12:41,188][00161] Loop rollout_proc7_evt_loop terminating...
518
+ [2024-05-17 06:12:41,189][00154] Stopping RolloutWorker_w1...
519
+ [2024-05-17 06:12:41,190][00154] Loop rollout_proc1_evt_loop terminating...
520
+ [2024-05-17 06:12:41,183][00159] Stopping RolloutWorker_w5...
521
+ [2024-05-17 06:12:41,189][00035] Component RolloutWorker_w1 stopped!
522
+ [2024-05-17 06:12:41,191][00159] Loop rollout_proc5_evt_loop terminating...
523
+ [2024-05-17 06:12:41,207][00153] Weights refcount: 2 0
524
+ [2024-05-17 06:12:41,213][00153] Stopping InferenceWorker_p0-w0...
525
+ [2024-05-17 06:12:41,213][00153] Loop inference_proc0-0_evt_loop terminating...
526
+ [2024-05-17 06:12:41,213][00035] Component InferenceWorker_p0-w0 stopped!
527
+ [2024-05-17 06:12:41,264][00140] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000645_2641920.pth
528
+ [2024-05-17 06:12:41,276][00140] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
529
+ [2024-05-17 06:12:41,393][00140] Stopping LearnerWorker_p0...
530
+ [2024-05-17 06:12:41,394][00140] Loop learner_proc0_evt_loop terminating...
531
+ [2024-05-17 06:12:41,393][00035] Component LearnerWorker_p0 stopped!
532
+ [2024-05-17 06:12:41,398][00035] Waiting for process learner_proc0 to stop...
533
+ [2024-05-17 06:12:42,824][00035] Waiting for process inference_proc0-0 to join...
534
+ [2024-05-17 06:12:42,826][00035] Waiting for process rollout_proc0 to join...
535
+ [2024-05-17 06:12:43,111][00035] Waiting for process rollout_proc1 to join...
536
+ [2024-05-17 06:12:43,330][00035] Waiting for process rollout_proc2 to join...
537
+ [2024-05-17 06:12:43,332][00035] Waiting for process rollout_proc3 to join...
538
+ [2024-05-17 06:12:43,333][00035] Waiting for process rollout_proc4 to join...
539
+ [2024-05-17 06:12:43,334][00035] Waiting for process rollout_proc5 to join...
540
+ [2024-05-17 06:12:43,335][00035] Waiting for process rollout_proc6 to join...
541
+ [2024-05-17 06:12:43,336][00035] Waiting for process rollout_proc7 to join...
542
+ [2024-05-17 06:12:43,338][00035] Batcher 0 profile tree view:
543
+ batching: 20.7267, releasing_batches: 0.0320
544
+ [2024-05-17 06:12:43,339][00035] InferenceWorker_p0-w0 profile tree view:
545
+ wait_policy: 0.0038
546
+ wait_policy_total: 46.2032
547
+ update_model: 8.3692
548
+ weight_update: 0.0019
549
+ one_step: 0.0031
550
+ handle_policy_step: 419.0435
551
+ deserialize: 20.2187, stack: 3.5514, obs_to_device_normalize: 104.3731, forward: 187.9854, send_messages: 29.4632
552
+ prepare_outputs: 47.5728
553
+ to_cpu: 28.3442
554
+ [2024-05-17 06:12:43,340][00035] Learner 0 profile tree view:
555
+ misc: 0.0067, prepare_batch: 12.6203
556
+ train: 61.2800
557
+ epoch_init: 0.0063, minibatch_init: 0.0067, losses_postprocess: 0.5641, kl_divergence: 0.5514, after_optimizer: 29.1803
558
+ calculate_losses: 20.8635
559
+ losses_init: 0.0043, forward_head: 0.8469, bptt_initial: 14.2874, tail: 0.8249, advantages_returns: 0.2451, losses: 2.8107
560
+ bptt: 1.6347
561
+ bptt_forward_core: 1.5204
562
+ update: 9.6189
563
+ clip: 0.9329
564
+ [2024-05-17 06:12:43,341][00035] RolloutWorker_w0 profile tree view:
565
+ wait_for_trajectories: 0.2433, enqueue_policy_requests: 10.9768, env_step: 303.5729, overhead: 8.0292, complete_rollouts: 2.2358
566
+ save_policy_outputs: 15.4290
567
+ split_output_tensors: 5.5474
568
+ [2024-05-17 06:12:43,342][00035] RolloutWorker_w7 profile tree view:
569
+ wait_for_trajectories: 0.2392, enqueue_policy_requests: 10.8111, env_step: 305.1350, overhead: 8.1960, complete_rollouts: 2.6916
570
+ save_policy_outputs: 15.4548
571
+ split_output_tensors: 5.5618
572
+ [2024-05-17 06:12:43,343][00035] Loop Runner_EvtLoop terminating...
573
+ [2024-05-17 06:12:43,345][00035] Runner profile tree view:
574
+ main_loop: 527.0088
575
+ [2024-05-17 06:12:43,346][00035] Collected {0: 4005888}, FPS: 7601.2
576
+ [2024-05-17 06:12:43,398][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
577
+ [2024-05-17 06:12:43,399][00035] Overriding arg 'num_workers' with value 1 passed from command line
578
+ [2024-05-17 06:12:43,400][00035] Adding new argument 'no_render'=True that is not in the saved config file!
579
+ [2024-05-17 06:12:43,402][00035] Adding new argument 'save_video'=True that is not in the saved config file!
580
+ [2024-05-17 06:12:43,402][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
581
+ [2024-05-17 06:12:43,404][00035] Adding new argument 'video_name'=None that is not in the saved config file!
582
+ [2024-05-17 06:12:43,405][00035] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
583
+ [2024-05-17 06:12:43,406][00035] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
584
+ [2024-05-17 06:12:43,407][00035] Adding new argument 'push_to_hub'=True that is not in the saved config file!
585
+ [2024-05-17 06:12:43,407][00035] Adding new argument 'hf_repository'='jaymanvirk/ppo_sample_factory_doom_health_gathering_supreme' that is not in the saved config file!
586
+ [2024-05-17 06:12:43,408][00035] Adding new argument 'policy_index'=0 that is not in the saved config file!
587
+ [2024-05-17 06:12:43,409][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
588
+ [2024-05-17 06:12:43,411][00035] Adding new argument 'train_script'=None that is not in the saved config file!
589
+ [2024-05-17 06:12:43,412][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file!
590
+ [2024-05-17 06:12:43,413][00035] Using frameskip 1 and render_action_repeat=4 for evaluation
591
+ [2024-05-17 06:12:43,441][00035] Doom resolution: 160x120, resize resolution: (128, 72)
592
+ [2024-05-17 06:12:43,445][00035] RunningMeanStd input shape: (3, 72, 128)
593
+ [2024-05-17 06:12:43,446][00035] RunningMeanStd input shape: (1,)
594
+ [2024-05-17 06:12:43,463][00035] ConvEncoder: input_channels=3
595
+ [2024-05-17 06:12:43,588][00035] Conv encoder output size: 512
596
+ [2024-05-17 06:12:43,590][00035] Policy head output size: 512
597
+ [2024-05-17 06:12:43,794][00035] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
598
+ [2024-05-17 06:12:44,655][00035] Num frames 100...
599
+ [2024-05-17 06:12:44,790][00035] Num frames 200...
600
+ [2024-05-17 06:12:44,926][00035] Num frames 300...
601
+ [2024-05-17 06:12:45,075][00035] Num frames 400...
602
+ [2024-05-17 06:12:45,228][00035] Num frames 500...
603
+ [2024-05-17 06:12:45,384][00035] Num frames 600...
604
+ [2024-05-17 06:12:45,518][00035] Num frames 700...
605
+ [2024-05-17 06:12:45,655][00035] Num frames 800...
606
+ [2024-05-17 06:12:45,794][00035] Num frames 900...
607
+ [2024-05-17 06:12:45,934][00035] Num frames 1000...
608
+ [2024-05-17 06:12:46,073][00035] Num frames 1100...
609
+ [2024-05-17 06:12:46,211][00035] Num frames 1200...
610
+ [2024-05-17 06:12:46,353][00035] Num frames 1300...
611
+ [2024-05-17 06:12:46,491][00035] Num frames 1400...
612
+ [2024-05-17 06:12:46,626][00035] Num frames 1500...
613
+ [2024-05-17 06:12:46,686][00035] Avg episode rewards: #0: 40.040, true rewards: #0: 15.040
614
+ [2024-05-17 06:12:46,687][00035] Avg episode reward: 40.040, avg true_objective: 15.040
615
+ [2024-05-17 06:12:46,819][00035] Num frames 1600...
616
+ [2024-05-17 06:12:46,955][00035] Num frames 1700...
617
+ [2024-05-17 06:12:47,093][00035] Num frames 1800...
618
+ [2024-05-17 06:12:47,248][00035] Num frames 1900...
619
+ [2024-05-17 06:12:47,384][00035] Num frames 2000...
620
+ [2024-05-17 06:12:47,517][00035] Num frames 2100...
621
+ [2024-05-17 06:12:47,589][00035] Avg episode rewards: #0: 26.560, true rewards: #0: 10.560
622
+ [2024-05-17 06:12:47,590][00035] Avg episode reward: 26.560, avg true_objective: 10.560
623
+ [2024-05-17 06:12:47,709][00035] Num frames 2200...
624
+ [2024-05-17 06:12:47,843][00035] Num frames 2300...
625
+ [2024-05-17 06:12:47,978][00035] Num frames 2400...
626
+ [2024-05-17 06:12:48,111][00035] Num frames 2500...
627
+ [2024-05-17 06:12:48,246][00035] Num frames 2600...
628
+ [2024-05-17 06:12:48,384][00035] Num frames 2700...
629
+ [2024-05-17 06:12:48,524][00035] Num frames 2800...
630
+ [2024-05-17 06:12:48,664][00035] Num frames 2900...
631
+ [2024-05-17 06:12:48,797][00035] Num frames 3000...
632
+ [2024-05-17 06:12:48,931][00035] Num frames 3100...
633
+ [2024-05-17 06:12:49,065][00035] Num frames 3200...
634
+ [2024-05-17 06:12:49,247][00035] Avg episode rewards: #0: 27.643, true rewards: #0: 10.977
635
+ [2024-05-17 06:12:49,249][00035] Avg episode reward: 27.643, avg true_objective: 10.977
636
+ [2024-05-17 06:12:49,260][00035] Num frames 3300...
637
+ [2024-05-17 06:12:49,394][00035] Num frames 3400...
638
+ [2024-05-17 06:12:49,529][00035] Num frames 3500...
639
+ [2024-05-17 06:12:49,666][00035] Num frames 3600...
640
+ [2024-05-17 06:12:49,798][00035] Num frames 3700...
641
+ [2024-05-17 06:12:49,932][00035] Num frames 3800...
642
+ [2024-05-17 06:12:50,063][00035] Num frames 3900...
643
+ [2024-05-17 06:12:50,201][00035] Num frames 4000...
644
+ [2024-05-17 06:12:50,343][00035] Num frames 4100...
645
+ [2024-05-17 06:12:50,480][00035] Num frames 4200...
646
+ [2024-05-17 06:12:50,617][00035] Num frames 4300...
647
+ [2024-05-17 06:12:50,753][00035] Num frames 4400...
648
+ [2024-05-17 06:12:50,894][00035] Num frames 4500...
649
+ [2024-05-17 06:12:51,034][00035] Num frames 4600...
650
+ [2024-05-17 06:12:51,175][00035] Num frames 4700...
651
+ [2024-05-17 06:12:51,315][00035] Num frames 4800...
652
+ [2024-05-17 06:12:51,460][00035] Num frames 4900...
653
+ [2024-05-17 06:12:51,628][00035] Num frames 5000...
654
+ [2024-05-17 06:12:51,779][00035] Num frames 5100...
655
+ [2024-05-17 06:12:51,944][00035] Num frames 5200...
656
+ [2024-05-17 06:12:52,104][00035] Avg episode rewards: #0: 33.680, true rewards: #0: 13.180
657
+ [2024-05-17 06:12:52,106][00035] Avg episode reward: 33.680, avg true_objective: 13.180
658
+ [2024-05-17 06:12:52,148][00035] Num frames 5300...
659
+ [2024-05-17 06:12:52,298][00035] Num frames 5400...
660
+ [2024-05-17 06:12:52,442][00035] Num frames 5500...
661
+ [2024-05-17 06:12:52,586][00035] Num frames 5600...
662
+ [2024-05-17 06:12:52,728][00035] Num frames 5700...
663
+ [2024-05-17 06:12:52,863][00035] Num frames 5800...
664
+ [2024-05-17 06:12:52,983][00035] Avg episode rewards: #0: 29.496, true rewards: #0: 11.696
665
+ [2024-05-17 06:12:52,985][00035] Avg episode reward: 29.496, avg true_objective: 11.696
666
+ [2024-05-17 06:12:53,059][00035] Num frames 5900...
667
+ [2024-05-17 06:12:53,195][00035] Num frames 6000...
668
+ [2024-05-17 06:12:53,330][00035] Num frames 6100...
669
+ [2024-05-17 06:12:53,463][00035] Num frames 6200...
670
+ [2024-05-17 06:12:53,604][00035] Num frames 6300...
671
+ [2024-05-17 06:12:53,747][00035] Num frames 6400...
672
+ [2024-05-17 06:12:53,897][00035] Num frames 6500...
673
+ [2024-05-17 06:12:54,043][00035] Num frames 6600...
674
+ [2024-05-17 06:12:54,192][00035] Num frames 6700...
675
+ [2024-05-17 06:12:54,328][00035] Num frames 6800...
676
+ [2024-05-17 06:12:54,462][00035] Num frames 6900...
677
+ [2024-05-17 06:12:54,594][00035] Num frames 7000...
678
+ [2024-05-17 06:12:54,731][00035] Num frames 7100...
679
+ [2024-05-17 06:12:54,868][00035] Num frames 7200...
680
+ [2024-05-17 06:12:55,002][00035] Num frames 7300...
681
+ [2024-05-17 06:12:55,141][00035] Num frames 7400...
682
+ [2024-05-17 06:12:55,278][00035] Num frames 7500...
683
+ [2024-05-17 06:12:55,414][00035] Num frames 7600...
684
+ [2024-05-17 06:12:55,551][00035] Num frames 7700...
685
+ [2024-05-17 06:12:55,612][00035] Avg episode rewards: #0: 33.006, true rewards: #0: 12.840
686
+ [2024-05-17 06:12:55,614][00035] Avg episode reward: 33.006, avg true_objective: 12.840
687
+ [2024-05-17 06:12:55,746][00035] Num frames 7800...
688
+ [2024-05-17 06:12:55,881][00035] Num frames 7900...
689
+ [2024-05-17 06:12:56,013][00035] Num frames 8000...
690
+ [2024-05-17 06:12:56,147][00035] Num frames 8100...
691
+ [2024-05-17 06:12:56,285][00035] Num frames 8200...
692
+ [2024-05-17 06:12:56,421][00035] Num frames 8300...
693
+ [2024-05-17 06:12:56,555][00035] Num frames 8400...
694
+ [2024-05-17 06:12:56,707][00035] Avg episode rewards: #0: 30.670, true rewards: #0: 12.099
695
+ [2024-05-17 06:12:56,708][00035] Avg episode reward: 30.670, avg true_objective: 12.099
696
+ [2024-05-17 06:12:56,751][00035] Num frames 8500...
697
+ [2024-05-17 06:12:56,886][00035] Num frames 8600...
698
+ [2024-05-17 06:12:57,018][00035] Num frames 8700...
699
+ [2024-05-17 06:12:57,153][00035] Num frames 8800...
700
+ [2024-05-17 06:12:57,290][00035] Num frames 8900...
701
+ [2024-05-17 06:12:57,427][00035] Num frames 9000...
702
+ [2024-05-17 06:12:57,569][00035] Num frames 9100...
703
+ [2024-05-17 06:12:57,707][00035] Num frames 9200...
704
+ [2024-05-17 06:12:57,840][00035] Num frames 9300...
705
+ [2024-05-17 06:12:57,976][00035] Num frames 9400...
706
+ [2024-05-17 06:12:58,109][00035] Num frames 9500...
707
+ [2024-05-17 06:12:58,247][00035] Num frames 9600...
708
+ [2024-05-17 06:12:58,383][00035] Num frames 9700...
709
+ [2024-05-17 06:12:58,523][00035] Num frames 9800...
710
+ [2024-05-17 06:12:58,660][00035] Num frames 9900...
711
+ [2024-05-17 06:12:58,796][00035] Num frames 10000...
712
+ [2024-05-17 06:12:58,935][00035] Num frames 10100...
713
+ [2024-05-17 06:12:59,075][00035] Num frames 10200...
714
+ [2024-05-17 06:12:59,222][00035] Num frames 10300...
715
+ [2024-05-17 06:12:59,370][00035] Num frames 10400...
716
+ [2024-05-17 06:12:59,509][00035] Num frames 10500...
717
+ [2024-05-17 06:12:59,662][00035] Avg episode rewards: #0: 33.836, true rewards: #0: 13.211
718
+ [2024-05-17 06:12:59,663][00035] Avg episode reward: 33.836, avg true_objective: 13.211
719
+ [2024-05-17 06:12:59,707][00035] Num frames 10600...
720
+ [2024-05-17 06:12:59,841][00035] Num frames 10700...
721
+ [2024-05-17 06:12:59,974][00035] Num frames 10800...
722
+ [2024-05-17 06:13:00,109][00035] Num frames 10900...
723
+ [2024-05-17 06:13:00,244][00035] Num frames 11000...
724
+ [2024-05-17 06:13:00,381][00035] Num frames 11100...
725
+ [2024-05-17 06:13:00,517][00035] Num frames 11200...
726
+ [2024-05-17 06:13:00,658][00035] Num frames 11300...
727
+ [2024-05-17 06:13:00,792][00035] Num frames 11400...
728
+ [2024-05-17 06:13:00,932][00035] Num frames 11500...
729
+ [2024-05-17 06:13:01,072][00035] Num frames 11600...
730
+ [2024-05-17 06:13:01,212][00035] Num frames 11700...
731
+ [2024-05-17 06:13:01,353][00035] Num frames 11800...
732
+ [2024-05-17 06:13:01,541][00035] Avg episode rewards: #0: 33.546, true rewards: #0: 13.213
733
+ [2024-05-17 06:13:01,543][00035] Avg episode reward: 33.546, avg true_objective: 13.213
734
+ [2024-05-17 06:13:01,555][00035] Num frames 11900...
735
+ [2024-05-17 06:13:01,690][00035] Num frames 12000...
736
+ [2024-05-17 06:13:01,825][00035] Num frames 12100...
737
+ [2024-05-17 06:13:01,959][00035] Num frames 12200...
738
+ [2024-05-17 06:13:02,093][00035] Num frames 12300...
739
+ [2024-05-17 06:13:02,229][00035] Num frames 12400...
740
+ [2024-05-17 06:13:02,370][00035] Num frames 12500...
741
+ [2024-05-17 06:13:02,511][00035] Num frames 12600...
742
+ [2024-05-17 06:13:02,654][00035] Num frames 12700...
743
+ [2024-05-17 06:13:02,722][00035] Avg episode rewards: #0: 32.509, true rewards: #0: 12.709
744
+ [2024-05-17 06:13:02,724][00035] Avg episode reward: 32.509, avg true_objective: 12.709
745
+ [2024-05-17 06:13:46,469][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
746
+ [2024-05-17 06:13:55,720][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
747
+ [2024-05-17 06:13:55,721][00035] Overriding arg 'num_workers' with value 1 passed from command line
748
+ [2024-05-17 06:13:55,722][00035] Adding new argument 'no_render'=True that is not in the saved config file!
749
+ [2024-05-17 06:13:55,723][00035] Adding new argument 'save_video'=True that is not in the saved config file!
750
+ [2024-05-17 06:13:55,724][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
751
+ [2024-05-17 06:13:55,725][00035] Adding new argument 'video_name'=None that is not in the saved config file!
752
+ [2024-05-17 06:13:55,726][00035] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
753
+ [2024-05-17 06:13:55,727][00035] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
754
+ [2024-05-17 06:13:55,728][00035] Adding new argument 'push_to_hub'=True that is not in the saved config file!
755
+ [2024-05-17 06:13:55,729][00035] Adding new argument 'hf_repository'='jaymanvirk/ppo_sample_factory_doom_health_gathering_supreme' that is not in the saved config file!
756
+ [2024-05-17 06:13:55,730][00035] Adding new argument 'policy_index'=0 that is not in the saved config file!
757
+ [2024-05-17 06:13:55,731][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
758
+ [2024-05-17 06:13:55,733][00035] Adding new argument 'train_script'=None that is not in the saved config file!
759
+ [2024-05-17 06:13:55,733][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file!
760
+ [2024-05-17 06:13:55,735][00035] Using frameskip 1 and render_action_repeat=4 for evaluation
761
+ [2024-05-17 06:13:55,764][00035] RunningMeanStd input shape: (3, 72, 128)
762
+ [2024-05-17 06:13:55,766][00035] RunningMeanStd input shape: (1,)
763
+ [2024-05-17 06:13:55,784][00035] ConvEncoder: input_channels=3
764
+ [2024-05-17 06:13:55,836][00035] Conv encoder output size: 512
765
+ [2024-05-17 06:13:55,837][00035] Policy head output size: 512
766
+ [2024-05-17 06:13:55,863][00035] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
767
+ [2024-05-17 06:13:56,376][00035] Num frames 100...
768
+ [2024-05-17 06:13:56,508][00035] Num frames 200...
769
+ [2024-05-17 06:13:56,640][00035] Num frames 300...
770
+ [2024-05-17 06:13:56,779][00035] Num frames 400...
771
+ [2024-05-17 06:13:56,917][00035] Num frames 500...
772
+ [2024-05-17 06:13:57,055][00035] Num frames 600...
773
+ [2024-05-17 06:13:57,193][00035] Num frames 700...
774
+ [2024-05-17 06:13:57,333][00035] Num frames 800...
775
+ [2024-05-17 06:13:57,434][00035] Avg episode rewards: #0: 15.320, true rewards: #0: 8.320
776
+ [2024-05-17 06:13:57,436][00035] Avg episode reward: 15.320, avg true_objective: 8.320
777
+ [2024-05-17 06:13:57,531][00035] Num frames 900...
778
+ [2024-05-17 06:13:57,664][00035] Num frames 1000...
779
+ [2024-05-17 06:13:57,800][00035] Num frames 1100...
780
+ [2024-05-17 06:13:57,939][00035] Num frames 1200...
781
+ [2024-05-17 06:13:58,077][00035] Num frames 1300...
782
+ [2024-05-17 06:13:58,218][00035] Num frames 1400...
783
+ [2024-05-17 06:13:58,355][00035] Num frames 1500...
784
+ [2024-05-17 06:13:58,491][00035] Num frames 1600...
785
+ [2024-05-17 06:13:58,635][00035] Num frames 1700...
786
+ [2024-05-17 06:13:58,729][00035] Avg episode rewards: #0: 17.140, true rewards: #0: 8.640
787
+ [2024-05-17 06:13:58,731][00035] Avg episode reward: 17.140, avg true_objective: 8.640
788
+ [2024-05-17 06:13:58,829][00035] Num frames 1800...
789
+ [2024-05-17 06:13:58,965][00035] Num frames 1900...
790
+ [2024-05-17 06:13:59,105][00035] Num frames 2000...
791
+ [2024-05-17 06:13:59,299][00035] Avg episode rewards: #0: 13.660, true rewards: #0: 6.993
792
+ [2024-05-17 06:13:59,301][00035] Avg episode reward: 13.660, avg true_objective: 6.993
793
+ [2024-05-17 06:13:59,305][00035] Num frames 2100...
794
+ [2024-05-17 06:13:59,440][00035] Num frames 2200...
795
+ [2024-05-17 06:13:59,574][00035] Num frames 2300...
796
+ [2024-05-17 06:13:59,712][00035] Num frames 2400...
797
+ [2024-05-17 06:13:59,850][00035] Num frames 2500...
798
+ [2024-05-17 06:13:59,981][00035] Num frames 2600...
799
+ [2024-05-17 06:14:00,117][00035] Num frames 2700...
800
+ [2024-05-17 06:14:00,249][00035] Num frames 2800...
801
+ [2024-05-17 06:14:00,384][00035] Num frames 2900...
802
+ [2024-05-17 06:14:00,522][00035] Num frames 3000...
803
+ [2024-05-17 06:14:00,656][00035] Num frames 3100...
804
+ [2024-05-17 06:14:00,743][00035] Avg episode rewards: #0: 15.555, true rewards: #0: 7.805
805
+ [2024-05-17 06:14:00,744][00035] Avg episode reward: 15.555, avg true_objective: 7.805
806
+ [2024-05-17 06:14:00,856][00035] Num frames 3200...
807
+ [2024-05-17 06:14:00,994][00035] Num frames 3300...
808
+ [2024-05-17 06:14:01,129][00035] Num frames 3400...
809
+ [2024-05-17 06:14:01,262][00035] Num frames 3500...
810
+ [2024-05-17 06:14:01,397][00035] Num frames 3600...
811
+ [2024-05-17 06:14:01,535][00035] Num frames 3700...
812
+ [2024-05-17 06:14:01,671][00035] Num frames 3800...
813
+ [2024-05-17 06:14:01,849][00035] Avg episode rewards: #0: 16.180, true rewards: #0: 7.780
814
+ [2024-05-17 06:14:01,851][00035] Avg episode reward: 16.180, avg true_objective: 7.780
815
+ [2024-05-17 06:14:01,866][00035] Num frames 3900...
816
+ [2024-05-17 06:14:02,003][00035] Num frames 4000...
817
+ [2024-05-17 06:14:02,138][00035] Num frames 4100...
818
+ [2024-05-17 06:14:02,272][00035] Num frames 4200...
819
+ [2024-05-17 06:14:02,409][00035] Num frames 4300...
820
+ [2024-05-17 06:14:02,516][00035] Avg episode rewards: #0: 15.397, true rewards: #0: 7.230
821
+ [2024-05-17 06:14:02,518][00035] Avg episode reward: 15.397, avg true_objective: 7.230
822
+ [2024-05-17 06:14:02,604][00035] Num frames 4400...
823
+ [2024-05-17 06:14:02,738][00035] Num frames 4500...
824
+ [2024-05-17 06:14:02,872][00035] Num frames 4600...
825
+ [2024-05-17 06:14:03,011][00035] Num frames 4700...
826
+ [2024-05-17 06:14:03,105][00035] Avg episode rewards: #0: 14.042, true rewards: #0: 6.756
827
+ [2024-05-17 06:14:03,106][00035] Avg episode reward: 14.042, avg true_objective: 6.756
828
+ [2024-05-17 06:14:03,201][00035] Num frames 4800...
829
+ [2024-05-17 06:14:03,335][00035] Num frames 4900...
830
+ [2024-05-17 06:14:03,473][00035] Num frames 5000...
831
+ [2024-05-17 06:14:03,613][00035] Num frames 5100...
832
+ [2024-05-17 06:14:03,746][00035] Num frames 5200...
833
+ [2024-05-17 06:14:03,893][00035] Num frames 5300...
834
+ [2024-05-17 06:14:04,030][00035] Num frames 5400...
835
+ [2024-05-17 06:14:04,181][00035] Num frames 5500...
836
+ [2024-05-17 06:14:04,316][00035] Num frames 5600...
837
+ [2024-05-17 06:14:04,455][00035] Num frames 5700...
838
+ [2024-05-17 06:14:04,599][00035] Num frames 5800...
839
+ [2024-05-17 06:14:04,734][00035] Num frames 5900...
840
+ [2024-05-17 06:14:04,870][00035] Num frames 6000...
841
+ [2024-05-17 06:14:05,011][00035] Num frames 6100...
842
+ [2024-05-17 06:14:05,152][00035] Num frames 6200...
843
+ [2024-05-17 06:14:05,286][00035] Num frames 6300...
844
+ [2024-05-17 06:14:05,428][00035] Num frames 6400...
845
+ [2024-05-17 06:14:05,571][00035] Num frames 6500...
846
+ [2024-05-17 06:14:05,712][00035] Num frames 6600...
847
+ [2024-05-17 06:14:05,850][00035] Num frames 6700...
848
+ [2024-05-17 06:14:05,985][00035] Num frames 6800...
849
+ [2024-05-17 06:14:06,072][00035] Avg episode rewards: #0: 18.905, true rewards: #0: 8.530
850
+ [2024-05-17 06:14:06,073][00035] Avg episode reward: 18.905, avg true_objective: 8.530
851
+ [2024-05-17 06:14:06,176][00035] Num frames 6900...
852
+ [2024-05-17 06:14:06,310][00035] Num frames 7000...
853
+ [2024-05-17 06:14:06,460][00035] Num frames 7100...
854
+ [2024-05-17 06:14:06,614][00035] Num frames 7200...
855
+ [2024-05-17 06:14:06,751][00035] Num frames 7300...
856
+ [2024-05-17 06:14:06,889][00035] Num frames 7400...
857
+ [2024-05-17 06:14:07,026][00035] Num frames 7500...
858
+ [2024-05-17 06:14:07,162][00035] Num frames 7600...
859
+ [2024-05-17 06:14:07,297][00035] Num frames 7700...
860
+ [2024-05-17 06:14:07,435][00035] Num frames 7800...
861
+ [2024-05-17 06:14:07,498][00035] Avg episode rewards: #0: 19.117, true rewards: #0: 8.672
862
+ [2024-05-17 06:14:07,499][00035] Avg episode reward: 19.117, avg true_objective: 8.672
863
+ [2024-05-17 06:14:07,629][00035] Num frames 7900...
864
+ [2024-05-17 06:14:07,765][00035] Num frames 8000...
865
+ [2024-05-17 06:14:07,901][00035] Num frames 8100...
866
+ [2024-05-17 06:14:08,037][00035] Num frames 8200...
867
+ [2024-05-17 06:14:08,173][00035] Num frames 8300...
868
+ [2024-05-17 06:14:08,315][00035] Avg episode rewards: #0: 18.363, true rewards: #0: 8.363
869
+ [2024-05-17 06:14:08,317][00035] Avg episode reward: 18.363, avg true_objective: 8.363
870
+ [2024-05-17 06:14:37,418][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!