Hugging Face's logo

aalva
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files
xet
Metrics Community
aalva commited on
Commit
51d96b1
·
verified ·
1 Parent(s): 774bfaf

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1746906469.a5c04b73a903 +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000837_3428352_reward_24.982.pth +3 -0
  5. checkpoint_p0/checkpoint_000000758_3104768.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 +820 -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.1746906469.a5c04b73a903 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:52f60cba0cbaeeb413ce49ca4fe9a45a1c5df3c11873dc37bff16c9c2928529f
3
+ size 414896
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: 8.87 +/- 3.11
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 aalva/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_000000837_3428352_reward_24.982.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9861194eea11ff9fbc61443149466498835e1c7fbf2d74e446e114a9bedc08fb
3
+ size 34929051
checkpoint_p0/checkpoint_000000758_3104768.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05214fdd4a509ed3b0fced95e86733ba80745befcff840228079e1abfe7b66ff
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 sha256:644312ea5817fa6200ccf6a6183fea47fd9744bdad5790aa9585b033c950f353
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:cca4f77fe62e2478c36871a333f8545d053e05f3ae8b4e201605b848e2373731
3
+ size 16775115
sf_log.txt ADDED
@@ -0,0 +1,820 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-05-10 19:47:54,490][00031] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json...
2
+ [2025-05-10 19:47:54,492][00031] Rollout worker 0 uses device cpu
3
+ [2025-05-10 19:47:54,493][00031] Rollout worker 1 uses device cpu
4
+ [2025-05-10 19:47:54,493][00031] Rollout worker 2 uses device cpu
5
+ [2025-05-10 19:47:54,494][00031] Rollout worker 3 uses device cpu
6
+ [2025-05-10 19:47:54,495][00031] Rollout worker 4 uses device cpu
7
+ [2025-05-10 19:47:54,495][00031] Rollout worker 5 uses device cpu
8
+ [2025-05-10 19:47:54,496][00031] Rollout worker 6 uses device cpu
9
+ [2025-05-10 19:47:54,498][00031] Rollout worker 7 uses device cpu
10
+ [2025-05-10 19:47:54,639][00031] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2025-05-10 19:47:54,640][00031] InferenceWorker_p0-w0: min num requests: 2
12
+ [2025-05-10 19:47:54,687][00031] Starting all processes...
13
+ [2025-05-10 19:47:54,688][00031] Starting process learner_proc0
14
+ [2025-05-10 19:47:54,792][00031] Starting all processes...
15
+ [2025-05-10 19:47:54,803][00031] Starting process inference_proc0-0
16
+ [2025-05-10 19:47:54,804][00031] Starting process rollout_proc0
17
+ [2025-05-10 19:47:54,804][00031] Starting process rollout_proc1
18
+ [2025-05-10 19:47:54,805][00031] Starting process rollout_proc2
19
+ [2025-05-10 19:47:54,805][00031] Starting process rollout_proc3
20
+ [2025-05-10 19:47:54,806][00031] Starting process rollout_proc4
21
+ [2025-05-10 19:47:54,807][00031] Starting process rollout_proc5
22
+ [2025-05-10 19:47:54,807][00031] Starting process rollout_proc6
23
+ [2025-05-10 19:47:54,811][00031] Starting process rollout_proc7
24
+ [2025-05-10 19:48:02,599][00206] Worker 5 uses CPU cores [1]
25
+ [2025-05-10 19:48:02,746][00187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
26
+ [2025-05-10 19:48:02,746][00187] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
27
+ [2025-05-10 19:48:02,798][00187] Num visible devices: 1
28
+ [2025-05-10 19:48:02,818][00187] Starting seed is not provided
29
+ [2025-05-10 19:48:02,818][00187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
30
+ [2025-05-10 19:48:02,818][00187] Initializing actor-critic model on device cuda:0
31
+ [2025-05-10 19:48:02,819][00187] RunningMeanStd input shape: (3, 72, 128)
32
+ [2025-05-10 19:48:02,824][00187] RunningMeanStd input shape: (1,)
33
+ [2025-05-10 19:48:02,867][00187] ConvEncoder: input_channels=3
34
+ [2025-05-10 19:48:02,970][00207] Worker 6 uses CPU cores [2]
35
+ [2025-05-10 19:48:03,292][00200] Using GPUs [0] for process 0 (actually maps to GPUs [0])
36
+ [2025-05-10 19:48:03,294][00200] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
37
+ [2025-05-10 19:48:03,310][00201] Worker 0 uses CPU cores [0]
38
+ [2025-05-10 19:48:03,355][00200] Num visible devices: 1
39
+ [2025-05-10 19:48:03,372][00205] Worker 4 uses CPU cores [0]
40
+ [2025-05-10 19:48:03,390][00202] Worker 1 uses CPU cores [1]
41
+ [2025-05-10 19:48:03,391][00187] Conv encoder output size: 512
42
+ [2025-05-10 19:48:03,391][00187] Policy head output size: 512
43
+ [2025-05-10 19:48:03,417][00203] Worker 2 uses CPU cores [2]
44
+ [2025-05-10 19:48:03,462][00187] Created Actor Critic model with architecture:
45
+ [2025-05-10 19:48:03,462][00187] ActorCriticSharedWeights(
46
+ (obs_normalizer): ObservationNormalizer(
47
+ (running_mean_std): RunningMeanStdDictInPlace(
48
+ (running_mean_std): ModuleDict(
49
+ (obs): RunningMeanStdInPlace()
50
+ )
51
+ )
52
+ )
53
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
54
+ (encoder): VizdoomEncoder(
55
+ (basic_encoder): ConvEncoder(
56
+ (enc): RecursiveScriptModule(
57
+ original_name=ConvEncoderImpl
58
+ (conv_head): RecursiveScriptModule(
59
+ original_name=Sequential
60
+ (0): RecursiveScriptModule(original_name=Conv2d)
61
+ (1): RecursiveScriptModule(original_name=ELU)
62
+ (2): RecursiveScriptModule(original_name=Conv2d)
63
+ (3): RecursiveScriptModule(original_name=ELU)
64
+ (4): RecursiveScriptModule(original_name=Conv2d)
65
+ (5): RecursiveScriptModule(original_name=ELU)
66
+ )
67
+ (mlp_layers): RecursiveScriptModule(
68
+ original_name=Sequential
69
+ (0): RecursiveScriptModule(original_name=Linear)
70
+ (1): RecursiveScriptModule(original_name=ELU)
71
+ )
72
+ )
73
+ )
74
+ )
75
+ (core): ModelCoreRNN(
76
+ (core): GRU(512, 512)
77
+ )
78
+ (decoder): MlpDecoder(
79
+ (mlp): Identity()
80
+ )
81
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
82
+ (action_parameterization): ActionParameterizationDefault(
83
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
84
+ )
85
+ )
86
+ [2025-05-10 19:48:03,550][00208] Worker 7 uses CPU cores [3]
87
+ [2025-05-10 19:48:03,630][00204] Worker 3 uses CPU cores [3]
88
+ [2025-05-10 19:48:03,747][00187] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2025-05-10 19:48:06,164][00187] No checkpoints found
90
+ [2025-05-10 19:48:06,164][00187] Did not load from checkpoint, starting from scratch!
91
+ [2025-05-10 19:48:06,164][00187] Initialized policy 0 weights for model version 0
92
+ [2025-05-10 19:48:06,166][00187] LearnerWorker_p0 finished initialization!
93
+ [2025-05-10 19:48:06,167][00187] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2025-05-10 19:48:06,280][00200] RunningMeanStd input shape: (3, 72, 128)
95
+ [2025-05-10 19:48:06,281][00200] RunningMeanStd input shape: (1,)
96
+ [2025-05-10 19:48:06,293][00200] ConvEncoder: input_channels=3
97
+ [2025-05-10 19:48:06,415][00200] Conv encoder output size: 512
98
+ [2025-05-10 19:48:06,415][00200] Policy head output size: 512
99
+ [2025-05-10 19:48:06,483][00031] Inference worker 0-0 is ready!
100
+ [2025-05-10 19:48:06,484][00031] All inference workers are ready! Signal rollout workers to start!
101
+ [2025-05-10 19:48:06,604][00203] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2025-05-10 19:48:06,605][00208] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2025-05-10 19:48:06,607][00206] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2025-05-10 19:48:06,606][00204] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2025-05-10 19:48:06,608][00205] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2025-05-10 19:48:06,606][00201] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2025-05-10 19:48:06,610][00207] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2025-05-10 19:48:06,609][00202] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2025-05-10 19:48:07,202][00202] Decorrelating experience for 0 frames...
110
+ [2025-05-10 19:48:07,202][00205] Decorrelating experience for 0 frames...
111
+ [2025-05-10 19:48:07,582][00204] Decorrelating experience for 0 frames...
112
+ [2025-05-10 19:48:07,585][00203] Decorrelating experience for 0 frames...
113
+ [2025-05-10 19:48:07,588][00207] Decorrelating experience for 0 frames...
114
+ [2025-05-10 19:48:07,586][00208] Decorrelating experience for 0 frames...
115
+ [2025-05-10 19:48:07,921][00201] Decorrelating experience for 0 frames...
116
+ [2025-05-10 19:48:07,929][00205] Decorrelating experience for 32 frames...
117
+ [2025-05-10 19:48:08,069][00206] Decorrelating experience for 0 frames...
118
+ [2025-05-10 19:48:08,080][00202] Decorrelating experience for 32 frames...
119
+ [2025-05-10 19:48:08,393][00203] Decorrelating experience for 32 frames...
120
+ [2025-05-10 19:48:08,488][00204] Decorrelating experience for 32 frames...
121
+ [2025-05-10 19:48:08,491][00208] Decorrelating experience for 32 frames...
122
+ [2025-05-10 19:48:08,692][00202] Decorrelating experience for 64 frames...
123
+ [2025-05-10 19:48:08,799][00201] Decorrelating experience for 32 frames...
124
+ [2025-05-10 19:48:09,075][00205] Decorrelating experience for 64 frames...
125
+ [2025-05-10 19:48:09,191][00207] Decorrelating experience for 32 frames...
126
+ [2025-05-10 19:48:09,204][00202] Decorrelating experience for 96 frames...
127
+ [2025-05-10 19:48:09,329][00204] Decorrelating experience for 64 frames...
128
+ [2025-05-10 19:48:09,596][00203] Decorrelating experience for 64 frames...
129
+ [2025-05-10 19:48:09,742][00031] 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
+ [2025-05-10 19:48:09,932][00208] Decorrelating experience for 64 frames...
131
+ [2025-05-10 19:48:09,962][00201] Decorrelating experience for 64 frames...
132
+ [2025-05-10 19:48:10,066][00205] Decorrelating experience for 96 frames...
133
+ [2025-05-10 19:48:10,175][00203] Decorrelating experience for 96 frames...
134
+ [2025-05-10 19:48:10,291][00206] Decorrelating experience for 32 frames...
135
+ [2025-05-10 19:48:10,407][00204] Decorrelating experience for 96 frames...
136
+ [2025-05-10 19:48:10,816][00207] Decorrelating experience for 64 frames...
137
+ [2025-05-10 19:48:10,938][00208] Decorrelating experience for 96 frames...
138
+ [2025-05-10 19:48:11,401][00206] Decorrelating experience for 64 frames...
139
+ [2025-05-10 19:48:11,475][00201] Decorrelating experience for 96 frames...
140
+ [2025-05-10 19:48:12,052][00207] Decorrelating experience for 96 frames...
141
+ [2025-05-10 19:48:12,430][00206] Decorrelating experience for 96 frames...
142
+ [2025-05-10 19:48:12,807][00187] Signal inference workers to stop experience collection...
143
+ [2025-05-10 19:48:12,814][00200] InferenceWorker_p0-w0: stopping experience collection
144
+ [2025-05-10 19:48:14,626][00031] Heartbeat connected on Batcher_0
145
+ [2025-05-10 19:48:14,639][00031] Heartbeat connected on InferenceWorker_p0-w0
146
+ [2025-05-10 19:48:14,650][00031] Heartbeat connected on RolloutWorker_w0
147
+ [2025-05-10 19:48:14,653][00031] Heartbeat connected on RolloutWorker_w1
148
+ [2025-05-10 19:48:14,662][00031] Heartbeat connected on RolloutWorker_w2
149
+ [2025-05-10 19:48:14,665][00031] Heartbeat connected on RolloutWorker_w3
150
+ [2025-05-10 19:48:14,670][00031] Heartbeat connected on RolloutWorker_w4
151
+ [2025-05-10 19:48:14,676][00031] Heartbeat connected on RolloutWorker_w5
152
+ [2025-05-10 19:48:14,683][00031] Heartbeat connected on RolloutWorker_w6
153
+ [2025-05-10 19:48:14,687][00031] Heartbeat connected on RolloutWorker_w7
154
+ [2025-05-10 19:48:14,741][00031] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 448.0. Samples: 2240. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
155
+ [2025-05-10 19:48:14,742][00031] Avg episode reward: [(0, '2.993')]
156
+ [2025-05-10 19:48:15,124][00187] Signal inference workers to resume experience collection...
157
+ [2025-05-10 19:48:15,125][00200] InferenceWorker_p0-w0: resuming experience collection
158
+ [2025-05-10 19:48:15,454][00031] Heartbeat connected on LearnerWorker_p0
159
+ [2025-05-10 19:48:18,794][00200] Updated weights for policy 0, policy_version 10 (0.0105)
160
+ [2025-05-10 19:48:19,742][00031] Fps is (10 sec: 4915.2, 60 sec: 4915.2, 300 sec: 4915.2). Total num frames: 49152. Throughput: 0: 1020.0. Samples: 10200. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
161
+ [2025-05-10 19:48:19,744][00031] Avg episode reward: [(0, '4.380')]
162
+ [2025-05-10 19:48:23,580][00200] Updated weights for policy 0, policy_version 20 (0.0015)
163
+ [2025-05-10 19:48:24,741][00031] Fps is (10 sec: 9011.1, 60 sec: 6007.5, 300 sec: 6007.5). Total num frames: 90112. Throughput: 0: 1514.8. Samples: 22722. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
164
+ [2025-05-10 19:48:24,743][00031] Avg episode reward: [(0, '4.240')]
165
+ [2025-05-10 19:48:28,216][00200] Updated weights for policy 0, policy_version 30 (0.0020)
166
+ [2025-05-10 19:48:29,742][00031] Fps is (10 sec: 8601.6, 60 sec: 6758.4, 300 sec: 6758.4). Total num frames: 135168. Throughput: 0: 1487.8. Samples: 29756. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
167
+ [2025-05-10 19:48:29,743][00031] Avg episode reward: [(0, '4.376')]
168
+ [2025-05-10 19:48:29,753][00187] Saving new best policy, reward=4.376!
169
+ [2025-05-10 19:48:32,616][00200] Updated weights for policy 0, policy_version 40 (0.0016)
170
+ [2025-05-10 19:48:34,741][00031] Fps is (10 sec: 9011.3, 60 sec: 7209.0, 300 sec: 7209.0). Total num frames: 180224. Throughput: 0: 1749.9. Samples: 43748. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
171
+ [2025-05-10 19:48:34,743][00031] Avg episode reward: [(0, '4.350')]
172
+ [2025-05-10 19:48:36,953][00200] Updated weights for policy 0, policy_version 50 (0.0018)
173
+ [2025-05-10 19:48:39,742][00031] Fps is (10 sec: 9420.7, 60 sec: 7645.9, 300 sec: 7645.9). Total num frames: 229376. Throughput: 0: 1931.5. Samples: 57946. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
174
+ [2025-05-10 19:48:39,744][00031] Avg episode reward: [(0, '4.514')]
175
+ [2025-05-10 19:48:39,759][00187] Saving new best policy, reward=4.514!
176
+ [2025-05-10 19:48:41,313][00200] Updated weights for policy 0, policy_version 60 (0.0018)
177
+ [2025-05-10 19:48:44,741][00031] Fps is (10 sec: 9830.3, 60 sec: 7958.0, 300 sec: 7958.0). Total num frames: 278528. Throughput: 0: 1855.9. Samples: 64956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
178
+ [2025-05-10 19:48:44,743][00031] Avg episode reward: [(0, '4.615')]
179
+ [2025-05-10 19:48:44,747][00187] Saving new best policy, reward=4.615!
180
+ [2025-05-10 19:48:45,587][00200] Updated weights for policy 0, policy_version 70 (0.0017)
181
+ [2025-05-10 19:48:49,741][00031] Fps is (10 sec: 9420.9, 60 sec: 8089.6, 300 sec: 8089.6). Total num frames: 323584. Throughput: 0: 1977.9. Samples: 79114. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
182
+ [2025-05-10 19:48:49,743][00031] Avg episode reward: [(0, '4.443')]
183
+ [2025-05-10 19:48:49,965][00200] Updated weights for policy 0, policy_version 80 (0.0016)
184
+ [2025-05-10 19:48:54,323][00200] Updated weights for policy 0, policy_version 90 (0.0018)
185
+ [2025-05-10 19:48:54,741][00031] Fps is (10 sec: 9011.3, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 368640. Throughput: 0: 2072.2. Samples: 93250. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
186
+ [2025-05-10 19:48:54,743][00031] Avg episode reward: [(0, '4.505')]
187
+ [2025-05-10 19:48:59,351][00200] Updated weights for policy 0, policy_version 100 (0.0017)
188
+ [2025-05-10 19:48:59,742][00031] Fps is (10 sec: 8601.6, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 409600. Throughput: 0: 2143.5. Samples: 98696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
189
+ [2025-05-10 19:48:59,744][00031] Avg episode reward: [(0, '4.452')]
190
+ [2025-05-10 19:49:03,704][00200] Updated weights for policy 0, policy_version 110 (0.0017)
191
+ [2025-05-10 19:49:04,741][00031] Fps is (10 sec: 9011.1, 60 sec: 8341.0, 300 sec: 8341.0). Total num frames: 458752. Throughput: 0: 2278.9. Samples: 112752. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
192
+ [2025-05-10 19:49:04,742][00031] Avg episode reward: [(0, '4.584')]
193
+ [2025-05-10 19:49:07,980][00200] Updated weights for policy 0, policy_version 120 (0.0017)
194
+ [2025-05-10 19:49:09,741][00031] Fps is (10 sec: 9830.4, 60 sec: 8465.1, 300 sec: 8465.1). Total num frames: 507904. Throughput: 0: 2319.3. Samples: 127090. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
195
+ [2025-05-10 19:49:09,744][00031] Avg episode reward: [(0, '4.550')]
196
+ [2025-05-10 19:49:12,388][00200] Updated weights for policy 0, policy_version 130 (0.0017)
197
+ [2025-05-10 19:49:14,742][00031] Fps is (10 sec: 9420.5, 60 sec: 9215.9, 300 sec: 8507.1). Total num frames: 552960. Throughput: 0: 2318.2. Samples: 134074. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
198
+ [2025-05-10 19:49:14,743][00031] Avg episode reward: [(0, '4.670')]
199
+ [2025-05-10 19:49:14,746][00187] Saving new best policy, reward=4.670!
200
+ [2025-05-10 19:49:16,680][00200] Updated weights for policy 0, policy_version 140 (0.0019)
201
+ [2025-05-10 19:49:19,742][00031] Fps is (10 sec: 9420.5, 60 sec: 9216.0, 300 sec: 8601.6). Total num frames: 602112. Throughput: 0: 2322.4. Samples: 148258. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
202
+ [2025-05-10 19:49:19,745][00031] Avg episode reward: [(0, '4.493')]
203
+ [2025-05-10 19:49:21,054][00200] Updated weights for policy 0, policy_version 150 (0.0017)
204
+ [2025-05-10 19:49:24,742][00031] Fps is (10 sec: 9420.1, 60 sec: 9284.1, 300 sec: 8628.8). Total num frames: 647168. Throughput: 0: 2324.7. Samples: 162558. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
205
+ [2025-05-10 19:49:24,745][00031] Avg episode reward: [(0, '4.724')]
206
+ [2025-05-10 19:49:24,746][00187] Saving new best policy, reward=4.724!
207
+ [2025-05-10 19:49:25,302][00200] Updated weights for policy 0, policy_version 160 (0.0016)
208
+ [2025-05-10 19:49:29,741][00031] Fps is (10 sec: 8601.9, 60 sec: 9216.0, 300 sec: 8601.6). Total num frames: 688128. Throughput: 0: 2326.8. Samples: 169662. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
209
+ [2025-05-10 19:49:29,744][00031] Avg episode reward: [(0, '4.505')]
210
+ [2025-05-10 19:49:30,278][00200] Updated weights for policy 0, policy_version 170 (0.0015)
211
+ [2025-05-10 19:49:34,741][00031] Fps is (10 sec: 9012.3, 60 sec: 9284.3, 300 sec: 8673.9). Total num frames: 737280. Throughput: 0: 2288.7. Samples: 182106. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
212
+ [2025-05-10 19:49:34,742][00200] Updated weights for policy 0, policy_version 180 (0.0019)
213
+ [2025-05-10 19:49:34,743][00031] Avg episode reward: [(0, '4.412')]
214
+ [2025-05-10 19:49:39,049][00200] Updated weights for policy 0, policy_version 190 (0.0018)
215
+ [2025-05-10 19:49:39,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8692.6). Total num frames: 782336. Throughput: 0: 2289.3. Samples: 196270. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
216
+ [2025-05-10 19:49:39,744][00031] Avg episode reward: [(0, '4.615')]
217
+ [2025-05-10 19:49:43,293][00200] Updated weights for policy 0, policy_version 200 (0.0017)
218
+ [2025-05-10 19:49:44,741][00031] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 8752.5). Total num frames: 831488. Throughput: 0: 2327.6. Samples: 203440. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
219
+ [2025-05-10 19:49:44,743][00031] Avg episode reward: [(0, '4.477')]
220
+ [2025-05-10 19:49:47,680][00200] Updated weights for policy 0, policy_version 210 (0.0014)
221
+ [2025-05-10 19:49:49,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8765.5). Total num frames: 876544. Throughput: 0: 2332.6. Samples: 217718. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
222
+ [2025-05-10 19:49:49,743][00031] Avg episode reward: [(0, '4.481')]
223
+ [2025-05-10 19:49:49,805][00187] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000215_880640.pth...
224
+ [2025-05-10 19:49:52,065][00200] Updated weights for policy 0, policy_version 220 (0.0018)
225
+ [2025-05-10 19:49:54,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8816.2). Total num frames: 925696. Throughput: 0: 2326.1. Samples: 231766. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
226
+ [2025-05-10 19:49:54,745][00031] Avg episode reward: [(0, '4.352')]
227
+ [2025-05-10 19:49:56,339][00200] Updated weights for policy 0, policy_version 230 (0.0016)
228
+ [2025-05-10 19:49:59,742][00031] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 8825.0). Total num frames: 970752. Throughput: 0: 2328.1. Samples: 238838. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
229
+ [2025-05-10 19:49:59,748][00031] Avg episode reward: [(0, '4.548')]
230
+ [2025-05-10 19:50:00,817][00200] Updated weights for policy 0, policy_version 240 (0.0018)
231
+ [2025-05-10 19:50:04,741][00031] Fps is (10 sec: 8601.6, 60 sec: 9216.0, 300 sec: 8797.5). Total num frames: 1011712. Throughput: 0: 2292.5. Samples: 251418. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
232
+ [2025-05-10 19:50:04,743][00031] Avg episode reward: [(0, '4.565')]
233
+ [2025-05-10 19:50:05,650][00200] Updated weights for policy 0, policy_version 250 (0.0015)
234
+ [2025-05-10 19:50:09,742][00031] Fps is (10 sec: 9011.1, 60 sec: 9216.0, 300 sec: 8840.5). Total num frames: 1060864. Throughput: 0: 2295.5. Samples: 265856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
235
+ [2025-05-10 19:50:09,744][00031] Avg episode reward: [(0, '4.754')]
236
+ [2025-05-10 19:50:09,752][00187] Saving new best policy, reward=4.754!
237
+ [2025-05-10 19:50:10,018][00200] Updated weights for policy 0, policy_version 260 (0.0018)
238
+ [2025-05-10 19:50:14,241][00200] Updated weights for policy 0, policy_version 270 (0.0017)
239
+ [2025-05-10 19:50:14,741][00031] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 8880.1). Total num frames: 1110016. Throughput: 0: 2296.1. Samples: 272986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
240
+ [2025-05-10 19:50:14,742][00031] Avg episode reward: [(0, '5.059')]
241
+ [2025-05-10 19:50:14,744][00187] Saving new best policy, reward=5.059!
242
+ [2025-05-10 19:50:18,523][00200] Updated weights for policy 0, policy_version 280 (0.0014)
243
+ [2025-05-10 19:50:19,741][00031] Fps is (10 sec: 9421.1, 60 sec: 9216.0, 300 sec: 8885.2). Total num frames: 1155072. Throughput: 0: 2338.2. Samples: 287326. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
244
+ [2025-05-10 19:50:19,745][00031] Avg episode reward: [(0, '5.490')]
245
+ [2025-05-10 19:50:19,805][00187] Saving new best policy, reward=5.490!
246
+ [2025-05-10 19:50:22,897][00200] Updated weights for policy 0, policy_version 290 (0.0017)
247
+ [2025-05-10 19:50:24,742][00031] Fps is (10 sec: 9420.6, 60 sec: 9284.4, 300 sec: 8920.2). Total num frames: 1204224. Throughput: 0: 2341.1. Samples: 301618. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
248
+ [2025-05-10 19:50:24,744][00031] Avg episode reward: [(0, '5.497')]
249
+ [2025-05-10 19:50:24,747][00187] Saving new best policy, reward=5.497!
250
+ [2025-05-10 19:50:27,139][00200] Updated weights for policy 0, policy_version 300 (0.0017)
251
+ [2025-05-10 19:50:29,741][00031] Fps is (10 sec: 9830.5, 60 sec: 9420.8, 300 sec: 8952.7). Total num frames: 1253376. Throughput: 0: 2339.9. Samples: 308734. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
252
+ [2025-05-10 19:50:29,744][00031] Avg episode reward: [(0, '5.779')]
253
+ [2025-05-10 19:50:29,754][00187] Saving new best policy, reward=5.779!
254
+ [2025-05-10 19:50:31,503][00200] Updated weights for policy 0, policy_version 310 (0.0017)
255
+ [2025-05-10 19:50:34,741][00031] Fps is (10 sec: 9011.4, 60 sec: 9284.3, 300 sec: 8926.5). Total num frames: 1294336. Throughput: 0: 2334.8. Samples: 322786. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
256
+ [2025-05-10 19:50:34,742][00031] Avg episode reward: [(0, '6.334')]
257
+ [2025-05-10 19:50:34,746][00187] Saving new best policy, reward=6.334!
258
+ [2025-05-10 19:50:36,333][00200] Updated weights for policy 0, policy_version 320 (0.0017)
259
+ [2025-05-10 19:50:39,741][00031] Fps is (10 sec: 8601.6, 60 sec: 9284.3, 300 sec: 8929.3). Total num frames: 1339392. Throughput: 0: 2308.2. Samples: 335634. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
260
+ [2025-05-10 19:50:39,743][00031] Avg episode reward: [(0, '7.028')]
261
+ [2025-05-10 19:50:39,754][00187] Saving new best policy, reward=7.028!
262
+ [2025-05-10 19:50:40,793][00200] Updated weights for policy 0, policy_version 330 (0.0015)
263
+ [2025-05-10 19:50:44,742][00031] Fps is (10 sec: 9420.4, 60 sec: 9284.2, 300 sec: 8958.3). Total num frames: 1388544. Throughput: 0: 2306.3. Samples: 342624. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
264
+ [2025-05-10 19:50:44,745][00031] Avg episode reward: [(0, '6.814')]
265
+ [2025-05-10 19:50:45,065][00200] Updated weights for policy 0, policy_version 340 (0.0018)
266
+ [2025-05-10 19:50:49,387][00200] Updated weights for policy 0, policy_version 350 (0.0017)
267
+ [2025-05-10 19:50:49,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8960.0). Total num frames: 1433600. Throughput: 0: 2344.8. Samples: 356932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
268
+ [2025-05-10 19:50:49,743][00031] Avg episode reward: [(0, '8.756')]
269
+ [2025-05-10 19:50:49,753][00187] Saving new best policy, reward=8.756!
270
+ [2025-05-10 19:50:53,791][00200] Updated weights for policy 0, policy_version 360 (0.0019)
271
+ [2025-05-10 19:50:54,741][00031] Fps is (10 sec: 9421.2, 60 sec: 9284.3, 300 sec: 8986.4). Total num frames: 1482752. Throughput: 0: 2335.0. Samples: 370932. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
272
+ [2025-05-10 19:50:54,745][00031] Avg episode reward: [(0, '8.241')]
273
+ [2025-05-10 19:50:58,250][00200] Updated weights for policy 0, policy_version 370 (0.0015)
274
+ [2025-05-10 19:50:59,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8987.1). Total num frames: 1527808. Throughput: 0: 2330.8. Samples: 377870. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
275
+ [2025-05-10 19:50:59,743][00031] Avg episode reward: [(0, '7.479')]
276
+ [2025-05-10 19:51:02,549][00200] Updated weights for policy 0, policy_version 380 (0.0017)
277
+ [2025-05-10 19:51:04,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9011.2). Total num frames: 1576960. Throughput: 0: 2323.4. Samples: 391880. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
278
+ [2025-05-10 19:51:04,743][00031] Avg episode reward: [(0, '8.174')]
279
+ [2025-05-10 19:51:07,319][00200] Updated weights for policy 0, policy_version 390 (0.0017)
280
+ [2025-05-10 19:51:09,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8988.5). Total num frames: 1617920. Throughput: 0: 2289.4. Samples: 404642. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
281
+ [2025-05-10 19:51:09,743][00031] Avg episode reward: [(0, '8.886')]
282
+ [2025-05-10 19:51:09,752][00187] Saving new best policy, reward=8.886!
283
+ [2025-05-10 19:51:11,994][00200] Updated weights for policy 0, policy_version 400 (0.0019)
284
+ [2025-05-10 19:51:14,741][00031] Fps is (10 sec: 8601.7, 60 sec: 9216.0, 300 sec: 8989.1). Total num frames: 1662976. Throughput: 0: 2282.3. Samples: 411438. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
285
+ [2025-05-10 19:51:14,743][00031] Avg episode reward: [(0, '9.292')]
286
+ [2025-05-10 19:51:14,745][00187] Saving new best policy, reward=9.292!
287
+ [2025-05-10 19:51:16,375][00200] Updated weights for policy 0, policy_version 410 (0.0019)
288
+ [2025-05-10 19:51:19,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 8989.6). Total num frames: 1708032. Throughput: 0: 2281.7. Samples: 425464. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
289
+ [2025-05-10 19:51:19,744][00031] Avg episode reward: [(0, '10.152')]
290
+ [2025-05-10 19:51:19,754][00187] Saving new best policy, reward=10.152!
291
+ [2025-05-10 19:51:20,877][00200] Updated weights for policy 0, policy_version 420 (0.0018)
292
+ [2025-05-10 19:51:24,741][00031] Fps is (10 sec: 9011.1, 60 sec: 9147.8, 300 sec: 8990.2). Total num frames: 1753088. Throughput: 0: 2300.6. Samples: 439160. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
293
+ [2025-05-10 19:51:24,743][00031] Avg episode reward: [(0, '10.967')]
294
+ [2025-05-10 19:51:24,746][00187] Saving new best policy, reward=10.967!
295
+ [2025-05-10 19:51:25,336][00200] Updated weights for policy 0, policy_version 430 (0.0015)
296
+ [2025-05-10 19:51:29,625][00200] Updated weights for policy 0, policy_version 440 (0.0016)
297
+ [2025-05-10 19:51:29,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9011.2). Total num frames: 1802240. Throughput: 0: 2301.5. Samples: 446190. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
298
+ [2025-05-10 19:51:29,743][00031] Avg episode reward: [(0, '9.521')]
299
+ [2025-05-10 19:51:33,971][00200] Updated weights for policy 0, policy_version 450 (0.0016)
300
+ [2025-05-10 19:51:34,741][00031] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 1847296. Throughput: 0: 2299.8. Samples: 460424. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
301
+ [2025-05-10 19:51:34,742][00031] Avg episode reward: [(0, '9.754')]
302
+ [2025-05-10 19:51:38,271][00200] Updated weights for policy 0, policy_version 460 (0.0019)
303
+ [2025-05-10 19:51:39,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 1892352. Throughput: 0: 2288.5. Samples: 473914. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
304
+ [2025-05-10 19:51:39,742][00031] Avg episode reward: [(0, '12.792')]
305
+ [2025-05-10 19:51:39,755][00187] Saving new best policy, reward=12.792!
306
+ [2025-05-10 19:51:43,251][00200] Updated weights for policy 0, policy_version 470 (0.0025)
307
+ [2025-05-10 19:51:44,741][00031] Fps is (10 sec: 9011.1, 60 sec: 9147.8, 300 sec: 9011.2). Total num frames: 1937408. Throughput: 0: 2271.8. Samples: 480100. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
308
+ [2025-05-10 19:51:44,743][00031] Avg episode reward: [(0, '12.889')]
309
+ [2025-05-10 19:51:44,744][00187] Saving new best policy, reward=12.889!
310
+ [2025-05-10 19:51:47,674][00200] Updated weights for policy 0, policy_version 480 (0.0015)
311
+ [2025-05-10 19:51:49,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9011.2). Total num frames: 1982464. Throughput: 0: 2272.0. Samples: 494118. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
312
+ [2025-05-10 19:51:49,743][00031] Avg episode reward: [(0, '12.484')]
313
+ [2025-05-10 19:51:49,777][00187] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000485_1986560.pth...
314
+ [2025-05-10 19:51:52,045][00200] Updated weights for policy 0, policy_version 490 (0.0016)
315
+ [2025-05-10 19:51:54,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9029.4). Total num frames: 2031616. Throughput: 0: 2300.5. Samples: 508166. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
316
+ [2025-05-10 19:51:54,743][00031] Avg episode reward: [(0, '12.508')]
317
+ [2025-05-10 19:51:56,421][00200] Updated weights for policy 0, policy_version 500 (0.0018)
318
+ [2025-05-10 19:51:59,742][00031] Fps is (10 sec: 9420.7, 60 sec: 9147.7, 300 sec: 9029.0). Total num frames: 2076672. Throughput: 0: 2305.3. Samples: 515178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
319
+ [2025-05-10 19:51:59,744][00031] Avg episode reward: [(0, '14.127')]
320
+ [2025-05-10 19:51:59,753][00187] Saving new best policy, reward=14.127!
321
+ [2025-05-10 19:52:00,814][00200] Updated weights for policy 0, policy_version 510 (0.0016)
322
+ [2025-05-10 19:52:04,741][00031] Fps is (10 sec: 9420.9, 60 sec: 9147.7, 300 sec: 9046.1). Total num frames: 2125824. Throughput: 0: 2303.2. Samples: 529108. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
323
+ [2025-05-10 19:52:04,743][00031] Avg episode reward: [(0, '14.486')]
324
+ [2025-05-10 19:52:04,744][00187] Saving new best policy, reward=14.486!
325
+ [2025-05-10 19:52:05,173][00200] Updated weights for policy 0, policy_version 520 (0.0016)
326
+ [2025-05-10 19:52:09,350][00200] Updated weights for policy 0, policy_version 530 (0.0016)
327
+ [2025-05-10 19:52:09,742][00031] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9045.3). Total num frames: 2170880. Throughput: 0: 2320.3. Samples: 543574. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
328
+ [2025-05-10 19:52:09,743][00031] Avg episode reward: [(0, '14.430')]
329
+ [2025-05-10 19:52:14,417][00200] Updated weights for policy 0, policy_version 540 (0.0014)
330
+ [2025-05-10 19:52:14,741][00031] Fps is (10 sec: 8601.6, 60 sec: 9147.7, 300 sec: 9027.9). Total num frames: 2211840. Throughput: 0: 2302.2. Samples: 549790. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
331
+ [2025-05-10 19:52:14,743][00031] Avg episode reward: [(0, '15.557')]
332
+ [2025-05-10 19:52:14,744][00187] Saving new best policy, reward=15.557!
333
+ [2025-05-10 19:52:18,688][00200] Updated weights for policy 0, policy_version 550 (0.0016)
334
+ [2025-05-10 19:52:19,741][00031] Fps is (10 sec: 9011.3, 60 sec: 9216.0, 300 sec: 9044.0). Total num frames: 2260992. Throughput: 0: 2289.1. Samples: 563434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
335
+ [2025-05-10 19:52:19,743][00031] Avg episode reward: [(0, '15.791')]
336
+ [2025-05-10 19:52:19,754][00187] Saving new best policy, reward=15.791!
337
+ [2025-05-10 19:52:23,071][00200] Updated weights for policy 0, policy_version 560 (0.0018)
338
+ [2025-05-10 19:52:24,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9043.3). Total num frames: 2306048. Throughput: 0: 2303.5. Samples: 577570. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
339
+ [2025-05-10 19:52:24,743][00031] Avg episode reward: [(0, '15.734')]
340
+ [2025-05-10 19:52:27,302][00200] Updated weights for policy 0, policy_version 570 (0.0017)
341
+ [2025-05-10 19:52:29,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9058.5). Total num frames: 2355200. Throughput: 0: 2328.4. Samples: 584880. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
342
+ [2025-05-10 19:52:29,742][00031] Avg episode reward: [(0, '16.379')]
343
+ [2025-05-10 19:52:29,783][00187] Saving new best policy, reward=16.379!
344
+ [2025-05-10 19:52:31,629][00200] Updated weights for policy 0, policy_version 580 (0.0016)
345
+ [2025-05-10 19:52:34,741][00031] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 9073.0). Total num frames: 2404352. Throughput: 0: 2335.0. Samples: 599192. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
346
+ [2025-05-10 19:52:34,744][00031] Avg episode reward: [(0, '17.857')]
347
+ [2025-05-10 19:52:34,746][00187] Saving new best policy, reward=17.857!
348
+ [2025-05-10 19:52:35,853][00200] Updated weights for policy 0, policy_version 590 (0.0015)
349
+ [2025-05-10 19:52:39,741][00031] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 9087.1). Total num frames: 2453504. Throughput: 0: 2342.5. Samples: 613580. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
350
+ [2025-05-10 19:52:39,742][00031] Avg episode reward: [(0, '16.599')]
351
+ [2025-05-10 19:52:40,109][00200] Updated weights for policy 0, policy_version 600 (0.0015)
352
+ [2025-05-10 19:52:44,619][00200] Updated weights for policy 0, policy_version 610 (0.0016)
353
+ [2025-05-10 19:52:44,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9085.7). Total num frames: 2498560. Throughput: 0: 2345.1. Samples: 620708. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
354
+ [2025-05-10 19:52:44,743][00031] Avg episode reward: [(0, '15.061')]
355
+ [2025-05-10 19:52:49,421][00200] Updated weights for policy 0, policy_version 620 (0.0019)
356
+ [2025-05-10 19:52:49,741][00031] Fps is (10 sec: 8601.6, 60 sec: 9284.3, 300 sec: 9069.7). Total num frames: 2539520. Throughput: 0: 2316.1. Samples: 633334. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
357
+ [2025-05-10 19:52:49,743][00031] Avg episode reward: [(0, '17.832')]
358
+ [2025-05-10 19:52:53,752][00200] Updated weights for policy 0, policy_version 630 (0.0014)
359
+ [2025-05-10 19:52:54,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9083.1). Total num frames: 2588672. Throughput: 0: 2310.8. Samples: 647558. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
360
+ [2025-05-10 19:52:54,743][00031] Avg episode reward: [(0, '19.165')]
361
+ [2025-05-10 19:52:54,745][00187] Saving new best policy, reward=19.165!
362
+ [2025-05-10 19:52:58,119][00200] Updated weights for policy 0, policy_version 640 (0.0017)
363
+ [2025-05-10 19:52:59,742][00031] Fps is (10 sec: 9420.2, 60 sec: 9284.2, 300 sec: 9081.8). Total num frames: 2633728. Throughput: 0: 2328.5. Samples: 654576. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
364
+ [2025-05-10 19:52:59,748][00031] Avg episode reward: [(0, '17.556')]
365
+ [2025-05-10 19:53:02,441][00200] Updated weights for policy 0, policy_version 650 (0.0019)
366
+ [2025-05-10 19:53:04,741][00031] Fps is (10 sec: 9420.7, 60 sec: 9284.2, 300 sec: 9094.5). Total num frames: 2682880. Throughput: 0: 2339.4. Samples: 668706. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
367
+ [2025-05-10 19:53:04,743][00031] Avg episode reward: [(0, '17.121')]
368
+ [2025-05-10 19:53:06,652][00200] Updated weights for policy 0, policy_version 660 (0.0018)
369
+ [2025-05-10 19:53:09,742][00031] Fps is (10 sec: 9830.9, 60 sec: 9352.5, 300 sec: 9261.1). Total num frames: 2732032. Throughput: 0: 2348.5. Samples: 683252. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
370
+ [2025-05-10 19:53:09,744][00031] Avg episode reward: [(0, '17.316')]
371
+ [2025-05-10 19:53:10,905][00200] Updated weights for policy 0, policy_version 670 (0.0014)
372
+ [2025-05-10 19:53:14,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9420.8, 300 sec: 9247.2). Total num frames: 2777088. Throughput: 0: 2343.8. Samples: 690350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
373
+ [2025-05-10 19:53:14,744][00031] Avg episode reward: [(0, '17.371')]
374
+ [2025-05-10 19:53:15,265][00200] Updated weights for policy 0, policy_version 680 (0.0013)
375
+ [2025-05-10 19:53:19,741][00031] Fps is (10 sec: 8601.7, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 2818048. Throughput: 0: 2318.4. Samples: 703520. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
376
+ [2025-05-10 19:53:19,742][00031] Avg episode reward: [(0, '17.110')]
377
+ [2025-05-10 19:53:20,224][00200] Updated weights for policy 0, policy_version 690 (0.0019)
378
+ [2025-05-10 19:53:24,561][00200] Updated weights for policy 0, policy_version 700 (0.0017)
379
+ [2025-05-10 19:53:24,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 9261.1). Total num frames: 2867200. Throughput: 0: 2307.1. Samples: 717398. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
380
+ [2025-05-10 19:53:24,743][00031] Avg episode reward: [(0, '17.884')]
381
+ [2025-05-10 19:53:28,784][00200] Updated weights for policy 0, policy_version 710 (0.0014)
382
+ [2025-05-10 19:53:29,741][00031] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 2916352. Throughput: 0: 2306.0. Samples: 724478. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
383
+ [2025-05-10 19:53:29,747][00031] Avg episode reward: [(0, '19.150')]
384
+ [2025-05-10 19:53:33,120][00200] Updated weights for policy 0, policy_version 720 (0.0015)
385
+ [2025-05-10 19:53:34,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 2961408. Throughput: 0: 2345.2. Samples: 738870. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
386
+ [2025-05-10 19:53:34,744][00031] Avg episode reward: [(0, '20.760')]
387
+ [2025-05-10 19:53:34,746][00187] Saving new best policy, reward=20.760!
388
+ [2025-05-10 19:53:37,353][00200] Updated weights for policy 0, policy_version 730 (0.0017)
389
+ [2025-05-10 19:53:39,741][00031] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3010560. Throughput: 0: 2349.5. Samples: 753286. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
390
+ [2025-05-10 19:53:39,743][00031] Avg episode reward: [(0, '21.914')]
391
+ [2025-05-10 19:53:39,755][00187] Saving new best policy, reward=21.914!
392
+ [2025-05-10 19:53:41,681][00200] Updated weights for policy 0, policy_version 740 (0.0016)
393
+ [2025-05-10 19:53:44,743][00031] Fps is (10 sec: 9829.1, 60 sec: 9352.3, 300 sec: 9275.0). Total num frames: 3059712. Throughput: 0: 2351.7. Samples: 760402. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
394
+ [2025-05-10 19:53:44,744][00031] Avg episode reward: [(0, '24.210')]
395
+ [2025-05-10 19:53:44,746][00187] Saving new best policy, reward=24.210!
396
+ [2025-05-10 19:53:46,030][00200] Updated weights for policy 0, policy_version 750 (0.0021)
397
+ [2025-05-10 19:53:49,741][00031] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 9275.0). Total num frames: 3104768. Throughput: 0: 2352.6. Samples: 774574. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
398
+ [2025-05-10 19:53:49,746][00031] Avg episode reward: [(0, '24.487')]
399
+ [2025-05-10 19:53:49,760][00187] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000758_3104768.pth...
400
+ [2025-05-10 19:53:49,847][00187] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000215_880640.pth
401
+ [2025-05-10 19:53:49,861][00187] Saving new best policy, reward=24.487!
402
+ [2025-05-10 19:53:50,772][00200] Updated weights for policy 0, policy_version 760 (0.0013)
403
+ [2025-05-10 19:53:54,742][00031] Fps is (10 sec: 8602.5, 60 sec: 9284.2, 300 sec: 9275.0). Total num frames: 3145728. Throughput: 0: 2311.0. Samples: 787248. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
404
+ [2025-05-10 19:53:54,743][00031] Avg episode reward: [(0, '20.059')]
405
+ [2025-05-10 19:53:55,280][00200] Updated weights for policy 0, policy_version 770 (0.0014)
406
+ [2025-05-10 19:53:59,699][00200] Updated weights for policy 0, policy_version 780 (0.0014)
407
+ [2025-05-10 19:53:59,742][00031] Fps is (10 sec: 9011.0, 60 sec: 9352.6, 300 sec: 9275.0). Total num frames: 3194880. Throughput: 0: 2308.2. Samples: 794220. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
408
+ [2025-05-10 19:53:59,743][00031] Avg episode reward: [(0, '18.747')]
409
+ [2025-05-10 19:54:03,936][00200] Updated weights for policy 0, policy_version 790 (0.0015)
410
+ [2025-05-10 19:54:04,742][00031] Fps is (10 sec: 9420.7, 60 sec: 9284.2, 300 sec: 9261.1). Total num frames: 3239936. Throughput: 0: 2334.4. Samples: 808570. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
411
+ [2025-05-10 19:54:04,745][00031] Avg episode reward: [(0, '19.168')]
412
+ [2025-05-10 19:54:08,084][00200] Updated weights for policy 0, policy_version 800 (0.0016)
413
+ [2025-05-10 19:54:09,744][00031] Fps is (10 sec: 9418.9, 60 sec: 9283.9, 300 sec: 9274.9). Total num frames: 3289088. Throughput: 0: 2351.7. Samples: 823228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
414
+ [2025-05-10 19:54:09,745][00031] Avg episode reward: [(0, '21.339')]
415
+ [2025-05-10 19:54:12,420][00200] Updated weights for policy 0, policy_version 810 (0.0016)
416
+ [2025-05-10 19:54:14,741][00031] Fps is (10 sec: 9830.7, 60 sec: 9352.5, 300 sec: 9275.0). Total num frames: 3338240. Throughput: 0: 2353.1. Samples: 830366. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
417
+ [2025-05-10 19:54:14,744][00031] Avg episode reward: [(0, '20.072')]
418
+ [2025-05-10 19:54:16,643][00200] Updated weights for policy 0, policy_version 820 (0.0016)
419
+ [2025-05-10 19:54:19,741][00031] Fps is (10 sec: 9832.6, 60 sec: 9489.1, 300 sec: 9288.9). Total num frames: 3387392. Throughput: 0: 2354.8. Samples: 844836. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
420
+ [2025-05-10 19:54:19,744][00031] Avg episode reward: [(0, '23.435')]
421
+ [2025-05-10 19:54:20,922][00200] Updated weights for policy 0, policy_version 830 (0.0018)
422
+ [2025-05-10 19:54:24,741][00031] Fps is (10 sec: 9011.1, 60 sec: 9352.5, 300 sec: 9288.9). Total num frames: 3428352. Throughput: 0: 2321.3. Samples: 857744. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
423
+ [2025-05-10 19:54:24,743][00031] Avg episode reward: [(0, '24.982')]
424
+ [2025-05-10 19:54:24,744][00187] Saving new best policy, reward=24.982!
425
+ [2025-05-10 19:54:25,883][00200] Updated weights for policy 0, policy_version 840 (0.0019)
426
+ [2025-05-10 19:54:29,743][00031] Fps is (10 sec: 9010.1, 60 sec: 9352.3, 300 sec: 9288.9). Total num frames: 3477504. Throughput: 0: 2323.8. Samples: 864972. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
427
+ [2025-05-10 19:54:29,744][00031] Avg episode reward: [(0, '21.124')]
428
+ [2025-05-10 19:54:30,071][00200] Updated weights for policy 0, policy_version 850 (0.0017)
429
+ [2025-05-10 19:54:34,332][00200] Updated weights for policy 0, policy_version 860 (0.0015)
430
+ [2025-05-10 19:54:34,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9288.9). Total num frames: 3522560. Throughput: 0: 2326.5. Samples: 879266. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
431
+ [2025-05-10 19:54:34,744][00031] Avg episode reward: [(0, '21.630')]
432
+ [2025-05-10 19:54:38,515][00200] Updated weights for policy 0, policy_version 870 (0.0014)
433
+ [2025-05-10 19:54:39,741][00031] Fps is (10 sec: 9422.1, 60 sec: 9352.5, 300 sec: 9288.9). Total num frames: 3571712. Throughput: 0: 2367.5. Samples: 893784. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
434
+ [2025-05-10 19:54:39,742][00031] Avg episode reward: [(0, '22.069')]
435
+ [2025-05-10 19:54:42,826][00200] Updated weights for policy 0, policy_version 880 (0.0016)
436
+ [2025-05-10 19:54:44,742][00031] Fps is (10 sec: 9830.1, 60 sec: 9352.7, 300 sec: 9302.8). Total num frames: 3620864. Throughput: 0: 2369.9. Samples: 900866. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
437
+ [2025-05-10 19:54:44,744][00031] Avg episode reward: [(0, '21.017')]
438
+ [2025-05-10 19:54:47,108][00200] Updated weights for policy 0, policy_version 890 (0.0015)
439
+ [2025-05-10 19:54:49,741][00031] Fps is (10 sec: 9830.3, 60 sec: 9420.8, 300 sec: 9302.8). Total num frames: 3670016. Throughput: 0: 2371.9. Samples: 915306. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
440
+ [2025-05-10 19:54:49,743][00031] Avg episode reward: [(0, '20.522')]
441
+ [2025-05-10 19:54:51,454][00200] Updated weights for policy 0, policy_version 900 (0.0016)
442
+ [2025-05-10 19:54:54,741][00031] Fps is (10 sec: 9421.1, 60 sec: 9489.1, 300 sec: 9302.8). Total num frames: 3715072. Throughput: 0: 2366.5. Samples: 929714. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
443
+ [2025-05-10 19:54:54,746][00031] Avg episode reward: [(0, '21.118')]
444
+ [2025-05-10 19:54:55,993][00200] Updated weights for policy 0, policy_version 910 (0.0017)
445
+ [2025-05-10 19:54:59,741][00031] Fps is (10 sec: 9011.2, 60 sec: 9420.8, 300 sec: 9316.7). Total num frames: 3760128. Throughput: 0: 2332.6. Samples: 935332. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
446
+ [2025-05-10 19:54:59,743][00031] Avg episode reward: [(0, '22.500')]
447
+ [2025-05-10 19:55:00,529][00200] Updated weights for policy 0, policy_version 920 (0.0015)
448
+ [2025-05-10 19:55:04,742][00031] Fps is (10 sec: 9010.7, 60 sec: 9420.8, 300 sec: 9302.8). Total num frames: 3805184. Throughput: 0: 2328.0. Samples: 949598. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
449
+ [2025-05-10 19:55:04,743][00031] Avg episode reward: [(0, '20.471')]
450
+ [2025-05-10 19:55:04,885][00200] Updated weights for policy 0, policy_version 930 (0.0019)
451
+ [2025-05-10 19:55:09,090][00200] Updated weights for policy 0, policy_version 940 (0.0016)
452
+ [2025-05-10 19:55:09,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9421.1, 300 sec: 9302.8). Total num frames: 3854336. Throughput: 0: 2366.7. Samples: 964246. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
453
+ [2025-05-10 19:55:09,743][00031] Avg episode reward: [(0, '19.768')]
454
+ [2025-05-10 19:55:13,301][00200] Updated weights for policy 0, policy_version 950 (0.0014)
455
+ [2025-05-10 19:55:14,741][00031] Fps is (10 sec: 9831.0, 60 sec: 9420.8, 300 sec: 9316.7). Total num frames: 3903488. Throughput: 0: 2365.9. Samples: 971434. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
456
+ [2025-05-10 19:55:14,742][00031] Avg episode reward: [(0, '21.574')]
457
+ [2025-05-10 19:55:17,573][00200] Updated weights for policy 0, policy_version 960 (0.0015)
458
+ [2025-05-10 19:55:19,741][00031] Fps is (10 sec: 9830.4, 60 sec: 9420.8, 300 sec: 9316.7). Total num frames: 3952640. Throughput: 0: 2370.7. Samples: 985948. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
459
+ [2025-05-10 19:55:19,743][00031] Avg episode reward: [(0, '21.834')]
460
+ [2025-05-10 19:55:21,841][00200] Updated weights for policy 0, policy_version 970 (0.0016)
461
+ [2025-05-10 19:55:24,741][00031] Fps is (10 sec: 9420.8, 60 sec: 9489.1, 300 sec: 9302.8). Total num frames: 3997696. Throughput: 0: 2370.2. Samples: 1000442. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
462
+ [2025-05-10 19:55:24,744][00031] Avg episode reward: [(0, '22.816')]
463
+ [2025-05-10 19:55:25,190][00187] Stopping Batcher_0...
464
+ [2025-05-10 19:55:25,192][00187] Loop batcher_evt_loop terminating...
465
+ [2025-05-10 19:55:25,191][00187] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
466
+ [2025-05-10 19:55:25,191][00031] Component Batcher_0 stopped!
467
+ [2025-05-10 19:55:25,224][00200] Weights refcount: 2 0
468
+ [2025-05-10 19:55:25,226][00200] Stopping InferenceWorker_p0-w0...
469
+ [2025-05-10 19:55:25,229][00200] Loop inference_proc0-0_evt_loop terminating...
470
+ [2025-05-10 19:55:25,227][00031] Component InferenceWorker_p0-w0 stopped!
471
+ [2025-05-10 19:55:25,285][00187] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000485_1986560.pth
472
+ [2025-05-10 19:55:25,300][00187] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
473
+ [2025-05-10 19:55:25,302][00206] Stopping RolloutWorker_w5...
474
+ [2025-05-10 19:55:25,302][00206] Loop rollout_proc5_evt_loop terminating...
475
+ [2025-05-10 19:55:25,301][00031] Component RolloutWorker_w2 stopped!
476
+ [2025-05-10 19:55:25,305][00031] Component RolloutWorker_w5 stopped!
477
+ [2025-05-10 19:55:25,307][00203] Stopping RolloutWorker_w2...
478
+ [2025-05-10 19:55:25,308][00203] Loop rollout_proc2_evt_loop terminating...
479
+ [2025-05-10 19:55:25,312][00031] Component RolloutWorker_w6 stopped!
480
+ [2025-05-10 19:55:25,311][00207] Stopping RolloutWorker_w6...
481
+ [2025-05-10 19:55:25,314][00031] Component RolloutWorker_w1 stopped!
482
+ [2025-05-10 19:55:25,313][00202] Stopping RolloutWorker_w1...
483
+ [2025-05-10 19:55:25,315][00202] Loop rollout_proc1_evt_loop terminating...
484
+ [2025-05-10 19:55:25,314][00207] Loop rollout_proc6_evt_loop terminating...
485
+ [2025-05-10 19:55:25,462][00187] Stopping LearnerWorker_p0...
486
+ [2025-05-10 19:55:25,462][00187] Loop learner_proc0_evt_loop terminating...
487
+ [2025-05-10 19:55:25,462][00031] Component LearnerWorker_p0 stopped!
488
+ [2025-05-10 19:55:25,497][00031] Component RolloutWorker_w7 stopped!
489
+ [2025-05-10 19:55:25,496][00208] Stopping RolloutWorker_w7...
490
+ [2025-05-10 19:55:25,500][00208] Loop rollout_proc7_evt_loop terminating...
491
+ [2025-05-10 19:55:25,501][00031] Component RolloutWorker_w3 stopped!
492
+ [2025-05-10 19:55:25,501][00204] Stopping RolloutWorker_w3...
493
+ [2025-05-10 19:55:25,503][00204] Loop rollout_proc3_evt_loop terminating...
494
+ [2025-05-10 19:55:25,509][00031] Component RolloutWorker_w0 stopped!
495
+ [2025-05-10 19:55:25,510][00205] Stopping RolloutWorker_w4...
496
+ [2025-05-10 19:55:25,511][00205] Loop rollout_proc4_evt_loop terminating...
497
+ [2025-05-10 19:55:25,512][00031] Component RolloutWorker_w4 stopped!
498
+ [2025-05-10 19:55:25,509][00201] Stopping RolloutWorker_w0...
499
+ [2025-05-10 19:55:25,517][00201] Loop rollout_proc0_evt_loop terminating...
500
+ [2025-05-10 19:55:25,515][00031] Waiting for process learner_proc0 to stop...
501
+ [2025-05-10 19:55:26,924][00031] Waiting for process inference_proc0-0 to join...
502
+ [2025-05-10 19:55:26,929][00031] Waiting for process rollout_proc0 to join...
503
+ [2025-05-10 19:55:27,203][00031] Waiting for process rollout_proc1 to join...
504
+ [2025-05-10 19:55:27,550][00031] Waiting for process rollout_proc2 to join...
505
+ [2025-05-10 19:55:27,552][00031] Waiting for process rollout_proc3 to join...
506
+ [2025-05-10 19:55:27,553][00031] Waiting for process rollout_proc4 to join...
507
+ [2025-05-10 19:55:27,554][00031] Waiting for process rollout_proc5 to join...
508
+ [2025-05-10 19:55:27,555][00031] Waiting for process rollout_proc6 to join...
509
+ [2025-05-10 19:55:27,556][00031] Waiting for process rollout_proc7 to join...
510
+ [2025-05-10 19:55:27,557][00031] Batcher 0 profile tree view:
511
+ batching: 20.5293, releasing_batches: 0.0235
512
+ [2025-05-10 19:55:27,558][00031] InferenceWorker_p0-w0 profile tree view:
513
+ wait_policy: 0.0000
514
+ wait_policy_total: 13.6289
515
+ update_model: 6.0515
516
+ weight_update: 0.0013
517
+ one_step: 0.0030
518
+ handle_policy_step: 397.8757
519
+ deserialize: 11.9171, stack: 2.4570, obs_to_device_normalize: 97.0456, forward: 195.9540, send_messages: 20.8423
520
+ prepare_outputs: 53.5468
521
+ to_cpu: 34.9484
522
+ [2025-05-10 19:55:27,558][00031] Learner 0 profile tree view:
523
+ misc: 0.0037, prepare_batch: 12.2781
524
+ train: 51.1951
525
+ epoch_init: 0.0045, minibatch_init: 0.0059, losses_postprocess: 0.5428, kl_divergence: 0.5473, after_optimizer: 22.6953
526
+ calculate_losses: 17.2665
527
+ losses_init: 0.0042, forward_head: 1.0267, bptt_initial: 11.9716, tail: 0.7288, advantages_returns: 0.1925, losses: 1.7550
528
+ bptt: 1.4069
529
+ bptt_forward_core: 1.3421
530
+ update: 9.7542
531
+ clip: 0.8316
532
+ [2025-05-10 19:55:27,559][00031] RolloutWorker_w0 profile tree view:
533
+ wait_for_trajectories: 0.1654, enqueue_policy_requests: 7.4893, env_step: 316.0504, overhead: 6.2936, complete_rollouts: 1.1252
534
+ save_policy_outputs: 8.8704
535
+ split_output_tensors: 3.4497
536
+ [2025-05-10 19:55:27,560][00031] RolloutWorker_w7 profile tree view:
537
+ wait_for_trajectories: 0.1546, enqueue_policy_requests: 7.7793, env_step: 314.2617, overhead: 6.5336, complete_rollouts: 1.0742
538
+ save_policy_outputs: 9.1472
539
+ split_output_tensors: 3.4687
540
+ [2025-05-10 19:55:27,562][00031] Loop Runner_EvtLoop terminating...
541
+ [2025-05-10 19:55:27,563][00031] Runner profile tree view:
542
+ main_loop: 452.8763
543
+ [2025-05-10 19:55:27,564][00031] Collected {0: 4005888}, FPS: 8845.4
544
+ [2025-05-10 19:55:27,996][00031] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
545
+ [2025-05-10 19:55:27,997][00031] Overriding arg 'num_workers' with value 1 passed from command line
546
+ [2025-05-10 19:55:27,997][00031] Adding new argument 'no_render'=True that is not in the saved config file!
547
+ [2025-05-10 19:55:27,998][00031] Adding new argument 'save_video'=True that is not in the saved config file!
548
+ [2025-05-10 19:55:27,999][00031] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
549
+ [2025-05-10 19:55:28,000][00031] Adding new argument 'video_name'=None that is not in the saved config file!
550
+ [2025-05-10 19:55:28,001][00031] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
551
+ [2025-05-10 19:55:28,002][00031] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
552
+ [2025-05-10 19:55:28,003][00031] Adding new argument 'push_to_hub'=False that is not in the saved config file!
553
+ [2025-05-10 19:55:28,003][00031] Adding new argument 'hf_repository'=None that is not in the saved config file!
554
+ [2025-05-10 19:55:28,004][00031] Adding new argument 'policy_index'=0 that is not in the saved config file!
555
+ [2025-05-10 19:55:28,006][00031] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
556
+ [2025-05-10 19:55:28,006][00031] Adding new argument 'train_script'=None that is not in the saved config file!
557
+ [2025-05-10 19:55:28,007][00031] Adding new argument 'enjoy_script'=None that is not in the saved config file!
558
+ [2025-05-10 19:55:28,008][00031] Using frameskip 1 and render_action_repeat=4 for evaluation
559
+ [2025-05-10 19:55:28,038][00031] Doom resolution: 160x120, resize resolution: (128, 72)
560
+ [2025-05-10 19:55:28,041][00031] RunningMeanStd input shape: (3, 72, 128)
561
+ [2025-05-10 19:55:28,042][00031] RunningMeanStd input shape: (1,)
562
+ [2025-05-10 19:55:28,059][00031] ConvEncoder: input_channels=3
563
+ [2025-05-10 19:55:28,172][00031] Conv encoder output size: 512
564
+ [2025-05-10 19:55:28,173][00031] Policy head output size: 512
565
+ [2025-05-10 19:55:28,372][00031] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
566
+ [2025-05-10 19:55:29,224][00031] Num frames 100...
567
+ [2025-05-10 19:55:29,338][00031] Num frames 200...
568
+ [2025-05-10 19:55:29,457][00031] Num frames 300...
569
+ [2025-05-10 19:55:29,571][00031] Num frames 400...
570
+ [2025-05-10 19:55:29,686][00031] Num frames 500...
571
+ [2025-05-10 19:55:29,845][00031] Avg episode rewards: #0: 13.920, true rewards: #0: 5.920
572
+ [2025-05-10 19:55:29,846][00031] Avg episode reward: 13.920, avg true_objective: 5.920
573
+ [2025-05-10 19:55:29,857][00031] Num frames 600...
574
+ [2025-05-10 19:55:29,977][00031] Num frames 700...
575
+ [2025-05-10 19:55:30,098][00031] Num frames 800...
576
+ [2025-05-10 19:55:30,222][00031] Num frames 900...
577
+ [2025-05-10 19:55:30,344][00031] Num frames 1000...
578
+ [2025-05-10 19:55:30,464][00031] Num frames 1100...
579
+ [2025-05-10 19:55:30,585][00031] Num frames 1200...
580
+ [2025-05-10 19:55:30,713][00031] Num frames 1300...
581
+ [2025-05-10 19:55:30,834][00031] Num frames 1400...
582
+ [2025-05-10 19:55:30,961][00031] Num frames 1500...
583
+ [2025-05-10 19:55:31,072][00031] Num frames 1600...
584
+ [2025-05-10 19:55:31,209][00031] Num frames 1700...
585
+ [2025-05-10 19:55:31,320][00031] Num frames 1800...
586
+ [2025-05-10 19:55:31,433][00031] Num frames 1900...
587
+ [2025-05-10 19:55:31,547][00031] Num frames 2000...
588
+ [2025-05-10 19:55:31,660][00031] Num frames 2100...
589
+ [2025-05-10 19:55:31,784][00031] Avg episode rewards: #0: 23.775, true rewards: #0: 10.775
590
+ [2025-05-10 19:55:31,785][00031] Avg episode reward: 23.775, avg true_objective: 10.775
591
+ [2025-05-10 19:55:31,841][00031] Num frames 2200...
592
+ [2025-05-10 19:55:31,963][00031] Num frames 2300...
593
+ [2025-05-10 19:55:32,078][00031] Num frames 2400...
594
+ [2025-05-10 19:55:32,189][00031] Num frames 2500...
595
+ [2025-05-10 19:55:32,305][00031] Num frames 2600...
596
+ [2025-05-10 19:55:32,418][00031] Num frames 2700...
597
+ [2025-05-10 19:55:32,530][00031] Num frames 2800...
598
+ [2025-05-10 19:55:32,644][00031] Num frames 2900...
599
+ [2025-05-10 19:55:32,756][00031] Num frames 3000...
600
+ [2025-05-10 19:55:32,873][00031] Num frames 3100...
601
+ [2025-05-10 19:55:32,985][00031] Num frames 3200...
602
+ [2025-05-10 19:55:33,098][00031] Num frames 3300...
603
+ [2025-05-10 19:55:33,217][00031] Num frames 3400...
604
+ [2025-05-10 19:55:33,335][00031] Num frames 3500...
605
+ [2025-05-10 19:55:33,449][00031] Num frames 3600...
606
+ [2025-05-10 19:55:33,544][00031] Avg episode rewards: #0: 27.780, true rewards: #0: 12.113
607
+ [2025-05-10 19:55:33,545][00031] Avg episode reward: 27.780, avg true_objective: 12.113
608
+ [2025-05-10 19:55:33,618][00031] Num frames 3700...
609
+ [2025-05-10 19:55:33,730][00031] Num frames 3800...
610
+ [2025-05-10 19:55:33,842][00031] Num frames 3900...
611
+ [2025-05-10 19:55:33,955][00031] Num frames 4000...
612
+ [2025-05-10 19:55:34,030][00031] Avg episode rewards: #0: 21.795, true rewards: #0: 10.045
613
+ [2025-05-10 19:55:34,031][00031] Avg episode reward: 21.795, avg true_objective: 10.045
614
+ [2025-05-10 19:55:34,124][00031] Num frames 4100...
615
+ [2025-05-10 19:55:34,243][00031] Num frames 4200...
616
+ [2025-05-10 19:55:34,369][00031] Num frames 4300...
617
+ [2025-05-10 19:55:34,487][00031] Num frames 4400...
618
+ [2025-05-10 19:55:34,603][00031] Num frames 4500...
619
+ [2025-05-10 19:55:34,715][00031] Num frames 4600...
620
+ [2025-05-10 19:55:34,828][00031] Num frames 4700...
621
+ [2025-05-10 19:55:34,944][00031] Num frames 4800...
622
+ [2025-05-10 19:55:35,062][00031] Num frames 4900...
623
+ [2025-05-10 19:55:35,184][00031] Num frames 5000...
624
+ [2025-05-10 19:55:35,306][00031] Num frames 5100...
625
+ [2025-05-10 19:55:35,422][00031] Num frames 5200...
626
+ [2025-05-10 19:55:35,542][00031] Num frames 5300...
627
+ [2025-05-10 19:55:35,661][00031] Num frames 5400...
628
+ [2025-05-10 19:55:35,780][00031] Num frames 5500...
629
+ [2025-05-10 19:55:35,903][00031] Num frames 5600...
630
+ [2025-05-10 19:55:36,014][00031] Avg episode rewards: #0: 25.500, true rewards: #0: 11.300
631
+ [2025-05-10 19:55:36,014][00031] Avg episode reward: 25.500, avg true_objective: 11.300
632
+ [2025-05-10 19:55:36,071][00031] Num frames 5700...
633
+ [2025-05-10 19:55:36,184][00031] Num frames 5800...
634
+ [2025-05-10 19:55:36,299][00031] Num frames 5900...
635
+ [2025-05-10 19:55:36,414][00031] Num frames 6000...
636
+ [2025-05-10 19:55:36,528][00031] Num frames 6100...
637
+ [2025-05-10 19:55:36,646][00031] Num frames 6200...
638
+ [2025-05-10 19:55:36,767][00031] Num frames 6300...
639
+ [2025-05-10 19:55:36,883][00031] Num frames 6400...
640
+ [2025-05-10 19:55:36,999][00031] Num frames 6500...
641
+ [2025-05-10 19:55:37,119][00031] Num frames 6600...
642
+ [2025-05-10 19:55:37,231][00031] Num frames 6700...
643
+ [2025-05-10 19:55:37,345][00031] Num frames 6800...
644
+ [2025-05-10 19:55:37,456][00031] Num frames 6900...
645
+ [2025-05-10 19:55:37,570][00031] Num frames 7000...
646
+ [2025-05-10 19:55:37,691][00031] Num frames 7100...
647
+ [2025-05-10 19:55:37,812][00031] Num frames 7200...
648
+ [2025-05-10 19:55:37,930][00031] Num frames 7300...
649
+ [2025-05-10 19:55:38,010][00031] Avg episode rewards: #0: 29.035, true rewards: #0: 12.202
650
+ [2025-05-10 19:55:38,010][00031] Avg episode reward: 29.035, avg true_objective: 12.202
651
+ [2025-05-10 19:55:38,097][00031] Num frames 7400...
652
+ [2025-05-10 19:55:38,213][00031] Num frames 7500...
653
+ [2025-05-10 19:55:38,326][00031] Num frames 7600...
654
+ [2025-05-10 19:55:38,445][00031] Num frames 7700...
655
+ [2025-05-10 19:55:38,565][00031] Num frames 7800...
656
+ [2025-05-10 19:55:38,660][00031] Avg episode rewards: #0: 26.047, true rewards: #0: 11.190
657
+ [2025-05-10 19:55:38,661][00031] Avg episode reward: 26.047, avg true_objective: 11.190
658
+ [2025-05-10 19:55:38,737][00031] Num frames 7900...
659
+ [2025-05-10 19:55:38,856][00031] Num frames 8000...
660
+ [2025-05-10 19:55:38,977][00031] Num frames 8100...
661
+ [2025-05-10 19:55:39,096][00031] Num frames 8200...
662
+ [2025-05-10 19:55:39,214][00031] Num frames 8300...
663
+ [2025-05-10 19:55:39,333][00031] Num frames 8400...
664
+ [2025-05-10 19:55:39,451][00031] Num frames 8500...
665
+ [2025-05-10 19:55:39,570][00031] Num frames 8600...
666
+ [2025-05-10 19:55:39,691][00031] Num frames 8700...
667
+ [2025-05-10 19:55:39,811][00031] Num frames 8800...
668
+ [2025-05-10 19:55:39,929][00031] Num frames 8900...
669
+ [2025-05-10 19:55:40,042][00031] Num frames 9000...
670
+ [2025-05-10 19:55:40,157][00031] Num frames 9100...
671
+ [2025-05-10 19:55:40,273][00031] Num frames 9200...
672
+ [2025-05-10 19:55:40,389][00031] Num frames 9300...
673
+ [2025-05-10 19:55:40,507][00031] Num frames 9400...
674
+ [2025-05-10 19:55:40,633][00031] Avg episode rewards: #0: 26.955, true rewards: #0: 11.830
675
+ [2025-05-10 19:55:40,634][00031] Avg episode reward: 26.955, avg true_objective: 11.830
676
+ [2025-05-10 19:55:40,675][00031] Num frames 9500...
677
+ [2025-05-10 19:55:40,787][00031] Num frames 9600...
678
+ [2025-05-10 19:55:40,906][00031] Num frames 9700...
679
+ [2025-05-10 19:55:41,029][00031] Num frames 9800...
680
+ [2025-05-10 19:55:41,168][00031] Num frames 9900...
681
+ [2025-05-10 19:55:41,284][00031] Num frames 10000...
682
+ [2025-05-10 19:55:41,404][00031] Num frames 10100...
683
+ [2025-05-10 19:55:41,502][00031] Avg episode rewards: #0: 25.707, true rewards: #0: 11.262
684
+ [2025-05-10 19:55:41,503][00031] Avg episode reward: 25.707, avg true_objective: 11.262
685
+ [2025-05-10 19:55:41,580][00031] Num frames 10200...
686
+ [2025-05-10 19:55:41,700][00031] Num frames 10300...
687
+ [2025-05-10 19:55:41,814][00031] Num frames 10400...
688
+ [2025-05-10 19:55:41,932][00031] Avg episode rewards: #0: 23.556, true rewards: #0: 10.456
689
+ [2025-05-10 19:55:41,933][00031] Avg episode reward: 23.556, avg true_objective: 10.456
690
+ [2025-05-10 19:56:17,261][00031] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
691
+ [2025-05-10 19:57:48,043][00031] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
692
+ [2025-05-10 19:57:48,044][00031] Overriding arg 'num_workers' with value 1 passed from command line
693
+ [2025-05-10 19:57:48,045][00031] Adding new argument 'no_render'=True that is not in the saved config file!
694
+ [2025-05-10 19:57:48,046][00031] Adding new argument 'save_video'=True that is not in the saved config file!
695
+ [2025-05-10 19:57:48,047][00031] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
696
+ [2025-05-10 19:57:48,048][00031] Adding new argument 'video_name'=None that is not in the saved config file!
697
+ [2025-05-10 19:57:48,049][00031] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
698
+ [2025-05-10 19:57:48,049][00031] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
699
+ [2025-05-10 19:57:48,051][00031] Adding new argument 'push_to_hub'=True that is not in the saved config file!
700
+ [2025-05-10 19:57:48,051][00031] Adding new argument 'hf_repository'='aalva/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
701
+ [2025-05-10 19:57:48,052][00031] Adding new argument 'policy_index'=0 that is not in the saved config file!
702
+ [2025-05-10 19:57:48,053][00031] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
703
+ [2025-05-10 19:57:48,054][00031] Adding new argument 'train_script'=None that is not in the saved config file!
704
+ [2025-05-10 19:57:48,054][00031] Adding new argument 'enjoy_script'=None that is not in the saved config file!
705
+ [2025-05-10 19:57:48,055][00031] Using frameskip 1 and render_action_repeat=4 for evaluation
706
+ [2025-05-10 19:57:48,087][00031] RunningMeanStd input shape: (3, 72, 128)
707
+ [2025-05-10 19:57:48,088][00031] RunningMeanStd input shape: (1,)
708
+ [2025-05-10 19:57:48,099][00031] ConvEncoder: input_channels=3
709
+ [2025-05-10 19:57:48,132][00031] Conv encoder output size: 512
710
+ [2025-05-10 19:57:48,133][00031] Policy head output size: 512
711
+ [2025-05-10 19:57:48,154][00031] Loading state from checkpoint /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
712
+ [2025-05-10 19:57:48,614][00031] Num frames 100...
713
+ [2025-05-10 19:57:48,727][00031] Num frames 200...
714
+ [2025-05-10 19:57:48,840][00031] Num frames 300...
715
+ [2025-05-10 19:57:48,952][00031] Num frames 400...
716
+ [2025-05-10 19:57:49,062][00031] Num frames 500...
717
+ [2025-05-10 19:57:49,179][00031] Num frames 600...
718
+ [2025-05-10 19:57:49,294][00031] Num frames 700...
719
+ [2025-05-10 19:57:49,402][00031] Num frames 800...
720
+ [2025-05-10 19:57:49,519][00031] Num frames 900...
721
+ [2025-05-10 19:57:49,634][00031] Num frames 1000...
722
+ [2025-05-10 19:57:49,774][00031] Avg episode rewards: #0: 23.700, true rewards: #0: 10.700
723
+ [2025-05-10 19:57:49,775][00031] Avg episode reward: 23.700, avg true_objective: 10.700
724
+ [2025-05-10 19:57:49,812][00031] Num frames 1100...
725
+ [2025-05-10 19:57:49,932][00031] Num frames 1200...
726
+ [2025-05-10 19:57:50,054][00031] Num frames 1300...
727
+ [2025-05-10 19:57:50,172][00031] Num frames 1400...
728
+ [2025-05-10 19:57:50,287][00031] Num frames 1500...
729
+ [2025-05-10 19:57:50,402][00031] Num frames 1600...
730
+ [2025-05-10 19:57:50,516][00031] Num frames 1700...
731
+ [2025-05-10 19:57:50,632][00031] Num frames 1800...
732
+ [2025-05-10 19:57:50,744][00031] Num frames 1900...
733
+ [2025-05-10 19:57:50,838][00031] Avg episode rewards: #0: 20.670, true rewards: #0: 9.670
734
+ [2025-05-10 19:57:50,839][00031] Avg episode reward: 20.670, avg true_objective: 9.670
735
+ [2025-05-10 19:57:50,916][00031] Num frames 2000...
736
+ [2025-05-10 19:57:51,040][00031] Num frames 2100...
737
+ [2025-05-10 19:57:51,177][00031] Num frames 2200...
738
+ [2025-05-10 19:57:51,297][00031] Num frames 2300...
739
+ [2025-05-10 19:57:51,418][00031] Num frames 2400...
740
+ [2025-05-10 19:57:51,540][00031] Num frames 2500...
741
+ [2025-05-10 19:57:51,660][00031] Num frames 2600...
742
+ [2025-05-10 19:57:51,777][00031] Num frames 2700...
743
+ [2025-05-10 19:57:51,894][00031] Num frames 2800...
744
+ [2025-05-10 19:57:52,056][00031] Avg episode rewards: #0: 20.647, true rewards: #0: 9.647
745
+ [2025-05-10 19:57:52,057][00031] Avg episode reward: 20.647, avg true_objective: 9.647
746
+ [2025-05-10 19:57:52,064][00031] Num frames 2900...
747
+ [2025-05-10 19:57:52,185][00031] Num frames 3000...
748
+ [2025-05-10 19:57:52,308][00031] Num frames 3100...
749
+ [2025-05-10 19:57:52,434][00031] Num frames 3200...
750
+ [2025-05-10 19:57:52,549][00031] Num frames 3300...
751
+ [2025-05-10 19:57:52,659][00031] Num frames 3400...
752
+ [2025-05-10 19:57:52,792][00031] Avg episode rewards: #0: 17.925, true rewards: #0: 8.675
753
+ [2025-05-10 19:57:52,793][00031] Avg episode reward: 17.925, avg true_objective: 8.675
754
+ [2025-05-10 19:57:52,828][00031] Num frames 3500...
755
+ [2025-05-10 19:57:52,945][00031] Num frames 3600...
756
+ [2025-05-10 19:57:53,054][00031] Num frames 3700...
757
+ [2025-05-10 19:57:53,168][00031] Num frames 3800...
758
+ [2025-05-10 19:57:53,288][00031] Num frames 3900...
759
+ [2025-05-10 19:57:53,436][00031] Avg episode rewards: #0: 16.156, true rewards: #0: 7.956
760
+ [2025-05-10 19:57:53,437][00031] Avg episode reward: 16.156, avg true_objective: 7.956
761
+ [2025-05-10 19:57:53,463][00031] Num frames 4000...
762
+ [2025-05-10 19:57:53,576][00031] Num frames 4100...
763
+ [2025-05-10 19:57:53,687][00031] Num frames 4200...
764
+ [2025-05-10 19:57:53,799][00031] Num frames 4300...
765
+ [2025-05-10 19:57:53,911][00031] Num frames 4400...
766
+ [2025-05-10 19:57:54,025][00031] Num frames 4500...
767
+ [2025-05-10 19:57:54,139][00031] Num frames 4600...
768
+ [2025-05-10 19:57:54,264][00031] Avg episode rewards: #0: 16.268, true rewards: #0: 7.768
769
+ [2025-05-10 19:57:54,265][00031] Avg episode reward: 16.268, avg true_objective: 7.768
770
+ [2025-05-10 19:57:54,314][00031] Num frames 4700...
771
+ [2025-05-10 19:57:54,432][00031] Num frames 4800...
772
+ [2025-05-10 19:57:54,546][00031] Num frames 4900...
773
+ [2025-05-10 19:57:54,662][00031] Num frames 5000...
774
+ [2025-05-10 19:57:54,783][00031] Num frames 5100...
775
+ [2025-05-10 19:57:54,902][00031] Num frames 5200...
776
+ [2025-05-10 19:57:55,019][00031] Num frames 5300...
777
+ [2025-05-10 19:57:55,140][00031] Num frames 5400...
778
+ [2025-05-10 19:57:55,258][00031] Num frames 5500...
779
+ [2025-05-10 19:57:55,370][00031] Num frames 5600...
780
+ [2025-05-10 19:57:55,481][00031] Num frames 5700...
781
+ [2025-05-10 19:57:55,596][00031] Num frames 5800...
782
+ [2025-05-10 19:57:55,704][00031] Avg episode rewards: #0: 17.779, true rewards: #0: 8.350
783
+ [2025-05-10 19:57:55,704][00031] Avg episode reward: 17.779, avg true_objective: 8.350
784
+ [2025-05-10 19:57:55,764][00031] Num frames 5900...
785
+ [2025-05-10 19:57:55,881][00031] Num frames 6000...
786
+ [2025-05-10 19:57:56,011][00031] Num frames 6100...
787
+ [2025-05-10 19:57:56,132][00031] Num frames 6200...
788
+ [2025-05-10 19:57:56,246][00031] Num frames 6300...
789
+ [2025-05-10 19:57:56,363][00031] Num frames 6400...
790
+ [2025-05-10 19:57:56,486][00031] Num frames 6500...
791
+ [2025-05-10 19:57:56,605][00031] Num frames 6600...
792
+ [2025-05-10 19:57:56,725][00031] Num frames 6700...
793
+ [2025-05-10 19:57:56,845][00031] Num frames 6800...
794
+ [2025-05-10 19:57:56,969][00031] Num frames 6900...
795
+ [2025-05-10 19:57:57,090][00031] Num frames 7000...
796
+ [2025-05-10 19:57:57,208][00031] Num frames 7100...
797
+ [2025-05-10 19:57:57,328][00031] Num frames 7200...
798
+ [2025-05-10 19:57:57,439][00031] Num frames 7300...
799
+ [2025-05-10 19:57:57,554][00031] Num frames 7400...
800
+ [2025-05-10 19:57:57,643][00031] Avg episode rewards: #0: 20.913, true rewards: #0: 9.287
801
+ [2025-05-10 19:57:57,644][00031] Avg episode reward: 20.913, avg true_objective: 9.287
802
+ [2025-05-10 19:57:57,722][00031] Num frames 7500...
803
+ [2025-05-10 19:57:57,836][00031] Num frames 7600...
804
+ [2025-05-10 19:57:57,950][00031] Num frames 7700...
805
+ [2025-05-10 19:57:58,070][00031] Num frames 7800...
806
+ [2025-05-10 19:57:58,183][00031] Num frames 7900...
807
+ [2025-05-10 19:57:58,298][00031] Num frames 8000...
808
+ [2025-05-10 19:57:58,410][00031] Num frames 8100...
809
+ [2025-05-10 19:57:58,523][00031] Num frames 8200...
810
+ [2025-05-10 19:57:58,614][00031] Avg episode rewards: #0: 20.256, true rewards: #0: 9.144
811
+ [2025-05-10 19:57:58,614][00031] Avg episode reward: 20.256, avg true_objective: 9.144
812
+ [2025-05-10 19:57:58,693][00031] Num frames 8300...
813
+ [2025-05-10 19:57:58,802][00031] Num frames 8400...
814
+ [2025-05-10 19:57:58,912][00031] Num frames 8500...
815
+ [2025-05-10 19:57:59,024][00031] Num frames 8600...
816
+ [2025-05-10 19:57:59,133][00031] Num frames 8700...
817
+ [2025-05-10 19:57:59,245][00031] Num frames 8800...
818
+ [2025-05-10 19:57:59,380][00031] Avg episode rewards: #0: 19.670, true rewards: #0: 8.870
819
+ [2025-05-10 19:57:59,381][00031] Avg episode reward: 19.670, avg true_objective: 8.870
820
+ [2025-05-10 19:58:29,074][00031] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!