Hugging Face's logo

wowthecoder
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
wowthecoder commited on
Commit
a433b92
·
verified ·
1 Parent(s): 551a1d2

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1748171378.8e9b4f0c3602 +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000724_2965504_reward_5.979.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 +686 -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.1748171378.8e9b4f0c3602 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9f84bbc695393995da8dd444d30ab264446d53d15f3627d81205c8e59198e422
3
+ size 417263
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: 4.01 +/- 0.49
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 wowthecoder/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_000000724_2965504_reward_5.979.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bbda5e1a44ce0ae59e7337e47e1f96a1ba680023ddb6ccbd7d075505b529b2ef
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 sha256:91acde48340597d72b5932052d404dcb52d71c6c6909a96200e5970629b910f2
3
+ size 34929541
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:377f92a2846ba91b553d71c83e4e6154589070b5d787290a69408979f7112e16
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 sha256:4ad9449019606121a5467fb1ff155f36ae329300f095d7a51691cfee599e679f
3
+ size 3607013
sf_log.txt ADDED
@@ -0,0 +1,686 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2025-05-25 11:09:42,915][00035] Saving configuration to /kaggle/working/train_dir/default_experiment/config.json...
2
+ [2025-05-25 11:09:42,917][00035] Rollout worker 0 uses device cpu
3
+ [2025-05-25 11:09:42,917][00035] Rollout worker 1 uses device cpu
4
+ [2025-05-25 11:09:42,918][00035] Rollout worker 2 uses device cpu
5
+ [2025-05-25 11:09:42,919][00035] Rollout worker 3 uses device cpu
6
+ [2025-05-25 11:09:42,920][00035] Rollout worker 4 uses device cpu
7
+ [2025-05-25 11:09:42,921][00035] Rollout worker 5 uses device cpu
8
+ [2025-05-25 11:09:42,921][00035] Rollout worker 6 uses device cpu
9
+ [2025-05-25 11:09:42,922][00035] Rollout worker 7 uses device cpu
10
+ [2025-05-25 11:09:43,047][00035] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2025-05-25 11:09:43,048][00035] InferenceWorker_p0-w0: min num requests: 2
12
+ [2025-05-25 11:09:43,092][00035] Starting all processes...
13
+ [2025-05-25 11:09:43,092][00035] Starting process learner_proc0
14
+ [2025-05-25 11:09:43,184][00035] Starting all processes...
15
+ [2025-05-25 11:09:43,195][00035] Starting process inference_proc0-0
16
+ [2025-05-25 11:09:43,195][00035] Starting process rollout_proc0
17
+ [2025-05-25 11:09:43,195][00035] Starting process rollout_proc1
18
+ [2025-05-25 11:09:43,196][00035] Starting process rollout_proc2
19
+ [2025-05-25 11:09:43,197][00035] Starting process rollout_proc3
20
+ [2025-05-25 11:09:43,197][00035] Starting process rollout_proc4
21
+ [2025-05-25 11:09:43,197][00035] Starting process rollout_proc5
22
+ [2025-05-25 11:09:43,198][00035] Starting process rollout_proc6
23
+ [2025-05-25 11:09:43,199][00035] Starting process rollout_proc7
24
+ [2025-05-25 11:09:50,891][01047] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2025-05-25 11:09:50,891][01047] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
26
+ [2025-05-25 11:09:50,957][01047] Num visible devices: 1
27
+ [2025-05-25 11:09:50,964][01047] Starting seed is not provided
28
+ [2025-05-25 11:09:50,965][01047] Using GPUs [0] for process 0 (actually maps to GPUs [0])
29
+ [2025-05-25 11:09:50,965][01047] Initializing actor-critic model on device cuda:0
30
+ [2025-05-25 11:09:50,966][01047] RunningMeanStd input shape: (3, 72, 128)
31
+ [2025-05-25 11:09:50,972][01047] RunningMeanStd input shape: (1,)
32
+ [2025-05-25 11:09:51,032][01047] ConvEncoder: input_channels=3
33
+ [2025-05-25 11:09:51,371][01061] Worker 2 uses CPU cores [2]
34
+ [2025-05-25 11:09:51,651][01060] Using GPUs [0] for process 0 (actually maps to GPUs [0])
35
+ [2025-05-25 11:09:51,652][01060] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
36
+ [2025-05-25 11:09:51,669][01047] Conv encoder output size: 512
37
+ [2025-05-25 11:09:51,670][01047] Policy head output size: 512
38
+ [2025-05-25 11:09:51,723][01060] Num visible devices: 1
39
+ [2025-05-25 11:09:51,826][01068] Worker 6 uses CPU cores [2]
40
+ [2025-05-25 11:09:51,837][01047] Created Actor Critic model with architecture:
41
+ [2025-05-25 11:09:51,837][01047] ActorCriticSharedWeights(
42
+ (obs_normalizer): ObservationNormalizer(
43
+ (running_mean_std): RunningMeanStdDictInPlace(
44
+ (running_mean_std): ModuleDict(
45
+ (obs): RunningMeanStdInPlace()
46
+ )
47
+ )
48
+ )
49
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
50
+ (encoder): VizdoomEncoder(
51
+ (basic_encoder): ConvEncoder(
52
+ (enc): RecursiveScriptModule(
53
+ original_name=ConvEncoderImpl
54
+ (conv_head): RecursiveScriptModule(
55
+ original_name=Sequential
56
+ (0): RecursiveScriptModule(original_name=Conv2d)
57
+ (1): RecursiveScriptModule(original_name=ELU)
58
+ (2): RecursiveScriptModule(original_name=Conv2d)
59
+ (3): RecursiveScriptModule(original_name=ELU)
60
+ (4): RecursiveScriptModule(original_name=Conv2d)
61
+ (5): RecursiveScriptModule(original_name=ELU)
62
+ )
63
+ (mlp_layers): RecursiveScriptModule(
64
+ original_name=Sequential
65
+ (0): RecursiveScriptModule(original_name=Linear)
66
+ (1): RecursiveScriptModule(original_name=ELU)
67
+ )
68
+ )
69
+ )
70
+ )
71
+ (core): ModelCoreRNN(
72
+ (core): GRU(512, 512)
73
+ )
74
+ (decoder): MlpDecoder(
75
+ (mlp): Identity()
76
+ )
77
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
78
+ (action_parameterization): ActionParameterizationDefault(
79
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
80
+ )
81
+ )
82
+ [2025-05-25 11:09:51,839][01067] Worker 7 uses CPU cores [3]
83
+ [2025-05-25 11:09:51,850][01066] Worker 5 uses CPU cores [1]
84
+ [2025-05-25 11:09:51,850][01063] Worker 0 uses CPU cores [0]
85
+ [2025-05-25 11:09:51,868][01064] Worker 4 uses CPU cores [0]
86
+ [2025-05-25 11:09:51,926][01065] Worker 3 uses CPU cores [3]
87
+ [2025-05-25 11:09:51,948][01062] Worker 1 uses CPU cores [1]
88
+ [2025-05-25 11:09:52,115][01047] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2025-05-25 11:09:54,770][01047] No checkpoints found
90
+ [2025-05-25 11:09:54,770][01047] Did not load from checkpoint, starting from scratch!
91
+ [2025-05-25 11:09:54,770][01047] Initialized policy 0 weights for model version 0
92
+ [2025-05-25 11:09:54,772][01047] LearnerWorker_p0 finished initialization!
93
+ [2025-05-25 11:09:54,773][01047] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2025-05-25 11:09:54,891][01060] RunningMeanStd input shape: (3, 72, 128)
95
+ [2025-05-25 11:09:54,892][01060] RunningMeanStd input shape: (1,)
96
+ [2025-05-25 11:09:54,903][01060] ConvEncoder: input_channels=3
97
+ [2025-05-25 11:09:55,016][01060] Conv encoder output size: 512
98
+ [2025-05-25 11:09:55,017][01060] Policy head output size: 512
99
+ [2025-05-25 11:09:55,074][00035] Inference worker 0-0 is ready!
100
+ [2025-05-25 11:09:55,075][00035] All inference workers are ready! Signal rollout workers to start!
101
+ [2025-05-25 11:09:55,197][01061] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2025-05-25 11:09:55,199][01064] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2025-05-25 11:09:55,200][01068] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2025-05-25 11:09:55,199][01065] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2025-05-25 11:09:55,200][01063] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2025-05-25 11:09:55,202][01066] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2025-05-25 11:09:55,203][01067] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2025-05-25 11:09:55,204][01062] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2025-05-25 11:09:55,805][01065] Decorrelating experience for 0 frames...
110
+ [2025-05-25 11:09:55,805][01061] Decorrelating experience for 0 frames...
111
+ [2025-05-25 11:09:55,805][01063] Decorrelating experience for 0 frames...
112
+ [2025-05-25 11:09:56,078][01061] Decorrelating experience for 32 frames...
113
+ [2025-05-25 11:09:56,186][01062] Decorrelating experience for 0 frames...
114
+ [2025-05-25 11:09:56,183][01066] Decorrelating experience for 0 frames...
115
+ [2025-05-25 11:09:56,255][01065] Decorrelating experience for 32 frames...
116
+ [2025-05-25 11:09:56,493][01061] Decorrelating experience for 64 frames...
117
+ [2025-05-25 11:09:56,744][01064] Decorrelating experience for 0 frames...
118
+ [2025-05-25 11:09:56,796][01062] Decorrelating experience for 32 frames...
119
+ [2025-05-25 11:09:56,795][01066] Decorrelating experience for 32 frames...
120
+ [2025-05-25 11:09:56,984][01061] Decorrelating experience for 96 frames...
121
+ [2025-05-25 11:09:57,301][01065] Decorrelating experience for 64 frames...
122
+ [2025-05-25 11:09:57,553][01064] Decorrelating experience for 32 frames...
123
+ [2025-05-25 11:09:57,673][01063] Decorrelating experience for 32 frames...
124
+ [2025-05-25 11:09:57,833][01066] Decorrelating experience for 64 frames...
125
+ [2025-05-25 11:09:57,836][01062] Decorrelating experience for 64 frames...
126
+ [2025-05-25 11:09:58,315][01067] Decorrelating experience for 0 frames...
127
+ [2025-05-25 11:09:58,325][00035] Fps is (10 sec: nan, 60 sec: nan, 300 sec: nan). Total num frames: 0. Throughput: 0: nan. Samples: 60. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
128
+ [2025-05-25 11:09:58,327][00035] Avg episode reward: [(0, '1.280')]
129
+ [2025-05-25 11:09:58,403][01062] Decorrelating experience for 96 frames...
130
+ [2025-05-25 11:09:58,487][01065] Decorrelating experience for 96 frames...
131
+ [2025-05-25 11:09:58,645][01064] Decorrelating experience for 64 frames...
132
+ [2025-05-25 11:09:58,761][01063] Decorrelating experience for 64 frames...
133
+ [2025-05-25 11:09:59,169][01067] Decorrelating experience for 32 frames...
134
+ [2025-05-25 11:09:59,194][01068] Decorrelating experience for 0 frames...
135
+ [2025-05-25 11:09:59,245][01064] Decorrelating experience for 96 frames...
136
+ [2025-05-25 11:10:00,207][01068] Decorrelating experience for 32 frames...
137
+ [2025-05-25 11:10:00,235][01066] Decorrelating experience for 96 frames...
138
+ [2025-05-25 11:10:00,298][01067] Decorrelating experience for 64 frames...
139
+ [2025-05-25 11:10:00,661][01047] Signal inference workers to stop experience collection...
140
+ [2025-05-25 11:10:00,669][01060] InferenceWorker_p0-w0: stopping experience collection
141
+ [2025-05-25 11:10:00,926][01067] Decorrelating experience for 96 frames...
142
+ [2025-05-25 11:10:01,019][01068] Decorrelating experience for 64 frames...
143
+ [2025-05-25 11:10:01,062][01063] Decorrelating experience for 96 frames...
144
+ [2025-05-25 11:10:01,385][01068] Decorrelating experience for 96 frames...
145
+ [2025-05-25 11:10:02,639][01047] Signal inference workers to resume experience collection...
146
+ [2025-05-25 11:10:02,640][01060] InferenceWorker_p0-w0: resuming experience collection
147
+ [2025-05-25 11:10:03,036][00035] Heartbeat connected on Batcher_0
148
+ [2025-05-25 11:10:03,041][00035] Heartbeat connected on LearnerWorker_p0
149
+ [2025-05-25 11:10:03,051][00035] Heartbeat connected on InferenceWorker_p0-w0
150
+ [2025-05-25 11:10:03,057][00035] Heartbeat connected on RolloutWorker_w0
151
+ [2025-05-25 11:10:03,067][00035] Heartbeat connected on RolloutWorker_w1
152
+ [2025-05-25 11:10:03,072][00035] Heartbeat connected on RolloutWorker_w3
153
+ [2025-05-25 11:10:03,074][00035] Heartbeat connected on RolloutWorker_w2
154
+ [2025-05-25 11:10:03,076][00035] Heartbeat connected on RolloutWorker_w4
155
+ [2025-05-25 11:10:03,081][00035] Heartbeat connected on RolloutWorker_w5
156
+ [2025-05-25 11:10:03,086][00035] Heartbeat connected on RolloutWorker_w6
157
+ [2025-05-25 11:10:03,104][00035] Heartbeat connected on RolloutWorker_w7
158
+ [2025-05-25 11:10:03,325][00035] Fps is (10 sec: 1638.4, 60 sec: 1638.4, 300 sec: 1638.4). Total num frames: 8192. Throughput: 0: 452.4. Samples: 2322. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
159
+ [2025-05-25 11:10:03,327][00035] Avg episode reward: [(0, '3.049')]
160
+ [2025-05-25 11:10:07,426][01060] Updated weights for policy 0, policy_version 10 (0.0100)
161
+ [2025-05-25 11:10:08,325][00035] Fps is (10 sec: 4505.6, 60 sec: 4505.6, 300 sec: 4505.6). Total num frames: 45056. Throughput: 0: 1020.2. Samples: 10262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
162
+ [2025-05-25 11:10:08,326][00035] Avg episode reward: [(0, '4.305')]
163
+ [2025-05-25 11:10:11,699][01060] Updated weights for policy 0, policy_version 20 (0.0016)
164
+ [2025-05-25 11:10:13,325][00035] Fps is (10 sec: 8601.6, 60 sec: 6280.5, 300 sec: 6280.5). Total num frames: 94208. Throughput: 0: 1624.4. Samples: 24426. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
165
+ [2025-05-25 11:10:13,327][00035] Avg episode reward: [(0, '4.254')]
166
+ [2025-05-25 11:10:16,062][01060] Updated weights for policy 0, policy_version 30 (0.0019)
167
+ [2025-05-25 11:10:18,326][00035] Fps is (10 sec: 9829.9, 60 sec: 7167.8, 300 sec: 7167.8). Total num frames: 143360. Throughput: 0: 1569.2. Samples: 31444. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
168
+ [2025-05-25 11:10:18,328][00035] Avg episode reward: [(0, '4.510')]
169
+ [2025-05-25 11:10:18,336][01047] Saving new best policy, reward=4.510!
170
+ [2025-05-25 11:10:20,320][01060] Updated weights for policy 0, policy_version 40 (0.0017)
171
+ [2025-05-25 11:10:23,325][00035] Fps is (10 sec: 9830.5, 60 sec: 7700.5, 300 sec: 7700.5). Total num frames: 192512. Throughput: 0: 1828.0. Samples: 45760. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
172
+ [2025-05-25 11:10:23,328][00035] Avg episode reward: [(0, '4.294')]
173
+ [2025-05-25 11:10:24,718][01060] Updated weights for policy 0, policy_version 50 (0.0015)
174
+ [2025-05-25 11:10:28,325][00035] Fps is (10 sec: 9421.2, 60 sec: 7918.9, 300 sec: 7918.9). Total num frames: 237568. Throughput: 0: 1991.2. Samples: 59796. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
175
+ [2025-05-25 11:10:28,326][00035] Avg episode reward: [(0, '4.298')]
176
+ [2025-05-25 11:10:28,975][01060] Updated weights for policy 0, policy_version 60 (0.0017)
177
+ [2025-05-25 11:10:33,325][00035] Fps is (10 sec: 9011.2, 60 sec: 8075.0, 300 sec: 8075.0). Total num frames: 282624. Throughput: 0: 1911.6. Samples: 66966. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
178
+ [2025-05-25 11:10:33,327][00035] Avg episode reward: [(0, '4.416')]
179
+ [2025-05-25 11:10:33,391][01060] Updated weights for policy 0, policy_version 70 (0.0015)
180
+ [2025-05-25 11:10:38,325][00035] Fps is (10 sec: 8601.7, 60 sec: 8089.6, 300 sec: 8089.6). Total num frames: 323584. Throughput: 0: 1988.3. Samples: 79590. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
181
+ [2025-05-25 11:10:38,327][00035] Avg episode reward: [(0, '4.345')]
182
+ [2025-05-25 11:10:38,347][01060] Updated weights for policy 0, policy_version 80 (0.0014)
183
+ [2025-05-25 11:10:42,635][01060] Updated weights for policy 0, policy_version 90 (0.0014)
184
+ [2025-05-25 11:10:43,325][00035] Fps is (10 sec: 9011.2, 60 sec: 8283.0, 300 sec: 8283.0). Total num frames: 372736. Throughput: 0: 2085.2. Samples: 93896. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
185
+ [2025-05-25 11:10:43,328][00035] Avg episode reward: [(0, '4.276')]
186
+ [2025-05-25 11:10:46,987][01060] Updated weights for policy 0, policy_version 100 (0.0017)
187
+ [2025-05-25 11:10:48,325][00035] Fps is (10 sec: 9830.3, 60 sec: 8437.8, 300 sec: 8437.8). Total num frames: 421888. Throughput: 0: 2192.2. Samples: 100970. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
188
+ [2025-05-25 11:10:48,327][00035] Avg episode reward: [(0, '4.723')]
189
+ [2025-05-25 11:10:48,340][01047] Saving new best policy, reward=4.723!
190
+ [2025-05-25 11:10:51,327][01060] Updated weights for policy 0, policy_version 110 (0.0017)
191
+ [2025-05-25 11:10:53,326][00035] Fps is (10 sec: 9419.7, 60 sec: 8489.7, 300 sec: 8489.7). Total num frames: 466944. Throughput: 0: 2330.9. Samples: 115154. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
192
+ [2025-05-25 11:10:53,328][00035] Avg episode reward: [(0, '4.337')]
193
+ [2025-05-25 11:10:55,634][01060] Updated weights for policy 0, policy_version 120 (0.0018)
194
+ [2025-05-25 11:10:58,325][00035] Fps is (10 sec: 9420.8, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 516096. Throughput: 0: 2331.9. Samples: 129360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
195
+ [2025-05-25 11:10:58,327][00035] Avg episode reward: [(0, '4.619')]
196
+ [2025-05-25 11:10:59,914][01060] Updated weights for policy 0, policy_version 130 (0.0019)
197
+ [2025-05-25 11:11:03,325][00035] Fps is (10 sec: 9421.9, 60 sec: 9216.0, 300 sec: 8633.1). Total num frames: 561152. Throughput: 0: 2334.4. Samples: 136490. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
198
+ [2025-05-25 11:11:03,327][00035] Avg episode reward: [(0, '4.545')]
199
+ [2025-05-25 11:11:04,325][01060] Updated weights for policy 0, policy_version 140 (0.0017)
200
+ [2025-05-25 11:11:08,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9352.5, 300 sec: 8660.1). Total num frames: 606208. Throughput: 0: 2322.6. Samples: 150278. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
201
+ [2025-05-25 11:11:08,329][00035] Avg episode reward: [(0, '4.622')]
202
+ [2025-05-25 11:11:09,245][01060] Updated weights for policy 0, policy_version 150 (0.0016)
203
+ [2025-05-25 11:11:13,325][00035] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 8683.5). Total num frames: 651264. Throughput: 0: 2303.1. Samples: 163436. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
204
+ [2025-05-25 11:11:13,326][00035] Avg episode reward: [(0, '4.569')]
205
+ [2025-05-25 11:11:13,604][01060] Updated weights for policy 0, policy_version 160 (0.0016)
206
+ [2025-05-25 11:11:17,920][01060] Updated weights for policy 0, policy_version 170 (0.0016)
207
+ [2025-05-25 11:11:18,326][00035] Fps is (10 sec: 9010.2, 60 sec: 9215.9, 300 sec: 8703.9). Total num frames: 696320. Throughput: 0: 2298.6. Samples: 170404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
208
+ [2025-05-25 11:11:18,327][00035] Avg episode reward: [(0, '4.691')]
209
+ [2025-05-25 11:11:22,236][01060] Updated weights for policy 0, policy_version 180 (0.0014)
210
+ [2025-05-25 11:11:23,325][00035] Fps is (10 sec: 9420.7, 60 sec: 9216.0, 300 sec: 8770.3). Total num frames: 745472. Throughput: 0: 2336.2. Samples: 184720. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
211
+ [2025-05-25 11:11:23,327][00035] Avg episode reward: [(0, '4.675')]
212
+ [2025-05-25 11:11:26,530][01060] Updated weights for policy 0, policy_version 190 (0.0015)
213
+ [2025-05-25 11:11:28,325][00035] Fps is (10 sec: 9831.5, 60 sec: 9284.3, 300 sec: 8829.2). Total num frames: 794624. Throughput: 0: 2336.0. Samples: 199014. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
214
+ [2025-05-25 11:11:28,327][00035] Avg episode reward: [(0, '4.634')]
215
+ [2025-05-25 11:11:30,816][01060] Updated weights for policy 0, policy_version 200 (0.0015)
216
+ [2025-05-25 11:11:33,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 8838.7). Total num frames: 839680. Throughput: 0: 2336.2. Samples: 206098. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
217
+ [2025-05-25 11:11:33,329][00035] Avg episode reward: [(0, '4.466')]
218
+ [2025-05-25 11:11:35,222][01060] Updated weights for policy 0, policy_version 210 (0.0017)
219
+ [2025-05-25 11:11:38,325][00035] Fps is (10 sec: 9420.7, 60 sec: 9420.8, 300 sec: 8888.3). Total num frames: 888832. Throughput: 0: 2332.1. Samples: 220098. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
220
+ [2025-05-25 11:11:38,327][00035] Avg episode reward: [(0, '4.307')]
221
+ [2025-05-25 11:11:38,338][01047] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000217_888832.pth...
222
+ [2025-05-25 11:11:39,629][01060] Updated weights for policy 0, policy_version 220 (0.0014)
223
+ [2025-05-25 11:11:43,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8855.2). Total num frames: 929792. Throughput: 0: 2298.3. Samples: 232782. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
224
+ [2025-05-25 11:11:43,327][00035] Avg episode reward: [(0, '4.415')]
225
+ [2025-05-25 11:11:44,595][01060] Updated weights for policy 0, policy_version 230 (0.0014)
226
+ [2025-05-25 11:11:48,325][00035] Fps is (10 sec: 8601.6, 60 sec: 9216.0, 300 sec: 8862.3). Total num frames: 974848. Throughput: 0: 2295.1. Samples: 239770. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
227
+ [2025-05-25 11:11:48,326][00035] Avg episode reward: [(0, '4.504')]
228
+ [2025-05-25 11:11:48,853][01060] Updated weights for policy 0, policy_version 240 (0.0015)
229
+ [2025-05-25 11:11:53,236][01060] Updated weights for policy 0, policy_version 250 (0.0017)
230
+ [2025-05-25 11:11:53,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.4, 300 sec: 8904.4). Total num frames: 1024000. Throughput: 0: 2307.2. Samples: 254104. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
231
+ [2025-05-25 11:11:53,327][00035] Avg episode reward: [(0, '4.490')]
232
+ [2025-05-25 11:11:57,483][01060] Updated weights for policy 0, policy_version 260 (0.0017)
233
+ [2025-05-25 11:11:58,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 8908.8). Total num frames: 1069056. Throughput: 0: 2331.1. Samples: 268338. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
234
+ [2025-05-25 11:11:58,327][00035] Avg episode reward: [(0, '4.684')]
235
+ [2025-05-25 11:12:01,749][01060] Updated weights for policy 0, policy_version 270 (0.0016)
236
+ [2025-05-25 11:12:03,325][00035] Fps is (10 sec: 9420.9, 60 sec: 9284.3, 300 sec: 8945.7). Total num frames: 1118208. Throughput: 0: 2336.9. Samples: 275562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
237
+ [2025-05-25 11:12:03,326][00035] Avg episode reward: [(0, '4.461')]
238
+ [2025-05-25 11:12:06,045][01060] Updated weights for policy 0, policy_version 280 (0.0020)
239
+ [2025-05-25 11:12:08,325][00035] Fps is (10 sec: 9830.4, 60 sec: 9352.5, 300 sec: 8979.7). Total num frames: 1167360. Throughput: 0: 2335.9. Samples: 289836. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
240
+ [2025-05-25 11:12:08,326][00035] Avg episode reward: [(0, '4.818')]
241
+ [2025-05-25 11:12:08,338][01047] Saving new best policy, reward=4.818!
242
+ [2025-05-25 11:12:10,364][01060] Updated weights for policy 0, policy_version 290 (0.0017)
243
+ [2025-05-25 11:12:13,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 8980.9). Total num frames: 1212416. Throughput: 0: 2317.7. Samples: 303310. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
244
+ [2025-05-25 11:12:13,326][00035] Avg episode reward: [(0, '4.870')]
245
+ [2025-05-25 11:12:13,331][01047] Saving new best policy, reward=4.870!
246
+ [2025-05-25 11:12:15,405][01060] Updated weights for policy 0, policy_version 300 (0.0015)
247
+ [2025-05-25 11:12:18,325][00035] Fps is (10 sec: 8601.6, 60 sec: 9284.4, 300 sec: 8952.7). Total num frames: 1253376. Throughput: 0: 2298.6. Samples: 309534. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
248
+ [2025-05-25 11:12:18,328][00035] Avg episode reward: [(0, '4.492')]
249
+ [2025-05-25 11:12:19,643][01060] Updated weights for policy 0, policy_version 310 (0.0015)
250
+ [2025-05-25 11:12:23,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 8983.0). Total num frames: 1302528. Throughput: 0: 2308.3. Samples: 323972. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
251
+ [2025-05-25 11:12:23,328][00035] Avg episode reward: [(0, '4.823')]
252
+ [2025-05-25 11:12:24,014][01060] Updated weights for policy 0, policy_version 320 (0.0019)
253
+ [2025-05-25 11:12:28,326][00035] Fps is (10 sec: 9420.4, 60 sec: 9215.9, 300 sec: 8983.9). Total num frames: 1347584. Throughput: 0: 2337.3. Samples: 337960. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
254
+ [2025-05-25 11:12:28,327][00035] Avg episode reward: [(0, '4.739')]
255
+ [2025-05-25 11:12:28,347][01060] Updated weights for policy 0, policy_version 330 (0.0018)
256
+ [2025-05-25 11:12:32,703][01060] Updated weights for policy 0, policy_version 340 (0.0017)
257
+ [2025-05-25 11:12:33,326][00035] Fps is (10 sec: 9420.3, 60 sec: 9284.2, 300 sec: 9011.2). Total num frames: 1396736. Throughput: 0: 2339.3. Samples: 345040. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
258
+ [2025-05-25 11:12:33,327][00035] Avg episode reward: [(0, '4.669')]
259
+ [2025-05-25 11:12:37,103][01060] Updated weights for policy 0, policy_version 350 (0.0014)
260
+ [2025-05-25 11:12:38,325][00035] Fps is (10 sec: 9421.2, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 1441792. Throughput: 0: 2332.7. Samples: 359074. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
261
+ [2025-05-25 11:12:38,326][00035] Avg episode reward: [(0, '4.659')]
262
+ [2025-05-25 11:12:41,364][01060] Updated weights for policy 0, policy_version 360 (0.0018)
263
+ [2025-05-25 11:12:43,325][00035] Fps is (10 sec: 9421.3, 60 sec: 9352.5, 300 sec: 9036.0). Total num frames: 1490944. Throughput: 0: 2331.3. Samples: 373246. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
264
+ [2025-05-25 11:12:43,328][00035] Avg episode reward: [(0, '4.626')]
265
+ [2025-05-25 11:12:46,160][01060] Updated weights for policy 0, policy_version 370 (0.0017)
266
+ [2025-05-25 11:12:48,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9011.2). Total num frames: 1531904. Throughput: 0: 2304.9. Samples: 379282. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
267
+ [2025-05-25 11:12:48,327][00035] Avg episode reward: [(0, '4.745')]
268
+ [2025-05-25 11:12:50,760][01060] Updated weights for policy 0, policy_version 380 (0.0018)
269
+ [2025-05-25 11:12:53,325][00035] Fps is (10 sec: 8601.6, 60 sec: 9216.0, 300 sec: 9011.2). Total num frames: 1576960. Throughput: 0: 2291.3. Samples: 392946. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
270
+ [2025-05-25 11:12:53,327][00035] Avg episode reward: [(0, '4.803')]
271
+ [2025-05-25 11:12:55,118][01060] Updated weights for policy 0, policy_version 390 (0.0017)
272
+ [2025-05-25 11:12:58,325][00035] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9034.0). Total num frames: 1626112. Throughput: 0: 2303.5. Samples: 406966. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
273
+ [2025-05-25 11:12:58,327][00035] Avg episode reward: [(0, '4.808')]
274
+ [2025-05-25 11:12:59,559][01060] Updated weights for policy 0, policy_version 400 (0.0022)
275
+ [2025-05-25 11:13:03,325][00035] Fps is (10 sec: 9420.6, 60 sec: 9216.0, 300 sec: 9033.3). Total num frames: 1671168. Throughput: 0: 2320.5. Samples: 413958. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
276
+ [2025-05-25 11:13:03,327][00035] Avg episode reward: [(0, '4.546')]
277
+ [2025-05-25 11:13:03,906][01060] Updated weights for policy 0, policy_version 410 (0.0017)
278
+ [2025-05-25 11:13:08,223][01060] Updated weights for policy 0, policy_version 420 (0.0015)
279
+ [2025-05-25 11:13:08,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9054.3). Total num frames: 1720320. Throughput: 0: 2311.5. Samples: 427988. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
280
+ [2025-05-25 11:13:08,327][00035] Avg episode reward: [(0, '4.971')]
281
+ [2025-05-25 11:13:08,338][01047] Saving new best policy, reward=4.971!
282
+ [2025-05-25 11:13:12,572][01060] Updated weights for policy 0, policy_version 430 (0.0018)
283
+ [2025-05-25 11:13:13,325][00035] Fps is (10 sec: 9421.0, 60 sec: 9216.0, 300 sec: 9053.2). Total num frames: 1765376. Throughput: 0: 2315.3. Samples: 442146. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
284
+ [2025-05-25 11:13:13,327][00035] Avg episode reward: [(0, '4.909')]
285
+ [2025-05-25 11:13:16,950][01060] Updated weights for policy 0, policy_version 440 (0.0014)
286
+ [2025-05-25 11:13:18,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9052.2). Total num frames: 1810432. Throughput: 0: 2314.3. Samples: 449184. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
287
+ [2025-05-25 11:13:18,327][00035] Avg episode reward: [(0, '4.971')]
288
+ [2025-05-25 11:13:21,857][01060] Updated weights for policy 0, policy_version 450 (0.0013)
289
+ [2025-05-25 11:13:23,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9051.2). Total num frames: 1855488. Throughput: 0: 2287.2. Samples: 461998. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
290
+ [2025-05-25 11:13:23,326][00035] Avg episode reward: [(0, '4.872')]
291
+ [2025-05-25 11:13:26,248][01060] Updated weights for policy 0, policy_version 460 (0.0018)
292
+ [2025-05-25 11:13:28,325][00035] Fps is (10 sec: 9011.0, 60 sec: 9216.0, 300 sec: 9050.2). Total num frames: 1900544. Throughput: 0: 2285.6. Samples: 476098. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
293
+ [2025-05-25 11:13:28,327][00035] Avg episode reward: [(0, '4.930')]
294
+ [2025-05-25 11:13:30,604][01060] Updated weights for policy 0, policy_version 470 (0.0015)
295
+ [2025-05-25 11:13:33,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.1, 300 sec: 9068.4). Total num frames: 1949696. Throughput: 0: 2305.4. Samples: 483026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
296
+ [2025-05-25 11:13:33,327][00035] Avg episode reward: [(0, '4.919')]
297
+ [2025-05-25 11:13:35,151][01060] Updated weights for policy 0, policy_version 480 (0.0014)
298
+ [2025-05-25 11:13:38,326][00035] Fps is (10 sec: 9420.1, 60 sec: 9215.8, 300 sec: 9067.0). Total num frames: 1994752. Throughput: 0: 2309.5. Samples: 496876. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
299
+ [2025-05-25 11:13:38,329][00035] Avg episode reward: [(0, '4.709')]
300
+ [2025-05-25 11:13:38,341][01047] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000487_1994752.pth...
301
+ [2025-05-25 11:13:39,490][01060] Updated weights for policy 0, policy_version 490 (0.0015)
302
+ [2025-05-25 11:13:43,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9147.7, 300 sec: 9065.8). Total num frames: 2039808. Throughput: 0: 2309.6. Samples: 510900. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
303
+ [2025-05-25 11:13:43,326][00035] Avg episode reward: [(0, '5.060')]
304
+ [2025-05-25 11:13:43,376][01047] Saving new best policy, reward=5.060!
305
+ [2025-05-25 11:13:43,903][01060] Updated weights for policy 0, policy_version 500 (0.0020)
306
+ [2025-05-25 11:13:48,248][01060] Updated weights for policy 0, policy_version 510 (0.0017)
307
+ [2025-05-25 11:13:48,325][00035] Fps is (10 sec: 9421.5, 60 sec: 9284.2, 300 sec: 9082.4). Total num frames: 2088960. Throughput: 0: 2307.4. Samples: 517790. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
308
+ [2025-05-25 11:13:48,327][00035] Avg episode reward: [(0, '5.235')]
309
+ [2025-05-25 11:13:48,338][01047] Saving new best policy, reward=5.235!
310
+ [2025-05-25 11:13:53,230][01060] Updated weights for policy 0, policy_version 520 (0.0016)
311
+ [2025-05-25 11:13:53,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9063.5). Total num frames: 2129920. Throughput: 0: 2277.9. Samples: 530494. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
312
+ [2025-05-25 11:13:53,326][00035] Avg episode reward: [(0, '4.951')]
313
+ [2025-05-25 11:13:57,558][01060] Updated weights for policy 0, policy_version 530 (0.0018)
314
+ [2025-05-25 11:13:58,325][00035] Fps is (10 sec: 8601.8, 60 sec: 9147.7, 300 sec: 9062.4). Total num frames: 2174976. Throughput: 0: 2278.1. Samples: 544660. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
315
+ [2025-05-25 11:13:58,327][00035] Avg episode reward: [(0, '5.032')]
316
+ [2025-05-25 11:14:01,877][01060] Updated weights for policy 0, policy_version 540 (0.0016)
317
+ [2025-05-25 11:14:03,325][00035] Fps is (10 sec: 9420.6, 60 sec: 9216.0, 300 sec: 9078.1). Total num frames: 2224128. Throughput: 0: 2281.6. Samples: 551856. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
318
+ [2025-05-25 11:14:03,327][00035] Avg episode reward: [(0, '5.191')]
319
+ [2025-05-25 11:14:06,245][01060] Updated weights for policy 0, policy_version 550 (0.0014)
320
+ [2025-05-25 11:14:08,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9147.7, 300 sec: 9076.7). Total num frames: 2269184. Throughput: 0: 2308.7. Samples: 565888. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
321
+ [2025-05-25 11:14:08,327][00035] Avg episode reward: [(0, '4.991')]
322
+ [2025-05-25 11:14:10,587][01060] Updated weights for policy 0, policy_version 560 (0.0014)
323
+ [2025-05-25 11:14:13,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9091.5). Total num frames: 2318336. Throughput: 0: 2310.0. Samples: 580046. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
324
+ [2025-05-25 11:14:13,327][00035] Avg episode reward: [(0, '5.251')]
325
+ [2025-05-25 11:14:13,332][01047] Saving new best policy, reward=5.251!
326
+ [2025-05-25 11:14:15,049][01060] Updated weights for policy 0, policy_version 570 (0.0016)
327
+ [2025-05-25 11:14:18,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9090.0). Total num frames: 2363392. Throughput: 0: 2306.0. Samples: 586798. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
328
+ [2025-05-25 11:14:18,327][00035] Avg episode reward: [(0, '4.570')]
329
+ [2025-05-25 11:14:19,385][01060] Updated weights for policy 0, policy_version 580 (0.0018)
330
+ [2025-05-25 11:14:23,326][00035] Fps is (10 sec: 9011.0, 60 sec: 9215.9, 300 sec: 9088.5). Total num frames: 2408448. Throughput: 0: 2312.6. Samples: 600940. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
331
+ [2025-05-25 11:14:23,327][00035] Avg episode reward: [(0, '4.864')]
332
+ [2025-05-25 11:14:24,252][01060] Updated weights for policy 0, policy_version 590 (0.0016)
333
+ [2025-05-25 11:14:28,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9087.1). Total num frames: 2453504. Throughput: 0: 2281.2. Samples: 613554. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
334
+ [2025-05-25 11:14:28,327][00035] Avg episode reward: [(0, '4.893')]
335
+ [2025-05-25 11:14:28,782][01060] Updated weights for policy 0, policy_version 600 (0.0016)
336
+ [2025-05-25 11:14:33,046][01060] Updated weights for policy 0, policy_version 610 (0.0017)
337
+ [2025-05-25 11:14:33,325][00035] Fps is (10 sec: 9011.6, 60 sec: 9147.7, 300 sec: 9085.7). Total num frames: 2498560. Throughput: 0: 2285.9. Samples: 620656. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
338
+ [2025-05-25 11:14:33,326][00035] Avg episode reward: [(0, '4.584')]
339
+ [2025-05-25 11:14:37,540][01060] Updated weights for policy 0, policy_version 620 (0.0014)
340
+ [2025-05-25 11:14:38,325][00035] Fps is (10 sec: 9011.1, 60 sec: 9147.9, 300 sec: 9084.3). Total num frames: 2543616. Throughput: 0: 2311.4. Samples: 634508. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
341
+ [2025-05-25 11:14:38,328][00035] Avg episode reward: [(0, '4.673')]
342
+ [2025-05-25 11:14:41,807][01060] Updated weights for policy 0, policy_version 630 (0.0016)
343
+ [2025-05-25 11:14:43,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9097.4). Total num frames: 2592768. Throughput: 0: 2315.9. Samples: 648874. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
344
+ [2025-05-25 11:14:43,326][00035] Avg episode reward: [(0, '4.641')]
345
+ [2025-05-25 11:14:46,083][01060] Updated weights for policy 0, policy_version 640 (0.0016)
346
+ [2025-05-25 11:14:48,325][00035] Fps is (10 sec: 9830.5, 60 sec: 9216.0, 300 sec: 9110.1). Total num frames: 2641920. Throughput: 0: 2312.9. Samples: 655934. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
347
+ [2025-05-25 11:14:48,330][00035] Avg episode reward: [(0, '5.311')]
348
+ [2025-05-25 11:14:48,340][01047] Saving new best policy, reward=5.311!
349
+ [2025-05-25 11:14:50,425][01060] Updated weights for policy 0, policy_version 650 (0.0016)
350
+ [2025-05-25 11:14:53,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9108.4). Total num frames: 2686976. Throughput: 0: 2319.4. Samples: 670262. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
351
+ [2025-05-25 11:14:53,328][00035] Avg episode reward: [(0, '4.891')]
352
+ [2025-05-25 11:14:54,765][01060] Updated weights for policy 0, policy_version 660 (0.0016)
353
+ [2025-05-25 11:14:58,325][00035] Fps is (10 sec: 8601.6, 60 sec: 9216.0, 300 sec: 9219.5). Total num frames: 2727936. Throughput: 0: 2281.0. Samples: 682690. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
354
+ [2025-05-25 11:14:58,327][00035] Avg episode reward: [(0, '4.978')]
355
+ [2025-05-25 11:14:59,766][01060] Updated weights for policy 0, policy_version 670 (0.0015)
356
+ [2025-05-25 11:15:03,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9261.1). Total num frames: 2777088. Throughput: 0: 2289.7. Samples: 689836. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
357
+ [2025-05-25 11:15:03,327][00035] Avg episode reward: [(0, '4.763')]
358
+ [2025-05-25 11:15:04,161][01060] Updated weights for policy 0, policy_version 680 (0.0020)
359
+ [2025-05-25 11:15:08,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 2822144. Throughput: 0: 2290.4. Samples: 704008. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
360
+ [2025-05-25 11:15:08,326][00035] Avg episode reward: [(0, '4.814')]
361
+ [2025-05-25 11:15:08,424][01060] Updated weights for policy 0, policy_version 690 (0.0016)
362
+ [2025-05-25 11:15:12,722][01060] Updated weights for policy 0, policy_version 700 (0.0016)
363
+ [2025-05-25 11:15:13,325][00035] Fps is (10 sec: 9420.6, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 2871296. Throughput: 0: 2327.4. Samples: 718286. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
364
+ [2025-05-25 11:15:13,327][00035] Avg episode reward: [(0, '5.006')]
365
+ [2025-05-25 11:15:17,098][01060] Updated weights for policy 0, policy_version 710 (0.0020)
366
+ [2025-05-25 11:15:18,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9233.4). Total num frames: 2916352. Throughput: 0: 2326.5. Samples: 725350. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
367
+ [2025-05-25 11:15:18,327][00035] Avg episode reward: [(0, '5.181')]
368
+ [2025-05-25 11:15:21,292][01060] Updated weights for policy 0, policy_version 720 (0.0017)
369
+ [2025-05-25 11:15:23,325][00035] Fps is (10 sec: 9421.0, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 2965504. Throughput: 0: 2340.7. Samples: 739838. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
370
+ [2025-05-25 11:15:23,327][00035] Avg episode reward: [(0, '5.979')]
371
+ [2025-05-25 11:15:23,329][01047] Saving new best policy, reward=5.979!
372
+ [2025-05-25 11:15:25,628][01060] Updated weights for policy 0, policy_version 730 (0.0017)
373
+ [2025-05-25 11:15:28,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3010560. Throughput: 0: 2330.8. Samples: 753762. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
374
+ [2025-05-25 11:15:28,327][00035] Avg episode reward: [(0, '4.867')]
375
+ [2025-05-25 11:15:30,499][01060] Updated weights for policy 0, policy_version 740 (0.0015)
376
+ [2025-05-25 11:15:33,325][00035] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3055616. Throughput: 0: 2306.3. Samples: 759716. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
377
+ [2025-05-25 11:15:33,327][00035] Avg episode reward: [(0, '5.079')]
378
+ [2025-05-25 11:15:34,851][01060] Updated weights for policy 0, policy_version 750 (0.0015)
379
+ [2025-05-25 11:15:38,325][00035] Fps is (10 sec: 9011.1, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3100672. Throughput: 0: 2304.2. Samples: 773952. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
380
+ [2025-05-25 11:15:38,326][00035] Avg episode reward: [(0, '5.331')]
381
+ [2025-05-25 11:15:38,345][01047] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000758_3104768.pth...
382
+ [2025-05-25 11:15:38,428][01047] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000217_888832.pth
383
+ [2025-05-25 11:15:39,263][01060] Updated weights for policy 0, policy_version 760 (0.0016)
384
+ [2025-05-25 11:15:43,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3149824. Throughput: 0: 2340.7. Samples: 788020. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
385
+ [2025-05-25 11:15:43,327][00035] Avg episode reward: [(0, '5.236')]
386
+ [2025-05-25 11:15:43,545][01060] Updated weights for policy 0, policy_version 770 (0.0017)
387
+ [2025-05-25 11:15:47,943][01060] Updated weights for policy 0, policy_version 780 (0.0017)
388
+ [2025-05-25 11:15:48,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9216.0, 300 sec: 9247.3). Total num frames: 3194880. Throughput: 0: 2337.9. Samples: 795042. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
389
+ [2025-05-25 11:15:48,327][00035] Avg episode reward: [(0, '5.114')]
390
+ [2025-05-25 11:15:52,181][01060] Updated weights for policy 0, policy_version 790 (0.0014)
391
+ [2025-05-25 11:15:53,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3244032. Throughput: 0: 2339.5. Samples: 809286. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
392
+ [2025-05-25 11:15:53,330][00035] Avg episode reward: [(0, '4.960')]
393
+ [2025-05-25 11:15:56,550][01060] Updated weights for policy 0, policy_version 800 (0.0016)
394
+ [2025-05-25 11:15:58,325][00035] Fps is (10 sec: 9830.5, 60 sec: 9420.8, 300 sec: 9261.1). Total num frames: 3293184. Throughput: 0: 2336.0. Samples: 823404. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
395
+ [2025-05-25 11:15:58,326][00035] Avg episode reward: [(0, '5.070')]
396
+ [2025-05-25 11:16:01,138][01060] Updated weights for policy 0, policy_version 810 (0.0018)
397
+ [2025-05-25 11:16:03,325][00035] Fps is (10 sec: 9011.3, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3334144. Throughput: 0: 2324.6. Samples: 829956. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
398
+ [2025-05-25 11:16:03,328][00035] Avg episode reward: [(0, '5.166')]
399
+ [2025-05-25 11:16:05,923][01060] Updated weights for policy 0, policy_version 820 (0.0015)
400
+ [2025-05-25 11:16:08,325][00035] Fps is (10 sec: 8601.6, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3379200. Throughput: 0: 2292.6. Samples: 843004. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
401
+ [2025-05-25 11:16:08,329][00035] Avg episode reward: [(0, '4.748')]
402
+ [2025-05-25 11:16:10,243][01060] Updated weights for policy 0, policy_version 830 (0.0017)
403
+ [2025-05-25 11:16:13,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9216.0, 300 sec: 9247.3). Total num frames: 3424256. Throughput: 0: 2299.3. Samples: 857232. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
404
+ [2025-05-25 11:16:13,326][00035] Avg episode reward: [(0, '4.711')]
405
+ [2025-05-25 11:16:14,749][01060] Updated weights for policy 0, policy_version 840 (0.0015)
406
+ [2025-05-25 11:16:18,325][00035] Fps is (10 sec: 9420.7, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3473408. Throughput: 0: 2320.2. Samples: 864126. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
407
+ [2025-05-25 11:16:18,327][00035] Avg episode reward: [(0, '5.047')]
408
+ [2025-05-25 11:16:19,039][01060] Updated weights for policy 0, policy_version 850 (0.0015)
409
+ [2025-05-25 11:16:23,312][01060] Updated weights for policy 0, policy_version 860 (0.0016)
410
+ [2025-05-25 11:16:23,325][00035] Fps is (10 sec: 9830.4, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3522560. Throughput: 0: 2322.8. Samples: 878476. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
411
+ [2025-05-25 11:16:23,328][00035] Avg episode reward: [(0, '4.728')]
412
+ [2025-05-25 11:16:27,638][01060] Updated weights for policy 0, policy_version 870 (0.0018)
413
+ [2025-05-25 11:16:28,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3567616. Throughput: 0: 2324.4. Samples: 892620. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
414
+ [2025-05-25 11:16:28,327][00035] Avg episode reward: [(0, '4.699')]
415
+ [2025-05-25 11:16:31,846][01060] Updated weights for policy 0, policy_version 880 (0.0019)
416
+ [2025-05-25 11:16:33,325][00035] Fps is (10 sec: 9420.7, 60 sec: 9352.5, 300 sec: 9247.2). Total num frames: 3616768. Throughput: 0: 2331.6. Samples: 899962. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
417
+ [2025-05-25 11:16:33,328][00035] Avg episode reward: [(0, '4.872')]
418
+ [2025-05-25 11:16:36,735][01060] Updated weights for policy 0, policy_version 890 (0.0016)
419
+ [2025-05-25 11:16:38,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3657728. Throughput: 0: 2299.2. Samples: 912750. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
420
+ [2025-05-25 11:16:38,327][00035] Avg episode reward: [(0, '4.904')]
421
+ [2025-05-25 11:16:41,142][01060] Updated weights for policy 0, policy_version 900 (0.0019)
422
+ [2025-05-25 11:16:43,325][00035] Fps is (10 sec: 9011.2, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3706880. Throughput: 0: 2300.6. Samples: 926932. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
423
+ [2025-05-25 11:16:43,326][00035] Avg episode reward: [(0, '4.862')]
424
+ [2025-05-25 11:16:45,449][01060] Updated weights for policy 0, policy_version 910 (0.0015)
425
+ [2025-05-25 11:16:48,325][00035] Fps is (10 sec: 9420.6, 60 sec: 9284.3, 300 sec: 9247.2). Total num frames: 3751936. Throughput: 0: 2309.8. Samples: 933898. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
426
+ [2025-05-25 11:16:48,327][00035] Avg episode reward: [(0, '4.784')]
427
+ [2025-05-25 11:16:49,832][01060] Updated weights for policy 0, policy_version 920 (0.0014)
428
+ [2025-05-25 11:16:53,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9284.3, 300 sec: 9261.1). Total num frames: 3801088. Throughput: 0: 2334.8. Samples: 948070. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
429
+ [2025-05-25 11:16:53,327][00035] Avg episode reward: [(0, '4.952')]
430
+ [2025-05-25 11:16:54,202][01060] Updated weights for policy 0, policy_version 930 (0.0016)
431
+ [2025-05-25 11:16:58,325][00035] Fps is (10 sec: 9420.9, 60 sec: 9216.0, 300 sec: 9247.2). Total num frames: 3846144. Throughput: 0: 2335.3. Samples: 962320. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
432
+ [2025-05-25 11:16:58,326][00035] Avg episode reward: [(0, '4.933')]
433
+ [2025-05-25 11:16:58,474][01060] Updated weights for policy 0, policy_version 940 (0.0017)
434
+ [2025-05-25 11:17:02,731][01060] Updated weights for policy 0, policy_version 950 (0.0018)
435
+ [2025-05-25 11:17:03,325][00035] Fps is (10 sec: 9420.8, 60 sec: 9352.5, 300 sec: 9247.2). Total num frames: 3895296. Throughput: 0: 2343.0. Samples: 969562. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
436
+ [2025-05-25 11:17:03,327][00035] Avg episode reward: [(0, '4.647')]
437
+ [2025-05-25 11:17:07,592][01060] Updated weights for policy 0, policy_version 960 (0.0014)
438
+ [2025-05-25 11:17:08,326][00035] Fps is (10 sec: 9010.6, 60 sec: 9284.2, 300 sec: 9233.3). Total num frames: 3936256. Throughput: 0: 2319.7. Samples: 982866. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
439
+ [2025-05-25 11:17:08,327][00035] Avg episode reward: [(0, '5.051')]
440
+ [2025-05-25 11:17:11,906][01060] Updated weights for policy 0, policy_version 970 (0.0015)
441
+ [2025-05-25 11:17:13,326][00035] Fps is (10 sec: 9010.5, 60 sec: 9352.4, 300 sec: 9261.1). Total num frames: 3985408. Throughput: 0: 2317.5. Samples: 996910. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
442
+ [2025-05-25 11:17:13,329][00035] Avg episode reward: [(0, '4.935')]
443
+ [2025-05-25 11:17:15,292][01047] Stopping Batcher_0...
444
+ [2025-05-25 11:17:15,292][01047] Loop batcher_evt_loop terminating...
445
+ [2025-05-25 11:17:15,293][01047] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
446
+ [2025-05-25 11:17:15,292][00035] Component Batcher_0 stopped!
447
+ [2025-05-25 11:17:15,324][01060] Weights refcount: 2 0
448
+ [2025-05-25 11:17:15,326][01060] Stopping InferenceWorker_p0-w0...
449
+ [2025-05-25 11:17:15,327][01060] Loop inference_proc0-0_evt_loop terminating...
450
+ [2025-05-25 11:17:15,327][00035] Component InferenceWorker_p0-w0 stopped!
451
+ [2025-05-25 11:17:15,382][01047] Removing /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000487_1994752.pth
452
+ [2025-05-25 11:17:15,396][00035] Component RolloutWorker_w6 stopped!
453
+ [2025-05-25 11:17:15,395][01068] Stopping RolloutWorker_w6...
454
+ [2025-05-25 11:17:15,400][01068] Loop rollout_proc6_evt_loop terminating...
455
+ [2025-05-25 11:17:15,401][01047] Saving /kaggle/working/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
456
+ [2025-05-25 11:17:15,402][01067] Stopping RolloutWorker_w7...
457
+ [2025-05-25 11:17:15,402][01067] Loop rollout_proc7_evt_loop terminating...
458
+ [2025-05-25 11:17:15,404][00035] Component RolloutWorker_w7 stopped!
459
+ [2025-05-25 11:17:15,409][01061] Stopping RolloutWorker_w2...
460
+ [2025-05-25 11:17:15,410][00035] Component RolloutWorker_w2 stopped!
461
+ [2025-05-25 11:17:15,411][00035] Component RolloutWorker_w3 stopped!
462
+ [2025-05-25 11:17:15,411][01065] Stopping RolloutWorker_w3...
463
+ [2025-05-25 11:17:15,413][01065] Loop rollout_proc3_evt_loop terminating...
464
+ [2025-05-25 11:17:15,413][01061] Loop rollout_proc2_evt_loop terminating...
465
+ [2025-05-25 11:17:15,525][00035] Component LearnerWorker_p0 stopped!
466
+ [2025-05-25 11:17:15,527][01047] Stopping LearnerWorker_p0...
467
+ [2025-05-25 11:17:15,527][01047] Loop learner_proc0_evt_loop terminating...
468
+ [2025-05-25 11:17:15,563][00035] Component RolloutWorker_w0 stopped!
469
+ [2025-05-25 11:17:15,565][01062] Stopping RolloutWorker_w1...
470
+ [2025-05-25 11:17:15,566][01062] Loop rollout_proc1_evt_loop terminating...
471
+ [2025-05-25 11:17:15,566][00035] Component RolloutWorker_w1 stopped!
472
+ [2025-05-25 11:17:15,565][01063] Stopping RolloutWorker_w0...
473
+ [2025-05-25 11:17:15,569][01063] Loop rollout_proc0_evt_loop terminating...
474
+ [2025-05-25 11:17:15,601][00035] Component RolloutWorker_w4 stopped!
475
+ [2025-05-25 11:17:15,601][01064] Stopping RolloutWorker_w4...
476
+ [2025-05-25 11:17:15,603][01064] Loop rollout_proc4_evt_loop terminating...
477
+ [2025-05-25 11:17:15,625][01066] Stopping RolloutWorker_w5...
478
+ [2025-05-25 11:17:15,626][01066] Loop rollout_proc5_evt_loop terminating...
479
+ [2025-05-25 11:17:15,628][00035] Component RolloutWorker_w5 stopped!
480
+ [2025-05-25 11:17:15,629][00035] Waiting for process learner_proc0 to stop...
481
+ [2025-05-25 11:17:17,018][00035] Waiting for process inference_proc0-0 to join...
482
+ [2025-05-25 11:17:17,021][00035] Waiting for process rollout_proc0 to join...
483
+ [2025-05-25 11:17:17,358][00035] Waiting for process rollout_proc1 to join...
484
+ [2025-05-25 11:17:17,555][00035] Waiting for process rollout_proc2 to join...
485
+ [2025-05-25 11:17:17,557][00035] Waiting for process rollout_proc3 to join...
486
+ [2025-05-25 11:17:17,558][00035] Waiting for process rollout_proc4 to join...
487
+ [2025-05-25 11:17:17,559][00035] Waiting for process rollout_proc5 to join...
488
+ [2025-05-25 11:17:17,560][00035] Waiting for process rollout_proc6 to join...
489
+ [2025-05-25 11:17:17,561][00035] Waiting for process rollout_proc7 to join...
490
+ [2025-05-25 11:17:17,562][00035] Batcher 0 profile tree view:
491
+ batching: 21.5743, releasing_batches: 0.0246
492
+ [2025-05-25 11:17:17,563][00035] InferenceWorker_p0-w0 profile tree view:
493
+ wait_policy: 0.0001
494
+ wait_policy_total: 13.4992
495
+ update_model: 6.2238
496
+ weight_update: 0.0015
497
+ one_step: 0.0046
498
+ handle_policy_step: 399.8286
499
+ deserialize: 11.6803, stack: 2.5635, obs_to_device_normalize: 98.9273, forward: 196.3114, send_messages: 20.6973
500
+ prepare_outputs: 53.6470
501
+ to_cpu: 34.9520
502
+ [2025-05-25 11:17:17,564][00035] Learner 0 profile tree view:
503
+ misc: 0.0036, prepare_batch: 12.0117
504
+ train: 51.2261
505
+ epoch_init: 0.0044, minibatch_init: 0.0069, losses_postprocess: 0.5186, kl_divergence: 0.5606, after_optimizer: 22.0477
506
+ calculate_losses: 17.7847
507
+ losses_init: 0.0034, forward_head: 1.0293, bptt_initial: 12.4695, tail: 0.7633, advantages_returns: 0.2058, losses: 1.6964
508
+ bptt: 1.4446
509
+ bptt_forward_core: 1.3814
510
+ update: 9.9105
511
+ clip: 0.9112
512
+ [2025-05-25 11:17:17,565][00035] RolloutWorker_w0 profile tree view:
513
+ wait_for_trajectories: 0.1511, enqueue_policy_requests: 7.6643, env_step: 316.0414, overhead: 6.3073, complete_rollouts: 1.0488
514
+ save_policy_outputs: 8.7204
515
+ split_output_tensors: 3.3696
516
+ [2025-05-25 11:17:17,565][00035] RolloutWorker_w7 profile tree view:
517
+ wait_for_trajectories: 0.1530, enqueue_policy_requests: 7.7979, env_step: 314.2266, overhead: 6.5045, complete_rollouts: 0.9601
518
+ save_policy_outputs: 8.9357
519
+ split_output_tensors: 3.3884
520
+ [2025-05-25 11:17:17,566][00035] Loop Runner_EvtLoop terminating...
521
+ [2025-05-25 11:17:17,567][00035] Runner profile tree view:
522
+ main_loop: 454.4760
523
+ [2025-05-25 11:17:17,568][00035] Collected {0: 4005888}, FPS: 8814.3
524
+ [2025-05-25 11:17:17,820][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
525
+ [2025-05-25 11:17:17,821][00035] Overriding arg 'num_workers' with value 1 passed from command line
526
+ [2025-05-25 11:17:17,822][00035] Adding new argument 'no_render'=True that is not in the saved config file!
527
+ [2025-05-25 11:17:17,823][00035] Adding new argument 'save_video'=True that is not in the saved config file!
528
+ [2025-05-25 11:17:17,824][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
529
+ [2025-05-25 11:17:17,825][00035] Adding new argument 'video_name'=None that is not in the saved config file!
530
+ [2025-05-25 11:17:17,825][00035] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
531
+ [2025-05-25 11:17:17,826][00035] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
532
+ [2025-05-25 11:17:17,827][00035] Adding new argument 'push_to_hub'=False that is not in the saved config file!
533
+ [2025-05-25 11:17:17,828][00035] Adding new argument 'hf_repository'=None that is not in the saved config file!
534
+ [2025-05-25 11:17:17,829][00035] Adding new argument 'policy_index'=0 that is not in the saved config file!
535
+ [2025-05-25 11:17:17,829][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
536
+ [2025-05-25 11:17:17,830][00035] Adding new argument 'train_script'=None that is not in the saved config file!
537
+ [2025-05-25 11:17:17,830][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file!
538
+ [2025-05-25 11:17:17,831][00035] Using frameskip 1 and render_action_repeat=4 for evaluation
539
+ [2025-05-25 11:17:17,860][00035] Doom resolution: 160x120, resize resolution: (128, 72)
540
+ [2025-05-25 11:17:17,862][00035] RunningMeanStd input shape: (3, 72, 128)
541
+ [2025-05-25 11:17:17,864][00035] RunningMeanStd input shape: (1,)
542
+ [2025-05-25 11:17:17,879][00035] ConvEncoder: input_channels=3
543
+ [2025-05-25 11:17:17,986][00035] Conv encoder output size: 512
544
+ [2025-05-25 11:17:17,987][00035] Policy head output size: 512
545
+ [2025-05-25 11:17:18,985][00035] Num frames 100...
546
+ [2025-05-25 11:17:19,099][00035] Num frames 200...
547
+ [2025-05-25 11:17:19,212][00035] Num frames 300...
548
+ [2025-05-25 11:17:19,365][00035] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
549
+ [2025-05-25 11:17:19,366][00035] Avg episode reward: 3.840, avg true_objective: 3.840
550
+ [2025-05-25 11:17:19,387][00035] Num frames 400...
551
+ [2025-05-25 11:17:19,499][00035] Num frames 500...
552
+ [2025-05-25 11:17:19,608][00035] Num frames 600...
553
+ [2025-05-25 11:17:19,716][00035] Num frames 700...
554
+ [2025-05-25 11:17:19,775][00035] Avg episode rewards: #0: 3.520, true rewards: #0: 3.520
555
+ [2025-05-25 11:17:19,776][00035] Avg episode reward: 3.520, avg true_objective: 3.520
556
+ [2025-05-25 11:17:19,883][00035] Num frames 800...
557
+ [2025-05-25 11:17:20,003][00035] Num frames 900...
558
+ [2025-05-25 11:17:20,125][00035] Num frames 1000...
559
+ [2025-05-25 11:17:20,282][00035] Avg episode rewards: #0: 3.627, true rewards: #0: 3.627
560
+ [2025-05-25 11:17:20,283][00035] Avg episode reward: 3.627, avg true_objective: 3.627
561
+ [2025-05-25 11:17:20,300][00035] Num frames 1100...
562
+ [2025-05-25 11:17:20,418][00035] Num frames 1200...
563
+ [2025-05-25 11:17:20,531][00035] Num frames 1300...
564
+ [2025-05-25 11:17:20,641][00035] Num frames 1400...
565
+ [2025-05-25 11:17:20,777][00035] Avg episode rewards: #0: 3.680, true rewards: #0: 3.680
566
+ [2025-05-25 11:17:20,777][00035] Avg episode reward: 3.680, avg true_objective: 3.680
567
+ [2025-05-25 11:17:20,810][00035] Num frames 1500...
568
+ [2025-05-25 11:17:20,921][00035] Num frames 1600...
569
+ [2025-05-25 11:17:21,031][00035] Num frames 1700...
570
+ [2025-05-25 11:17:21,141][00035] Num frames 1800...
571
+ [2025-05-25 11:17:21,257][00035] Avg episode rewards: #0: 3.712, true rewards: #0: 3.712
572
+ [2025-05-25 11:17:21,257][00035] Avg episode reward: 3.712, avg true_objective: 3.712
573
+ [2025-05-25 11:17:21,309][00035] Num frames 1900...
574
+ [2025-05-25 11:17:21,425][00035] Num frames 2000...
575
+ [2025-05-25 11:17:21,537][00035] Num frames 2100...
576
+ [2025-05-25 11:17:21,653][00035] Num frames 2200...
577
+ [2025-05-25 11:17:21,770][00035] Num frames 2300...
578
+ [2025-05-25 11:17:21,829][00035] Avg episode rewards: #0: 4.007, true rewards: #0: 3.840
579
+ [2025-05-25 11:17:21,830][00035] Avg episode reward: 4.007, avg true_objective: 3.840
580
+ [2025-05-25 11:17:21,944][00035] Num frames 2400...
581
+ [2025-05-25 11:17:22,062][00035] Num frames 2500...
582
+ [2025-05-25 11:17:22,171][00035] Num frames 2600...
583
+ [2025-05-25 11:17:22,283][00035] Num frames 2700...
584
+ [2025-05-25 11:17:22,427][00035] Avg episode rewards: #0: 4.406, true rewards: #0: 3.977
585
+ [2025-05-25 11:17:22,428][00035] Avg episode reward: 4.406, avg true_objective: 3.977
586
+ [2025-05-25 11:17:22,447][00035] Num frames 2800...
587
+ [2025-05-25 11:17:22,562][00035] Num frames 2900...
588
+ [2025-05-25 11:17:22,675][00035] Num frames 3000...
589
+ [2025-05-25 11:17:22,788][00035] Num frames 3100...
590
+ [2025-05-25 11:17:22,920][00035] Avg episode rewards: #0: 4.335, true rewards: #0: 3.960
591
+ [2025-05-25 11:17:22,921][00035] Avg episode reward: 4.335, avg true_objective: 3.960
592
+ [2025-05-25 11:17:22,959][00035] Num frames 3200...
593
+ [2025-05-25 11:17:23,076][00035] Num frames 3300...
594
+ [2025-05-25 11:17:23,195][00035] Num frames 3400...
595
+ [2025-05-25 11:17:23,310][00035] Num frames 3500...
596
+ [2025-05-25 11:17:23,427][00035] Avg episode rewards: #0: 4.280, true rewards: #0: 3.947
597
+ [2025-05-25 11:17:23,428][00035] Avg episode reward: 4.280, avg true_objective: 3.947
598
+ [2025-05-25 11:17:23,486][00035] Num frames 3600...
599
+ [2025-05-25 11:17:23,622][00035] Num frames 3700...
600
+ [2025-05-25 11:17:23,737][00035] Num frames 3800...
601
+ [2025-05-25 11:17:23,849][00035] Num frames 3900...
602
+ [2025-05-25 11:17:23,961][00035] Num frames 4000...
603
+ [2025-05-25 11:17:24,013][00035] Avg episode rewards: #0: 4.400, true rewards: #0: 4.000
604
+ [2025-05-25 11:17:24,014][00035] Avg episode reward: 4.400, avg true_objective: 4.000
605
+ [2025-05-25 11:17:34,266][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!
606
+ [2025-05-25 11:20:23,684][00035] Loading existing experiment configuration from /kaggle/working/train_dir/default_experiment/config.json
607
+ [2025-05-25 11:20:23,685][00035] Overriding arg 'num_workers' with value 1 passed from command line
608
+ [2025-05-25 11:20:23,685][00035] Adding new argument 'no_render'=True that is not in the saved config file!
609
+ [2025-05-25 11:20:23,686][00035] Adding new argument 'save_video'=True that is not in the saved config file!
610
+ [2025-05-25 11:20:23,687][00035] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
611
+ [2025-05-25 11:20:23,687][00035] Adding new argument 'video_name'=None that is not in the saved config file!
612
+ [2025-05-25 11:20:23,689][00035] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
613
+ [2025-05-25 11:20:23,689][00035] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
614
+ [2025-05-25 11:20:23,690][00035] Adding new argument 'push_to_hub'=True that is not in the saved config file!
615
+ [2025-05-25 11:20:23,691][00035] Adding new argument 'hf_repository'='wowthecoder/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
616
+ [2025-05-25 11:20:23,691][00035] Adding new argument 'policy_index'=0 that is not in the saved config file!
617
+ [2025-05-25 11:20:23,692][00035] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
618
+ [2025-05-25 11:20:23,693][00035] Adding new argument 'train_script'=None that is not in the saved config file!
619
+ [2025-05-25 11:20:23,694][00035] Adding new argument 'enjoy_script'=None that is not in the saved config file!
620
+ [2025-05-25 11:20:23,695][00035] Using frameskip 1 and render_action_repeat=4 for evaluation
621
+ [2025-05-25 11:20:23,719][00035] RunningMeanStd input shape: (3, 72, 128)
622
+ [2025-05-25 11:20:23,720][00035] RunningMeanStd input shape: (1,)
623
+ [2025-05-25 11:20:23,731][00035] ConvEncoder: input_channels=3
624
+ [2025-05-25 11:20:23,763][00035] Conv encoder output size: 512
625
+ [2025-05-25 11:20:23,764][00035] Policy head output size: 512
626
+ [2025-05-25 11:20:24,219][00035] Num frames 100...
627
+ [2025-05-25 11:20:24,328][00035] Num frames 200...
628
+ [2025-05-25 11:20:24,437][00035] Num frames 300...
629
+ [2025-05-25 11:20:24,583][00035] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
630
+ [2025-05-25 11:20:24,584][00035] Avg episode reward: 3.840, avg true_objective: 3.840
631
+ [2025-05-25 11:20:24,604][00035] Num frames 400...
632
+ [2025-05-25 11:20:24,713][00035] Num frames 500...
633
+ [2025-05-25 11:20:24,823][00035] Num frames 600...
634
+ [2025-05-25 11:20:24,946][00035] Num frames 700...
635
+ [2025-05-25 11:20:25,081][00035] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
636
+ [2025-05-25 11:20:25,082][00035] Avg episode reward: 3.840, avg true_objective: 3.840
637
+ [2025-05-25 11:20:25,119][00035] Num frames 800...
638
+ [2025-05-25 11:20:25,224][00035] Num frames 900...
639
+ [2025-05-25 11:20:25,330][00035] Num frames 1000...
640
+ [2025-05-25 11:20:25,436][00035] Num frames 1100...
641
+ [2025-05-25 11:20:25,545][00035] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
642
+ [2025-05-25 11:20:25,545][00035] Avg episode reward: 3.840, avg true_objective: 3.840
643
+ [2025-05-25 11:20:25,598][00035] Num frames 1200...
644
+ [2025-05-25 11:20:25,709][00035] Num frames 1300...
645
+ [2025-05-25 11:20:25,826][00035] Num frames 1400...
646
+ [2025-05-25 11:20:25,950][00035] Num frames 1500...
647
+ [2025-05-25 11:20:26,052][00035] Avg episode rewards: #0: 3.840, true rewards: #0: 3.840
648
+ [2025-05-25 11:20:26,052][00035] Avg episode reward: 3.840, avg true_objective: 3.840
649
+ [2025-05-25 11:20:26,133][00035] Num frames 1600...
650
+ [2025-05-25 11:20:26,239][00035] Num frames 1700...
651
+ [2025-05-25 11:20:26,344][00035] Num frames 1800...
652
+ [2025-05-25 11:20:26,454][00035] Num frames 1900...
653
+ [2025-05-25 11:20:26,565][00035] Avg episode rewards: #0: 4.104, true rewards: #0: 3.904
654
+ [2025-05-25 11:20:26,566][00035] Avg episode reward: 4.104, avg true_objective: 3.904
655
+ [2025-05-25 11:20:26,620][00035] Num frames 2000...
656
+ [2025-05-25 11:20:26,736][00035] Num frames 2100...
657
+ [2025-05-25 11:20:26,852][00035] Num frames 2200...
658
+ [2025-05-25 11:20:26,964][00035] Num frames 2300...
659
+ [2025-05-25 11:20:27,078][00035] Num frames 2400...
660
+ [2025-05-25 11:20:27,241][00035] Avg episode rewards: #0: 4.660, true rewards: #0: 4.160
661
+ [2025-05-25 11:20:27,242][00035] Avg episode reward: 4.660, avg true_objective: 4.160
662
+ [2025-05-25 11:20:27,248][00035] Num frames 2500...
663
+ [2025-05-25 11:20:27,366][00035] Num frames 2600...
664
+ [2025-05-25 11:20:27,481][00035] Num frames 2700...
665
+ [2025-05-25 11:20:27,598][00035] Num frames 2800...
666
+ [2025-05-25 11:20:27,744][00035] Avg episode rewards: #0: 4.543, true rewards: #0: 4.114
667
+ [2025-05-25 11:20:27,744][00035] Avg episode reward: 4.543, avg true_objective: 4.114
668
+ [2025-05-25 11:20:27,770][00035] Num frames 2900...
669
+ [2025-05-25 11:20:27,890][00035] Num frames 3000...
670
+ [2025-05-25 11:20:28,004][00035] Num frames 3100...
671
+ [2025-05-25 11:20:28,118][00035] Num frames 3200...
672
+ [2025-05-25 11:20:28,244][00035] Avg episode rewards: #0: 4.455, true rewards: #0: 4.080
673
+ [2025-05-25 11:20:28,245][00035] Avg episode reward: 4.455, avg true_objective: 4.080
674
+ [2025-05-25 11:20:28,289][00035] Num frames 3300...
675
+ [2025-05-25 11:20:28,407][00035] Num frames 3400...
676
+ [2025-05-25 11:20:28,524][00035] Num frames 3500...
677
+ [2025-05-25 11:20:28,636][00035] Num frames 3600...
678
+ [2025-05-25 11:20:28,722][00035] Avg episode rewards: #0: 4.364, true rewards: #0: 4.031
679
+ [2025-05-25 11:20:28,723][00035] Avg episode reward: 4.364, avg true_objective: 4.031
680
+ [2025-05-25 11:20:28,810][00035] Num frames 3700...
681
+ [2025-05-25 11:20:28,919][00035] Num frames 3800...
682
+ [2025-05-25 11:20:29,027][00035] Num frames 3900...
683
+ [2025-05-25 11:20:29,134][00035] Num frames 4000...
684
+ [2025-05-25 11:20:29,201][00035] Avg episode rewards: #0: 4.312, true rewards: #0: 4.012
685
+ [2025-05-25 11:20:29,202][00035] Avg episode reward: 4.312, avg true_objective: 4.012
686
+ [2025-05-25 11:20:39,527][00035] Replay video saved to /kaggle/working/train_dir/default_experiment/replay.mp4!