Hugging Face's logo

dogukankartal
/
SampleFactory_ViZDoom

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
dogukankartal commited on
Commit
0afee17
•
1 Parent(s): 4ba4565

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1722777062.d1db8a0a426f +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000958_3923968_reward_18.898.pth +3 -0
  5. checkpoint_p0/checkpoint_000000501_2052096.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 +854 -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.1722777062.d1db8a0a426f ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c12be3de4d048ab336565d8cdcc252dcc23813e1199c9f8c7c583077ad7264e5
3
+ size 204717
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 9.96 +/- 4.52
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 dogukankartal/SampleFactory_ViZDoom
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=SampleFactory_ViZDoom
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=SampleFactory_ViZDoom --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_000000958_3923968_reward_18.898.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:27930fb063c3868fc350b308e9e249b518d99e94082d0c360a9b5bf0241773dc
3
+ size 34929051
checkpoint_p0/checkpoint_000000501_2052096.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b384bccd543fcb625eaa7282e0d8947376bd7383e6d416ae1d473d1a5848dbf1
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 sha256:438b13904f92ac6fe32a2077461acfa5a768a1aa755ecd69e060c5cb4906d2e7
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": "/content/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:d5d8684f25f5432cda0946dd28952525571400936db30b2651879d054bf1d287
3
+ size 19087252
sf_log.txt ADDED
@@ -0,0 +1,854 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-08-04 13:11:06,292][00695] Saving configuration to /content/train_dir/default_experiment/config.json...
2
+ [2024-08-04 13:11:06,294][00695] Rollout worker 0 uses device cpu
3
+ [2024-08-04 13:11:06,295][00695] Rollout worker 1 uses device cpu
4
+ [2024-08-04 13:11:06,296][00695] Rollout worker 2 uses device cpu
5
+ [2024-08-04 13:11:06,297][00695] Rollout worker 3 uses device cpu
6
+ [2024-08-04 13:11:06,300][00695] Rollout worker 4 uses device cpu
7
+ [2024-08-04 13:11:06,301][00695] Rollout worker 5 uses device cpu
8
+ [2024-08-04 13:11:06,302][00695] Rollout worker 6 uses device cpu
9
+ [2024-08-04 13:11:06,305][00695] Rollout worker 7 uses device cpu
10
+ [2024-08-04 13:11:06,398][00695] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-08-04 13:11:06,399][00695] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-08-04 13:11:06,432][00695] Starting all processes...
13
+ [2024-08-04 13:11:06,433][00695] Starting process learner_proc0
14
+ [2024-08-04 13:11:07,608][00695] Starting all processes...
15
+ [2024-08-04 13:11:07,614][00695] Starting process inference_proc0-0
16
+ [2024-08-04 13:11:07,616][00695] Starting process rollout_proc0
17
+ [2024-08-04 13:11:07,616][00695] Starting process rollout_proc1
18
+ [2024-08-04 13:11:07,622][00695] Starting process rollout_proc2
19
+ [2024-08-04 13:11:07,625][00695] Starting process rollout_proc3
20
+ [2024-08-04 13:11:07,626][00695] Starting process rollout_proc4
21
+ [2024-08-04 13:11:07,627][00695] Starting process rollout_proc5
22
+ [2024-08-04 13:11:07,628][00695] Starting process rollout_proc6
23
+ [2024-08-04 13:11:07,634][00695] Starting process rollout_proc7
24
+ [2024-08-04 13:11:10,181][01571] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
25
+ [2024-08-04 13:11:10,196][01567] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
26
+ [2024-08-04 13:11:10,305][01584] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
27
+ [2024-08-04 13:11:10,350][01569] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
28
+ [2024-08-04 13:11:10,407][01566] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
29
+ [2024-08-04 13:11:10,440][01572] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
30
+ [2024-08-04 13:11:10,475][01552] Using GPUs [0] for process 0 (actually maps to GPUs [0])
31
+ [2024-08-04 13:11:10,475][01552] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
32
+ [2024-08-04 13:11:10,490][01552] Num visible devices: 1
33
+ [2024-08-04 13:11:10,504][01552] Starting seed is not provided
34
+ [2024-08-04 13:11:10,504][01552] Using GPUs [0] for process 0 (actually maps to GPUs [0])
35
+ [2024-08-04 13:11:10,504][01552] Initializing actor-critic model on device cuda:0
36
+ [2024-08-04 13:11:10,505][01552] RunningMeanStd input shape: (3, 72, 128)
37
+ [2024-08-04 13:11:10,507][01552] RunningMeanStd input shape: (1,)
38
+ [2024-08-04 13:11:10,512][01568] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
39
+ [2024-08-04 13:11:10,521][01552] ConvEncoder: input_channels=3
40
+ [2024-08-04 13:11:10,532][01565] Using GPUs [0] for process 0 (actually maps to GPUs [0])
41
+ [2024-08-04 13:11:10,532][01565] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
42
+ [2024-08-04 13:11:10,547][01565] Num visible devices: 1
43
+ [2024-08-04 13:11:10,590][01570] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
44
+ [2024-08-04 13:11:10,734][01552] Conv encoder output size: 512
45
+ [2024-08-04 13:11:10,734][01552] Policy head output size: 512
46
+ [2024-08-04 13:11:10,784][01552] Created Actor Critic model with architecture:
47
+ [2024-08-04 13:11:10,784][01552] ActorCriticSharedWeights(
48
+ (obs_normalizer): ObservationNormalizer(
49
+ (running_mean_std): RunningMeanStdDictInPlace(
50
+ (running_mean_std): ModuleDict(
51
+ (obs): RunningMeanStdInPlace()
52
+ )
53
+ )
54
+ )
55
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
56
+ (encoder): VizdoomEncoder(
57
+ (basic_encoder): ConvEncoder(
58
+ (enc): RecursiveScriptModule(
59
+ original_name=ConvEncoderImpl
60
+ (conv_head): RecursiveScriptModule(
61
+ original_name=Sequential
62
+ (0): RecursiveScriptModule(original_name=Conv2d)
63
+ (1): RecursiveScriptModule(original_name=ELU)
64
+ (2): RecursiveScriptModule(original_name=Conv2d)
65
+ (3): RecursiveScriptModule(original_name=ELU)
66
+ (4): RecursiveScriptModule(original_name=Conv2d)
67
+ (5): RecursiveScriptModule(original_name=ELU)
68
+ )
69
+ (mlp_layers): RecursiveScriptModule(
70
+ original_name=Sequential
71
+ (0): RecursiveScriptModule(original_name=Linear)
72
+ (1): RecursiveScriptModule(original_name=ELU)
73
+ )
74
+ )
75
+ )
76
+ )
77
+ (core): ModelCoreRNN(
78
+ (core): GRU(512, 512)
79
+ )
80
+ (decoder): MlpDecoder(
81
+ (mlp): Identity()
82
+ )
83
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
84
+ (action_parameterization): ActionParameterizationDefault(
85
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
86
+ )
87
+ )
88
+ [2024-08-04 13:11:10,979][01552] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-08-04 13:11:11,705][01552] No checkpoints found
90
+ [2024-08-04 13:11:11,705][01552] Did not load from checkpoint, starting from scratch!
91
+ [2024-08-04 13:11:11,706][01552] Initialized policy 0 weights for model version 0
92
+ [2024-08-04 13:11:11,708][01552] LearnerWorker_p0 finished initialization!
93
+ [2024-08-04 13:11:11,708][01552] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-08-04 13:11:11,788][01565] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-08-04 13:11:11,789][01565] RunningMeanStd input shape: (1,)
96
+ [2024-08-04 13:11:11,801][01565] ConvEncoder: input_channels=3
97
+ [2024-08-04 13:11:11,909][01565] Conv encoder output size: 512
98
+ [2024-08-04 13:11:11,909][01565] Policy head output size: 512
99
+ [2024-08-04 13:11:11,963][00695] Inference worker 0-0 is ready!
100
+ [2024-08-04 13:11:11,964][00695] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-08-04 13:11:11,997][01584] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-08-04 13:11:11,997][01569] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-08-04 13:11:12,016][01572] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-08-04 13:11:12,017][01570] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-08-04 13:11:12,018][01566] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-08-04 13:11:12,018][01568] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-08-04 13:11:12,018][01567] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-08-04 13:11:12,018][01571] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-08-04 13:11:12,306][01584] Decorrelating experience for 0 frames...
110
+ [2024-08-04 13:11:12,306][01569] Decorrelating experience for 0 frames...
111
+ [2024-08-04 13:11:12,324][01572] Decorrelating experience for 0 frames...
112
+ [2024-08-04 13:11:12,325][01568] Decorrelating experience for 0 frames...
113
+ [2024-08-04 13:11:12,326][01567] Decorrelating experience for 0 frames...
114
+ [2024-08-04 13:11:12,332][00695] 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)
115
+ [2024-08-04 13:11:12,333][01566] Decorrelating experience for 0 frames...
116
+ [2024-08-04 13:11:12,547][01584] Decorrelating experience for 32 frames...
117
+ [2024-08-04 13:11:12,550][01569] Decorrelating experience for 32 frames...
118
+ [2024-08-04 13:11:12,568][01572] Decorrelating experience for 32 frames...
119
+ [2024-08-04 13:11:12,568][01567] Decorrelating experience for 32 frames...
120
+ [2024-08-04 13:11:12,614][01570] Decorrelating experience for 0 frames...
121
+ [2024-08-04 13:11:12,652][01568] Decorrelating experience for 32 frames...
122
+ [2024-08-04 13:11:12,809][01571] Decorrelating experience for 0 frames...
123
+ [2024-08-04 13:11:12,852][01570] Decorrelating experience for 32 frames...
124
+ [2024-08-04 13:11:12,897][01584] Decorrelating experience for 64 frames...
125
+ [2024-08-04 13:11:12,920][01572] Decorrelating experience for 64 frames...
126
+ [2024-08-04 13:11:12,955][01567] Decorrelating experience for 64 frames...
127
+ [2024-08-04 13:11:13,064][01571] Decorrelating experience for 32 frames...
128
+ [2024-08-04 13:11:13,073][01568] Decorrelating experience for 64 frames...
129
+ [2024-08-04 13:11:13,148][01569] Decorrelating experience for 64 frames...
130
+ [2024-08-04 13:11:13,210][01584] Decorrelating experience for 96 frames...
131
+ [2024-08-04 13:11:13,227][01570] Decorrelating experience for 64 frames...
132
+ [2024-08-04 13:11:13,323][01572] Decorrelating experience for 96 frames...
133
+ [2024-08-04 13:11:13,354][01566] Decorrelating experience for 32 frames...
134
+ [2024-08-04 13:11:13,402][01571] Decorrelating experience for 64 frames...
135
+ [2024-08-04 13:11:13,436][01568] Decorrelating experience for 96 frames...
136
+ [2024-08-04 13:11:13,500][01569] Decorrelating experience for 96 frames...
137
+ [2024-08-04 13:11:13,538][01567] Decorrelating experience for 96 frames...
138
+ [2024-08-04 13:11:13,631][01570] Decorrelating experience for 96 frames...
139
+ [2024-08-04 13:11:13,768][01571] Decorrelating experience for 96 frames...
140
+ [2024-08-04 13:11:13,776][01566] Decorrelating experience for 64 frames...
141
+ [2024-08-04 13:11:14,053][01566] Decorrelating experience for 96 frames...
142
+ [2024-08-04 13:11:14,922][01552] Signal inference workers to stop experience collection...
143
+ [2024-08-04 13:11:14,926][01565] InferenceWorker_p0-w0: stopping experience collection
144
+ [2024-08-04 13:11:17,161][01552] Signal inference workers to resume experience collection...
145
+ [2024-08-04 13:11:17,162][01565] InferenceWorker_p0-w0: resuming experience collection
146
+ [2024-08-04 13:11:17,332][00695] Fps is (10 sec: 819.2, 60 sec: 819.2, 300 sec: 819.2). Total num frames: 4096. Throughput: 0: 484.8. Samples: 2424. Policy #0 lag: (min: 0.0, avg: 0.0, max: 0.0)
147
+ [2024-08-04 13:11:17,333][00695] Avg episode reward: [(0, '1.863')]
148
+ [2024-08-04 13:11:19,216][01565] Updated weights for policy 0, policy_version 10 (0.0190)
149
+ [2024-08-04 13:11:21,399][01565] Updated weights for policy 0, policy_version 20 (0.0013)
150
+ [2024-08-04 13:11:22,332][00695] Fps is (10 sec: 9830.4, 60 sec: 9830.4, 300 sec: 9830.4). Total num frames: 98304. Throughput: 0: 1882.4. Samples: 18824. Policy #0 lag: (min: 0.0, avg: 0.2, max: 1.0)
151
+ [2024-08-04 13:11:22,336][00695] Avg episode reward: [(0, '4.437')]
152
+ [2024-08-04 13:11:23,551][01565] Updated weights for policy 0, policy_version 30 (0.0013)
153
+ [2024-08-04 13:11:25,611][01565] Updated weights for policy 0, policy_version 40 (0.0012)
154
+ [2024-08-04 13:11:26,393][00695] Heartbeat connected on LearnerWorker_p0
155
+ [2024-08-04 13:11:26,396][00695] Heartbeat connected on Batcher_0
156
+ [2024-08-04 13:11:26,405][00695] Heartbeat connected on RolloutWorker_w0
157
+ [2024-08-04 13:11:26,408][00695] Heartbeat connected on InferenceWorker_p0-w0
158
+ [2024-08-04 13:11:26,411][00695] Heartbeat connected on RolloutWorker_w1
159
+ [2024-08-04 13:11:26,414][00695] Heartbeat connected on RolloutWorker_w2
160
+ [2024-08-04 13:11:26,418][00695] Heartbeat connected on RolloutWorker_w3
161
+ [2024-08-04 13:11:26,420][00695] Heartbeat connected on RolloutWorker_w4
162
+ [2024-08-04 13:11:26,426][00695] Heartbeat connected on RolloutWorker_w5
163
+ [2024-08-04 13:11:26,428][00695] Heartbeat connected on RolloutWorker_w6
164
+ [2024-08-04 13:11:26,433][00695] Heartbeat connected on RolloutWorker_w7
165
+ [2024-08-04 13:11:27,332][00695] Fps is (10 sec: 19251.0, 60 sec: 13107.2, 300 sec: 13107.2). Total num frames: 196608. Throughput: 0: 3212.8. Samples: 48192. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
166
+ [2024-08-04 13:11:27,334][00695] Avg episode reward: [(0, '4.414')]
167
+ [2024-08-04 13:11:27,337][01552] Saving new best policy, reward=4.414!
168
+ [2024-08-04 13:11:27,684][01565] Updated weights for policy 0, policy_version 50 (0.0012)
169
+ [2024-08-04 13:11:29,750][01565] Updated weights for policy 0, policy_version 60 (0.0012)
170
+ [2024-08-04 13:11:31,816][01565] Updated weights for policy 0, policy_version 70 (0.0012)
171
+ [2024-08-04 13:11:32,332][00695] Fps is (10 sec: 19660.8, 60 sec: 14745.6, 300 sec: 14745.6). Total num frames: 294912. Throughput: 0: 3152.7. Samples: 63054. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
172
+ [2024-08-04 13:11:32,334][00695] Avg episode reward: [(0, '4.503')]
173
+ [2024-08-04 13:11:32,342][01552] Saving new best policy, reward=4.503!
174
+ [2024-08-04 13:11:33,894][01565] Updated weights for policy 0, policy_version 80 (0.0013)
175
+ [2024-08-04 13:11:36,055][01565] Updated weights for policy 0, policy_version 90 (0.0013)
176
+ [2024-08-04 13:11:37,332][00695] Fps is (10 sec: 19251.3, 60 sec: 15564.8, 300 sec: 15564.8). Total num frames: 389120. Throughput: 0: 3697.1. Samples: 92428. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
177
+ [2024-08-04 13:11:37,334][00695] Avg episode reward: [(0, '4.490')]
178
+ [2024-08-04 13:11:38,155][01565] Updated weights for policy 0, policy_version 100 (0.0012)
179
+ [2024-08-04 13:11:40,197][01565] Updated weights for policy 0, policy_version 110 (0.0012)
180
+ [2024-08-04 13:11:42,264][01565] Updated weights for policy 0, policy_version 120 (0.0013)
181
+ [2024-08-04 13:11:42,332][00695] Fps is (10 sec: 19660.7, 60 sec: 16384.0, 300 sec: 16384.0). Total num frames: 491520. Throughput: 0: 4066.9. Samples: 122008. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
182
+ [2024-08-04 13:11:42,335][00695] Avg episode reward: [(0, '4.385')]
183
+ [2024-08-04 13:11:44,339][01565] Updated weights for policy 0, policy_version 130 (0.0013)
184
+ [2024-08-04 13:11:46,418][01565] Updated weights for policy 0, policy_version 140 (0.0012)
185
+ [2024-08-04 13:11:47,332][00695] Fps is (10 sec: 20070.4, 60 sec: 16852.1, 300 sec: 16852.1). Total num frames: 589824. Throughput: 0: 3908.2. Samples: 136786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
186
+ [2024-08-04 13:11:47,334][00695] Avg episode reward: [(0, '4.487')]
187
+ [2024-08-04 13:11:48,535][01565] Updated weights for policy 0, policy_version 150 (0.0012)
188
+ [2024-08-04 13:11:50,687][01565] Updated weights for policy 0, policy_version 160 (0.0013)
189
+ [2024-08-04 13:11:52,332][00695] Fps is (10 sec: 19251.2, 60 sec: 17100.8, 300 sec: 17100.8). Total num frames: 684032. Throughput: 0: 4141.5. Samples: 165660. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
190
+ [2024-08-04 13:11:52,334][00695] Avg episode reward: [(0, '4.638')]
191
+ [2024-08-04 13:11:52,372][01552] Saving new best policy, reward=4.638!
192
+ [2024-08-04 13:11:52,794][01565] Updated weights for policy 0, policy_version 170 (0.0012)
193
+ [2024-08-04 13:11:54,861][01565] Updated weights for policy 0, policy_version 180 (0.0012)
194
+ [2024-08-04 13:11:56,919][01565] Updated weights for policy 0, policy_version 190 (0.0012)
195
+ [2024-08-04 13:11:57,332][00695] Fps is (10 sec: 19660.8, 60 sec: 17476.3, 300 sec: 17476.3). Total num frames: 786432. Throughput: 0: 4342.6. Samples: 195418. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
196
+ [2024-08-04 13:11:57,334][00695] Avg episode reward: [(0, '4.570')]
197
+ [2024-08-04 13:11:58,968][01565] Updated weights for policy 0, policy_version 200 (0.0012)
198
+ [2024-08-04 13:12:01,026][01565] Updated weights for policy 0, policy_version 210 (0.0013)
199
+ [2024-08-04 13:12:02,332][00695] Fps is (10 sec: 20070.5, 60 sec: 17694.7, 300 sec: 17694.7). Total num frames: 884736. Throughput: 0: 4620.6. Samples: 210350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
200
+ [2024-08-04 13:12:02,335][00695] Avg episode reward: [(0, '4.711')]
201
+ [2024-08-04 13:12:02,342][01552] Saving new best policy, reward=4.711!
202
+ [2024-08-04 13:12:03,205][01565] Updated weights for policy 0, policy_version 220 (0.0013)
203
+ [2024-08-04 13:12:05,363][01565] Updated weights for policy 0, policy_version 230 (0.0013)
204
+ [2024-08-04 13:12:07,332][00695] Fps is (10 sec: 19251.3, 60 sec: 17799.0, 300 sec: 17799.0). Total num frames: 978944. Throughput: 0: 4896.9. Samples: 239184. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
205
+ [2024-08-04 13:12:07,334][00695] Avg episode reward: [(0, '4.390')]
206
+ [2024-08-04 13:12:07,420][01565] Updated weights for policy 0, policy_version 240 (0.0012)
207
+ [2024-08-04 13:12:09,477][01565] Updated weights for policy 0, policy_version 250 (0.0012)
208
+ [2024-08-04 13:12:11,544][01565] Updated weights for policy 0, policy_version 260 (0.0012)
209
+ [2024-08-04 13:12:12,332][00695] Fps is (10 sec: 19251.2, 60 sec: 17954.1, 300 sec: 17954.1). Total num frames: 1077248. Throughput: 0: 4906.6. Samples: 268990. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
210
+ [2024-08-04 13:12:12,334][00695] Avg episode reward: [(0, '4.775')]
211
+ [2024-08-04 13:12:12,342][01552] Saving new best policy, reward=4.775!
212
+ [2024-08-04 13:12:13,613][01565] Updated weights for policy 0, policy_version 270 (0.0012)
213
+ [2024-08-04 13:12:15,727][01565] Updated weights for policy 0, policy_version 280 (0.0013)
214
+ [2024-08-04 13:12:17,332][00695] Fps is (10 sec: 19660.7, 60 sec: 19524.3, 300 sec: 18085.4). Total num frames: 1175552. Throughput: 0: 4909.8. Samples: 283994. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
215
+ [2024-08-04 13:12:17,334][00695] Avg episode reward: [(0, '4.494')]
216
+ [2024-08-04 13:12:17,978][01565] Updated weights for policy 0, policy_version 290 (0.0012)
217
+ [2024-08-04 13:12:20,075][01565] Updated weights for policy 0, policy_version 300 (0.0013)
218
+ [2024-08-04 13:12:22,137][01565] Updated weights for policy 0, policy_version 310 (0.0013)
219
+ [2024-08-04 13:12:22,332][00695] Fps is (10 sec: 19251.2, 60 sec: 19524.3, 300 sec: 18139.4). Total num frames: 1269760. Throughput: 0: 4891.4. Samples: 312540. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
220
+ [2024-08-04 13:12:22,334][00695] Avg episode reward: [(0, '4.701')]
221
+ [2024-08-04 13:12:24,196][01565] Updated weights for policy 0, policy_version 320 (0.0013)
222
+ [2024-08-04 13:12:26,248][01565] Updated weights for policy 0, policy_version 330 (0.0013)
223
+ [2024-08-04 13:12:27,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19592.5, 300 sec: 18295.5). Total num frames: 1372160. Throughput: 0: 4896.2. Samples: 342336. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
224
+ [2024-08-04 13:12:27,335][00695] Avg episode reward: [(0, '4.511')]
225
+ [2024-08-04 13:12:28,305][01565] Updated weights for policy 0, policy_version 340 (0.0013)
226
+ [2024-08-04 13:12:30,411][01565] Updated weights for policy 0, policy_version 350 (0.0012)
227
+ [2024-08-04 13:12:32,332][00695] Fps is (10 sec: 20070.4, 60 sec: 19592.5, 300 sec: 18380.8). Total num frames: 1470464. Throughput: 0: 4896.7. Samples: 357140. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
228
+ [2024-08-04 13:12:32,334][00695] Avg episode reward: [(0, '4.791')]
229
+ [2024-08-04 13:12:32,341][01552] Saving new best policy, reward=4.791!
230
+ [2024-08-04 13:12:32,546][01565] Updated weights for policy 0, policy_version 360 (0.0013)
231
+ [2024-08-04 13:12:34,617][01565] Updated weights for policy 0, policy_version 370 (0.0012)
232
+ [2024-08-04 13:12:36,699][01565] Updated weights for policy 0, policy_version 380 (0.0013)
233
+ [2024-08-04 13:12:37,332][00695] Fps is (10 sec: 19251.1, 60 sec: 19592.5, 300 sec: 18407.9). Total num frames: 1564672. Throughput: 0: 4904.0. Samples: 386340. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
234
+ [2024-08-04 13:12:37,334][00695] Avg episode reward: [(0, '4.897')]
235
+ [2024-08-04 13:12:37,337][01552] Saving new best policy, reward=4.897!
236
+ [2024-08-04 13:12:38,801][01565] Updated weights for policy 0, policy_version 390 (0.0013)
237
+ [2024-08-04 13:12:40,904][01565] Updated weights for policy 0, policy_version 400 (0.0012)
238
+ [2024-08-04 13:12:42,332][00695] Fps is (10 sec: 19251.2, 60 sec: 19524.3, 300 sec: 18477.5). Total num frames: 1662976. Throughput: 0: 4893.1. Samples: 415606. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
239
+ [2024-08-04 13:12:42,334][00695] Avg episode reward: [(0, '4.707')]
240
+ [2024-08-04 13:12:42,985][01565] Updated weights for policy 0, policy_version 410 (0.0013)
241
+ [2024-08-04 13:12:45,197][01565] Updated weights for policy 0, policy_version 420 (0.0013)
242
+ [2024-08-04 13:12:47,332][00695] Fps is (10 sec: 19251.2, 60 sec: 19456.0, 300 sec: 18496.7). Total num frames: 1757184. Throughput: 0: 4879.7. Samples: 429936. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
243
+ [2024-08-04 13:12:47,334][00695] Avg episode reward: [(0, '5.160')]
244
+ [2024-08-04 13:12:47,350][01552] Saving new best policy, reward=5.160!
245
+ [2024-08-04 13:12:47,351][01565] Updated weights for policy 0, policy_version 430 (0.0012)
246
+ [2024-08-04 13:12:49,415][01565] Updated weights for policy 0, policy_version 440 (0.0012)
247
+ [2024-08-04 13:12:51,496][01565] Updated weights for policy 0, policy_version 450 (0.0012)
248
+ [2024-08-04 13:12:52,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19592.6, 300 sec: 18595.8). Total num frames: 1859584. Throughput: 0: 4884.7. Samples: 458994. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
249
+ [2024-08-04 13:12:52,335][00695] Avg episode reward: [(0, '5.076')]
250
+ [2024-08-04 13:12:53,581][01565] Updated weights for policy 0, policy_version 460 (0.0012)
251
+ [2024-08-04 13:12:55,657][01565] Updated weights for policy 0, policy_version 470 (0.0012)
252
+ [2024-08-04 13:12:57,332][00695] Fps is (10 sec: 20070.4, 60 sec: 19524.3, 300 sec: 18646.6). Total num frames: 1957888. Throughput: 0: 4877.9. Samples: 488496. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
253
+ [2024-08-04 13:12:57,335][00695] Avg episode reward: [(0, '5.323')]
254
+ [2024-08-04 13:12:57,336][01552] Saving new best policy, reward=5.323!
255
+ [2024-08-04 13:12:57,781][01565] Updated weights for policy 0, policy_version 480 (0.0013)
256
+ [2024-08-04 13:12:59,930][01565] Updated weights for policy 0, policy_version 490 (0.0013)
257
+ [2024-08-04 13:13:02,047][01565] Updated weights for policy 0, policy_version 500 (0.0013)
258
+ [2024-08-04 13:13:02,332][00695] Fps is (10 sec: 19251.2, 60 sec: 19456.0, 300 sec: 18655.4). Total num frames: 2052096. Throughput: 0: 4859.5. Samples: 502674. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
259
+ [2024-08-04 13:13:02,336][00695] Avg episode reward: [(0, '5.068')]
260
+ [2024-08-04 13:13:02,346][01552] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000501_2052096.pth...
261
+ [2024-08-04 13:13:04,107][01565] Updated weights for policy 0, policy_version 510 (0.0013)
262
+ [2024-08-04 13:13:06,166][01565] Updated weights for policy 0, policy_version 520 (0.0012)
263
+ [2024-08-04 13:13:07,332][00695] Fps is (10 sec: 19251.2, 60 sec: 19524.2, 300 sec: 18699.1). Total num frames: 2150400. Throughput: 0: 4882.7. Samples: 532260. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
264
+ [2024-08-04 13:13:07,334][00695] Avg episode reward: [(0, '4.931')]
265
+ [2024-08-04 13:13:08,227][01565] Updated weights for policy 0, policy_version 530 (0.0013)
266
+ [2024-08-04 13:13:10,282][01565] Updated weights for policy 0, policy_version 540 (0.0012)
267
+ [2024-08-04 13:13:12,332][00695] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 18739.2). Total num frames: 2248704. Throughput: 0: 4882.3. Samples: 562040. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
268
+ [2024-08-04 13:13:12,334][00695] Avg episode reward: [(0, '5.982')]
269
+ [2024-08-04 13:13:12,364][01552] Saving new best policy, reward=5.982!
270
+ [2024-08-04 13:13:12,365][01565] Updated weights for policy 0, policy_version 550 (0.0013)
271
+ [2024-08-04 13:13:14,530][01565] Updated weights for policy 0, policy_version 560 (0.0013)
272
+ [2024-08-04 13:13:16,605][01565] Updated weights for policy 0, policy_version 570 (0.0012)
273
+ [2024-08-04 13:13:17,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19524.2, 300 sec: 18776.1). Total num frames: 2347008. Throughput: 0: 4872.3. Samples: 576392. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
274
+ [2024-08-04 13:13:17,334][00695] Avg episode reward: [(0, '7.751')]
275
+ [2024-08-04 13:13:17,337][01552] Saving new best policy, reward=7.751!
276
+ [2024-08-04 13:13:18,702][01565] Updated weights for policy 0, policy_version 580 (0.0012)
277
+ [2024-08-04 13:13:20,750][01565] Updated weights for policy 0, policy_version 590 (0.0013)
278
+ [2024-08-04 13:13:22,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19592.5, 300 sec: 18810.1). Total num frames: 2445312. Throughput: 0: 4881.8. Samples: 606020. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
279
+ [2024-08-04 13:13:22,334][00695] Avg episode reward: [(0, '6.969')]
280
+ [2024-08-04 13:13:22,801][01565] Updated weights for policy 0, policy_version 600 (0.0013)
281
+ [2024-08-04 13:13:24,838][01565] Updated weights for policy 0, policy_version 610 (0.0013)
282
+ [2024-08-04 13:13:26,979][01565] Updated weights for policy 0, policy_version 620 (0.0013)
283
+ [2024-08-04 13:13:27,332][00695] Fps is (10 sec: 19660.9, 60 sec: 19524.3, 300 sec: 18841.6). Total num frames: 2543616. Throughput: 0: 4889.3. Samples: 635622. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
284
+ [2024-08-04 13:13:27,334][00695] Avg episode reward: [(0, '7.280')]
285
+ [2024-08-04 13:13:29,124][01565] Updated weights for policy 0, policy_version 630 (0.0013)
286
+ [2024-08-04 13:13:31,180][01565] Updated weights for policy 0, policy_version 640 (0.0012)
287
+ [2024-08-04 13:13:32,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19524.3, 300 sec: 18870.9). Total num frames: 2641920. Throughput: 0: 4891.2. Samples: 650042. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
288
+ [2024-08-04 13:13:32,334][00695] Avg episode reward: [(0, '7.480')]
289
+ [2024-08-04 13:13:33,233][01565] Updated weights for policy 0, policy_version 650 (0.0012)
290
+ [2024-08-04 13:13:35,299][01565] Updated weights for policy 0, policy_version 660 (0.0013)
291
+ [2024-08-04 13:13:37,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19592.5, 300 sec: 18898.1). Total num frames: 2740224. Throughput: 0: 4907.4. Samples: 679828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
292
+ [2024-08-04 13:13:37,334][00695] Avg episode reward: [(0, '8.700')]
293
+ [2024-08-04 13:13:37,336][01552] Saving new best policy, reward=8.700!
294
+ [2024-08-04 13:13:37,450][01565] Updated weights for policy 0, policy_version 670 (0.0012)
295
+ [2024-08-04 13:13:39,478][01565] Updated weights for policy 0, policy_version 680 (0.0013)
296
+ [2024-08-04 13:13:41,608][01565] Updated weights for policy 0, policy_version 690 (0.0013)
297
+ [2024-08-04 13:13:42,332][00695] Fps is (10 sec: 19660.5, 60 sec: 19592.5, 300 sec: 18923.5). Total num frames: 2838528. Throughput: 0: 4900.5. Samples: 709018. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
298
+ [2024-08-04 13:13:42,335][00695] Avg episode reward: [(0, '9.553')]
299
+ [2024-08-04 13:13:42,343][01552] Saving new best policy, reward=9.553!
300
+ [2024-08-04 13:13:43,722][01565] Updated weights for policy 0, policy_version 700 (0.0013)
301
+ [2024-08-04 13:13:45,770][01565] Updated weights for policy 0, policy_version 710 (0.0013)
302
+ [2024-08-04 13:13:47,332][00695] Fps is (10 sec: 19661.0, 60 sec: 19660.8, 300 sec: 18947.3). Total num frames: 2936832. Throughput: 0: 4912.5. Samples: 723736. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
303
+ [2024-08-04 13:13:47,335][00695] Avg episode reward: [(0, '10.370')]
304
+ [2024-08-04 13:13:47,337][01552] Saving new best policy, reward=10.370!
305
+ [2024-08-04 13:13:47,845][01565] Updated weights for policy 0, policy_version 720 (0.0013)
306
+ [2024-08-04 13:13:49,891][01565] Updated weights for policy 0, policy_version 730 (0.0013)
307
+ [2024-08-04 13:13:51,936][01565] Updated weights for policy 0, policy_version 740 (0.0012)
308
+ [2024-08-04 13:13:52,332][00695] Fps is (10 sec: 19661.1, 60 sec: 19592.5, 300 sec: 18969.6). Total num frames: 3035136. Throughput: 0: 4919.1. Samples: 753618. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
309
+ [2024-08-04 13:13:52,334][00695] Avg episode reward: [(0, '12.279')]
310
+ [2024-08-04 13:13:52,347][01552] Saving new best policy, reward=12.279!
311
+ [2024-08-04 13:13:54,032][01565] Updated weights for policy 0, policy_version 750 (0.0013)
312
+ [2024-08-04 13:13:56,157][01565] Updated weights for policy 0, policy_version 760 (0.0012)
313
+ [2024-08-04 13:13:57,332][00695] Fps is (10 sec: 19660.6, 60 sec: 19592.5, 300 sec: 18990.5). Total num frames: 3133440. Throughput: 0: 4909.2. Samples: 782954. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
314
+ [2024-08-04 13:13:57,335][00695] Avg episode reward: [(0, '11.959')]
315
+ [2024-08-04 13:13:58,241][01565] Updated weights for policy 0, policy_version 770 (0.0013)
316
+ [2024-08-04 13:14:00,290][01565] Updated weights for policy 0, policy_version 780 (0.0012)
317
+ [2024-08-04 13:14:02,322][01565] Updated weights for policy 0, policy_version 790 (0.0013)
318
+ [2024-08-04 13:14:02,332][00695] Fps is (10 sec: 20070.4, 60 sec: 19729.1, 300 sec: 19034.4). Total num frames: 3235840. Throughput: 0: 4921.9. Samples: 797878. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
319
+ [2024-08-04 13:14:02,334][00695] Avg episode reward: [(0, '13.126')]
320
+ [2024-08-04 13:14:02,343][01552] Saving new best policy, reward=13.126!
321
+ [2024-08-04 13:14:04,399][01565] Updated weights for policy 0, policy_version 800 (0.0013)
322
+ [2024-08-04 13:14:06,469][01565] Updated weights for policy 0, policy_version 810 (0.0012)
323
+ [2024-08-04 13:14:07,332][00695] Fps is (10 sec: 20070.4, 60 sec: 19729.1, 300 sec: 19052.3). Total num frames: 3334144. Throughput: 0: 4926.5. Samples: 827712. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
324
+ [2024-08-04 13:14:07,334][00695] Avg episode reward: [(0, '14.790')]
325
+ [2024-08-04 13:14:07,337][01552] Saving new best policy, reward=14.790!
326
+ [2024-08-04 13:14:08,562][01565] Updated weights for policy 0, policy_version 820 (0.0013)
327
+ [2024-08-04 13:14:10,717][01565] Updated weights for policy 0, policy_version 830 (0.0013)
328
+ [2024-08-04 13:14:12,332][00695] Fps is (10 sec: 19251.3, 60 sec: 19660.8, 300 sec: 19046.4). Total num frames: 3428352. Throughput: 0: 4916.9. Samples: 856884. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
329
+ [2024-08-04 13:14:12,334][00695] Avg episode reward: [(0, '16.816')]
330
+ [2024-08-04 13:14:12,372][01552] Saving new best policy, reward=16.816!
331
+ [2024-08-04 13:14:12,780][01565] Updated weights for policy 0, policy_version 840 (0.0013)
332
+ [2024-08-04 13:14:14,802][01565] Updated weights for policy 0, policy_version 850 (0.0013)
333
+ [2024-08-04 13:14:16,851][01565] Updated weights for policy 0, policy_version 860 (0.0013)
334
+ [2024-08-04 13:14:17,332][00695] Fps is (10 sec: 19660.8, 60 sec: 19729.1, 300 sec: 19085.2). Total num frames: 3530752. Throughput: 0: 4931.7. Samples: 871968. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
335
+ [2024-08-04 13:14:17,335][00695] Avg episode reward: [(0, '17.412')]
336
+ [2024-08-04 13:14:17,337][01552] Saving new best policy, reward=17.412!
337
+ [2024-08-04 13:14:18,937][01565] Updated weights for policy 0, policy_version 870 (0.0013)
338
+ [2024-08-04 13:14:21,051][01565] Updated weights for policy 0, policy_version 880 (0.0013)
339
+ [2024-08-04 13:14:22,332][00695] Fps is (10 sec: 20070.8, 60 sec: 19729.1, 300 sec: 19100.3). Total num frames: 3629056. Throughput: 0: 4925.2. Samples: 901462. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
340
+ [2024-08-04 13:14:22,334][00695] Avg episode reward: [(0, '17.746')]
341
+ [2024-08-04 13:14:22,343][01552] Saving new best policy, reward=17.746!
342
+ [2024-08-04 13:14:23,184][01565] Updated weights for policy 0, policy_version 890 (0.0013)
343
+ [2024-08-04 13:14:25,307][01565] Updated weights for policy 0, policy_version 900 (0.0013)
344
+ [2024-08-04 13:14:27,332][00695] Fps is (10 sec: 19251.4, 60 sec: 19660.9, 300 sec: 19093.7). Total num frames: 3723264. Throughput: 0: 4923.4. Samples: 930568. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
345
+ [2024-08-04 13:14:27,334][00695] Avg episode reward: [(0, '17.407')]
346
+ [2024-08-04 13:14:27,360][01565] Updated weights for policy 0, policy_version 910 (0.0013)
347
+ [2024-08-04 13:14:29,389][01565] Updated weights for policy 0, policy_version 920 (0.0013)
348
+ [2024-08-04 13:14:31,427][01565] Updated weights for policy 0, policy_version 930 (0.0013)
349
+ [2024-08-04 13:14:32,332][00695] Fps is (10 sec: 19660.5, 60 sec: 19729.1, 300 sec: 19128.3). Total num frames: 3825664. Throughput: 0: 4934.0. Samples: 945768. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
350
+ [2024-08-04 13:14:32,334][00695] Avg episode reward: [(0, '17.492')]
351
+ [2024-08-04 13:14:33,474][01565] Updated weights for policy 0, policy_version 940 (0.0013)
352
+ [2024-08-04 13:14:35,537][01565] Updated weights for policy 0, policy_version 950 (0.0012)
353
+ [2024-08-04 13:14:37,332][00695] Fps is (10 sec: 20069.6, 60 sec: 19729.0, 300 sec: 19141.3). Total num frames: 3923968. Throughput: 0: 4933.8. Samples: 975640. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
354
+ [2024-08-04 13:14:37,334][00695] Avg episode reward: [(0, '18.898')]
355
+ [2024-08-04 13:14:37,337][01552] Saving new best policy, reward=18.898!
356
+ [2024-08-04 13:14:37,659][01565] Updated weights for policy 0, policy_version 960 (0.0013)
357
+ [2024-08-04 13:14:39,749][01565] Updated weights for policy 0, policy_version 970 (0.0013)
358
+ [2024-08-04 13:14:41,351][01552] Stopping Batcher_0...
359
+ [2024-08-04 13:14:41,352][01552] Loop batcher_evt_loop terminating...
360
+ [2024-08-04 13:14:41,352][01552] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
361
+ [2024-08-04 13:14:41,351][00695] Component Batcher_0 stopped!
362
+ [2024-08-04 13:14:41,368][01567] Stopping RolloutWorker_w1...
363
+ [2024-08-04 13:14:41,368][01565] Weights refcount: 2 0
364
+ [2024-08-04 13:14:41,368][01567] Loop rollout_proc1_evt_loop terminating...
365
+ [2024-08-04 13:14:41,369][01584] Stopping RolloutWorker_w7...
366
+ [2024-08-04 13:14:41,369][01584] Loop rollout_proc7_evt_loop terminating...
367
+ [2024-08-04 13:14:41,370][01570] Stopping RolloutWorker_w4...
368
+ [2024-08-04 13:14:41,370][01565] Stopping InferenceWorker_p0-w0...
369
+ [2024-08-04 13:14:41,370][01571] Stopping RolloutWorker_w5...
370
+ [2024-08-04 13:14:41,370][01566] Stopping RolloutWorker_w0...
371
+ [2024-08-04 13:14:41,370][01570] Loop rollout_proc4_evt_loop terminating...
372
+ [2024-08-04 13:14:41,370][01565] Loop inference_proc0-0_evt_loop terminating...
373
+ [2024-08-04 13:14:41,371][01571] Loop rollout_proc5_evt_loop terminating...
374
+ [2024-08-04 13:14:41,371][01566] Loop rollout_proc0_evt_loop terminating...
375
+ [2024-08-04 13:14:41,371][01569] Stopping RolloutWorker_w3...
376
+ [2024-08-04 13:14:41,371][01568] Stopping RolloutWorker_w2...
377
+ [2024-08-04 13:14:41,368][00695] Component RolloutWorker_w1 stopped!
378
+ [2024-08-04 13:14:41,372][01569] Loop rollout_proc3_evt_loop terminating...
379
+ [2024-08-04 13:14:41,372][01568] Loop rollout_proc2_evt_loop terminating...
380
+ [2024-08-04 13:14:41,372][01572] Stopping RolloutWorker_w6...
381
+ [2024-08-04 13:14:41,373][01572] Loop rollout_proc6_evt_loop terminating...
382
+ [2024-08-04 13:14:41,372][00695] Component RolloutWorker_w7 stopped!
383
+ [2024-08-04 13:14:41,374][00695] Component RolloutWorker_w4 stopped!
384
+ [2024-08-04 13:14:41,377][00695] Component InferenceWorker_p0-w0 stopped!
385
+ [2024-08-04 13:14:41,379][00695] Component RolloutWorker_w5 stopped!
386
+ [2024-08-04 13:14:41,381][00695] Component RolloutWorker_w0 stopped!
387
+ [2024-08-04 13:14:41,384][00695] Component RolloutWorker_w2 stopped!
388
+ [2024-08-04 13:14:41,386][00695] Component RolloutWorker_w3 stopped!
389
+ [2024-08-04 13:14:41,390][00695] Component RolloutWorker_w6 stopped!
390
+ [2024-08-04 13:14:41,432][01552] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
391
+ [2024-08-04 13:14:41,571][01552] Stopping LearnerWorker_p0...
392
+ [2024-08-04 13:14:41,572][01552] Loop learner_proc0_evt_loop terminating...
393
+ [2024-08-04 13:14:41,571][00695] Component LearnerWorker_p0 stopped!
394
+ [2024-08-04 13:14:41,573][00695] Waiting for process learner_proc0 to stop...
395
+ [2024-08-04 13:14:42,318][00695] Waiting for process inference_proc0-0 to join...
396
+ [2024-08-04 13:14:42,321][00695] Waiting for process rollout_proc0 to join...
397
+ [2024-08-04 13:14:42,323][00695] Waiting for process rollout_proc1 to join...
398
+ [2024-08-04 13:14:42,325][00695] Waiting for process rollout_proc2 to join...
399
+ [2024-08-04 13:14:42,327][00695] Waiting for process rollout_proc3 to join...
400
+ [2024-08-04 13:14:42,329][00695] Waiting for process rollout_proc4 to join...
401
+ [2024-08-04 13:14:42,331][00695] Waiting for process rollout_proc5 to join...
402
+ [2024-08-04 13:14:42,333][00695] Waiting for process rollout_proc6 to join...
403
+ [2024-08-04 13:14:42,335][00695] Waiting for process rollout_proc7 to join...
404
+ [2024-08-04 13:14:42,337][00695] Batcher 0 profile tree view:
405
+ batching: 11.2535, releasing_batches: 0.0233
406
+ [2024-08-04 13:14:42,338][00695] InferenceWorker_p0-w0 profile tree view:
407
+ wait_policy: 0.0001
408
+ wait_policy_total: 3.8458
409
+ update_model: 3.4116
410
+ weight_update: 0.0013
411
+ one_step: 0.0025
412
+ handle_policy_step: 190.4432
413
+ deserialize: 8.1147, stack: 1.2636, obs_to_device_normalize: 44.4669, forward: 93.7349, send_messages: 13.6313
414
+ prepare_outputs: 20.8268
415
+ to_cpu: 12.6829
416
+ [2024-08-04 13:14:42,339][00695] Learner 0 profile tree view:
417
+ misc: 0.0045, prepare_batch: 10.1533
418
+ train: 23.3225
419
+ epoch_init: 0.0053, minibatch_init: 0.0062, losses_postprocess: 0.2948, kl_divergence: 0.4003, after_optimizer: 5.5042
420
+ calculate_losses: 9.6017
421
+ losses_init: 0.0033, forward_head: 0.6912, bptt_initial: 5.9082, tail: 0.5724, advantages_returns: 0.1480, losses: 1.0713
422
+ bptt: 1.0338
423
+ bptt_forward_core: 0.9800
424
+ update: 7.1648
425
+ clip: 0.7562
426
+ [2024-08-04 13:14:42,343][00695] RolloutWorker_w0 profile tree view:
427
+ wait_for_trajectories: 0.1445, enqueue_policy_requests: 7.5329, env_step: 125.5377, overhead: 6.0592, complete_rollouts: 0.2284
428
+ save_policy_outputs: 8.7593
429
+ split_output_tensors: 3.4895
430
+ [2024-08-04 13:14:42,344][00695] RolloutWorker_w7 profile tree view:
431
+ wait_for_trajectories: 0.1478, enqueue_policy_requests: 7.5370, env_step: 125.2499, overhead: 6.2157, complete_rollouts: 0.2298
432
+ save_policy_outputs: 8.7719
433
+ split_output_tensors: 3.5418
434
+ [2024-08-04 13:14:42,346][00695] Loop Runner_EvtLoop terminating...
435
+ [2024-08-04 13:14:42,347][00695] Runner profile tree view:
436
+ main_loop: 215.9152
437
+ [2024-08-04 13:14:42,349][00695] Collected {0: 4005888}, FPS: 18553.1
438
+ [2024-08-04 13:15:09,203][00695] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
439
+ [2024-08-04 13:15:09,204][00695] Overriding arg 'num_workers' with value 1 passed from command line
440
+ [2024-08-04 13:15:09,206][00695] Adding new argument 'no_render'=True that is not in the saved config file!
441
+ [2024-08-04 13:15:09,208][00695] Adding new argument 'save_video'=True that is not in the saved config file!
442
+ [2024-08-04 13:15:09,208][00695] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
443
+ [2024-08-04 13:15:09,211][00695] Adding new argument 'video_name'=None that is not in the saved config file!
444
+ [2024-08-04 13:15:09,212][00695] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
445
+ [2024-08-04 13:15:09,213][00695] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
446
+ [2024-08-04 13:15:09,214][00695] Adding new argument 'push_to_hub'=False that is not in the saved config file!
447
+ [2024-08-04 13:15:09,215][00695] Adding new argument 'hf_repository'=None that is not in the saved config file!
448
+ [2024-08-04 13:15:09,217][00695] Adding new argument 'policy_index'=0 that is not in the saved config file!
449
+ [2024-08-04 13:15:09,217][00695] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
450
+ [2024-08-04 13:15:09,219][00695] Adding new argument 'train_script'=None that is not in the saved config file!
451
+ [2024-08-04 13:15:09,220][00695] Adding new argument 'enjoy_script'=None that is not in the saved config file!
452
+ [2024-08-04 13:15:09,222][00695] Using frameskip 1 and render_action_repeat=4 for evaluation
453
+ [2024-08-04 13:15:09,250][00695] Doom resolution: 160x120, resize resolution: (128, 72)
454
+ [2024-08-04 13:15:09,253][00695] RunningMeanStd input shape: (3, 72, 128)
455
+ [2024-08-04 13:15:09,255][00695] RunningMeanStd input shape: (1,)
456
+ [2024-08-04 13:15:09,271][00695] ConvEncoder: input_channels=3
457
+ [2024-08-04 13:15:09,384][00695] Conv encoder output size: 512
458
+ [2024-08-04 13:15:09,385][00695] Policy head output size: 512
459
+ [2024-08-04 13:15:09,532][00695] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
460
+ [2024-08-04 13:15:10,343][00695] Num frames 100...
461
+ [2024-08-04 13:15:10,464][00695] Num frames 200...
462
+ [2024-08-04 13:15:10,581][00695] Num frames 300...
463
+ [2024-08-04 13:15:10,702][00695] Num frames 400...
464
+ [2024-08-04 13:15:10,818][00695] Num frames 500...
465
+ [2024-08-04 13:15:10,936][00695] Num frames 600...
466
+ [2024-08-04 13:15:11,054][00695] Num frames 700...
467
+ [2024-08-04 13:15:11,114][00695] Avg episode rewards: #0: 11.040, true rewards: #0: 7.040
468
+ [2024-08-04 13:15:11,115][00695] Avg episode reward: 11.040, avg true_objective: 7.040
469
+ [2024-08-04 13:15:11,229][00695] Num frames 800...
470
+ [2024-08-04 13:15:11,349][00695] Num frames 900...
471
+ [2024-08-04 13:15:11,468][00695] Num frames 1000...
472
+ [2024-08-04 13:15:11,586][00695] Num frames 1100...
473
+ [2024-08-04 13:15:11,706][00695] Num frames 1200...
474
+ [2024-08-04 13:15:11,827][00695] Num frames 1300...
475
+ [2024-08-04 13:15:11,949][00695] Num frames 1400...
476
+ [2024-08-04 13:15:12,081][00695] Num frames 1500...
477
+ [2024-08-04 13:15:12,201][00695] Num frames 1600...
478
+ [2024-08-04 13:15:12,253][00695] Avg episode rewards: #0: 14.000, true rewards: #0: 8.000
479
+ [2024-08-04 13:15:12,255][00695] Avg episode reward: 14.000, avg true_objective: 8.000
480
+ [2024-08-04 13:15:12,373][00695] Num frames 1700...
481
+ [2024-08-04 13:15:12,490][00695] Num frames 1800...
482
+ [2024-08-04 13:15:12,608][00695] Num frames 1900...
483
+ [2024-08-04 13:15:12,731][00695] Num frames 2000...
484
+ [2024-08-04 13:15:12,858][00695] Num frames 2100...
485
+ [2024-08-04 13:15:12,985][00695] Num frames 2200...
486
+ [2024-08-04 13:15:13,114][00695] Num frames 2300...
487
+ [2024-08-04 13:15:13,233][00695] Num frames 2400...
488
+ [2024-08-04 13:15:13,351][00695] Num frames 2500...
489
+ [2024-08-04 13:15:13,437][00695] Avg episode rewards: #0: 14.760, true rewards: #0: 8.427
490
+ [2024-08-04 13:15:13,439][00695] Avg episode reward: 14.760, avg true_objective: 8.427
491
+ [2024-08-04 13:15:13,524][00695] Num frames 2600...
492
+ [2024-08-04 13:15:13,643][00695] Num frames 2700...
493
+ [2024-08-04 13:15:13,760][00695] Num frames 2800...
494
+ [2024-08-04 13:15:13,878][00695] Num frames 2900...
495
+ [2024-08-04 13:15:13,997][00695] Num frames 3000...
496
+ [2024-08-04 13:15:14,116][00695] Num frames 3100...
497
+ [2024-08-04 13:15:14,236][00695] Num frames 3200...
498
+ [2024-08-04 13:15:14,354][00695] Num frames 3300...
499
+ [2024-08-04 13:15:14,485][00695] Avg episode rewards: #0: 15.408, true rewards: #0: 8.407
500
+ [2024-08-04 13:15:14,486][00695] Avg episode reward: 15.408, avg true_objective: 8.407
501
+ [2024-08-04 13:15:14,531][00695] Num frames 3400...
502
+ [2024-08-04 13:15:14,649][00695] Num frames 3500...
503
+ [2024-08-04 13:15:14,768][00695] Num frames 3600...
504
+ [2024-08-04 13:15:14,884][00695] Num frames 3700...
505
+ [2024-08-04 13:15:15,002][00695] Num frames 3800...
506
+ [2024-08-04 13:15:15,123][00695] Num frames 3900...
507
+ [2024-08-04 13:15:15,240][00695] Num frames 4000...
508
+ [2024-08-04 13:15:15,360][00695] Num frames 4100...
509
+ [2024-08-04 13:15:15,479][00695] Num frames 4200...
510
+ [2024-08-04 13:15:15,596][00695] Num frames 4300...
511
+ [2024-08-04 13:15:15,717][00695] Num frames 4400...
512
+ [2024-08-04 13:15:15,887][00695] Avg episode rewards: #0: 17.592, true rewards: #0: 8.992
513
+ [2024-08-04 13:15:15,888][00695] Avg episode reward: 17.592, avg true_objective: 8.992
514
+ [2024-08-04 13:15:15,895][00695] Num frames 4500...
515
+ [2024-08-04 13:15:16,014][00695] Num frames 4600...
516
+ [2024-08-04 13:15:16,131][00695] Num frames 4700...
517
+ [2024-08-04 13:15:16,246][00695] Num frames 4800...
518
+ [2024-08-04 13:15:16,363][00695] Num frames 4900...
519
+ [2024-08-04 13:15:16,479][00695] Num frames 5000...
520
+ [2024-08-04 13:15:16,597][00695] Num frames 5100...
521
+ [2024-08-04 13:15:16,714][00695] Num frames 5200...
522
+ [2024-08-04 13:15:16,841][00695] Avg episode rewards: #0: 16.773, true rewards: #0: 8.773
523
+ [2024-08-04 13:15:16,842][00695] Avg episode reward: 16.773, avg true_objective: 8.773
524
+ [2024-08-04 13:15:16,887][00695] Num frames 5300...
525
+ [2024-08-04 13:15:17,010][00695] Num frames 5400...
526
+ [2024-08-04 13:15:17,126][00695] Num frames 5500...
527
+ [2024-08-04 13:15:17,246][00695] Num frames 5600...
528
+ [2024-08-04 13:15:17,362][00695] Num frames 5700...
529
+ [2024-08-04 13:15:17,479][00695] Num frames 5800...
530
+ [2024-08-04 13:15:17,598][00695] Num frames 5900...
531
+ [2024-08-04 13:15:17,715][00695] Num frames 6000...
532
+ [2024-08-04 13:15:17,832][00695] Num frames 6100...
533
+ [2024-08-04 13:15:17,953][00695] Num frames 6200...
534
+ [2024-08-04 13:15:18,071][00695] Num frames 6300...
535
+ [2024-08-04 13:15:18,190][00695] Num frames 6400...
536
+ [2024-08-04 13:15:18,310][00695] Num frames 6500...
537
+ [2024-08-04 13:15:18,453][00695] Avg episode rewards: #0: 18.966, true rewards: #0: 9.394
538
+ [2024-08-04 13:15:18,455][00695] Avg episode reward: 18.966, avg true_objective: 9.394
539
+ [2024-08-04 13:15:18,485][00695] Num frames 6600...
540
+ [2024-08-04 13:15:18,600][00695] Num frames 6700...
541
+ [2024-08-04 13:15:18,720][00695] Num frames 6800...
542
+ [2024-08-04 13:15:18,837][00695] Num frames 6900...
543
+ [2024-08-04 13:15:18,951][00695] Num frames 7000...
544
+ [2024-08-04 13:15:19,066][00695] Num frames 7100...
545
+ [2024-08-04 13:15:19,157][00695] Avg episode rewards: #0: 17.788, true rewards: #0: 8.912
546
+ [2024-08-04 13:15:19,159][00695] Avg episode reward: 17.788, avg true_objective: 8.912
547
+ [2024-08-04 13:15:19,241][00695] Num frames 7200...
548
+ [2024-08-04 13:15:19,359][00695] Num frames 7300...
549
+ [2024-08-04 13:15:19,476][00695] Num frames 7400...
550
+ [2024-08-04 13:15:19,592][00695] Num frames 7500...
551
+ [2024-08-04 13:15:19,707][00695] Num frames 7600...
552
+ [2024-08-04 13:15:19,826][00695] Num frames 7700...
553
+ [2024-08-04 13:15:19,946][00695] Num frames 7800...
554
+ [2024-08-04 13:15:20,063][00695] Num frames 7900...
555
+ [2024-08-04 13:15:20,182][00695] Num frames 8000...
556
+ [2024-08-04 13:15:20,299][00695] Num frames 8100...
557
+ [2024-08-04 13:15:20,416][00695] Num frames 8200...
558
+ [2024-08-04 13:15:20,567][00695] Avg episode rewards: #0: 18.425, true rewards: #0: 9.202
559
+ [2024-08-04 13:15:20,569][00695] Avg episode reward: 18.425, avg true_objective: 9.202
560
+ [2024-08-04 13:15:20,590][00695] Num frames 8300...
561
+ [2024-08-04 13:15:20,707][00695] Num frames 8400...
562
+ [2024-08-04 13:15:20,920][00695] Num frames 8500...
563
+ [2024-08-04 13:15:21,036][00695] Num frames 8600...
564
+ [2024-08-04 13:15:21,153][00695] Num frames 8700...
565
+ [2024-08-04 13:15:21,271][00695] Num frames 8800...
566
+ [2024-08-04 13:15:21,390][00695] Num frames 8900...
567
+ [2024-08-04 13:15:21,509][00695] Num frames 9000...
568
+ [2024-08-04 13:15:21,628][00695] Num frames 9100...
569
+ [2024-08-04 13:15:21,748][00695] Num frames 9200...
570
+ [2024-08-04 13:15:21,865][00695] Num frames 9300...
571
+ [2024-08-04 13:15:22,009][00695] Avg episode rewards: #0: 18.775, true rewards: #0: 9.375
572
+ [2024-08-04 13:15:22,010][00695] Avg episode reward: 18.775, avg true_objective: 9.375
573
+ [2024-08-04 13:15:44,218][00695] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
574
+ [2024-08-04 13:19:20,884][00695] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
575
+ [2024-08-04 13:19:20,885][00695] Overriding arg 'num_workers' with value 1 passed from command line
576
+ [2024-08-04 13:19:20,886][00695] Adding new argument 'no_render'=True that is not in the saved config file!
577
+ [2024-08-04 13:19:20,888][00695] Adding new argument 'save_video'=True that is not in the saved config file!
578
+ [2024-08-04 13:19:20,889][00695] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
579
+ [2024-08-04 13:19:20,890][00695] Adding new argument 'video_name'=None that is not in the saved config file!
580
+ [2024-08-04 13:19:20,892][00695] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
581
+ [2024-08-04 13:19:20,893][00695] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
582
+ [2024-08-04 13:19:20,894][00695] Adding new argument 'push_to_hub'=True that is not in the saved config file!
583
+ [2024-08-04 13:19:20,895][00695] Adding new argument 'hf_repository'='dogukankartal/SampleFactory_ViZDoom' that is not in the saved config file!
584
+ [2024-08-04 13:19:20,896][00695] Adding new argument 'policy_index'=0 that is not in the saved config file!
585
+ [2024-08-04 13:19:20,897][00695] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
586
+ [2024-08-04 13:19:20,898][00695] Adding new argument 'train_script'=None that is not in the saved config file!
587
+ [2024-08-04 13:19:20,901][00695] Adding new argument 'enjoy_script'=None that is not in the saved config file!
588
+ [2024-08-04 13:19:20,902][00695] Using frameskip 1 and render_action_repeat=4 for evaluation
589
+ [2024-08-04 13:19:20,924][00695] RunningMeanStd input shape: (3, 72, 128)
590
+ [2024-08-04 13:19:20,926][00695] RunningMeanStd input shape: (1,)
591
+ [2024-08-04 13:19:20,937][00695] ConvEncoder: input_channels=3
592
+ [2024-08-04 13:19:20,976][00695] Conv encoder output size: 512
593
+ [2024-08-04 13:19:20,977][00695] Policy head output size: 512
594
+ [2024-08-04 13:19:20,998][00695] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
595
+ [2024-08-04 13:19:21,418][00695] Num frames 100...
596
+ [2024-08-04 13:19:21,534][00695] Num frames 200...
597
+ [2024-08-04 13:19:21,653][00695] Num frames 300...
598
+ [2024-08-04 13:19:21,769][00695] Num frames 400...
599
+ [2024-08-04 13:19:21,879][00695] Avg episode rewards: #0: 7.480, true rewards: #0: 4.480
600
+ [2024-08-04 13:19:21,880][00695] Avg episode reward: 7.480, avg true_objective: 4.480
601
+ [2024-08-04 13:19:21,943][00695] Num frames 500...
602
+ [2024-08-04 13:19:22,059][00695] Num frames 600...
603
+ [2024-08-04 13:19:22,175][00695] Num frames 700...
604
+ [2024-08-04 13:19:22,292][00695] Num frames 800...
605
+ [2024-08-04 13:19:22,410][00695] Num frames 900...
606
+ [2024-08-04 13:19:22,528][00695] Num frames 1000...
607
+ [2024-08-04 13:19:22,645][00695] Num frames 1100...
608
+ [2024-08-04 13:19:22,763][00695] Num frames 1200...
609
+ [2024-08-04 13:19:22,884][00695] Num frames 1300...
610
+ [2024-08-04 13:19:23,004][00695] Num frames 1400...
611
+ [2024-08-04 13:19:23,125][00695] Num frames 1500...
612
+ [2024-08-04 13:19:23,242][00695] Num frames 1600...
613
+ [2024-08-04 13:19:23,361][00695] Num frames 1700...
614
+ [2024-08-04 13:19:23,478][00695] Num frames 1800...
615
+ [2024-08-04 13:19:23,598][00695] Num frames 1900...
616
+ [2024-08-04 13:19:23,717][00695] Num frames 2000...
617
+ [2024-08-04 13:19:23,838][00695] Num frames 2100...
618
+ [2024-08-04 13:19:23,959][00695] Num frames 2200...
619
+ [2024-08-04 13:19:24,085][00695] Num frames 2300...
620
+ [2024-08-04 13:19:24,213][00695] Num frames 2400...
621
+ [2024-08-04 13:19:24,342][00695] Num frames 2500...
622
+ [2024-08-04 13:19:24,457][00695] Avg episode rewards: #0: 29.240, true rewards: #0: 12.740
623
+ [2024-08-04 13:19:24,458][00695] Avg episode reward: 29.240, avg true_objective: 12.740
624
+ [2024-08-04 13:19:24,525][00695] Num frames 2600...
625
+ [2024-08-04 13:19:24,652][00695] Num frames 2700...
626
+ [2024-08-04 13:19:24,778][00695] Num frames 2800...
627
+ [2024-08-04 13:19:24,902][00695] Num frames 2900...
628
+ [2024-08-04 13:19:25,028][00695] Num frames 3000...
629
+ [2024-08-04 13:19:25,153][00695] Num frames 3100...
630
+ [2024-08-04 13:19:25,281][00695] Num frames 3200...
631
+ [2024-08-04 13:19:25,401][00695] Avg episode rewards: #0: 24.506, true rewards: #0: 10.840
632
+ [2024-08-04 13:19:25,402][00695] Avg episode reward: 24.506, avg true_objective: 10.840
633
+ [2024-08-04 13:19:25,465][00695] Num frames 3300...
634
+ [2024-08-04 13:19:25,590][00695] Num frames 3400...
635
+ [2024-08-04 13:19:25,717][00695] Num frames 3500...
636
+ [2024-08-04 13:19:25,840][00695] Num frames 3600...
637
+ [2024-08-04 13:19:25,957][00695] Num frames 3700...
638
+ [2024-08-04 13:19:26,085][00695] Num frames 3800...
639
+ [2024-08-04 13:19:26,211][00695] Num frames 3900...
640
+ [2024-08-04 13:19:26,337][00695] Num frames 4000...
641
+ [2024-08-04 13:19:26,462][00695] Num frames 4100...
642
+ [2024-08-04 13:19:26,673][00695] Num frames 4200...
643
+ [2024-08-04 13:19:26,799][00695] Num frames 4300...
644
+ [2024-08-04 13:19:26,864][00695] Avg episode rewards: #0: 25.270, true rewards: #0: 10.770
645
+ [2024-08-04 13:19:26,866][00695] Avg episode reward: 25.270, avg true_objective: 10.770
646
+ [2024-08-04 13:19:26,979][00695] Num frames 4400...
647
+ [2024-08-04 13:19:27,106][00695] Num frames 4500...
648
+ [2024-08-04 13:19:27,232][00695] Num frames 4600...
649
+ [2024-08-04 13:19:27,356][00695] Num frames 4700...
650
+ [2024-08-04 13:19:27,481][00695] Num frames 4800...
651
+ [2024-08-04 13:19:27,608][00695] Num frames 4900...
652
+ [2024-08-04 13:19:27,735][00695] Num frames 5000...
653
+ [2024-08-04 13:19:27,860][00695] Num frames 5100...
654
+ [2024-08-04 13:19:27,985][00695] Num frames 5200...
655
+ [2024-08-04 13:19:28,113][00695] Num frames 5300...
656
+ [2024-08-04 13:19:28,238][00695] Num frames 5400...
657
+ [2024-08-04 13:19:28,363][00695] Num frames 5500...
658
+ [2024-08-04 13:19:28,485][00695] Num frames 5600...
659
+ [2024-08-04 13:19:28,609][00695] Num frames 5700...
660
+ [2024-08-04 13:19:28,734][00695] Num frames 5800...
661
+ [2024-08-04 13:19:28,857][00695] Num frames 5900...
662
+ [2024-08-04 13:19:28,997][00695] Avg episode rewards: #0: 28.144, true rewards: #0: 11.944
663
+ [2024-08-04 13:19:28,998][00695] Avg episode reward: 28.144, avg true_objective: 11.944
664
+ [2024-08-04 13:19:29,033][00695] Num frames 6000...
665
+ [2024-08-04 13:19:29,150][00695] Num frames 6100...
666
+ [2024-08-04 13:19:29,271][00695] Num frames 6200...
667
+ [2024-08-04 13:19:29,389][00695] Num frames 6300...
668
+ [2024-08-04 13:19:29,505][00695] Num frames 6400...
669
+ [2024-08-04 13:19:29,584][00695] Avg episode rewards: #0: 24.700, true rewards: #0: 10.700
670
+ [2024-08-04 13:19:29,585][00695] Avg episode reward: 24.700, avg true_objective: 10.700
671
+ [2024-08-04 13:19:29,676][00695] Num frames 6500...
672
+ [2024-08-04 13:19:29,794][00695] Num frames 6600...
673
+ [2024-08-04 13:19:29,910][00695] Num frames 6700...
674
+ [2024-08-04 13:19:30,029][00695] Num frames 6800...
675
+ [2024-08-04 13:19:30,154][00695] Num frames 6900...
676
+ [2024-08-04 13:19:30,281][00695] Num frames 7000...
677
+ [2024-08-04 13:19:30,406][00695] Num frames 7100...
678
+ [2024-08-04 13:19:30,530][00695] Num frames 7200...
679
+ [2024-08-04 13:19:30,653][00695] Num frames 7300...
680
+ [2024-08-04 13:19:30,759][00695] Avg episode rewards: #0: 24.058, true rewards: #0: 10.487
681
+ [2024-08-04 13:19:30,761][00695] Avg episode reward: 24.058, avg true_objective: 10.487
682
+ [2024-08-04 13:19:30,834][00695] Num frames 7400...
683
+ [2024-08-04 13:19:30,957][00695] Num frames 7500...
684
+ [2024-08-04 13:19:31,079][00695] Num frames 7600...
685
+ [2024-08-04 13:19:31,197][00695] Num frames 7700...
686
+ [2024-08-04 13:19:31,317][00695] Num frames 7800...
687
+ [2024-08-04 13:19:31,441][00695] Num frames 7900...
688
+ [2024-08-04 13:19:31,565][00695] Num frames 8000...
689
+ [2024-08-04 13:19:31,692][00695] Num frames 8100...
690
+ [2024-08-04 13:19:31,839][00695] Avg episode rewards: #0: 23.466, true rewards: #0: 10.216
691
+ [2024-08-04 13:19:31,841][00695] Avg episode reward: 23.466, avg true_objective: 10.216
692
+ [2024-08-04 13:19:31,875][00695] Num frames 8200...
693
+ [2024-08-04 13:19:32,000][00695] Num frames 8300...
694
+ [2024-08-04 13:19:32,125][00695] Num frames 8400...
695
+ [2024-08-04 13:19:32,251][00695] Num frames 8500...
696
+ [2024-08-04 13:19:32,375][00695] Num frames 8600...
697
+ [2024-08-04 13:19:32,501][00695] Num frames 8700...
698
+ [2024-08-04 13:19:32,628][00695] Num frames 8800...
699
+ [2024-08-04 13:19:32,753][00695] Num frames 8900...
700
+ [2024-08-04 13:19:32,871][00695] Num frames 9000...
701
+ [2024-08-04 13:19:32,989][00695] Num frames 9100...
702
+ [2024-08-04 13:19:33,047][00695] Avg episode rewards: #0: 23.001, true rewards: #0: 10.112
703
+ [2024-08-04 13:19:33,048][00695] Avg episode reward: 23.001, avg true_objective: 10.112
704
+ [2024-08-04 13:19:33,163][00695] Num frames 9200...
705
+ [2024-08-04 13:19:33,278][00695] Num frames 9300...
706
+ [2024-08-04 13:19:33,393][00695] Num frames 9400...
707
+ [2024-08-04 13:19:33,513][00695] Num frames 9500...
708
+ [2024-08-04 13:19:33,628][00695] Num frames 9600...
709
+ [2024-08-04 13:19:33,746][00695] Num frames 9700...
710
+ [2024-08-04 13:19:33,863][00695] Num frames 9800...
711
+ [2024-08-04 13:19:33,925][00695] Avg episode rewards: #0: 21.905, true rewards: #0: 9.805
712
+ [2024-08-04 13:19:33,927][00695] Avg episode reward: 21.905, avg true_objective: 9.805
713
+ [2024-08-04 13:19:56,989][00695] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
714
+ [2024-08-04 13:20:17,944][00695] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
715
+ [2024-08-04 13:20:17,945][00695] Overriding arg 'num_workers' with value 1 passed from command line
716
+ [2024-08-04 13:20:17,946][00695] Adding new argument 'no_render'=True that is not in the saved config file!
717
+ [2024-08-04 13:20:17,947][00695] Adding new argument 'save_video'=True that is not in the saved config file!
718
+ [2024-08-04 13:20:17,949][00695] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
719
+ [2024-08-04 13:20:17,951][00695] Adding new argument 'video_name'=None that is not in the saved config file!
720
+ [2024-08-04 13:20:17,952][00695] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
721
+ [2024-08-04 13:20:17,953][00695] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
722
+ [2024-08-04 13:20:17,955][00695] Adding new argument 'push_to_hub'=True that is not in the saved config file!
723
+ [2024-08-04 13:20:17,956][00695] Adding new argument 'hf_repository'='dogukankartal/SampleFactory_ViZDoom' that is not in the saved config file!
724
+ [2024-08-04 13:20:17,957][00695] Adding new argument 'policy_index'=0 that is not in the saved config file!
725
+ [2024-08-04 13:20:17,959][00695] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
726
+ [2024-08-04 13:20:17,960][00695] Adding new argument 'train_script'=None that is not in the saved config file!
727
+ [2024-08-04 13:20:17,961][00695] Adding new argument 'enjoy_script'=None that is not in the saved config file!
728
+ [2024-08-04 13:20:17,963][00695] Using frameskip 1 and render_action_repeat=4 for evaluation
729
+ [2024-08-04 13:20:17,991][00695] RunningMeanStd input shape: (3, 72, 128)
730
+ [2024-08-04 13:20:17,993][00695] RunningMeanStd input shape: (1,)
731
+ [2024-08-04 13:20:18,005][00695] ConvEncoder: input_channels=3
732
+ [2024-08-04 13:20:18,042][00695] Conv encoder output size: 512
733
+ [2024-08-04 13:20:18,044][00695] Policy head output size: 512
734
+ [2024-08-04 13:20:18,063][00695] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
735
+ [2024-08-04 13:20:18,477][00695] Num frames 100...
736
+ [2024-08-04 13:20:18,593][00695] Num frames 200...
737
+ [2024-08-04 13:20:18,710][00695] Num frames 300...
738
+ [2024-08-04 13:20:18,830][00695] Num frames 400...
739
+ [2024-08-04 13:20:18,941][00695] Avg episode rewards: #0: 5.480, true rewards: #0: 4.480
740
+ [2024-08-04 13:20:18,943][00695] Avg episode reward: 5.480, avg true_objective: 4.480
741
+ [2024-08-04 13:20:19,011][00695] Num frames 500...
742
+ [2024-08-04 13:20:19,131][00695] Num frames 600...
743
+ [2024-08-04 13:20:19,246][00695] Num frames 700...
744
+ [2024-08-04 13:20:19,363][00695] Num frames 800...
745
+ [2024-08-04 13:20:19,483][00695] Num frames 900...
746
+ [2024-08-04 13:20:19,598][00695] Num frames 1000...
747
+ [2024-08-04 13:20:19,720][00695] Num frames 1100...
748
+ [2024-08-04 13:20:19,839][00695] Num frames 1200...
749
+ [2024-08-04 13:20:19,959][00695] Num frames 1300...
750
+ [2024-08-04 13:20:20,087][00695] Num frames 1400...
751
+ [2024-08-04 13:20:20,206][00695] Num frames 1500...
752
+ [2024-08-04 13:20:20,327][00695] Num frames 1600...
753
+ [2024-08-04 13:20:20,449][00695] Num frames 1700...
754
+ [2024-08-04 13:20:20,572][00695] Num frames 1800...
755
+ [2024-08-04 13:20:20,692][00695] Num frames 1900...
756
+ [2024-08-04 13:20:20,816][00695] Num frames 2000...
757
+ [2024-08-04 13:20:20,941][00695] Num frames 2100...
758
+ [2024-08-04 13:20:21,087][00695] Avg episode rewards: #0: 25.380, true rewards: #0: 10.880
759
+ [2024-08-04 13:20:21,089][00695] Avg episode reward: 25.380, avg true_objective: 10.880
760
+ [2024-08-04 13:20:21,132][00695] Num frames 2200...
761
+ [2024-08-04 13:20:21,255][00695] Num frames 2300...
762
+ [2024-08-04 13:20:21,378][00695] Num frames 2400...
763
+ [2024-08-04 13:20:21,498][00695] Num frames 2500...
764
+ [2024-08-04 13:20:21,619][00695] Num frames 2600...
765
+ [2024-08-04 13:20:21,740][00695] Num frames 2700...
766
+ [2024-08-04 13:20:21,862][00695] Num frames 2800...
767
+ [2024-08-04 13:20:21,936][00695] Avg episode rewards: #0: 20.717, true rewards: #0: 9.383
768
+ [2024-08-04 13:20:21,937][00695] Avg episode reward: 20.717, avg true_objective: 9.383
769
+ [2024-08-04 13:20:22,038][00695] Num frames 2900...
770
+ [2024-08-04 13:20:22,159][00695] Num frames 3000...
771
+ [2024-08-04 13:20:22,275][00695] Num frames 3100...
772
+ [2024-08-04 13:20:22,396][00695] Num frames 3200...
773
+ [2024-08-04 13:20:22,516][00695] Num frames 3300...
774
+ [2024-08-04 13:20:22,635][00695] Num frames 3400...
775
+ [2024-08-04 13:20:22,756][00695] Num frames 3500...
776
+ [2024-08-04 13:20:22,876][00695] Num frames 3600...
777
+ [2024-08-04 13:20:22,997][00695] Num frames 3700...
778
+ [2024-08-04 13:20:23,120][00695] Num frames 3800...
779
+ [2024-08-04 13:20:23,240][00695] Num frames 3900...
780
+ [2024-08-04 13:20:23,375][00695] Avg episode rewards: #0: 22.417, true rewards: #0: 9.917
781
+ [2024-08-04 13:20:23,377][00695] Avg episode reward: 22.417, avg true_objective: 9.917
782
+ [2024-08-04 13:20:23,419][00695] Num frames 4000...
783
+ [2024-08-04 13:20:23,540][00695] Num frames 4100...
784
+ [2024-08-04 13:20:23,664][00695] Num frames 4200...
785
+ [2024-08-04 13:20:23,783][00695] Num frames 4300...
786
+ [2024-08-04 13:20:23,901][00695] Num frames 4400...
787
+ [2024-08-04 13:20:23,975][00695] Avg episode rewards: #0: 19.030, true rewards: #0: 8.830
788
+ [2024-08-04 13:20:23,976][00695] Avg episode reward: 19.030, avg true_objective: 8.830
789
+ [2024-08-04 13:20:24,079][00695] Num frames 4500...
790
+ [2024-08-04 13:20:24,198][00695] Num frames 4600...
791
+ [2024-08-04 13:20:24,323][00695] Num frames 4700...
792
+ [2024-08-04 13:20:24,450][00695] Num frames 4800...
793
+ [2024-08-04 13:20:24,571][00695] Num frames 4900...
794
+ [2024-08-04 13:20:24,693][00695] Num frames 5000...
795
+ [2024-08-04 13:20:24,815][00695] Avg episode rewards: #0: 17.758, true rewards: #0: 8.425
796
+ [2024-08-04 13:20:24,816][00695] Avg episode reward: 17.758, avg true_objective: 8.425
797
+ [2024-08-04 13:20:24,870][00695] Num frames 5100...
798
+ [2024-08-04 13:20:24,987][00695] Num frames 5200...
799
+ [2024-08-04 13:20:25,109][00695] Num frames 5300...
800
+ [2024-08-04 13:20:25,227][00695] Num frames 5400...
801
+ [2024-08-04 13:20:25,343][00695] Num frames 5500...
802
+ [2024-08-04 13:20:25,462][00695] Num frames 5600...
803
+ [2024-08-04 13:20:25,577][00695] Num frames 5700...
804
+ [2024-08-04 13:20:25,701][00695] Avg episode rewards: #0: 16.799, true rewards: #0: 8.227
805
+ [2024-08-04 13:20:25,703][00695] Avg episode reward: 16.799, avg true_objective: 8.227
806
+ [2024-08-04 13:20:25,751][00695] Num frames 5800...
807
+ [2024-08-04 13:20:25,868][00695] Num frames 5900...
808
+ [2024-08-04 13:20:25,990][00695] Num frames 6000...
809
+ [2024-08-04 13:20:26,107][00695] Num frames 6100...
810
+ [2024-08-04 13:20:26,224][00695] Num frames 6200...
811
+ [2024-08-04 13:20:26,343][00695] Num frames 6300...
812
+ [2024-08-04 13:20:26,460][00695] Num frames 6400...
813
+ [2024-08-04 13:20:26,581][00695] Num frames 6500...
814
+ [2024-08-04 13:20:26,700][00695] Num frames 6600...
815
+ [2024-08-04 13:20:26,819][00695] Num frames 6700...
816
+ [2024-08-04 13:20:26,938][00695] Num frames 6800...
817
+ [2024-08-04 13:20:27,059][00695] Num frames 6900...
818
+ [2024-08-04 13:20:27,207][00695] Avg episode rewards: #0: 18.225, true rewards: #0: 8.725
819
+ [2024-08-04 13:20:27,208][00695] Avg episode reward: 18.225, avg true_objective: 8.725
820
+ [2024-08-04 13:20:27,235][00695] Num frames 7000...
821
+ [2024-08-04 13:20:27,351][00695] Num frames 7100...
822
+ [2024-08-04 13:20:27,468][00695] Num frames 7200...
823
+ [2024-08-04 13:20:27,588][00695] Num frames 7300...
824
+ [2024-08-04 13:20:27,704][00695] Num frames 7400...
825
+ [2024-08-04 13:20:27,822][00695] Num frames 7500...
826
+ [2024-08-04 13:20:27,938][00695] Num frames 7600...
827
+ [2024-08-04 13:20:28,150][00695] Num frames 7700...
828
+ [2024-08-04 13:20:28,268][00695] Num frames 7800...
829
+ [2024-08-04 13:20:28,387][00695] Num frames 7900...
830
+ [2024-08-04 13:20:28,505][00695] Num frames 8000...
831
+ [2024-08-04 13:20:28,622][00695] Num frames 8100...
832
+ [2024-08-04 13:20:28,739][00695] Num frames 8200...
833
+ [2024-08-04 13:20:28,858][00695] Num frames 8300...
834
+ [2024-08-04 13:20:28,977][00695] Num frames 8400...
835
+ [2024-08-04 13:20:29,095][00695] Avg episode rewards: #0: 19.836, true rewards: #0: 9.391
836
+ [2024-08-04 13:20:29,096][00695] Avg episode reward: 19.836, avg true_objective: 9.391
837
+ [2024-08-04 13:20:29,155][00695] Num frames 8500...
838
+ [2024-08-04 13:20:29,274][00695] Num frames 8600...
839
+ [2024-08-04 13:20:29,394][00695] Num frames 8700...
840
+ [2024-08-04 13:20:29,515][00695] Num frames 8800...
841
+ [2024-08-04 13:20:29,635][00695] Num frames 8900...
842
+ [2024-08-04 13:20:29,757][00695] Num frames 9000...
843
+ [2024-08-04 13:20:29,878][00695] Num frames 9100...
844
+ [2024-08-04 13:20:29,997][00695] Num frames 9200...
845
+ [2024-08-04 13:20:30,114][00695] Num frames 9300...
846
+ [2024-08-04 13:20:30,233][00695] Num frames 9400...
847
+ [2024-08-04 13:20:30,352][00695] Num frames 9500...
848
+ [2024-08-04 13:20:30,472][00695] Num frames 9600...
849
+ [2024-08-04 13:20:30,591][00695] Num frames 9700...
850
+ [2024-08-04 13:20:30,713][00695] Num frames 9800...
851
+ [2024-08-04 13:20:30,834][00695] Num frames 9900...
852
+ [2024-08-04 13:20:30,969][00695] Avg episode rewards: #0: 21.365, true rewards: #0: 9.965
853
+ [2024-08-04 13:20:30,970][00695] Avg episode reward: 21.365, avg true_objective: 9.965
854
+ [2024-08-04 13:20:54,302][00695] Replay video saved to /content/train_dir/default_experiment/replay.mp4!