Hugging Face's logo

lahirum
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
lahirum commited on
Commit
94befc5
•
1 Parent(s): 048579c

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1731166102.fa3bfb27046e +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000903_3698688_reward_28.112.pth +3 -0
  5. checkpoint_p0/checkpoint_000000947_3878912.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 +703 -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.1731166102.fa3bfb27046e ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:309e7998630795a6c06a65b696e4277163c2ec9a25c6141fd43c86e84956013b
3
+ size 224476
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: 9.05 +/- 4.30
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 lahirum/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_000000903_3698688_reward_28.112.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b269d816e396fe29db2f20be65b4e1e41f547348594784a397695631aaaaa830
3
+ size 34929051
checkpoint_p0/checkpoint_000000947_3878912.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a55540d96b0ed79aad89a759b79d4c8aa5fb028cc40dd2c790c25039f3f3ad4
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 sha256:30d262002c00bd696983ffb82815d47990759a3dfb579cbeccc36de13658b7ac
3
+ size 34929477
config.json ADDED
@@ -0,0 +1,142 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "help": false,
3
+ "algo": "APPO",
4
+ "env": "doom_health_gathering_supreme",
5
+ "experiment": "default_experiment",
6
+ "train_dir": "/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:c5eeae3e9e853c5717bdda01fa509af78baf4b7f7af2d3df9b1069df39fa24e2
3
+ size 17258602
sf_log.txt ADDED
@@ -0,0 +1,703 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2024-11-09 15:28:28,043][00359] Saving configuration to /content/train_dir/default_experiment/config.json...
2
+ [2024-11-09 15:28:28,045][00359] Rollout worker 0 uses device cpu
3
+ [2024-11-09 15:28:28,046][00359] Rollout worker 1 uses device cpu
4
+ [2024-11-09 15:28:28,047][00359] Rollout worker 2 uses device cpu
5
+ [2024-11-09 15:28:28,050][00359] Rollout worker 3 uses device cpu
6
+ [2024-11-09 15:28:28,050][00359] Rollout worker 4 uses device cpu
7
+ [2024-11-09 15:28:28,052][00359] Rollout worker 5 uses device cpu
8
+ [2024-11-09 15:28:28,053][00359] Rollout worker 6 uses device cpu
9
+ [2024-11-09 15:28:28,055][00359] Rollout worker 7 uses device cpu
10
+ [2024-11-09 15:28:28,174][00359] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2024-11-09 15:28:28,176][00359] InferenceWorker_p0-w0: min num requests: 2
12
+ [2024-11-09 15:28:28,208][00359] Starting all processes...
13
+ [2024-11-09 15:28:28,210][00359] Starting process learner_proc0
14
+ [2024-11-09 15:28:28,255][00359] Starting all processes...
15
+ [2024-11-09 15:28:28,262][00359] Starting process inference_proc0-0
16
+ [2024-11-09 15:28:28,263][00359] Starting process rollout_proc0
17
+ [2024-11-09 15:28:28,263][00359] Starting process rollout_proc1
18
+ [2024-11-09 15:28:28,265][00359] Starting process rollout_proc2
19
+ [2024-11-09 15:28:28,266][00359] Starting process rollout_proc3
20
+ [2024-11-09 15:28:28,266][00359] Starting process rollout_proc4
21
+ [2024-11-09 15:28:28,266][00359] Starting process rollout_proc5
22
+ [2024-11-09 15:28:28,267][00359] Starting process rollout_proc6
23
+ [2024-11-09 15:28:28,267][00359] Starting process rollout_proc7
24
+ [2024-11-09 15:28:31,281][02442] Using GPUs [0] for process 0 (actually maps to GPUs [0])
25
+ [2024-11-09 15:28:31,281][02442] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
26
+ [2024-11-09 15:28:31,299][02442] Num visible devices: 1
27
+ [2024-11-09 15:28:31,342][02442] Starting seed is not provided
28
+ [2024-11-09 15:28:31,343][02442] Using GPUs [0] for process 0 (actually maps to GPUs [0])
29
+ [2024-11-09 15:28:31,343][02442] Initializing actor-critic model on device cuda:0
30
+ [2024-11-09 15:28:31,344][02442] RunningMeanStd input shape: (3, 72, 128)
31
+ [2024-11-09 15:28:31,347][02442] RunningMeanStd input shape: (1,)
32
+ [2024-11-09 15:28:31,368][02442] ConvEncoder: input_channels=3
33
+ [2024-11-09 15:28:31,402][02456] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
34
+ [2024-11-09 15:28:31,650][02455] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
35
+ [2024-11-09 15:28:31,674][02457] Using GPUs [0] for process 0 (actually maps to GPUs [0])
36
+ [2024-11-09 15:28:31,674][02457] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
37
+ [2024-11-09 15:28:31,692][02457] Num visible devices: 1
38
+ [2024-11-09 15:28:31,710][02463] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
39
+ [2024-11-09 15:28:31,737][02442] Conv encoder output size: 512
40
+ [2024-11-09 15:28:31,737][02442] Policy head output size: 512
41
+ [2024-11-09 15:28:31,784][02461] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
42
+ [2024-11-09 15:28:31,802][02442] Created Actor Critic model with architecture:
43
+ [2024-11-09 15:28:31,802][02442] ActorCriticSharedWeights(
44
+ (obs_normalizer): ObservationNormalizer(
45
+ (running_mean_std): RunningMeanStdDictInPlace(
46
+ (running_mean_std): ModuleDict(
47
+ (obs): RunningMeanStdInPlace()
48
+ )
49
+ )
50
+ )
51
+ (returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
52
+ (encoder): VizdoomEncoder(
53
+ (basic_encoder): ConvEncoder(
54
+ (enc): RecursiveScriptModule(
55
+ original_name=ConvEncoderImpl
56
+ (conv_head): RecursiveScriptModule(
57
+ original_name=Sequential
58
+ (0): RecursiveScriptModule(original_name=Conv2d)
59
+ (1): RecursiveScriptModule(original_name=ELU)
60
+ (2): RecursiveScriptModule(original_name=Conv2d)
61
+ (3): RecursiveScriptModule(original_name=ELU)
62
+ (4): RecursiveScriptModule(original_name=Conv2d)
63
+ (5): RecursiveScriptModule(original_name=ELU)
64
+ )
65
+ (mlp_layers): RecursiveScriptModule(
66
+ original_name=Sequential
67
+ (0): RecursiveScriptModule(original_name=Linear)
68
+ (1): RecursiveScriptModule(original_name=ELU)
69
+ )
70
+ )
71
+ )
72
+ )
73
+ (core): ModelCoreRNN(
74
+ (core): GRU(512, 512)
75
+ )
76
+ (decoder): MlpDecoder(
77
+ (mlp): Identity()
78
+ )
79
+ (critic_linear): Linear(in_features=512, out_features=1, bias=True)
80
+ (action_parameterization): ActionParameterizationDefault(
81
+ (distribution_linear): Linear(in_features=512, out_features=5, bias=True)
82
+ )
83
+ )
84
+ [2024-11-09 15:28:31,807][02458] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
85
+ [2024-11-09 15:28:31,830][02460] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
86
+ [2024-11-09 15:28:31,851][02459] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
87
+ [2024-11-09 15:28:31,853][02462] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
88
+ [2024-11-09 15:28:32,118][02442] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2024-11-09 15:28:35,743][02442] No checkpoints found
90
+ [2024-11-09 15:28:35,744][02442] Did not load from checkpoint, starting from scratch!
91
+ [2024-11-09 15:28:35,744][02442] Initialized policy 0 weights for model version 0
92
+ [2024-11-09 15:28:35,746][02442] LearnerWorker_p0 finished initialization!
93
+ [2024-11-09 15:28:35,747][02442] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2024-11-09 15:28:35,823][02457] RunningMeanStd input shape: (3, 72, 128)
95
+ [2024-11-09 15:28:35,824][02457] RunningMeanStd input shape: (1,)
96
+ [2024-11-09 15:28:35,837][02457] ConvEncoder: input_channels=3
97
+ [2024-11-09 15:28:35,948][02457] Conv encoder output size: 512
98
+ [2024-11-09 15:28:35,949][02457] Policy head output size: 512
99
+ [2024-11-09 15:28:36,004][00359] Inference worker 0-0 is ready!
100
+ [2024-11-09 15:28:36,006][00359] All inference workers are ready! Signal rollout workers to start!
101
+ [2024-11-09 15:28:36,039][02458] Doom resolution: 160x120, resize resolution: (128, 72)
102
+ [2024-11-09 15:28:36,039][02463] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2024-11-09 15:28:36,040][02461] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2024-11-09 15:28:36,040][02459] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2024-11-09 15:28:36,060][02460] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2024-11-09 15:28:36,060][02456] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2024-11-09 15:28:36,060][02462] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2024-11-09 15:28:36,060][02455] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2024-11-09 15:28:36,356][02461] Decorrelating experience for 0 frames...
110
+ [2024-11-09 15:28:36,356][02458] Decorrelating experience for 0 frames...
111
+ [2024-11-09 15:28:36,358][02463] Decorrelating experience for 0 frames...
112
+ [2024-11-09 15:28:36,363][02455] Decorrelating experience for 0 frames...
113
+ [2024-11-09 15:28:36,364][02456] Decorrelating experience for 0 frames...
114
+ [2024-11-09 15:28:36,461][02460] Decorrelating experience for 0 frames...
115
+ [2024-11-09 15:28:36,618][02463] Decorrelating experience for 32 frames...
116
+ [2024-11-09 15:28:36,626][02456] Decorrelating experience for 32 frames...
117
+ [2024-11-09 15:28:36,630][02461] Decorrelating experience for 32 frames...
118
+ [2024-11-09 15:28:36,631][02462] Decorrelating experience for 0 frames...
119
+ [2024-11-09 15:28:36,664][02458] Decorrelating experience for 32 frames...
120
+ [2024-11-09 15:28:36,707][02460] Decorrelating experience for 32 frames...
121
+ [2024-11-09 15:28:36,913][02462] Decorrelating experience for 32 frames...
122
+ [2024-11-09 15:28:36,914][02455] Decorrelating experience for 32 frames...
123
+ [2024-11-09 15:28:36,947][02463] Decorrelating experience for 64 frames...
124
+ [2024-11-09 15:28:36,999][02461] Decorrelating experience for 64 frames...
125
+ [2024-11-09 15:28:37,019][02456] Decorrelating experience for 64 frames...
126
+ [2024-11-09 15:28:37,051][02460] Decorrelating experience for 64 frames...
127
+ [2024-11-09 15:28:37,225][00359] 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)
128
+ [2024-11-09 15:28:37,261][02458] Decorrelating experience for 64 frames...
129
+ [2024-11-09 15:28:37,281][02455] Decorrelating experience for 64 frames...
130
+ [2024-11-09 15:28:37,294][02461] Decorrelating experience for 96 frames...
131
+ [2024-11-09 15:28:37,297][02462] Decorrelating experience for 64 frames...
132
+ [2024-11-09 15:28:37,353][02460] Decorrelating experience for 96 frames...
133
+ [2024-11-09 15:28:37,573][02463] Decorrelating experience for 96 frames...
134
+ [2024-11-09 15:28:37,578][02456] Decorrelating experience for 96 frames...
135
+ [2024-11-09 15:28:37,591][02455] Decorrelating experience for 96 frames...
136
+ [2024-11-09 15:28:37,606][02462] Decorrelating experience for 96 frames...
137
+ [2024-11-09 15:28:37,611][02458] Decorrelating experience for 96 frames...
138
+ [2024-11-09 15:28:40,023][02442] Signal inference workers to stop experience collection...
139
+ [2024-11-09 15:28:40,029][02457] InferenceWorker_p0-w0: stopping experience collection
140
+ [2024-11-09 15:28:42,225][00359] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 599.2. Samples: 2996. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
141
+ [2024-11-09 15:28:42,227][00359] Avg episode reward: [(0, '2.709')]
142
+ [2024-11-09 15:28:42,698][02442] Signal inference workers to resume experience collection...
143
+ [2024-11-09 15:28:42,699][02457] InferenceWorker_p0-w0: resuming experience collection
144
+ [2024-11-09 15:28:44,751][02457] Updated weights for policy 0, policy_version 10 (0.0151)
145
+ [2024-11-09 15:28:47,215][02457] Updated weights for policy 0, policy_version 20 (0.0013)
146
+ [2024-11-09 15:28:47,225][00359] Fps is (10 sec: 8192.0, 60 sec: 8192.0, 300 sec: 8192.0). Total num frames: 81920. Throughput: 0: 1175.6. Samples: 11756. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
147
+ [2024-11-09 15:28:47,227][00359] Avg episode reward: [(0, '4.433')]
148
+ [2024-11-09 15:28:48,166][00359] Heartbeat connected on Batcher_0
149
+ [2024-11-09 15:28:48,170][00359] Heartbeat connected on LearnerWorker_p0
150
+ [2024-11-09 15:28:48,178][00359] Heartbeat connected on InferenceWorker_p0-w0
151
+ [2024-11-09 15:28:48,183][00359] Heartbeat connected on RolloutWorker_w0
152
+ [2024-11-09 15:28:48,187][00359] Heartbeat connected on RolloutWorker_w1
153
+ [2024-11-09 15:28:48,193][00359] Heartbeat connected on RolloutWorker_w2
154
+ [2024-11-09 15:28:48,203][00359] Heartbeat connected on RolloutWorker_w5
155
+ [2024-11-09 15:28:48,205][00359] Heartbeat connected on RolloutWorker_w4
156
+ [2024-11-09 15:28:48,207][00359] Heartbeat connected on RolloutWorker_w6
157
+ [2024-11-09 15:28:48,209][00359] Heartbeat connected on RolloutWorker_w7
158
+ [2024-11-09 15:28:49,571][02457] Updated weights for policy 0, policy_version 30 (0.0013)
159
+ [2024-11-09 15:28:52,001][02457] Updated weights for policy 0, policy_version 40 (0.0012)
160
+ [2024-11-09 15:28:52,225][00359] Fps is (10 sec: 16793.6, 60 sec: 11195.8, 300 sec: 11195.8). Total num frames: 167936. Throughput: 0: 2484.0. Samples: 37260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
161
+ [2024-11-09 15:28:52,227][00359] Avg episode reward: [(0, '4.300')]
162
+ [2024-11-09 15:28:52,235][02442] Saving new best policy, reward=4.300!
163
+ [2024-11-09 15:28:54,265][02457] Updated weights for policy 0, policy_version 50 (0.0012)
164
+ [2024-11-09 15:28:56,596][02457] Updated weights for policy 0, policy_version 60 (0.0012)
165
+ [2024-11-09 15:28:57,225][00359] Fps is (10 sec: 17203.4, 60 sec: 12697.6, 300 sec: 12697.6). Total num frames: 253952. Throughput: 0: 3203.0. Samples: 64060. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
166
+ [2024-11-09 15:28:57,228][00359] Avg episode reward: [(0, '4.372')]
167
+ [2024-11-09 15:28:57,231][02442] Saving new best policy, reward=4.372!
168
+ [2024-11-09 15:28:58,865][02457] Updated weights for policy 0, policy_version 70 (0.0013)
169
+ [2024-11-09 15:29:01,318][02457] Updated weights for policy 0, policy_version 80 (0.0013)
170
+ [2024-11-09 15:29:02,225][00359] Fps is (10 sec: 17203.1, 60 sec: 13598.7, 300 sec: 13598.7). Total num frames: 339968. Throughput: 0: 3086.9. Samples: 77172. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
171
+ [2024-11-09 15:29:02,227][00359] Avg episode reward: [(0, '4.550')]
172
+ [2024-11-09 15:29:02,236][02442] Saving new best policy, reward=4.550!
173
+ [2024-11-09 15:29:03,702][02457] Updated weights for policy 0, policy_version 90 (0.0012)
174
+ [2024-11-09 15:29:05,986][02457] Updated weights for policy 0, policy_version 100 (0.0012)
175
+ [2024-11-09 15:29:07,225][00359] Fps is (10 sec: 17612.8, 60 sec: 14336.0, 300 sec: 14336.0). Total num frames: 430080. Throughput: 0: 3432.6. Samples: 102978. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
176
+ [2024-11-09 15:29:07,227][00359] Avg episode reward: [(0, '4.466')]
177
+ [2024-11-09 15:29:08,328][02457] Updated weights for policy 0, policy_version 110 (0.0012)
178
+ [2024-11-09 15:29:10,611][02457] Updated weights for policy 0, policy_version 120 (0.0013)
179
+ [2024-11-09 15:29:12,225][00359] Fps is (10 sec: 18022.3, 60 sec: 14862.6, 300 sec: 14862.6). Total num frames: 520192. Throughput: 0: 3704.4. Samples: 129654. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
180
+ [2024-11-09 15:29:12,228][00359] Avg episode reward: [(0, '4.672')]
181
+ [2024-11-09 15:29:12,235][02442] Saving new best policy, reward=4.672!
182
+ [2024-11-09 15:29:12,946][02457] Updated weights for policy 0, policy_version 130 (0.0012)
183
+ [2024-11-09 15:29:15,304][02457] Updated weights for policy 0, policy_version 140 (0.0013)
184
+ [2024-11-09 15:29:17,225][00359] Fps is (10 sec: 17612.8, 60 sec: 15155.2, 300 sec: 15155.2). Total num frames: 606208. Throughput: 0: 3564.6. Samples: 142584. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
185
+ [2024-11-09 15:29:17,228][00359] Avg episode reward: [(0, '4.327')]
186
+ [2024-11-09 15:29:17,654][02457] Updated weights for policy 0, policy_version 150 (0.0012)
187
+ [2024-11-09 15:29:19,934][02457] Updated weights for policy 0, policy_version 160 (0.0013)
188
+ [2024-11-09 15:29:22,225][00359] Fps is (10 sec: 17203.3, 60 sec: 15382.8, 300 sec: 15382.8). Total num frames: 692224. Throughput: 0: 3760.1. Samples: 169206. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
189
+ [2024-11-09 15:29:22,228][00359] Avg episode reward: [(0, '5.117')]
190
+ [2024-11-09 15:29:22,247][02442] Saving new best policy, reward=5.117!
191
+ [2024-11-09 15:29:22,250][02457] Updated weights for policy 0, policy_version 170 (0.0013)
192
+ [2024-11-09 15:29:24,568][02457] Updated weights for policy 0, policy_version 180 (0.0013)
193
+ [2024-11-09 15:29:26,862][02457] Updated weights for policy 0, policy_version 190 (0.0013)
194
+ [2024-11-09 15:29:27,225][00359] Fps is (10 sec: 17612.8, 60 sec: 15646.7, 300 sec: 15646.7). Total num frames: 782336. Throughput: 0: 4282.2. Samples: 195696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
195
+ [2024-11-09 15:29:27,228][00359] Avg episode reward: [(0, '5.222')]
196
+ [2024-11-09 15:29:27,230][02442] Saving new best policy, reward=5.222!
197
+ [2024-11-09 15:29:29,338][02457] Updated weights for policy 0, policy_version 200 (0.0013)
198
+ [2024-11-09 15:29:31,622][02457] Updated weights for policy 0, policy_version 210 (0.0012)
199
+ [2024-11-09 15:29:32,225][00359] Fps is (10 sec: 17612.7, 60 sec: 15788.2, 300 sec: 15788.2). Total num frames: 868352. Throughput: 0: 4368.8. Samples: 208350. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
200
+ [2024-11-09 15:29:32,227][00359] Avg episode reward: [(0, '5.105')]
201
+ [2024-11-09 15:29:33,969][02457] Updated weights for policy 0, policy_version 220 (0.0012)
202
+ [2024-11-09 15:29:36,241][02457] Updated weights for policy 0, policy_version 230 (0.0013)
203
+ [2024-11-09 15:29:37,225][00359] Fps is (10 sec: 17612.8, 60 sec: 15974.4, 300 sec: 15974.4). Total num frames: 958464. Throughput: 0: 4396.3. Samples: 235094. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
204
+ [2024-11-09 15:29:37,228][00359] Avg episode reward: [(0, '5.521')]
205
+ [2024-11-09 15:29:37,230][02442] Saving new best policy, reward=5.521!
206
+ [2024-11-09 15:29:38,577][02457] Updated weights for policy 0, policy_version 240 (0.0013)
207
+ [2024-11-09 15:29:40,902][02457] Updated weights for policy 0, policy_version 250 (0.0012)
208
+ [2024-11-09 15:29:42,225][00359] Fps is (10 sec: 17612.9, 60 sec: 17408.0, 300 sec: 16068.9). Total num frames: 1044480. Throughput: 0: 4382.9. Samples: 261292. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
209
+ [2024-11-09 15:29:42,228][00359] Avg episode reward: [(0, '6.115')]
210
+ [2024-11-09 15:29:42,234][02442] Saving new best policy, reward=6.115!
211
+ [2024-11-09 15:29:43,323][02457] Updated weights for policy 0, policy_version 260 (0.0013)
212
+ [2024-11-09 15:29:45,693][02457] Updated weights for policy 0, policy_version 270 (0.0013)
213
+ [2024-11-09 15:29:47,225][00359] Fps is (10 sec: 17203.1, 60 sec: 17476.3, 300 sec: 16149.9). Total num frames: 1130496. Throughput: 0: 4378.7. Samples: 274212. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
214
+ [2024-11-09 15:29:47,227][00359] Avg episode reward: [(0, '6.678')]
215
+ [2024-11-09 15:29:47,229][02442] Saving new best policy, reward=6.678!
216
+ [2024-11-09 15:29:47,979][02457] Updated weights for policy 0, policy_version 280 (0.0013)
217
+ [2024-11-09 15:29:50,390][02457] Updated weights for policy 0, policy_version 290 (0.0012)
218
+ [2024-11-09 15:29:52,225][00359] Fps is (10 sec: 17203.2, 60 sec: 17476.3, 300 sec: 16220.2). Total num frames: 1216512. Throughput: 0: 4387.0. Samples: 300394. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
219
+ [2024-11-09 15:29:52,227][00359] Avg episode reward: [(0, '8.474')]
220
+ [2024-11-09 15:29:52,253][02442] Saving new best policy, reward=8.474!
221
+ [2024-11-09 15:29:52,760][02457] Updated weights for policy 0, policy_version 300 (0.0013)
222
+ [2024-11-09 15:29:55,088][02457] Updated weights for policy 0, policy_version 310 (0.0012)
223
+ [2024-11-09 15:29:57,225][00359] Fps is (10 sec: 17203.1, 60 sec: 17476.2, 300 sec: 16281.6). Total num frames: 1302528. Throughput: 0: 4366.5. Samples: 326146. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
224
+ [2024-11-09 15:29:57,228][00359] Avg episode reward: [(0, '9.249')]
225
+ [2024-11-09 15:29:57,229][02442] Saving new best policy, reward=9.249!
226
+ [2024-11-09 15:29:57,498][02457] Updated weights for policy 0, policy_version 320 (0.0013)
227
+ [2024-11-09 15:29:59,748][02457] Updated weights for policy 0, policy_version 330 (0.0012)
228
+ [2024-11-09 15:30:02,085][02457] Updated weights for policy 0, policy_version 340 (0.0012)
229
+ [2024-11-09 15:30:02,225][00359] Fps is (10 sec: 17612.9, 60 sec: 17544.5, 300 sec: 16384.0). Total num frames: 1392640. Throughput: 0: 4378.0. Samples: 339594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
230
+ [2024-11-09 15:30:02,228][00359] Avg episode reward: [(0, '11.648')]
231
+ [2024-11-09 15:30:02,234][02442] Saving new best policy, reward=11.648!
232
+ [2024-11-09 15:30:04,372][02457] Updated weights for policy 0, policy_version 350 (0.0012)
233
+ [2024-11-09 15:30:06,671][02457] Updated weights for policy 0, policy_version 360 (0.0012)
234
+ [2024-11-09 15:30:07,225][00359] Fps is (10 sec: 18022.6, 60 sec: 17544.5, 300 sec: 16475.0). Total num frames: 1482752. Throughput: 0: 4380.0. Samples: 366304. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
235
+ [2024-11-09 15:30:07,228][00359] Avg episode reward: [(0, '11.806')]
236
+ [2024-11-09 15:30:07,230][02442] Saving new best policy, reward=11.806!
237
+ [2024-11-09 15:30:09,022][02457] Updated weights for policy 0, policy_version 370 (0.0013)
238
+ [2024-11-09 15:30:11,410][02457] Updated weights for policy 0, policy_version 380 (0.0013)
239
+ [2024-11-09 15:30:12,225][00359] Fps is (10 sec: 17612.7, 60 sec: 17476.3, 300 sec: 16513.3). Total num frames: 1568768. Throughput: 0: 4374.3. Samples: 392538. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
240
+ [2024-11-09 15:30:12,228][00359] Avg episode reward: [(0, '10.272')]
241
+ [2024-11-09 15:30:13,678][02457] Updated weights for policy 0, policy_version 390 (0.0013)
242
+ [2024-11-09 15:30:15,946][02457] Updated weights for policy 0, policy_version 400 (0.0012)
243
+ [2024-11-09 15:30:17,225][00359] Fps is (10 sec: 17612.9, 60 sec: 17544.5, 300 sec: 16588.8). Total num frames: 1658880. Throughput: 0: 4391.5. Samples: 405966. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
244
+ [2024-11-09 15:30:17,227][00359] Avg episode reward: [(0, '12.584')]
245
+ [2024-11-09 15:30:17,230][02442] Saving new best policy, reward=12.584!
246
+ [2024-11-09 15:30:18,277][02457] Updated weights for policy 0, policy_version 410 (0.0012)
247
+ [2024-11-09 15:30:20,512][02457] Updated weights for policy 0, policy_version 420 (0.0012)
248
+ [2024-11-09 15:30:22,225][00359] Fps is (10 sec: 18022.4, 60 sec: 17612.8, 300 sec: 16657.1). Total num frames: 1748992. Throughput: 0: 4394.2. Samples: 432834. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
249
+ [2024-11-09 15:30:22,228][00359] Avg episode reward: [(0, '17.082')]
250
+ [2024-11-09 15:30:22,234][02442] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000427_1748992.pth...
251
+ [2024-11-09 15:30:22,310][02442] Saving new best policy, reward=17.082!
252
+ [2024-11-09 15:30:22,939][02457] Updated weights for policy 0, policy_version 430 (0.0013)
253
+ [2024-11-09 15:30:25,262][02457] Updated weights for policy 0, policy_version 440 (0.0013)
254
+ [2024-11-09 15:30:27,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17544.6, 300 sec: 16681.9). Total num frames: 1835008. Throughput: 0: 4392.2. Samples: 458942. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
255
+ [2024-11-09 15:30:27,228][00359] Avg episode reward: [(0, '18.357')]
256
+ [2024-11-09 15:30:27,230][02442] Saving new best policy, reward=18.357!
257
+ [2024-11-09 15:30:27,598][02457] Updated weights for policy 0, policy_version 450 (0.0013)
258
+ [2024-11-09 15:30:29,836][02457] Updated weights for policy 0, policy_version 460 (0.0012)
259
+ [2024-11-09 15:30:32,121][02457] Updated weights for policy 0, policy_version 470 (0.0013)
260
+ [2024-11-09 15:30:32,225][00359] Fps is (10 sec: 17612.9, 60 sec: 17612.8, 300 sec: 16740.2). Total num frames: 1925120. Throughput: 0: 4403.7. Samples: 472376. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
261
+ [2024-11-09 15:30:32,227][00359] Avg episode reward: [(0, '14.650')]
262
+ [2024-11-09 15:30:34,439][02457] Updated weights for policy 0, policy_version 480 (0.0012)
263
+ [2024-11-09 15:30:36,789][02457] Updated weights for policy 0, policy_version 490 (0.0013)
264
+ [2024-11-09 15:30:37,225][00359] Fps is (10 sec: 17612.6, 60 sec: 17544.5, 300 sec: 16759.5). Total num frames: 2011136. Throughput: 0: 4414.0. Samples: 499026. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
265
+ [2024-11-09 15:30:37,227][00359] Avg episode reward: [(0, '17.953')]
266
+ [2024-11-09 15:30:39,181][02457] Updated weights for policy 0, policy_version 500 (0.0012)
267
+ [2024-11-09 15:30:41,430][02457] Updated weights for policy 0, policy_version 510 (0.0012)
268
+ [2024-11-09 15:30:42,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17612.8, 300 sec: 16810.0). Total num frames: 2101248. Throughput: 0: 4428.2. Samples: 525414. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
269
+ [2024-11-09 15:30:42,228][00359] Avg episode reward: [(0, '21.904')]
270
+ [2024-11-09 15:30:42,235][02442] Saving new best policy, reward=21.904!
271
+ [2024-11-09 15:30:43,724][02457] Updated weights for policy 0, policy_version 520 (0.0012)
272
+ [2024-11-09 15:30:45,995][02457] Updated weights for policy 0, policy_version 530 (0.0012)
273
+ [2024-11-09 15:30:47,225][00359] Fps is (10 sec: 18022.5, 60 sec: 17681.1, 300 sec: 16856.6). Total num frames: 2191360. Throughput: 0: 4428.7. Samples: 538886. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
274
+ [2024-11-09 15:30:47,227][00359] Avg episode reward: [(0, '18.915')]
275
+ [2024-11-09 15:30:48,264][02457] Updated weights for policy 0, policy_version 540 (0.0012)
276
+ [2024-11-09 15:30:50,693][02457] Updated weights for policy 0, policy_version 550 (0.0013)
277
+ [2024-11-09 15:30:52,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17681.1, 300 sec: 16869.5). Total num frames: 2277376. Throughput: 0: 4420.8. Samples: 565238. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
278
+ [2024-11-09 15:30:52,228][00359] Avg episode reward: [(0, '18.689')]
279
+ [2024-11-09 15:30:52,997][02457] Updated weights for policy 0, policy_version 560 (0.0013)
280
+ [2024-11-09 15:30:55,372][02457] Updated weights for policy 0, policy_version 570 (0.0012)
281
+ [2024-11-09 15:30:57,225][00359] Fps is (10 sec: 17612.7, 60 sec: 17749.4, 300 sec: 16910.6). Total num frames: 2367488. Throughput: 0: 4426.5. Samples: 591730. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
282
+ [2024-11-09 15:30:57,227][00359] Avg episode reward: [(0, '20.785')]
283
+ [2024-11-09 15:30:57,622][02457] Updated weights for policy 0, policy_version 580 (0.0013)
284
+ [2024-11-09 15:30:59,910][02457] Updated weights for policy 0, policy_version 590 (0.0013)
285
+ [2024-11-09 15:31:02,205][02457] Updated weights for policy 0, policy_version 600 (0.0012)
286
+ [2024-11-09 15:31:02,225][00359] Fps is (10 sec: 18022.2, 60 sec: 17749.3, 300 sec: 16949.0). Total num frames: 2457600. Throughput: 0: 4428.7. Samples: 605260. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
287
+ [2024-11-09 15:31:02,227][00359] Avg episode reward: [(0, '25.186')]
288
+ [2024-11-09 15:31:02,234][02442] Saving new best policy, reward=25.186!
289
+ [2024-11-09 15:31:04,548][02457] Updated weights for policy 0, policy_version 610 (0.0013)
290
+ [2024-11-09 15:31:06,922][02457] Updated weights for policy 0, policy_version 620 (0.0013)
291
+ [2024-11-09 15:31:07,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17681.1, 300 sec: 16957.4). Total num frames: 2543616. Throughput: 0: 4412.3. Samples: 631386. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
292
+ [2024-11-09 15:31:07,228][00359] Avg episode reward: [(0, '25.674')]
293
+ [2024-11-09 15:31:07,230][02442] Saving new best policy, reward=25.674!
294
+ [2024-11-09 15:31:09,183][02457] Updated weights for policy 0, policy_version 630 (0.0012)
295
+ [2024-11-09 15:31:11,515][02457] Updated weights for policy 0, policy_version 640 (0.0012)
296
+ [2024-11-09 15:31:12,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17749.3, 300 sec: 16991.8). Total num frames: 2633728. Throughput: 0: 4428.0. Samples: 658204. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
297
+ [2024-11-09 15:31:12,227][00359] Avg episode reward: [(0, '24.820')]
298
+ [2024-11-09 15:31:13,792][02457] Updated weights for policy 0, policy_version 650 (0.0012)
299
+ [2024-11-09 15:31:16,121][02457] Updated weights for policy 0, policy_version 660 (0.0012)
300
+ [2024-11-09 15:31:17,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17681.0, 300 sec: 16998.4). Total num frames: 2719744. Throughput: 0: 4427.7. Samples: 671622. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
301
+ [2024-11-09 15:31:17,228][00359] Avg episode reward: [(0, '23.935')]
302
+ [2024-11-09 15:31:18,488][02457] Updated weights for policy 0, policy_version 670 (0.0013)
303
+ [2024-11-09 15:31:20,806][02457] Updated weights for policy 0, policy_version 680 (0.0013)
304
+ [2024-11-09 15:31:22,225][00359] Fps is (10 sec: 17613.0, 60 sec: 17681.1, 300 sec: 17029.4). Total num frames: 2809856. Throughput: 0: 4417.7. Samples: 697822. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
305
+ [2024-11-09 15:31:22,227][00359] Avg episode reward: [(0, '21.884')]
306
+ [2024-11-09 15:31:23,097][02457] Updated weights for policy 0, policy_version 690 (0.0012)
307
+ [2024-11-09 15:31:25,384][02457] Updated weights for policy 0, policy_version 700 (0.0013)
308
+ [2024-11-09 15:31:27,225][00359] Fps is (10 sec: 18022.4, 60 sec: 17749.3, 300 sec: 17058.6). Total num frames: 2899968. Throughput: 0: 4430.7. Samples: 724794. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
309
+ [2024-11-09 15:31:27,227][00359] Avg episode reward: [(0, '23.741')]
310
+ [2024-11-09 15:31:27,637][02457] Updated weights for policy 0, policy_version 710 (0.0012)
311
+ [2024-11-09 15:31:29,915][02457] Updated weights for policy 0, policy_version 720 (0.0012)
312
+ [2024-11-09 15:31:32,225][00359] Fps is (10 sec: 17612.6, 60 sec: 17681.0, 300 sec: 17062.8). Total num frames: 2985984. Throughput: 0: 4431.7. Samples: 738314. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
313
+ [2024-11-09 15:31:32,228][00359] Avg episode reward: [(0, '25.367')]
314
+ [2024-11-09 15:31:32,292][02457] Updated weights for policy 0, policy_version 730 (0.0013)
315
+ [2024-11-09 15:31:34,608][02457] Updated weights for policy 0, policy_version 740 (0.0012)
316
+ [2024-11-09 15:31:36,895][02457] Updated weights for policy 0, policy_version 750 (0.0012)
317
+ [2024-11-09 15:31:37,225][00359] Fps is (10 sec: 17613.0, 60 sec: 17749.4, 300 sec: 17089.4). Total num frames: 3076096. Throughput: 0: 4431.6. Samples: 764658. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
318
+ [2024-11-09 15:31:37,227][00359] Avg episode reward: [(0, '26.540')]
319
+ [2024-11-09 15:31:37,230][02442] Saving new best policy, reward=26.540!
320
+ [2024-11-09 15:31:39,154][02457] Updated weights for policy 0, policy_version 760 (0.0013)
321
+ [2024-11-09 15:31:41,416][02457] Updated weights for policy 0, policy_version 770 (0.0012)
322
+ [2024-11-09 15:31:42,225][00359] Fps is (10 sec: 18022.3, 60 sec: 17749.3, 300 sec: 17114.6). Total num frames: 3166208. Throughput: 0: 4443.0. Samples: 791664. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
323
+ [2024-11-09 15:31:42,227][00359] Avg episode reward: [(0, '23.020')]
324
+ [2024-11-09 15:31:43,719][02457] Updated weights for policy 0, policy_version 780 (0.0012)
325
+ [2024-11-09 15:31:46,102][02457] Updated weights for policy 0, policy_version 790 (0.0013)
326
+ [2024-11-09 15:31:47,225][00359] Fps is (10 sec: 17612.6, 60 sec: 17681.0, 300 sec: 17117.0). Total num frames: 3252224. Throughput: 0: 4433.2. Samples: 804754. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
327
+ [2024-11-09 15:31:47,228][00359] Avg episode reward: [(0, '22.193')]
328
+ [2024-11-09 15:31:48,425][02457] Updated weights for policy 0, policy_version 800 (0.0012)
329
+ [2024-11-09 15:31:50,665][02457] Updated weights for policy 0, policy_version 810 (0.0012)
330
+ [2024-11-09 15:31:52,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17749.3, 300 sec: 17140.2). Total num frames: 3342336. Throughput: 0: 4447.1. Samples: 831504. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
331
+ [2024-11-09 15:31:52,227][00359] Avg episode reward: [(0, '24.621')]
332
+ [2024-11-09 15:31:53,000][02457] Updated weights for policy 0, policy_version 820 (0.0012)
333
+ [2024-11-09 15:31:55,220][02457] Updated weights for policy 0, policy_version 830 (0.0013)
334
+ [2024-11-09 15:31:57,225][00359] Fps is (10 sec: 18022.5, 60 sec: 17749.3, 300 sec: 17162.2). Total num frames: 3432448. Throughput: 0: 4446.2. Samples: 858284. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
335
+ [2024-11-09 15:31:57,227][00359] Avg episode reward: [(0, '23.619')]
336
+ [2024-11-09 15:31:57,553][02457] Updated weights for policy 0, policy_version 840 (0.0012)
337
+ [2024-11-09 15:31:59,968][02457] Updated weights for policy 0, policy_version 850 (0.0013)
338
+ [2024-11-09 15:32:02,225][00359] Fps is (10 sec: 17612.8, 60 sec: 17681.1, 300 sec: 17163.2). Total num frames: 3518464. Throughput: 0: 4434.2. Samples: 871162. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
339
+ [2024-11-09 15:32:02,227][00359] Avg episode reward: [(0, '23.879')]
340
+ [2024-11-09 15:32:02,229][02457] Updated weights for policy 0, policy_version 860 (0.0013)
341
+ [2024-11-09 15:32:04,527][02457] Updated weights for policy 0, policy_version 870 (0.0013)
342
+ [2024-11-09 15:32:06,758][02457] Updated weights for policy 0, policy_version 880 (0.0012)
343
+ [2024-11-09 15:32:07,225][00359] Fps is (10 sec: 18022.4, 60 sec: 17817.6, 300 sec: 17203.2). Total num frames: 3612672. Throughput: 0: 4454.9. Samples: 898294. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
344
+ [2024-11-09 15:32:07,228][00359] Avg episode reward: [(0, '26.899')]
345
+ [2024-11-09 15:32:07,231][02442] Saving new best policy, reward=26.899!
346
+ [2024-11-09 15:32:09,054][02457] Updated weights for policy 0, policy_version 890 (0.0012)
347
+ [2024-11-09 15:32:11,349][02457] Updated weights for policy 0, policy_version 900 (0.0013)
348
+ [2024-11-09 15:32:12,225][00359] Fps is (10 sec: 18022.6, 60 sec: 17749.4, 300 sec: 17203.2). Total num frames: 3698688. Throughput: 0: 4448.1. Samples: 924958. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
349
+ [2024-11-09 15:32:12,228][00359] Avg episode reward: [(0, '28.112')]
350
+ [2024-11-09 15:32:12,236][02442] Saving new best policy, reward=28.112!
351
+ [2024-11-09 15:32:13,752][02457] Updated weights for policy 0, policy_version 910 (0.0013)
352
+ [2024-11-09 15:32:16,073][02457] Updated weights for policy 0, policy_version 920 (0.0012)
353
+ [2024-11-09 15:32:17,225][00359] Fps is (10 sec: 17613.0, 60 sec: 17817.6, 300 sec: 17221.8). Total num frames: 3788800. Throughput: 0: 4435.6. Samples: 937916. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
354
+ [2024-11-09 15:32:17,228][00359] Avg episode reward: [(0, '23.384')]
355
+ [2024-11-09 15:32:18,335][02457] Updated weights for policy 0, policy_version 930 (0.0012)
356
+ [2024-11-09 15:32:20,615][02457] Updated weights for policy 0, policy_version 940 (0.0013)
357
+ [2024-11-09 15:32:22,225][00359] Fps is (10 sec: 18022.3, 60 sec: 17817.6, 300 sec: 17239.6). Total num frames: 3878912. Throughput: 0: 4450.7. Samples: 964942. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
358
+ [2024-11-09 15:32:22,227][00359] Avg episode reward: [(0, '20.857')]
359
+ [2024-11-09 15:32:22,235][02442] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000947_3878912.pth...
360
+ [2024-11-09 15:32:22,887][02457] Updated weights for policy 0, policy_version 950 (0.0012)
361
+ [2024-11-09 15:32:25,198][02457] Updated weights for policy 0, policy_version 960 (0.0012)
362
+ [2024-11-09 15:32:27,225][00359] Fps is (10 sec: 17612.6, 60 sec: 17749.3, 300 sec: 17238.8). Total num frames: 3964928. Throughput: 0: 4440.2. Samples: 991472. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
363
+ [2024-11-09 15:32:27,228][00359] Avg episode reward: [(0, '24.351')]
364
+ [2024-11-09 15:32:27,563][02457] Updated weights for policy 0, policy_version 970 (0.0013)
365
+ [2024-11-09 15:32:29,404][02442] Stopping Batcher_0...
366
+ [2024-11-09 15:32:29,404][02442] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
367
+ [2024-11-09 15:32:29,404][00359] Component Batcher_0 stopped!
368
+ [2024-11-09 15:32:29,408][00359] Component RolloutWorker_w3 process died already! Don't wait for it.
369
+ [2024-11-09 15:32:29,404][02442] Loop batcher_evt_loop terminating...
370
+ [2024-11-09 15:32:29,423][02457] Weights refcount: 2 0
371
+ [2024-11-09 15:32:29,425][02457] Stopping InferenceWorker_p0-w0...
372
+ [2024-11-09 15:32:29,426][02457] Loop inference_proc0-0_evt_loop terminating...
373
+ [2024-11-09 15:32:29,426][00359] Component InferenceWorker_p0-w0 stopped!
374
+ [2024-11-09 15:32:29,454][02462] Stopping RolloutWorker_w5...
375
+ [2024-11-09 15:32:29,454][02455] Stopping RolloutWorker_w0...
376
+ [2024-11-09 15:32:29,455][02462] Loop rollout_proc5_evt_loop terminating...
377
+ [2024-11-09 15:32:29,455][02455] Loop rollout_proc0_evt_loop terminating...
378
+ [2024-11-09 15:32:29,454][00359] Component RolloutWorker_w5 stopped!
379
+ [2024-11-09 15:32:29,457][02460] Stopping RolloutWorker_w6...
380
+ [2024-11-09 15:32:29,458][02460] Loop rollout_proc6_evt_loop terminating...
381
+ [2024-11-09 15:32:29,458][02461] Stopping RolloutWorker_w4...
382
+ [2024-11-09 15:32:29,459][02456] Stopping RolloutWorker_w1...
383
+ [2024-11-09 15:32:29,457][00359] Component RolloutWorker_w0 stopped!
384
+ [2024-11-09 15:32:29,459][02456] Loop rollout_proc1_evt_loop terminating...
385
+ [2024-11-09 15:32:29,459][02461] Loop rollout_proc4_evt_loop terminating...
386
+ [2024-11-09 15:32:29,460][02458] Stopping RolloutWorker_w2...
387
+ [2024-11-09 15:32:29,459][00359] Component RolloutWorker_w6 stopped!
388
+ [2024-11-09 15:32:29,461][02458] Loop rollout_proc2_evt_loop terminating...
389
+ [2024-11-09 15:32:29,461][02463] Stopping RolloutWorker_w7...
390
+ [2024-11-09 15:32:29,461][02463] Loop rollout_proc7_evt_loop terminating...
391
+ [2024-11-09 15:32:29,461][00359] Component RolloutWorker_w4 stopped!
392
+ [2024-11-09 15:32:29,464][00359] Component RolloutWorker_w1 stopped!
393
+ [2024-11-09 15:32:29,465][00359] Component RolloutWorker_w2 stopped!
394
+ [2024-11-09 15:32:29,469][00359] Component RolloutWorker_w7 stopped!
395
+ [2024-11-09 15:32:29,483][02442] Removing /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000427_1748992.pth
396
+ [2024-11-09 15:32:29,494][02442] Saving /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
397
+ [2024-11-09 15:32:29,616][02442] Stopping LearnerWorker_p0...
398
+ [2024-11-09 15:32:29,616][02442] Loop learner_proc0_evt_loop terminating...
399
+ [2024-11-09 15:32:29,616][00359] Component LearnerWorker_p0 stopped!
400
+ [2024-11-09 15:32:29,620][00359] Waiting for process learner_proc0 to stop...
401
+ [2024-11-09 15:32:30,529][00359] Waiting for process inference_proc0-0 to join...
402
+ [2024-11-09 15:32:30,532][00359] Waiting for process rollout_proc0 to join...
403
+ [2024-11-09 15:32:30,535][00359] Waiting for process rollout_proc1 to join...
404
+ [2024-11-09 15:32:30,536][00359] Waiting for process rollout_proc2 to join...
405
+ [2024-11-09 15:32:30,539][00359] Waiting for process rollout_proc3 to join...
406
+ [2024-11-09 15:32:30,539][00359] Waiting for process rollout_proc4 to join...
407
+ [2024-11-09 15:32:30,541][00359] Waiting for process rollout_proc5 to join...
408
+ [2024-11-09 15:32:30,543][00359] Waiting for process rollout_proc6 to join...
409
+ [2024-11-09 15:32:30,545][00359] Waiting for process rollout_proc7 to join...
410
+ [2024-11-09 15:32:30,547][00359] Batcher 0 profile tree view:
411
+ batching: 16.5471, releasing_batches: 0.0256
412
+ [2024-11-09 15:32:30,548][00359] InferenceWorker_p0-w0 profile tree view:
413
+ wait_policy: 0.0001
414
+ wait_policy_total: 3.8880
415
+ update_model: 3.8373
416
+ weight_update: 0.0013
417
+ one_step: 0.0033
418
+ handle_policy_step: 212.5154
419
+ deserialize: 8.0454, stack: 1.4952, obs_to_device_normalize: 51.5267, forward: 102.7698, send_messages: 13.8758
420
+ prepare_outputs: 25.2332
421
+ to_cpu: 15.3834
422
+ [2024-11-09 15:32:30,551][00359] Learner 0 profile tree view:
423
+ misc: 0.0054, prepare_batch: 7.0491
424
+ train: 19.0067
425
+ epoch_init: 0.0057, minibatch_init: 0.0058, losses_postprocess: 0.3408, kl_divergence: 0.3495, after_optimizer: 1.8542
426
+ calculate_losses: 8.6386
427
+ losses_init: 0.0034, forward_head: 0.6446, bptt_initial: 4.7573, tail: 0.6363, advantages_returns: 0.1560, losses: 1.1651
428
+ bptt: 1.0986
429
+ bptt_forward_core: 1.0472
430
+ update: 7.4516
431
+ clip: 0.8148
432
+ [2024-11-09 15:32:30,554][00359] RolloutWorker_w0 profile tree view:
433
+ wait_for_trajectories: 0.1659, enqueue_policy_requests: 8.9870, env_step: 143.2896, overhead: 7.1047, complete_rollouts: 0.2728
434
+ save_policy_outputs: 10.0892
435
+ split_output_tensors: 4.0277
436
+ [2024-11-09 15:32:30,555][00359] RolloutWorker_w7 profile tree view:
437
+ wait_for_trajectories: 0.1650, enqueue_policy_requests: 8.9906, env_step: 142.8375, overhead: 6.9846, complete_rollouts: 0.2706
438
+ save_policy_outputs: 10.1767
439
+ split_output_tensors: 4.0813
440
+ [2024-11-09 15:32:30,557][00359] Loop Runner_EvtLoop terminating...
441
+ [2024-11-09 15:32:30,558][00359] Runner profile tree view:
442
+ main_loop: 242.3498
443
+ [2024-11-09 15:32:30,560][00359] Collected {0: 4005888}, FPS: 16529.4
444
+ [2024-11-09 15:32:30,606][00359] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
445
+ [2024-11-09 15:32:30,607][00359] Overriding arg 'num_workers' with value 1 passed from command line
446
+ [2024-11-09 15:32:30,609][00359] Adding new argument 'no_render'=True that is not in the saved config file!
447
+ [2024-11-09 15:32:30,610][00359] Adding new argument 'save_video'=True that is not in the saved config file!
448
+ [2024-11-09 15:32:30,611][00359] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
449
+ [2024-11-09 15:32:30,613][00359] Adding new argument 'video_name'=None that is not in the saved config file!
450
+ [2024-11-09 15:32:30,615][00359] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
451
+ [2024-11-09 15:32:30,615][00359] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
452
+ [2024-11-09 15:32:30,617][00359] Adding new argument 'push_to_hub'=False that is not in the saved config file!
453
+ [2024-11-09 15:32:30,618][00359] Adding new argument 'hf_repository'=None that is not in the saved config file!
454
+ [2024-11-09 15:32:30,619][00359] Adding new argument 'policy_index'=0 that is not in the saved config file!
455
+ [2024-11-09 15:32:30,621][00359] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
456
+ [2024-11-09 15:32:30,622][00359] Adding new argument 'train_script'=None that is not in the saved config file!
457
+ [2024-11-09 15:32:30,623][00359] Adding new argument 'enjoy_script'=None that is not in the saved config file!
458
+ [2024-11-09 15:32:30,624][00359] Using frameskip 1 and render_action_repeat=4 for evaluation
459
+ [2024-11-09 15:32:30,653][00359] Doom resolution: 160x120, resize resolution: (128, 72)
460
+ [2024-11-09 15:32:30,656][00359] RunningMeanStd input shape: (3, 72, 128)
461
+ [2024-11-09 15:32:30,658][00359] RunningMeanStd input shape: (1,)
462
+ [2024-11-09 15:32:30,672][00359] ConvEncoder: input_channels=3
463
+ [2024-11-09 15:32:30,786][00359] Conv encoder output size: 512
464
+ [2024-11-09 15:32:30,788][00359] Policy head output size: 512
465
+ [2024-11-09 15:32:30,945][00359] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
466
+ [2024-11-09 15:32:31,754][00359] Num frames 100...
467
+ [2024-11-09 15:32:31,881][00359] Num frames 200...
468
+ [2024-11-09 15:32:32,001][00359] Num frames 300...
469
+ [2024-11-09 15:32:32,124][00359] Num frames 400...
470
+ [2024-11-09 15:32:32,247][00359] Num frames 500...
471
+ [2024-11-09 15:32:32,368][00359] Num frames 600...
472
+ [2024-11-09 15:32:32,489][00359] Num frames 700...
473
+ [2024-11-09 15:32:32,609][00359] Num frames 800...
474
+ [2024-11-09 15:32:32,743][00359] Avg episode rewards: #0: 17.640, true rewards: #0: 8.640
475
+ [2024-11-09 15:32:32,745][00359] Avg episode reward: 17.640, avg true_objective: 8.640
476
+ [2024-11-09 15:32:32,792][00359] Num frames 900...
477
+ [2024-11-09 15:32:32,913][00359] Num frames 1000...
478
+ [2024-11-09 15:32:33,036][00359] Num frames 1100...
479
+ [2024-11-09 15:32:33,160][00359] Num frames 1200...
480
+ [2024-11-09 15:32:33,282][00359] Num frames 1300...
481
+ [2024-11-09 15:32:33,405][00359] Num frames 1400...
482
+ [2024-11-09 15:32:33,530][00359] Num frames 1500...
483
+ [2024-11-09 15:32:33,652][00359] Num frames 1600...
484
+ [2024-11-09 15:32:33,770][00359] Num frames 1700...
485
+ [2024-11-09 15:32:33,893][00359] Num frames 1800...
486
+ [2024-11-09 15:32:34,021][00359] Num frames 1900...
487
+ [2024-11-09 15:32:34,144][00359] Num frames 2000...
488
+ [2024-11-09 15:32:34,258][00359] Avg episode rewards: #0: 24.740, true rewards: #0: 10.240
489
+ [2024-11-09 15:32:34,259][00359] Avg episode reward: 24.740, avg true_objective: 10.240
490
+ [2024-11-09 15:32:34,324][00359] Num frames 2100...
491
+ [2024-11-09 15:32:34,448][00359] Num frames 2200...
492
+ [2024-11-09 15:32:34,576][00359] Num frames 2300...
493
+ [2024-11-09 15:32:34,698][00359] Num frames 2400...
494
+ [2024-11-09 15:32:34,823][00359] Num frames 2500...
495
+ [2024-11-09 15:32:34,946][00359] Num frames 2600...
496
+ [2024-11-09 15:32:35,070][00359] Num frames 2700...
497
+ [2024-11-09 15:32:35,193][00359] Num frames 2800...
498
+ [2024-11-09 15:32:35,317][00359] Num frames 2900...
499
+ [2024-11-09 15:32:35,439][00359] Num frames 3000...
500
+ [2024-11-09 15:32:35,500][00359] Avg episode rewards: #0: 23.680, true rewards: #0: 10.013
501
+ [2024-11-09 15:32:35,502][00359] Avg episode reward: 23.680, avg true_objective: 10.013
502
+ [2024-11-09 15:32:35,621][00359] Num frames 3100...
503
+ [2024-11-09 15:32:35,743][00359] Num frames 3200...
504
+ [2024-11-09 15:32:35,864][00359] Num frames 3300...
505
+ [2024-11-09 15:32:35,987][00359] Num frames 3400...
506
+ [2024-11-09 15:32:36,066][00359] Avg episode rewards: #0: 19.300, true rewards: #0: 8.550
507
+ [2024-11-09 15:32:36,068][00359] Avg episode reward: 19.300, avg true_objective: 8.550
508
+ [2024-11-09 15:32:36,167][00359] Num frames 3500...
509
+ [2024-11-09 15:32:36,289][00359] Num frames 3600...
510
+ [2024-11-09 15:32:36,414][00359] Num frames 3700...
511
+ [2024-11-09 15:32:36,539][00359] Num frames 3800...
512
+ [2024-11-09 15:32:36,662][00359] Num frames 3900...
513
+ [2024-11-09 15:32:36,782][00359] Num frames 4000...
514
+ [2024-11-09 15:32:36,905][00359] Num frames 4100...
515
+ [2024-11-09 15:32:37,026][00359] Num frames 4200...
516
+ [2024-11-09 15:32:37,149][00359] Num frames 4300...
517
+ [2024-11-09 15:32:37,275][00359] Num frames 4400...
518
+ [2024-11-09 15:32:37,423][00359] Avg episode rewards: #0: 20.552, true rewards: #0: 8.952
519
+ [2024-11-09 15:32:37,425][00359] Avg episode reward: 20.552, avg true_objective: 8.952
520
+ [2024-11-09 15:32:37,458][00359] Num frames 4500...
521
+ [2024-11-09 15:32:37,581][00359] Num frames 4600...
522
+ [2024-11-09 15:32:37,704][00359] Num frames 4700...
523
+ [2024-11-09 15:32:37,828][00359] Num frames 4800...
524
+ [2024-11-09 15:32:37,953][00359] Num frames 4900...
525
+ [2024-11-09 15:32:38,085][00359] Num frames 5000...
526
+ [2024-11-09 15:32:38,247][00359] Avg episode rewards: #0: 19.473, true rewards: #0: 8.473
527
+ [2024-11-09 15:32:38,248][00359] Avg episode reward: 19.473, avg true_objective: 8.473
528
+ [2024-11-09 15:32:38,271][00359] Num frames 5100...
529
+ [2024-11-09 15:32:38,393][00359] Num frames 5200...
530
+ [2024-11-09 15:32:38,518][00359] Num frames 5300...
531
+ [2024-11-09 15:32:38,641][00359] Num frames 5400...
532
+ [2024-11-09 15:32:38,765][00359] Num frames 5500...
533
+ [2024-11-09 15:32:38,893][00359] Num frames 5600...
534
+ [2024-11-09 15:32:39,019][00359] Num frames 5700...
535
+ [2024-11-09 15:32:39,185][00359] Avg episode rewards: #0: 18.269, true rewards: #0: 8.269
536
+ [2024-11-09 15:32:39,187][00359] Avg episode reward: 18.269, avg true_objective: 8.269
537
+ [2024-11-09 15:32:39,206][00359] Num frames 5800...
538
+ [2024-11-09 15:32:39,330][00359] Num frames 5900...
539
+ [2024-11-09 15:32:39,458][00359] Num frames 6000...
540
+ [2024-11-09 15:32:39,583][00359] Num frames 6100...
541
+ [2024-11-09 15:32:39,705][00359] Num frames 6200...
542
+ [2024-11-09 15:32:39,823][00359] Num frames 6300...
543
+ [2024-11-09 15:32:39,915][00359] Avg episode rewards: #0: 16.915, true rewards: #0: 7.915
544
+ [2024-11-09 15:32:39,917][00359] Avg episode reward: 16.915, avg true_objective: 7.915
545
+ [2024-11-09 15:32:40,001][00359] Num frames 6400...
546
+ [2024-11-09 15:32:40,122][00359] Num frames 6500...
547
+ [2024-11-09 15:32:40,241][00359] Num frames 6600...
548
+ [2024-11-09 15:32:40,370][00359] Num frames 6700...
549
+ [2024-11-09 15:32:40,505][00359] Num frames 6800...
550
+ [2024-11-09 15:32:40,626][00359] Num frames 6900...
551
+ [2024-11-09 15:32:40,747][00359] Num frames 7000...
552
+ [2024-11-09 15:32:40,868][00359] Num frames 7100...
553
+ [2024-11-09 15:32:40,990][00359] Num frames 7200...
554
+ [2024-11-09 15:32:41,079][00359] Avg episode rewards: #0: 17.253, true rewards: #0: 8.031
555
+ [2024-11-09 15:32:41,081][00359] Avg episode reward: 17.253, avg true_objective: 8.031
556
+ [2024-11-09 15:32:41,170][00359] Num frames 7300...
557
+ [2024-11-09 15:32:41,291][00359] Num frames 7400...
558
+ [2024-11-09 15:32:41,414][00359] Num frames 7500...
559
+ [2024-11-09 15:32:41,541][00359] Num frames 7600...
560
+ [2024-11-09 15:32:41,663][00359] Num frames 7700...
561
+ [2024-11-09 15:32:41,788][00359] Num frames 7800...
562
+ [2024-11-09 15:32:41,911][00359] Num frames 7900...
563
+ [2024-11-09 15:32:42,031][00359] Num frames 8000...
564
+ [2024-11-09 15:32:42,154][00359] Num frames 8100...
565
+ [2024-11-09 15:32:42,276][00359] Num frames 8200...
566
+ [2024-11-09 15:32:42,397][00359] Num frames 8300...
567
+ [2024-11-09 15:32:42,526][00359] Num frames 8400...
568
+ [2024-11-09 15:32:42,650][00359] Num frames 8500...
569
+ [2024-11-09 15:32:42,793][00359] Avg episode rewards: #0: 18.872, true rewards: #0: 8.572
570
+ [2024-11-09 15:32:42,795][00359] Avg episode reward: 18.872, avg true_objective: 8.572
571
+ [2024-11-09 15:33:03,546][00359] Replay video saved to /content/train_dir/default_experiment/replay.mp4!
572
+ [2024-11-09 15:33:33,953][00359] Loading existing experiment configuration from /content/train_dir/default_experiment/config.json
573
+ [2024-11-09 15:33:33,954][00359] Overriding arg 'num_workers' with value 1 passed from command line
574
+ [2024-11-09 15:33:33,956][00359] Adding new argument 'no_render'=True that is not in the saved config file!
575
+ [2024-11-09 15:33:33,957][00359] Adding new argument 'save_video'=True that is not in the saved config file!
576
+ [2024-11-09 15:33:33,958][00359] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
577
+ [2024-11-09 15:33:33,960][00359] Adding new argument 'video_name'=None that is not in the saved config file!
578
+ [2024-11-09 15:33:33,961][00359] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
579
+ [2024-11-09 15:33:33,962][00359] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
580
+ [2024-11-09 15:33:33,963][00359] Adding new argument 'push_to_hub'=True that is not in the saved config file!
581
+ [2024-11-09 15:33:33,965][00359] Adding new argument 'hf_repository'='lahirum/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
582
+ [2024-11-09 15:33:33,966][00359] Adding new argument 'policy_index'=0 that is not in the saved config file!
583
+ [2024-11-09 15:33:33,967][00359] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
584
+ [2024-11-09 15:33:33,968][00359] Adding new argument 'train_script'=None that is not in the saved config file!
585
+ [2024-11-09 15:33:33,970][00359] Adding new argument 'enjoy_script'=None that is not in the saved config file!
586
+ [2024-11-09 15:33:33,971][00359] Using frameskip 1 and render_action_repeat=4 for evaluation
587
+ [2024-11-09 15:33:33,994][00359] RunningMeanStd input shape: (3, 72, 128)
588
+ [2024-11-09 15:33:33,996][00359] RunningMeanStd input shape: (1,)
589
+ [2024-11-09 15:33:34,008][00359] ConvEncoder: input_channels=3
590
+ [2024-11-09 15:33:34,048][00359] Conv encoder output size: 512
591
+ [2024-11-09 15:33:34,050][00359] Policy head output size: 512
592
+ [2024-11-09 15:33:34,069][00359] Loading state from checkpoint /content/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
593
+ [2024-11-09 15:33:34,491][00359] Num frames 100...
594
+ [2024-11-09 15:33:34,617][00359] Num frames 200...
595
+ [2024-11-09 15:33:34,736][00359] Num frames 300...
596
+ [2024-11-09 15:33:34,859][00359] Num frames 400...
597
+ [2024-11-09 15:33:34,981][00359] Num frames 500...
598
+ [2024-11-09 15:33:35,056][00359] Avg episode rewards: #0: 8.160, true rewards: #0: 5.160
599
+ [2024-11-09 15:33:35,058][00359] Avg episode reward: 8.160, avg true_objective: 5.160
600
+ [2024-11-09 15:33:35,159][00359] Num frames 600...
601
+ [2024-11-09 15:33:35,280][00359] Num frames 700...
602
+ [2024-11-09 15:33:35,399][00359] Num frames 800...
603
+ [2024-11-09 15:33:35,520][00359] Num frames 900...
604
+ [2024-11-09 15:33:35,637][00359] Num frames 1000...
605
+ [2024-11-09 15:33:35,803][00359] Avg episode rewards: #0: 9.960, true rewards: #0: 5.460
606
+ [2024-11-09 15:33:35,805][00359] Avg episode reward: 9.960, avg true_objective: 5.460
607
+ [2024-11-09 15:33:35,818][00359] Num frames 1100...
608
+ [2024-11-09 15:33:35,938][00359] Num frames 1200...
609
+ [2024-11-09 15:33:36,058][00359] Num frames 1300...
610
+ [2024-11-09 15:33:36,176][00359] Num frames 1400...
611
+ [2024-11-09 15:33:36,298][00359] Num frames 1500...
612
+ [2024-11-09 15:33:36,423][00359] Num frames 1600...
613
+ [2024-11-09 15:33:36,551][00359] Num frames 1700...
614
+ [2024-11-09 15:33:36,679][00359] Num frames 1800...
615
+ [2024-11-09 15:33:36,806][00359] Num frames 1900...
616
+ [2024-11-09 15:33:36,936][00359] Num frames 2000...
617
+ [2024-11-09 15:33:37,060][00359] Num frames 2100...
618
+ [2024-11-09 15:33:37,181][00359] Num frames 2200...
619
+ [2024-11-09 15:33:37,307][00359] Num frames 2300...
620
+ [2024-11-09 15:33:37,414][00359] Avg episode rewards: #0: 15.467, true rewards: #0: 7.800
621
+ [2024-11-09 15:33:37,415][00359] Avg episode reward: 15.467, avg true_objective: 7.800
622
+ [2024-11-09 15:33:37,494][00359] Num frames 2400...
623
+ [2024-11-09 15:33:37,615][00359] Num frames 2500...
624
+ [2024-11-09 15:33:37,738][00359] Num frames 2600...
625
+ [2024-11-09 15:33:37,867][00359] Num frames 2700...
626
+ [2024-11-09 15:33:37,989][00359] Num frames 2800...
627
+ [2024-11-09 15:33:38,111][00359] Num frames 2900...
628
+ [2024-11-09 15:33:38,231][00359] Num frames 3000...
629
+ [2024-11-09 15:33:38,351][00359] Num frames 3100...
630
+ [2024-11-09 15:33:38,474][00359] Num frames 3200...
631
+ [2024-11-09 15:33:38,575][00359] Avg episode rewards: #0: 16.840, true rewards: #0: 8.090
632
+ [2024-11-09 15:33:38,577][00359] Avg episode reward: 16.840, avg true_objective: 8.090
633
+ [2024-11-09 15:33:38,654][00359] Num frames 3300...
634
+ [2024-11-09 15:33:38,779][00359] Num frames 3400...
635
+ [2024-11-09 15:33:38,901][00359] Num frames 3500...
636
+ [2024-11-09 15:33:39,021][00359] Num frames 3600...
637
+ [2024-11-09 15:33:39,144][00359] Num frames 3700...
638
+ [2024-11-09 15:33:39,264][00359] Num frames 3800...
639
+ [2024-11-09 15:33:39,387][00359] Num frames 3900...
640
+ [2024-11-09 15:33:39,471][00359] Avg episode rewards: #0: 16.044, true rewards: #0: 7.844
641
+ [2024-11-09 15:33:39,473][00359] Avg episode reward: 16.044, avg true_objective: 7.844
642
+ [2024-11-09 15:33:39,569][00359] Num frames 4000...
643
+ [2024-11-09 15:33:39,691][00359] Num frames 4100...
644
+ [2024-11-09 15:33:39,812][00359] Num frames 4200...
645
+ [2024-11-09 15:33:39,935][00359] Num frames 4300...
646
+ [2024-11-09 15:33:40,059][00359] Num frames 4400...
647
+ [2024-11-09 15:33:40,178][00359] Num frames 4500...
648
+ [2024-11-09 15:33:40,301][00359] Num frames 4600...
649
+ [2024-11-09 15:33:40,424][00359] Num frames 4700...
650
+ [2024-11-09 15:33:40,507][00359] Avg episode rewards: #0: 16.703, true rewards: #0: 7.870
651
+ [2024-11-09 15:33:40,509][00359] Avg episode reward: 16.703, avg true_objective: 7.870
652
+ [2024-11-09 15:33:40,608][00359] Num frames 4800...
653
+ [2024-11-09 15:33:40,734][00359] Num frames 4900...
654
+ [2024-11-09 15:33:40,855][00359] Num frames 5000...
655
+ [2024-11-09 15:33:40,978][00359] Num frames 5100...
656
+ [2024-11-09 15:33:41,101][00359] Num frames 5200...
657
+ [2024-11-09 15:33:41,224][00359] Num frames 5300...
658
+ [2024-11-09 15:33:41,350][00359] Num frames 5400...
659
+ [2024-11-09 15:33:41,472][00359] Num frames 5500...
660
+ [2024-11-09 15:33:41,579][00359] Avg episode rewards: #0: 16.203, true rewards: #0: 7.917
661
+ [2024-11-09 15:33:41,581][00359] Avg episode reward: 16.203, avg true_objective: 7.917
662
+ [2024-11-09 15:33:41,652][00359] Num frames 5600...
663
+ [2024-11-09 15:33:41,774][00359] Num frames 5700...
664
+ [2024-11-09 15:33:41,899][00359] Num frames 5800...
665
+ [2024-11-09 15:33:42,021][00359] Num frames 5900...
666
+ [2024-11-09 15:33:42,145][00359] Num frames 6000...
667
+ [2024-11-09 15:33:42,303][00359] Avg episode rewards: #0: 15.608, true rewards: #0: 7.607
668
+ [2024-11-09 15:33:42,305][00359] Avg episode reward: 15.608, avg true_objective: 7.607
669
+ [2024-11-09 15:33:42,325][00359] Num frames 6100...
670
+ [2024-11-09 15:33:42,448][00359] Num frames 6200...
671
+ [2024-11-09 15:33:42,572][00359] Num frames 6300...
672
+ [2024-11-09 15:33:42,694][00359] Num frames 6400...
673
+ [2024-11-09 15:33:42,814][00359] Num frames 6500...
674
+ [2024-11-09 15:33:42,938][00359] Num frames 6600...
675
+ [2024-11-09 15:33:43,058][00359] Num frames 6700...
676
+ [2024-11-09 15:33:43,181][00359] Num frames 6800...
677
+ [2024-11-09 15:33:43,303][00359] Num frames 6900...
678
+ [2024-11-09 15:33:43,426][00359] Num frames 7000...
679
+ [2024-11-09 15:33:43,500][00359] Avg episode rewards: #0: 16.016, true rewards: #0: 7.793
680
+ [2024-11-09 15:33:43,501][00359] Avg episode reward: 16.016, avg true_objective: 7.793
681
+ [2024-11-09 15:33:43,605][00359] Num frames 7100...
682
+ [2024-11-09 15:33:43,726][00359] Num frames 7200...
683
+ [2024-11-09 15:33:43,848][00359] Num frames 7300...
684
+ [2024-11-09 15:33:43,970][00359] Num frames 7400...
685
+ [2024-11-09 15:33:44,092][00359] Num frames 7500...
686
+ [2024-11-09 15:33:44,214][00359] Num frames 7600...
687
+ [2024-11-09 15:33:44,342][00359] Num frames 7700...
688
+ [2024-11-09 15:33:44,469][00359] Num frames 7800...
689
+ [2024-11-09 15:33:44,595][00359] Num frames 7900...
690
+ [2024-11-09 15:33:44,719][00359] Num frames 8000...
691
+ [2024-11-09 15:33:44,844][00359] Num frames 8100...
692
+ [2024-11-09 15:33:44,968][00359] Num frames 8200...
693
+ [2024-11-09 15:33:45,089][00359] Num frames 8300...
694
+ [2024-11-09 15:33:45,215][00359] Num frames 8400...
695
+ [2024-11-09 15:33:45,338][00359] Num frames 8500...
696
+ [2024-11-09 15:33:45,462][00359] Num frames 8600...
697
+ [2024-11-09 15:33:45,584][00359] Num frames 8700...
698
+ [2024-11-09 15:33:45,711][00359] Num frames 8800...
699
+ [2024-11-09 15:33:45,834][00359] Num frames 8900...
700
+ [2024-11-09 15:33:45,959][00359] Num frames 9000...
701
+ [2024-11-09 15:33:46,073][00359] Avg episode rewards: #0: 19.548, true rewards: #0: 9.048
702
+ [2024-11-09 15:33:46,074][00359] Avg episode reward: 19.548, avg true_objective: 9.048
703
+ [2024-11-09 15:34:07,689][00359] Replay video saved to /content/train_dir/default_experiment/replay.mp4!