Hugging Face's logo

GrimReaperSam
/
rl_course_vizdoom_health_gathering_supreme

Reinforcement Learning
sample-factory
TensorBoard
deep-reinforcement-learning
Eval Results
Model card Files Metrics Community
GrimReaperSam commited on
Commit
2ef0e15
·
1 Parent(s): 8ded26a

Upload . with huggingface_hub

Browse files
Files changed (9) hide show
  1. .gitattributes +1 -0
  2. .summary/0/events.out.tfevents.1677097368.VDI-H-LIN-P-003.vdi.pix4d.com +3 -0
  3. README.md +56 -0
  4. checkpoint_p0/best_000000978_4005888_reward_28.129.pth +3 -0
  5. checkpoint_p0/checkpoint_000000605_2478080.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 +679 -0
.gitattributes CHANGED
@@ -32,3 +32,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
32
  *.zip filter=lfs diff=lfs merge=lfs -text
33
  *.zst filter=lfs diff=lfs merge=lfs -text
34
  *tfevents* filter=lfs diff=lfs merge=lfs -text
35
+ replay.mp4 filter=lfs diff=lfs merge=lfs -text
.summary/0/events.out.tfevents.1677097368.VDI-H-LIN-P-003.vdi.pix4d.com ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cee58dc980336acb6755301252348cc8733f064224cc002959c43b2384cefee6
3
+ size 169248
README.md ADDED
@@ -0,0 +1,56 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: sample-factory
3
+ tags:
4
+ - deep-reinforcement-learning
5
+ - reinforcement-learning
6
+ - sample-factory
7
+ model-index:
8
+ - name: APPO
9
+ results:
10
+ - task:
11
+ type: reinforcement-learning
12
+ name: reinforcement-learning
13
+ dataset:
14
+ name: doom_health_gathering_supreme
15
+ type: doom_health_gathering_supreme
16
+ metrics:
17
+ - type: mean_reward
18
+ value: 8.78 +/- 4.49
19
+ name: mean_reward
20
+ verified: false
21
+ ---
22
+
23
+ A(n) **APPO** model trained on the **doom_health_gathering_supreme** environment.
24
+
25
+ This model was trained using Sample-Factory 2.0: https://github.com/alex-petrenko/sample-factory.
26
+ Documentation for how to use Sample-Factory can be found at https://www.samplefactory.dev/
27
+
28
+
29
+ ## Downloading the model
30
+
31
+ After installing Sample-Factory, download the model with:
32
+ ```
33
+ python -m sample_factory.huggingface.load_from_hub -r GrimReaperSam/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_000000978_4005888_reward_28.129.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7ec0957818ed6776821ebdc0f2f6f0737085ad0fe7f34094242fce5f5337966f
3
+ size 34928614
checkpoint_p0/checkpoint_000000605_2478080.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7af59cf1d899591c69ab7417df7b8a66619f104f75fef1f0a31a5419d71c3ee
3
+ size 34929028
checkpoint_p0/checkpoint_000000978_4005888.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b27857647b3368f84c7b3f78a4cc114d1d0da3759f78f083e32bc1d6ff4ee593
3
+ size 34929028
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": "/home/flahoud/studies/collab/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 sha256:105886dddb3b8178b9711d80f6b769188a241967a34dcb263c92b9fe52682358
3
+ size 16569762
sf_log.txt ADDED
@@ -0,0 +1,679 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [2023-02-22 21:22:50,811][24717] Saving configuration to /home/flahoud/studies/collab/train_dir/default_experiment/config.json...
2
+ [2023-02-22 21:22:50,812][24717] Rollout worker 0 uses device cpu
3
+ [2023-02-22 21:22:50,813][24717] Rollout worker 1 uses device cpu
4
+ [2023-02-22 21:22:50,813][24717] Rollout worker 2 uses device cpu
5
+ [2023-02-22 21:22:50,814][24717] Rollout worker 3 uses device cpu
6
+ [2023-02-22 21:22:50,815][24717] Rollout worker 4 uses device cpu
7
+ [2023-02-22 21:22:50,815][24717] Rollout worker 5 uses device cpu
8
+ [2023-02-22 21:22:50,816][24717] Rollout worker 6 uses device cpu
9
+ [2023-02-22 21:22:50,817][24717] Rollout worker 7 uses device cpu
10
+ [2023-02-22 21:22:50,874][24717] Using GPUs [0] for process 0 (actually maps to GPUs [0])
11
+ [2023-02-22 21:22:50,875][24717] InferenceWorker_p0-w0: min num requests: 2
12
+ [2023-02-22 21:22:50,907][24717] Starting all processes...
13
+ [2023-02-22 21:22:50,908][24717] Starting process learner_proc0
14
+ [2023-02-22 21:22:50,957][24717] Starting all processes...
15
+ [2023-02-22 21:22:50,964][24717] Starting process inference_proc0-0
16
+ [2023-02-22 21:22:50,965][24717] Starting process rollout_proc0
17
+ [2023-02-22 21:22:50,965][24717] Starting process rollout_proc1
18
+ [2023-02-22 21:22:50,966][24717] Starting process rollout_proc2
19
+ [2023-02-22 21:22:50,967][24717] Starting process rollout_proc3
20
+ [2023-02-22 21:22:50,967][24717] Starting process rollout_proc4
21
+ [2023-02-22 21:22:50,968][24717] Starting process rollout_proc5
22
+ [2023-02-22 21:22:50,968][24717] Starting process rollout_proc6
23
+ [2023-02-22 21:22:50,968][24717] Starting process rollout_proc7
24
+ [2023-02-22 21:22:52,699][32247] Worker 1 uses CPU cores [1]
25
+ [2023-02-22 21:22:52,745][32230] Using GPUs [0] for process 0 (actually maps to GPUs [0])
26
+ [2023-02-22 21:22:52,745][32230] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
27
+ [2023-02-22 21:22:52,758][32230] Num visible devices: 1
28
+ [2023-02-22 21:22:52,803][32230] Starting seed is not provided
29
+ [2023-02-22 21:22:52,803][32230] Using GPUs [0] for process 0 (actually maps to GPUs [0])
30
+ [2023-02-22 21:22:52,803][32230] Initializing actor-critic model on device cuda:0
31
+ [2023-02-22 21:22:52,803][32230] RunningMeanStd input shape: (3, 72, 128)
32
+ [2023-02-22 21:22:52,804][32230] RunningMeanStd input shape: (1,)
33
+ [2023-02-22 21:22:52,815][32230] ConvEncoder: input_channels=3
34
+ [2023-02-22 21:22:52,855][32246] Worker 0 uses CPU cores [0]
35
+ [2023-02-22 21:22:52,864][32245] Using GPUs [0] for process 0 (actually maps to GPUs [0])
36
+ [2023-02-22 21:22:52,864][32245] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
37
+ [2023-02-22 21:22:52,878][32245] Num visible devices: 1
38
+ [2023-02-22 21:22:52,943][32249] Worker 3 uses CPU cores [3]
39
+ [2023-02-22 21:22:52,955][32253] Worker 4 uses CPU cores [4]
40
+ [2023-02-22 21:22:52,969][32230] Conv encoder output size: 512
41
+ [2023-02-22 21:22:52,970][32230] Policy head output size: 512
42
+ [2023-02-22 21:22:52,983][32230] Created Actor Critic model with architecture:
43
+ [2023-02-22 21:22:52,984][32230] 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
+ [2023-02-22 21:22:52,989][32262] Worker 6 uses CPU cores [6]
85
+ [2023-02-22 21:22:53,089][32248] Worker 2 uses CPU cores [2]
86
+ [2023-02-22 21:22:53,090][32252] Worker 5 uses CPU cores [5]
87
+ [2023-02-22 21:22:53,203][32263] Worker 7 uses CPU cores [7]
88
+ [2023-02-22 21:22:55,724][32230] Using optimizer <class 'torch.optim.adam.Adam'>
89
+ [2023-02-22 21:22:55,725][32230] No checkpoints found
90
+ [2023-02-22 21:22:55,725][32230] Did not load from checkpoint, starting from scratch!
91
+ [2023-02-22 21:22:55,725][32230] Initialized policy 0 weights for model version 0
92
+ [2023-02-22 21:22:55,727][32230] LearnerWorker_p0 finished initialization!
93
+ [2023-02-22 21:22:55,728][32230] Using GPUs [0] for process 0 (actually maps to GPUs [0])
94
+ [2023-02-22 21:22:55,918][32245] RunningMeanStd input shape: (3, 72, 128)
95
+ [2023-02-22 21:22:55,919][32245] RunningMeanStd input shape: (1,)
96
+ [2023-02-22 21:22:55,929][32245] ConvEncoder: input_channels=3
97
+ [2023-02-22 21:22:56,020][32245] Conv encoder output size: 512
98
+ [2023-02-22 21:22:56,021][32245] Policy head output size: 512
99
+ [2023-02-22 21:22:58,156][24717] 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)
100
+ [2023-02-22 21:22:58,538][24717] Inference worker 0-0 is ready!
101
+ [2023-02-22 21:22:58,539][24717] All inference workers are ready! Signal rollout workers to start!
102
+ [2023-02-22 21:22:58,557][32247] Doom resolution: 160x120, resize resolution: (128, 72)
103
+ [2023-02-22 21:22:58,558][32262] Doom resolution: 160x120, resize resolution: (128, 72)
104
+ [2023-02-22 21:22:58,558][32263] Doom resolution: 160x120, resize resolution: (128, 72)
105
+ [2023-02-22 21:22:58,558][32248] Doom resolution: 160x120, resize resolution: (128, 72)
106
+ [2023-02-22 21:22:58,558][32246] Doom resolution: 160x120, resize resolution: (128, 72)
107
+ [2023-02-22 21:22:58,559][32253] Doom resolution: 160x120, resize resolution: (128, 72)
108
+ [2023-02-22 21:22:58,560][32249] Doom resolution: 160x120, resize resolution: (128, 72)
109
+ [2023-02-22 21:22:58,579][32252] Doom resolution: 160x120, resize resolution: (128, 72)
110
+ [2023-02-22 21:22:59,188][32247] Decorrelating experience for 0 frames...
111
+ [2023-02-22 21:22:59,191][32246] Decorrelating experience for 0 frames...
112
+ [2023-02-22 21:22:59,192][32249] Decorrelating experience for 0 frames...
113
+ [2023-02-22 21:22:59,193][32252] Decorrelating experience for 0 frames...
114
+ [2023-02-22 21:22:59,194][32262] Decorrelating experience for 0 frames...
115
+ [2023-02-22 21:22:59,195][32263] Decorrelating experience for 0 frames...
116
+ [2023-02-22 21:22:59,738][32249] Decorrelating experience for 32 frames...
117
+ [2023-02-22 21:22:59,739][32263] Decorrelating experience for 32 frames...
118
+ [2023-02-22 21:22:59,739][32246] Decorrelating experience for 32 frames...
119
+ [2023-02-22 21:22:59,740][32253] Decorrelating experience for 0 frames...
120
+ [2023-02-22 21:22:59,744][32248] Decorrelating experience for 0 frames...
121
+ [2023-02-22 21:22:59,745][32247] Decorrelating experience for 32 frames...
122
+ [2023-02-22 21:23:00,186][32253] Decorrelating experience for 32 frames...
123
+ [2023-02-22 21:23:00,320][32252] Decorrelating experience for 32 frames...
124
+ [2023-02-22 21:23:00,322][32248] Decorrelating experience for 32 frames...
125
+ [2023-02-22 21:23:00,323][32263] Decorrelating experience for 64 frames...
126
+ [2023-02-22 21:23:00,324][32246] Decorrelating experience for 64 frames...
127
+ [2023-02-22 21:23:00,324][32262] Decorrelating experience for 32 frames...
128
+ [2023-02-22 21:23:00,527][32249] Decorrelating experience for 64 frames...
129
+ [2023-02-22 21:23:00,770][32246] Decorrelating experience for 96 frames...
130
+ [2023-02-22 21:23:00,863][32253] Decorrelating experience for 64 frames...
131
+ [2023-02-22 21:23:00,863][32263] Decorrelating experience for 96 frames...
132
+ [2023-02-22 21:23:00,863][32252] Decorrelating experience for 64 frames...
133
+ [2023-02-22 21:23:00,865][32247] Decorrelating experience for 64 frames...
134
+ [2023-02-22 21:23:01,383][32252] Decorrelating experience for 96 frames...
135
+ [2023-02-22 21:23:01,384][32253] Decorrelating experience for 96 frames...
136
+ [2023-02-22 21:23:01,384][32247] Decorrelating experience for 96 frames...
137
+ [2023-02-22 21:23:01,386][32249] Decorrelating experience for 96 frames...
138
+ [2023-02-22 21:23:01,386][32248] Decorrelating experience for 64 frames...
139
+ [2023-02-22 21:23:01,776][32262] Decorrelating experience for 64 frames...
140
+ [2023-02-22 21:23:01,777][32248] Decorrelating experience for 96 frames...
141
+ [2023-02-22 21:23:02,120][32262] Decorrelating experience for 96 frames...
142
+ [2023-02-22 21:23:02,338][32230] Signal inference workers to stop experience collection...
143
+ [2023-02-22 21:23:02,342][32245] InferenceWorker_p0-w0: stopping experience collection
144
+ [2023-02-22 21:23:03,156][24717] Fps is (10 sec: 0.0, 60 sec: 0.0, 300 sec: 0.0). Total num frames: 0. Throughput: 0: 7.2. Samples: 36. Policy #0 lag: (min: -1.0, avg: -1.0, max: -1.0)
145
+ [2023-02-22 21:23:03,158][24717] Avg episode reward: [(0, '2.456')]
146
+ [2023-02-22 21:23:04,256][32230] Signal inference workers to resume experience collection...
147
+ [2023-02-22 21:23:04,256][32245] InferenceWorker_p0-w0: resuming experience collection
148
+ [2023-02-22 21:23:06,289][32245] Updated weights for policy 0, policy_version 10 (0.0008)
149
+ [2023-02-22 21:23:07,913][32245] Updated weights for policy 0, policy_version 20 (0.0010)
150
+ [2023-02-22 21:23:08,156][24717] Fps is (10 sec: 8601.6, 60 sec: 8601.6, 300 sec: 8601.6). Total num frames: 86016. Throughput: 0: 1899.2. Samples: 18992. Policy #0 lag: (min: 0.0, avg: 0.9, max: 2.0)
151
+ [2023-02-22 21:23:08,157][24717] Avg episode reward: [(0, '4.545')]
152
+ [2023-02-22 21:23:09,552][32245] Updated weights for policy 0, policy_version 30 (0.0007)
153
+ [2023-02-22 21:23:10,866][24717] Heartbeat connected on Batcher_0
154
+ [2023-02-22 21:23:10,869][24717] Heartbeat connected on LearnerWorker_p0
155
+ [2023-02-22 21:23:10,881][24717] Heartbeat connected on InferenceWorker_p0-w0
156
+ [2023-02-22 21:23:10,887][24717] Heartbeat connected on RolloutWorker_w2
157
+ [2023-02-22 21:23:10,890][24717] Heartbeat connected on RolloutWorker_w0
158
+ [2023-02-22 21:23:10,892][24717] Heartbeat connected on RolloutWorker_w3
159
+ [2023-02-22 21:23:10,893][24717] Heartbeat connected on RolloutWorker_w1
160
+ [2023-02-22 21:23:10,898][24717] Heartbeat connected on RolloutWorker_w4
161
+ [2023-02-22 21:23:10,900][24717] Heartbeat connected on RolloutWorker_w5
162
+ [2023-02-22 21:23:10,905][24717] Heartbeat connected on RolloutWorker_w6
163
+ [2023-02-22 21:23:10,907][24717] Heartbeat connected on RolloutWorker_w7
164
+ [2023-02-22 21:23:11,206][32245] Updated weights for policy 0, policy_version 40 (0.0007)
165
+ [2023-02-22 21:23:12,868][32245] Updated weights for policy 0, policy_version 50 (0.0008)
166
+ [2023-02-22 21:23:13,156][24717] Fps is (10 sec: 20889.3, 60 sec: 13926.3, 300 sec: 13926.3). Total num frames: 208896. Throughput: 0: 2502.7. Samples: 37540. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
167
+ [2023-02-22 21:23:13,158][24717] Avg episode reward: [(0, '4.397')]
168
+ [2023-02-22 21:23:13,159][32230] Saving new best policy, reward=4.397!
169
+ [2023-02-22 21:23:14,551][32245] Updated weights for policy 0, policy_version 60 (0.0007)
170
+ [2023-02-22 21:23:16,232][32245] Updated weights for policy 0, policy_version 70 (0.0006)
171
+ [2023-02-22 21:23:17,952][32245] Updated weights for policy 0, policy_version 80 (0.0007)
172
+ [2023-02-22 21:23:18,156][24717] Fps is (10 sec: 24575.9, 60 sec: 16588.8, 300 sec: 16588.8). Total num frames: 331776. Throughput: 0: 3717.4. Samples: 74348. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
173
+ [2023-02-22 21:23:18,157][24717] Avg episode reward: [(0, '4.329')]
174
+ [2023-02-22 21:23:19,740][32245] Updated weights for policy 0, policy_version 90 (0.0010)
175
+ [2023-02-22 21:23:21,483][32245] Updated weights for policy 0, policy_version 100 (0.0007)
176
+ [2023-02-22 21:23:23,156][24717] Fps is (10 sec: 23757.1, 60 sec: 17858.6, 300 sec: 17858.6). Total num frames: 446464. Throughput: 0: 4375.5. Samples: 109386. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
177
+ [2023-02-22 21:23:23,157][24717] Avg episode reward: [(0, '4.485')]
178
+ [2023-02-22 21:23:23,159][32230] Saving new best policy, reward=4.485!
179
+ [2023-02-22 21:23:23,248][32245] Updated weights for policy 0, policy_version 110 (0.0009)
180
+ [2023-02-22 21:23:25,020][32245] Updated weights for policy 0, policy_version 120 (0.0008)
181
+ [2023-02-22 21:23:26,756][32245] Updated weights for policy 0, policy_version 130 (0.0007)
182
+ [2023-02-22 21:23:28,156][24717] Fps is (10 sec: 23347.1, 60 sec: 18841.6, 300 sec: 18841.6). Total num frames: 565248. Throughput: 0: 4225.1. Samples: 126752. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
183
+ [2023-02-22 21:23:28,158][24717] Avg episode reward: [(0, '4.570')]
184
+ [2023-02-22 21:23:28,162][32230] Saving new best policy, reward=4.570!
185
+ [2023-02-22 21:23:28,520][32245] Updated weights for policy 0, policy_version 140 (0.0008)
186
+ [2023-02-22 21:23:30,204][32245] Updated weights for policy 0, policy_version 150 (0.0007)
187
+ [2023-02-22 21:23:31,950][32245] Updated weights for policy 0, policy_version 160 (0.0008)
188
+ [2023-02-22 21:23:33,156][24717] Fps is (10 sec: 23756.7, 60 sec: 19543.8, 300 sec: 19543.8). Total num frames: 684032. Throughput: 0: 4632.2. Samples: 162128. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
189
+ [2023-02-22 21:23:33,157][24717] Avg episode reward: [(0, '4.758')]
190
+ [2023-02-22 21:23:33,159][32230] Saving new best policy, reward=4.758!
191
+ [2023-02-22 21:23:33,637][32245] Updated weights for policy 0, policy_version 170 (0.0006)
192
+ [2023-02-22 21:23:35,345][32245] Updated weights for policy 0, policy_version 180 (0.0008)
193
+ [2023-02-22 21:23:37,053][32245] Updated weights for policy 0, policy_version 190 (0.0007)
194
+ [2023-02-22 21:23:38,156][24717] Fps is (10 sec: 23757.0, 60 sec: 20070.4, 300 sec: 20070.4). Total num frames: 802816. Throughput: 0: 4956.4. Samples: 198256. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
195
+ [2023-02-22 21:23:38,158][24717] Avg episode reward: [(0, '5.231')]
196
+ [2023-02-22 21:23:38,163][32230] Saving new best policy, reward=5.231!
197
+ [2023-02-22 21:23:38,776][32245] Updated weights for policy 0, policy_version 200 (0.0006)
198
+ [2023-02-22 21:23:40,492][32245] Updated weights for policy 0, policy_version 210 (0.0008)
199
+ [2023-02-22 21:23:42,206][32245] Updated weights for policy 0, policy_version 220 (0.0007)
200
+ [2023-02-22 21:23:43,156][24717] Fps is (10 sec: 23756.8, 60 sec: 20480.0, 300 sec: 20480.0). Total num frames: 921600. Throughput: 0: 4802.7. Samples: 216120. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
201
+ [2023-02-22 21:23:43,159][24717] Avg episode reward: [(0, '6.078')]
202
+ [2023-02-22 21:23:43,160][32230] Saving new best policy, reward=6.078!
203
+ [2023-02-22 21:23:43,956][32245] Updated weights for policy 0, policy_version 230 (0.0010)
204
+ [2023-02-22 21:23:45,660][32245] Updated weights for policy 0, policy_version 240 (0.0008)
205
+ [2023-02-22 21:23:47,448][32245] Updated weights for policy 0, policy_version 250 (0.0006)
206
+ [2023-02-22 21:23:48,156][24717] Fps is (10 sec: 23346.9, 60 sec: 20725.7, 300 sec: 20725.7). Total num frames: 1036288. Throughput: 0: 5590.7. Samples: 251620. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
207
+ [2023-02-22 21:23:48,161][24717] Avg episode reward: [(0, '6.450')]
208
+ [2023-02-22 21:23:48,167][32230] Saving new best policy, reward=6.450!
209
+ [2023-02-22 21:23:49,218][32245] Updated weights for policy 0, policy_version 260 (0.0008)
210
+ [2023-02-22 21:23:50,966][32245] Updated weights for policy 0, policy_version 270 (0.0012)
211
+ [2023-02-22 21:23:52,686][32245] Updated weights for policy 0, policy_version 280 (0.0008)
212
+ [2023-02-22 21:23:53,156][24717] Fps is (10 sec: 23347.1, 60 sec: 21001.3, 300 sec: 21001.3). Total num frames: 1155072. Throughput: 0: 5946.3. Samples: 286574. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
213
+ [2023-02-22 21:23:53,159][24717] Avg episode reward: [(0, '7.235')]
214
+ [2023-02-22 21:23:53,160][32230] Saving new best policy, reward=7.235!
215
+ [2023-02-22 21:23:54,405][32245] Updated weights for policy 0, policy_version 290 (0.0008)
216
+ [2023-02-22 21:23:56,162][32245] Updated weights for policy 0, policy_version 300 (0.0008)
217
+ [2023-02-22 21:23:57,856][32245] Updated weights for policy 0, policy_version 310 (0.0007)
218
+ [2023-02-22 21:23:58,156][24717] Fps is (10 sec: 23757.1, 60 sec: 21230.9, 300 sec: 21230.9). Total num frames: 1273856. Throughput: 0: 5927.5. Samples: 304276. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
219
+ [2023-02-22 21:23:58,160][24717] Avg episode reward: [(0, '7.943')]
220
+ [2023-02-22 21:23:58,164][32230] Saving new best policy, reward=7.943!
221
+ [2023-02-22 21:23:59,584][32245] Updated weights for policy 0, policy_version 320 (0.0006)
222
+ [2023-02-22 21:24:01,399][32245] Updated weights for policy 0, policy_version 330 (0.0007)
223
+ [2023-02-22 21:24:03,081][32245] Updated weights for policy 0, policy_version 340 (0.0008)
224
+ [2023-02-22 21:24:03,156][24717] Fps is (10 sec: 23756.8, 60 sec: 23210.7, 300 sec: 21425.2). Total num frames: 1392640. Throughput: 0: 5894.8. Samples: 339612. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
225
+ [2023-02-22 21:24:03,158][24717] Avg episode reward: [(0, '9.597')]
226
+ [2023-02-22 21:24:03,160][32230] Saving new best policy, reward=9.597!
227
+ [2023-02-22 21:24:04,774][32245] Updated weights for policy 0, policy_version 350 (0.0006)
228
+ [2023-02-22 21:24:06,472][32245] Updated weights for policy 0, policy_version 360 (0.0007)
229
+ [2023-02-22 21:24:08,079][32245] Updated weights for policy 0, policy_version 370 (0.0008)
230
+ [2023-02-22 21:24:08,156][24717] Fps is (10 sec: 24166.4, 60 sec: 23825.1, 300 sec: 21650.3). Total num frames: 1515520. Throughput: 0: 5926.3. Samples: 376070. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
231
+ [2023-02-22 21:24:08,159][24717] Avg episode reward: [(0, '11.741')]
232
+ [2023-02-22 21:24:08,164][32230] Saving new best policy, reward=11.741!
233
+ [2023-02-22 21:24:09,745][32245] Updated weights for policy 0, policy_version 380 (0.0006)
234
+ [2023-02-22 21:24:11,395][32245] Updated weights for policy 0, policy_version 390 (0.0006)
235
+ [2023-02-22 21:24:13,047][32245] Updated weights for policy 0, policy_version 400 (0.0007)
236
+ [2023-02-22 21:24:13,156][24717] Fps is (10 sec: 24576.1, 60 sec: 23825.1, 300 sec: 21845.4). Total num frames: 1638400. Throughput: 0: 5958.9. Samples: 394900. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
237
+ [2023-02-22 21:24:13,157][24717] Avg episode reward: [(0, '17.552')]
238
+ [2023-02-22 21:24:13,158][32230] Saving new best policy, reward=17.552!
239
+ [2023-02-22 21:24:14,722][32245] Updated weights for policy 0, policy_version 410 (0.0006)
240
+ [2023-02-22 21:24:16,491][32245] Updated weights for policy 0, policy_version 420 (0.0007)
241
+ [2023-02-22 21:24:18,156][24717] Fps is (10 sec: 24166.4, 60 sec: 23756.8, 300 sec: 21964.8). Total num frames: 1757184. Throughput: 0: 5979.0. Samples: 431182. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
242
+ [2023-02-22 21:24:18,158][24717] Avg episode reward: [(0, '17.099')]
243
+ [2023-02-22 21:24:18,175][32245] Updated weights for policy 0, policy_version 430 (0.0008)
244
+ [2023-02-22 21:24:19,921][32245] Updated weights for policy 0, policy_version 440 (0.0006)
245
+ [2023-02-22 21:24:21,535][32245] Updated weights for policy 0, policy_version 450 (0.0008)
246
+ [2023-02-22 21:24:23,156][24717] Fps is (10 sec: 24166.4, 60 sec: 23893.3, 300 sec: 22118.4). Total num frames: 1880064. Throughput: 0: 5985.9. Samples: 467622. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
247
+ [2023-02-22 21:24:23,157][24717] Avg episode reward: [(0, '16.734')]
248
+ [2023-02-22 21:24:23,244][32245] Updated weights for policy 0, policy_version 460 (0.0007)
249
+ [2023-02-22 21:24:24,887][32245] Updated weights for policy 0, policy_version 470 (0.0006)
250
+ [2023-02-22 21:24:26,622][32245] Updated weights for policy 0, policy_version 480 (0.0006)
251
+ [2023-02-22 21:24:28,157][24717] Fps is (10 sec: 24575.5, 60 sec: 23961.5, 300 sec: 22254.9). Total num frames: 2002944. Throughput: 0: 5995.7. Samples: 485926. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
252
+ [2023-02-22 21:24:28,158][24717] Avg episode reward: [(0, '15.807')]
253
+ [2023-02-22 21:24:28,351][32245] Updated weights for policy 0, policy_version 490 (0.0007)
254
+ [2023-02-22 21:24:30,011][32245] Updated weights for policy 0, policy_version 500 (0.0008)
255
+ [2023-02-22 21:24:31,794][32245] Updated weights for policy 0, policy_version 510 (0.0008)
256
+ [2023-02-22 21:24:33,156][24717] Fps is (10 sec: 24166.3, 60 sec: 23961.6, 300 sec: 22334.0). Total num frames: 2121728. Throughput: 0: 5997.7. Samples: 521516. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
257
+ [2023-02-22 21:24:33,157][24717] Avg episode reward: [(0, '20.357')]
258
+ [2023-02-22 21:24:33,159][32230] Saving new best policy, reward=20.357!
259
+ [2023-02-22 21:24:33,468][32245] Updated weights for policy 0, policy_version 520 (0.0006)
260
+ [2023-02-22 21:24:35,160][32245] Updated weights for policy 0, policy_version 530 (0.0006)
261
+ [2023-02-22 21:24:36,867][32245] Updated weights for policy 0, policy_version 540 (0.0007)
262
+ [2023-02-22 21:24:38,156][24717] Fps is (10 sec: 23757.3, 60 sec: 23961.6, 300 sec: 22405.1). Total num frames: 2240512. Throughput: 0: 6027.9. Samples: 557828. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
263
+ [2023-02-22 21:24:38,157][24717] Avg episode reward: [(0, '18.501')]
264
+ [2023-02-22 21:24:38,559][32245] Updated weights for policy 0, policy_version 550 (0.0008)
265
+ [2023-02-22 21:24:40,271][32245] Updated weights for policy 0, policy_version 560 (0.0008)
266
+ [2023-02-22 21:24:41,996][32245] Updated weights for policy 0, policy_version 570 (0.0007)
267
+ [2023-02-22 21:24:43,156][24717] Fps is (10 sec: 24166.5, 60 sec: 24029.9, 300 sec: 22508.5). Total num frames: 2363392. Throughput: 0: 6032.4. Samples: 575736. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
268
+ [2023-02-22 21:24:43,157][24717] Avg episode reward: [(0, '20.253')]
269
+ [2023-02-22 21:24:43,651][32245] Updated weights for policy 0, policy_version 580 (0.0006)
270
+ [2023-02-22 21:24:45,447][32245] Updated weights for policy 0, policy_version 590 (0.0008)
271
+ [2023-02-22 21:24:47,173][32245] Updated weights for policy 0, policy_version 600 (0.0007)
272
+ [2023-02-22 21:24:48,156][24717] Fps is (10 sec: 23756.8, 60 sec: 24029.9, 300 sec: 22528.0). Total num frames: 2478080. Throughput: 0: 6041.4. Samples: 611476. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
273
+ [2023-02-22 21:24:48,160][24717] Avg episode reward: [(0, '19.851')]
274
+ [2023-02-22 21:24:48,164][32230] Saving /home/flahoud/studies/collab/train_dir/default_experiment/checkpoint_p0/checkpoint_000000605_2478080.pth...
275
+ [2023-02-22 21:24:48,870][32245] Updated weights for policy 0, policy_version 610 (0.0008)
276
+ [2023-02-22 21:24:50,606][32245] Updated weights for policy 0, policy_version 620 (0.0009)
277
+ [2023-02-22 21:24:52,395][32245] Updated weights for policy 0, policy_version 630 (0.0009)
278
+ [2023-02-22 21:24:53,156][24717] Fps is (10 sec: 23347.2, 60 sec: 24029.9, 300 sec: 22581.4). Total num frames: 2596864. Throughput: 0: 6013.9. Samples: 646694. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
279
+ [2023-02-22 21:24:53,157][24717] Avg episode reward: [(0, '22.850')]
280
+ [2023-02-22 21:24:53,160][32230] Saving new best policy, reward=22.850!
281
+ [2023-02-22 21:24:54,156][32245] Updated weights for policy 0, policy_version 640 (0.0008)
282
+ [2023-02-22 21:24:55,879][32245] Updated weights for policy 0, policy_version 650 (0.0007)
283
+ [2023-02-22 21:24:57,621][32245] Updated weights for policy 0, policy_version 660 (0.0007)
284
+ [2023-02-22 21:24:58,156][24717] Fps is (10 sec: 23756.8, 60 sec: 24029.9, 300 sec: 22630.4). Total num frames: 2715648. Throughput: 0: 5991.9. Samples: 664536. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
285
+ [2023-02-22 21:24:58,157][24717] Avg episode reward: [(0, '23.369')]
286
+ [2023-02-22 21:24:58,161][32230] Saving new best policy, reward=23.369!
287
+ [2023-02-22 21:24:59,373][32245] Updated weights for policy 0, policy_version 670 (0.0008)
288
+ [2023-02-22 21:25:01,221][32245] Updated weights for policy 0, policy_version 680 (0.0009)
289
+ [2023-02-22 21:25:02,970][32245] Updated weights for policy 0, policy_version 690 (0.0007)
290
+ [2023-02-22 21:25:03,156][24717] Fps is (10 sec: 23347.2, 60 sec: 23961.6, 300 sec: 22642.7). Total num frames: 2830336. Throughput: 0: 5951.6. Samples: 699006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
291
+ [2023-02-22 21:25:03,157][24717] Avg episode reward: [(0, '21.691')]
292
+ [2023-02-22 21:25:04,706][32245] Updated weights for policy 0, policy_version 700 (0.0007)
293
+ [2023-02-22 21:25:06,440][32245] Updated weights for policy 0, policy_version 710 (0.0007)
294
+ [2023-02-22 21:25:08,156][24717] Fps is (10 sec: 22937.6, 60 sec: 23825.1, 300 sec: 22654.0). Total num frames: 2945024. Throughput: 0: 5924.6. Samples: 734228. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
295
+ [2023-02-22 21:25:08,159][24717] Avg episode reward: [(0, '20.888')]
296
+ [2023-02-22 21:25:08,168][32245] Updated weights for policy 0, policy_version 720 (0.0008)
297
+ [2023-02-22 21:25:09,866][32245] Updated weights for policy 0, policy_version 730 (0.0009)
298
+ [2023-02-22 21:25:11,496][32245] Updated weights for policy 0, policy_version 740 (0.0008)
299
+ [2023-02-22 21:25:13,140][32245] Updated weights for policy 0, policy_version 750 (0.0007)
300
+ [2023-02-22 21:25:13,156][24717] Fps is (10 sec: 24166.4, 60 sec: 23893.3, 300 sec: 22755.6). Total num frames: 3072000. Throughput: 0: 5921.3. Samples: 752384. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
301
+ [2023-02-22 21:25:13,157][24717] Avg episode reward: [(0, '22.374')]
302
+ [2023-02-22 21:25:14,875][32245] Updated weights for policy 0, policy_version 760 (0.0008)
303
+ [2023-02-22 21:25:16,543][32245] Updated weights for policy 0, policy_version 770 (0.0007)
304
+ [2023-02-22 21:25:18,156][24717] Fps is (10 sec: 24576.0, 60 sec: 23893.3, 300 sec: 22791.3). Total num frames: 3190784. Throughput: 0: 5945.4. Samples: 789058. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
305
+ [2023-02-22 21:25:18,157][24717] Avg episode reward: [(0, '22.226')]
306
+ [2023-02-22 21:25:18,258][32245] Updated weights for policy 0, policy_version 780 (0.0006)
307
+ [2023-02-22 21:25:19,995][32245] Updated weights for policy 0, policy_version 790 (0.0007)
308
+ [2023-02-22 21:25:21,683][32245] Updated weights for policy 0, policy_version 800 (0.0006)
309
+ [2023-02-22 21:25:23,156][24717] Fps is (10 sec: 23756.7, 60 sec: 23825.0, 300 sec: 22824.6). Total num frames: 3309568. Throughput: 0: 5944.3. Samples: 825322. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
310
+ [2023-02-22 21:25:23,158][24717] Avg episode reward: [(0, '23.568')]
311
+ [2023-02-22 21:25:23,159][32230] Saving new best policy, reward=23.568!
312
+ [2023-02-22 21:25:23,385][32245] Updated weights for policy 0, policy_version 810 (0.0007)
313
+ [2023-02-22 21:25:25,018][32245] Updated weights for policy 0, policy_version 820 (0.0006)
314
+ [2023-02-22 21:25:26,705][32245] Updated weights for policy 0, policy_version 830 (0.0006)
315
+ [2023-02-22 21:25:28,156][24717] Fps is (10 sec: 24166.4, 60 sec: 23825.2, 300 sec: 22883.0). Total num frames: 3432448. Throughput: 0: 5950.8. Samples: 843522. Policy #0 lag: (min: 0.0, avg: 0.8, max: 2.0)
316
+ [2023-02-22 21:25:28,157][24717] Avg episode reward: [(0, '21.152')]
317
+ [2023-02-22 21:25:28,392][32245] Updated weights for policy 0, policy_version 840 (0.0008)
318
+ [2023-02-22 21:25:30,067][32245] Updated weights for policy 0, policy_version 850 (0.0006)
319
+ [2023-02-22 21:25:31,809][32245] Updated weights for policy 0, policy_version 860 (0.0009)
320
+ [2023-02-22 21:25:33,156][24717] Fps is (10 sec: 24576.2, 60 sec: 23893.4, 300 sec: 22937.6). Total num frames: 3555328. Throughput: 0: 5961.2. Samples: 879730. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
321
+ [2023-02-22 21:25:33,157][24717] Avg episode reward: [(0, '25.351')]
322
+ [2023-02-22 21:25:33,159][32230] Saving new best policy, reward=25.351!
323
+ [2023-02-22 21:25:33,498][32245] Updated weights for policy 0, policy_version 870 (0.0006)
324
+ [2023-02-22 21:25:35,212][32245] Updated weights for policy 0, policy_version 880 (0.0007)
325
+ [2023-02-22 21:25:37,001][32245] Updated weights for policy 0, policy_version 890 (0.0012)
326
+ [2023-02-22 21:25:38,156][24717] Fps is (10 sec: 23756.8, 60 sec: 23825.1, 300 sec: 22937.6). Total num frames: 3670016. Throughput: 0: 5960.4. Samples: 914910. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
327
+ [2023-02-22 21:25:38,158][24717] Avg episode reward: [(0, '24.882')]
328
+ [2023-02-22 21:25:38,807][32245] Updated weights for policy 0, policy_version 900 (0.0010)
329
+ [2023-02-22 21:25:40,496][32245] Updated weights for policy 0, policy_version 910 (0.0006)
330
+ [2023-02-22 21:25:42,288][32245] Updated weights for policy 0, policy_version 920 (0.0008)
331
+ [2023-02-22 21:25:43,157][24717] Fps is (10 sec: 22935.2, 60 sec: 23688.1, 300 sec: 22937.5). Total num frames: 3784704. Throughput: 0: 5959.6. Samples: 932726. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
332
+ [2023-02-22 21:25:43,158][24717] Avg episode reward: [(0, '23.635')]
333
+ [2023-02-22 21:25:44,045][32245] Updated weights for policy 0, policy_version 930 (0.0008)
334
+ [2023-02-22 21:25:45,787][32245] Updated weights for policy 0, policy_version 940 (0.0008)
335
+ [2023-02-22 21:25:47,486][32245] Updated weights for policy 0, policy_version 950 (0.0007)
336
+ [2023-02-22 21:25:48,156][24717] Fps is (10 sec: 23347.0, 60 sec: 23756.8, 300 sec: 22961.7). Total num frames: 3903488. Throughput: 0: 5975.9. Samples: 967920. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
337
+ [2023-02-22 21:25:48,158][24717] Avg episode reward: [(0, '25.987')]
338
+ [2023-02-22 21:25:48,180][32230] Saving new best policy, reward=25.987!
339
+ [2023-02-22 21:25:49,224][32245] Updated weights for policy 0, policy_version 960 (0.0008)
340
+ [2023-02-22 21:25:50,941][32245] Updated weights for policy 0, policy_version 970 (0.0008)
341
+ [2023-02-22 21:25:52,319][32230] Stopping Batcher_0...
342
+ [2023-02-22 21:25:52,319][32230] Saving /home/flahoud/studies/collab/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
343
+ [2023-02-22 21:25:52,319][24717] Component Batcher_0 stopped!
344
+ [2023-02-22 21:25:52,319][32230] Loop batcher_evt_loop terminating...
345
+ [2023-02-22 21:25:52,333][24717] Component RolloutWorker_w5 stopped!
346
+ [2023-02-22 21:25:52,334][32253] Stopping RolloutWorker_w4...
347
+ [2023-02-22 21:25:52,335][32253] Loop rollout_proc4_evt_loop terminating...
348
+ [2023-02-22 21:25:52,335][24717] Component RolloutWorker_w4 stopped!
349
+ [2023-02-22 21:25:52,335][32252] Stopping RolloutWorker_w5...
350
+ [2023-02-22 21:25:52,336][32252] Loop rollout_proc5_evt_loop terminating...
351
+ [2023-02-22 21:25:52,337][32248] Stopping RolloutWorker_w2...
352
+ [2023-02-22 21:25:52,337][32248] Loop rollout_proc2_evt_loop terminating...
353
+ [2023-02-22 21:25:52,337][24717] Component RolloutWorker_w2 stopped!
354
+ [2023-02-22 21:25:52,338][32247] Stopping RolloutWorker_w1...
355
+ [2023-02-22 21:25:52,338][24717] Component RolloutWorker_w1 stopped!
356
+ [2023-02-22 21:25:52,341][32262] Stopping RolloutWorker_w6...
357
+ [2023-02-22 21:25:52,341][24717] Component RolloutWorker_w6 stopped!
358
+ [2023-02-22 21:25:52,342][32262] Loop rollout_proc6_evt_loop terminating...
359
+ [2023-02-22 21:25:52,339][32247] Loop rollout_proc1_evt_loop terminating...
360
+ [2023-02-22 21:25:52,344][32245] Weights refcount: 2 0
361
+ [2023-02-22 21:25:52,345][32245] Stopping InferenceWorker_p0-w0...
362
+ [2023-02-22 21:25:52,345][32245] Loop inference_proc0-0_evt_loop terminating...
363
+ [2023-02-22 21:25:52,345][24717] Component InferenceWorker_p0-w0 stopped!
364
+ [2023-02-22 21:25:52,348][24717] Component RolloutWorker_w0 stopped!
365
+ [2023-02-22 21:25:52,348][32246] Stopping RolloutWorker_w0...
366
+ [2023-02-22 21:25:52,349][32246] Loop rollout_proc0_evt_loop terminating...
367
+ [2023-02-22 21:25:52,353][32263] Stopping RolloutWorker_w7...
368
+ [2023-02-22 21:25:52,353][32263] Loop rollout_proc7_evt_loop terminating...
369
+ [2023-02-22 21:25:52,353][24717] Component RolloutWorker_w7 stopped!
370
+ [2023-02-22 21:25:52,380][32230] Saving new best policy, reward=28.129!
371
+ [2023-02-22 21:25:52,411][32249] Stopping RolloutWorker_w3...
372
+ [2023-02-22 21:25:52,411][32249] Loop rollout_proc3_evt_loop terminating...
373
+ [2023-02-22 21:25:52,411][24717] Component RolloutWorker_w3 stopped!
374
+ [2023-02-22 21:25:52,447][32230] Saving /home/flahoud/studies/collab/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
375
+ [2023-02-22 21:25:52,520][32230] Stopping LearnerWorker_p0...
376
+ [2023-02-22 21:25:52,521][32230] Loop learner_proc0_evt_loop terminating...
377
+ [2023-02-22 21:25:52,520][24717] Component LearnerWorker_p0 stopped!
378
+ [2023-02-22 21:25:52,522][24717] Waiting for process learner_proc0 to stop...
379
+ [2023-02-22 21:25:53,288][24717] Waiting for process inference_proc0-0 to join...
380
+ [2023-02-22 21:25:53,289][24717] Waiting for process rollout_proc0 to join...
381
+ [2023-02-22 21:25:53,290][24717] Waiting for process rollout_proc1 to join...
382
+ [2023-02-22 21:25:53,290][24717] Waiting for process rollout_proc2 to join...
383
+ [2023-02-22 21:25:53,291][24717] Waiting for process rollout_proc3 to join...
384
+ [2023-02-22 21:25:53,292][24717] Waiting for process rollout_proc4 to join...
385
+ [2023-02-22 21:25:53,293][24717] Waiting for process rollout_proc5 to join...
386
+ [2023-02-22 21:25:53,293][24717] Waiting for process rollout_proc6 to join...
387
+ [2023-02-22 21:25:53,294][24717] Waiting for process rollout_proc7 to join...
388
+ [2023-02-22 21:25:53,295][24717] Batcher 0 profile tree view:
389
+ batching: 13.1577, releasing_batches: 0.0181
390
+ [2023-02-22 21:25:53,295][24717] InferenceWorker_p0-w0 profile tree view:
391
+ wait_policy: 0.0000
392
+ wait_policy_total: 4.3703
393
+ update_model: 2.3692
394
+ weight_update: 0.0008
395
+ one_step: 0.0019
396
+ handle_policy_step: 155.6174
397
+ deserialize: 7.8731, stack: 0.8396, obs_to_device_normalize: 39.5270, forward: 65.6351, send_messages: 13.4852
398
+ prepare_outputs: 21.2746
399
+ to_cpu: 12.7880
400
+ [2023-02-22 21:25:53,296][24717] Learner 0 profile tree view:
401
+ misc: 0.0051, prepare_batch: 6.8617
402
+ train: 17.8979
403
+ epoch_init: 0.0044, minibatch_init: 0.0044, losses_postprocess: 0.2348, kl_divergence: 0.2579, after_optimizer: 3.0676
404
+ calculate_losses: 7.3319
405
+ losses_init: 0.0024, forward_head: 0.7714, bptt_initial: 4.3619, tail: 0.4261, advantages_returns: 0.1152, losses: 0.7021
406
+ bptt: 0.8259
407
+ bptt_forward_core: 0.7938
408
+ update: 6.7190
409
+ clip: 0.8093
410
+ [2023-02-22 21:25:53,297][24717] RolloutWorker_w0 profile tree view:
411
+ wait_for_trajectories: 0.0989, enqueue_policy_requests: 5.3262, env_step: 71.2475, overhead: 6.5361, complete_rollouts: 0.5137
412
+ save_policy_outputs: 5.6181
413
+ split_output_tensors: 2.7734
414
+ [2023-02-22 21:25:53,297][24717] RolloutWorker_w7 profile tree view:
415
+ wait_for_trajectories: 0.1168, enqueue_policy_requests: 5.4305, env_step: 72.9827, overhead: 6.5238, complete_rollouts: 0.4607
416
+ save_policy_outputs: 5.7456
417
+ split_output_tensors: 2.8446
418
+ [2023-02-22 21:25:53,299][24717] Loop Runner_EvtLoop terminating...
419
+ [2023-02-22 21:25:53,300][24717] Runner profile tree view:
420
+ main_loop: 182.3930
421
+ [2023-02-22 21:25:53,301][24717] Collected {0: 4005888}, FPS: 21962.9
422
+ [2023-02-22 21:26:34,224][24717] Loading existing experiment configuration from /home/flahoud/studies/collab/train_dir/default_experiment/config.json
423
+ [2023-02-22 21:26:34,225][24717] Overriding arg 'num_workers' with value 1 passed from command line
424
+ [2023-02-22 21:26:34,226][24717] Adding new argument 'no_render'=True that is not in the saved config file!
425
+ [2023-02-22 21:26:34,226][24717] Adding new argument 'save_video'=True that is not in the saved config file!
426
+ [2023-02-22 21:26:34,227][24717] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
427
+ [2023-02-22 21:26:34,228][24717] Adding new argument 'video_name'=None that is not in the saved config file!
428
+ [2023-02-22 21:26:34,228][24717] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
429
+ [2023-02-22 21:26:34,229][24717] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
430
+ [2023-02-22 21:26:34,229][24717] Adding new argument 'push_to_hub'=False that is not in the saved config file!
431
+ [2023-02-22 21:26:34,230][24717] Adding new argument 'hf_repository'=None that is not in the saved config file!
432
+ [2023-02-22 21:26:34,230][24717] Adding new argument 'policy_index'=0 that is not in the saved config file!
433
+ [2023-02-22 21:26:34,231][24717] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
434
+ [2023-02-22 21:26:34,231][24717] Adding new argument 'train_script'=None that is not in the saved config file!
435
+ [2023-02-22 21:26:34,232][24717] Adding new argument 'enjoy_script'=None that is not in the saved config file!
436
+ [2023-02-22 21:26:34,233][24717] Using frameskip 1 and render_action_repeat=4 for evaluation
437
+ [2023-02-22 21:26:34,249][24717] Doom resolution: 160x120, resize resolution: (128, 72)
438
+ [2023-02-22 21:26:34,251][24717] RunningMeanStd input shape: (3, 72, 128)
439
+ [2023-02-22 21:26:34,252][24717] RunningMeanStd input shape: (1,)
440
+ [2023-02-22 21:26:34,264][24717] ConvEncoder: input_channels=3
441
+ [2023-02-22 21:26:34,367][24717] Conv encoder output size: 512
442
+ [2023-02-22 21:26:34,369][24717] Policy head output size: 512
443
+ [2023-02-22 21:26:37,138][24717] Loading state from checkpoint /home/flahoud/studies/collab/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
444
+ [2023-02-22 21:26:38,361][24717] Num frames 100...
445
+ [2023-02-22 21:26:38,459][24717] Num frames 200...
446
+ [2023-02-22 21:26:38,556][24717] Num frames 300...
447
+ [2023-02-22 21:26:38,658][24717] Num frames 400...
448
+ [2023-02-22 21:26:38,753][24717] Num frames 500...
449
+ [2023-02-22 21:26:38,849][24717] Num frames 600...
450
+ [2023-02-22 21:26:38,945][24717] Num frames 700...
451
+ [2023-02-22 21:26:39,045][24717] Num frames 800...
452
+ [2023-02-22 21:26:39,097][24717] Avg episode rewards: #0: 16.000, true rewards: #0: 8.000
453
+ [2023-02-22 21:26:39,098][24717] Avg episode reward: 16.000, avg true_objective: 8.000
454
+ [2023-02-22 21:26:39,202][24717] Num frames 900...
455
+ [2023-02-22 21:26:39,299][24717] Num frames 1000...
456
+ [2023-02-22 21:26:39,395][24717] Num frames 1100...
457
+ [2023-02-22 21:26:39,491][24717] Num frames 1200...
458
+ [2023-02-22 21:26:39,588][24717] Num frames 1300...
459
+ [2023-02-22 21:26:39,690][24717] Num frames 1400...
460
+ [2023-02-22 21:26:39,803][24717] Avg episode rewards: #0: 14.805, true rewards: #0: 7.305
461
+ [2023-02-22 21:26:39,804][24717] Avg episode reward: 14.805, avg true_objective: 7.305
462
+ [2023-02-22 21:26:39,843][24717] Num frames 1500...
463
+ [2023-02-22 21:26:39,946][24717] Num frames 1600...
464
+ [2023-02-22 21:26:40,046][24717] Num frames 1700...
465
+ [2023-02-22 21:26:40,148][24717] Num frames 1800...
466
+ [2023-02-22 21:26:40,247][24717] Num frames 1900...
467
+ [2023-02-22 21:26:40,346][24717] Num frames 2000...
468
+ [2023-02-22 21:26:40,445][24717] Num frames 2100...
469
+ [2023-02-22 21:26:40,542][24717] Num frames 2200...
470
+ [2023-02-22 21:26:40,689][24717] Avg episode rewards: #0: 14.977, true rewards: #0: 7.643
471
+ [2023-02-22 21:26:40,690][24717] Avg episode reward: 14.977, avg true_objective: 7.643
472
+ [2023-02-22 21:26:40,698][24717] Num frames 2300...
473
+ [2023-02-22 21:26:40,798][24717] Num frames 2400...
474
+ [2023-02-22 21:26:40,901][24717] Num frames 2500...
475
+ [2023-02-22 21:26:40,999][24717] Num frames 2600...
476
+ [2023-02-22 21:26:41,095][24717] Num frames 2700...
477
+ [2023-02-22 21:26:41,199][24717] Num frames 2800...
478
+ [2023-02-22 21:26:41,293][24717] Num frames 2900...
479
+ [2023-02-22 21:26:41,384][24717] Num frames 3000...
480
+ [2023-02-22 21:26:41,475][24717] Num frames 3100...
481
+ [2023-02-22 21:26:41,570][24717] Num frames 3200...
482
+ [2023-02-22 21:26:41,668][24717] Num frames 3300...
483
+ [2023-02-22 21:26:41,772][24717] Num frames 3400...
484
+ [2023-02-22 21:26:41,875][24717] Num frames 3500...
485
+ [2023-02-22 21:26:42,000][24717] Avg episode rewards: #0: 18.183, true rewards: #0: 8.932
486
+ [2023-02-22 21:26:42,001][24717] Avg episode reward: 18.183, avg true_objective: 8.932
487
+ [2023-02-22 21:26:42,034][24717] Num frames 3600...
488
+ [2023-02-22 21:26:42,140][24717] Num frames 3700...
489
+ [2023-02-22 21:26:42,243][24717] Num frames 3800...
490
+ [2023-02-22 21:26:42,342][24717] Num frames 3900...
491
+ [2023-02-22 21:26:42,446][24717] Num frames 4000...
492
+ [2023-02-22 21:26:42,548][24717] Num frames 4100...
493
+ [2023-02-22 21:26:42,648][24717] Num frames 4200...
494
+ [2023-02-22 21:26:42,776][24717] Avg episode rewards: #0: 16.954, true rewards: #0: 8.554
495
+ [2023-02-22 21:26:42,777][24717] Avg episode reward: 16.954, avg true_objective: 8.554
496
+ [2023-02-22 21:26:42,800][24717] Num frames 4300...
497
+ [2023-02-22 21:26:42,898][24717] Num frames 4400...
498
+ [2023-02-22 21:26:42,995][24717] Num frames 4500...
499
+ [2023-02-22 21:26:43,090][24717] Num frames 4600...
500
+ [2023-02-22 21:26:43,194][24717] Num frames 4700...
501
+ [2023-02-22 21:26:43,294][24717] Num frames 4800...
502
+ [2023-02-22 21:26:43,391][24717] Num frames 4900...
503
+ [2023-02-22 21:26:43,491][24717] Num frames 5000...
504
+ [2023-02-22 21:26:43,590][24717] Num frames 5100...
505
+ [2023-02-22 21:26:43,687][24717] Num frames 5200...
506
+ [2023-02-22 21:26:43,789][24717] Num frames 5300...
507
+ [2023-02-22 21:26:43,889][24717] Num frames 5400...
508
+ [2023-02-22 21:26:43,992][24717] Num frames 5500...
509
+ [2023-02-22 21:26:44,093][24717] Num frames 5600...
510
+ [2023-02-22 21:26:44,171][24717] Avg episode rewards: #0: 19.535, true rewards: #0: 9.368
511
+ [2023-02-22 21:26:44,172][24717] Avg episode reward: 19.535, avg true_objective: 9.368
512
+ [2023-02-22 21:26:44,254][24717] Num frames 5700...
513
+ [2023-02-22 21:26:44,359][24717] Num frames 5800...
514
+ [2023-02-22 21:26:44,461][24717] Num frames 5900...
515
+ [2023-02-22 21:26:44,563][24717] Num frames 6000...
516
+ [2023-02-22 21:26:44,663][24717] Num frames 6100...
517
+ [2023-02-22 21:26:44,815][24717] Avg episode rewards: #0: 18.139, true rewards: #0: 8.853
518
+ [2023-02-22 21:26:44,817][24717] Avg episode reward: 18.139, avg true_objective: 8.853
519
+ [2023-02-22 21:26:44,820][24717] Num frames 6200...
520
+ [2023-02-22 21:26:44,921][24717] Num frames 6300...
521
+ [2023-02-22 21:26:45,024][24717] Num frames 6400...
522
+ [2023-02-22 21:26:45,122][24717] Num frames 6500...
523
+ [2023-02-22 21:26:45,222][24717] Num frames 6600...
524
+ [2023-02-22 21:26:45,317][24717] Num frames 6700...
525
+ [2023-02-22 21:26:45,413][24717] Num frames 6800...
526
+ [2023-02-22 21:26:45,510][24717] Num frames 6900...
527
+ [2023-02-22 21:26:45,604][24717] Num frames 7000...
528
+ [2023-02-22 21:26:45,703][24717] Num frames 7100...
529
+ [2023-02-22 21:26:45,813][24717] Num frames 7200...
530
+ [2023-02-22 21:26:45,923][24717] Avg episode rewards: #0: 18.571, true rewards: #0: 9.071
531
+ [2023-02-22 21:26:45,924][24717] Avg episode reward: 18.571, avg true_objective: 9.071
532
+ [2023-02-22 21:26:45,967][24717] Num frames 7300...
533
+ [2023-02-22 21:26:46,066][24717] Num frames 7400...
534
+ [2023-02-22 21:26:46,160][24717] Num frames 7500...
535
+ [2023-02-22 21:26:46,259][24717] Num frames 7600...
536
+ [2023-02-22 21:26:46,352][24717] Num frames 7700...
537
+ [2023-02-22 21:26:46,451][24717] Num frames 7800...
538
+ [2023-02-22 21:26:46,548][24717] Num frames 7900...
539
+ [2023-02-22 21:26:46,646][24717] Num frames 8000...
540
+ [2023-02-22 21:26:46,726][24717] Avg episode rewards: #0: 18.250, true rewards: #0: 8.917
541
+ [2023-02-22 21:26:46,727][24717] Avg episode reward: 18.250, avg true_objective: 8.917
542
+ [2023-02-22 21:26:46,803][24717] Num frames 8100...
543
+ [2023-02-22 21:26:46,897][24717] Num frames 8200...
544
+ [2023-02-22 21:26:46,991][24717] Num frames 8300...
545
+ [2023-02-22 21:26:47,084][24717] Num frames 8400...
546
+ [2023-02-22 21:26:47,177][24717] Num frames 8500...
547
+ [2023-02-22 21:26:47,270][24717] Num frames 8600...
548
+ [2023-02-22 21:26:47,383][24717] Avg episode rewards: #0: 17.462, true rewards: #0: 8.662
549
+ [2023-02-22 21:26:47,384][24717] Avg episode reward: 17.462, avg true_objective: 8.662
550
+ [2023-02-22 21:27:02,989][24717] Replay video saved to /home/flahoud/studies/collab/train_dir/default_experiment/replay.mp4!
551
+ [2023-02-22 21:32:31,282][24717] Loading existing experiment configuration from /home/flahoud/studies/collab/train_dir/default_experiment/config.json
552
+ [2023-02-22 21:32:31,283][24717] Overriding arg 'num_workers' with value 1 passed from command line
553
+ [2023-02-22 21:32:31,284][24717] Adding new argument 'no_render'=True that is not in the saved config file!
554
+ [2023-02-22 21:32:31,285][24717] Adding new argument 'save_video'=True that is not in the saved config file!
555
+ [2023-02-22 21:32:31,286][24717] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
556
+ [2023-02-22 21:32:31,286][24717] Adding new argument 'video_name'=None that is not in the saved config file!
557
+ [2023-02-22 21:32:31,286][24717] Adding new argument 'max_num_frames'=100000 that is not in the saved config file!
558
+ [2023-02-22 21:32:31,287][24717] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
559
+ [2023-02-22 21:32:31,287][24717] Adding new argument 'push_to_hub'=True that is not in the saved config file!
560
+ [2023-02-22 21:32:31,288][24717] Adding new argument 'hf_repository'='GrimReaperSam/rl_course_vizdoom_health_gathering_supreme' that is not in the saved config file!
561
+ [2023-02-22 21:32:31,288][24717] Adding new argument 'policy_index'=0 that is not in the saved config file!
562
+ [2023-02-22 21:32:31,289][24717] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
563
+ [2023-02-22 21:32:31,289][24717] Adding new argument 'train_script'=None that is not in the saved config file!
564
+ [2023-02-22 21:32:31,291][24717] Adding new argument 'enjoy_script'=None that is not in the saved config file!
565
+ [2023-02-22 21:32:31,292][24717] Using frameskip 1 and render_action_repeat=4 for evaluation
566
+ [2023-02-22 21:32:31,303][24717] RunningMeanStd input shape: (3, 72, 128)
567
+ [2023-02-22 21:32:31,304][24717] RunningMeanStd input shape: (1,)
568
+ [2023-02-22 21:32:31,315][24717] ConvEncoder: input_channels=3
569
+ [2023-02-22 21:32:31,371][24717] Conv encoder output size: 512
570
+ [2023-02-22 21:32:31,372][24717] Policy head output size: 512
571
+ [2023-02-22 21:32:31,403][24717] Loading state from checkpoint /home/flahoud/studies/collab/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
572
+ [2023-02-22 21:32:31,890][24717] Num frames 100...
573
+ [2023-02-22 21:32:31,981][24717] Num frames 200...
574
+ [2023-02-22 21:32:32,072][24717] Num frames 300...
575
+ [2023-02-22 21:32:32,172][24717] Num frames 400...
576
+ [2023-02-22 21:32:32,320][24717] Avg episode rewards: #0: 7.980, true rewards: #0: 4.980
577
+ [2023-02-22 21:32:32,321][24717] Avg episode reward: 7.980, avg true_objective: 4.980
578
+ [2023-02-22 21:32:32,323][24717] Num frames 500...
579
+ [2023-02-22 21:32:32,420][24717] Num frames 600...
580
+ [2023-02-22 21:32:32,518][24717] Num frames 700...
581
+ [2023-02-22 21:32:32,623][24717] Num frames 800...
582
+ [2023-02-22 21:32:32,718][24717] Num frames 900...
583
+ [2023-02-22 21:32:32,811][24717] Num frames 1000...
584
+ [2023-02-22 21:32:32,928][24717] Num frames 1100...
585
+ [2023-02-22 21:32:33,028][24717] Num frames 1200...
586
+ [2023-02-22 21:32:33,125][24717] Num frames 1300...
587
+ [2023-02-22 21:32:33,222][24717] Num frames 1400...
588
+ [2023-02-22 21:32:33,324][24717] Num frames 1500...
589
+ [2023-02-22 21:32:33,427][24717] Num frames 1600...
590
+ [2023-02-22 21:32:33,531][24717] Num frames 1700...
591
+ [2023-02-22 21:32:33,631][24717] Num frames 1800...
592
+ [2023-02-22 21:32:33,730][24717] Num frames 1900...
593
+ [2023-02-22 21:32:33,835][24717] Num frames 2000...
594
+ [2023-02-22 21:32:33,937][24717] Num frames 2100...
595
+ [2023-02-22 21:32:34,048][24717] Num frames 2200...
596
+ [2023-02-22 21:32:34,193][24717] Avg episode rewards: #0: 26.950, true rewards: #0: 11.450
597
+ [2023-02-22 21:32:34,194][24717] Avg episode reward: 26.950, avg true_objective: 11.450
598
+ [2023-02-22 21:32:34,206][24717] Num frames 2300...
599
+ [2023-02-22 21:32:34,315][24717] Num frames 2400...
600
+ [2023-02-22 21:32:34,424][24717] Num frames 2500...
601
+ [2023-02-22 21:32:34,528][24717] Num frames 2600...
602
+ [2023-02-22 21:32:34,632][24717] Num frames 2700...
603
+ [2023-02-22 21:32:34,736][24717] Num frames 2800...
604
+ [2023-02-22 21:32:34,843][24717] Num frames 2900...
605
+ [2023-02-22 21:32:34,943][24717] Num frames 3000...
606
+ [2023-02-22 21:32:35,049][24717] Num frames 3100...
607
+ [2023-02-22 21:32:35,153][24717] Num frames 3200...
608
+ [2023-02-22 21:32:35,254][24717] Num frames 3300...
609
+ [2023-02-22 21:32:35,356][24717] Num frames 3400...
610
+ [2023-02-22 21:32:35,457][24717] Num frames 3500...
611
+ [2023-02-22 21:32:35,558][24717] Num frames 3600...
612
+ [2023-02-22 21:32:35,655][24717] Num frames 3700...
613
+ [2023-02-22 21:32:35,741][24717] Avg episode rewards: #0: 30.766, true rewards: #0: 12.433
614
+ [2023-02-22 21:32:35,742][24717] Avg episode reward: 30.766, avg true_objective: 12.433
615
+ [2023-02-22 21:32:35,816][24717] Num frames 3800...
616
+ [2023-02-22 21:32:35,916][24717] Num frames 3900...
617
+ [2023-02-22 21:32:36,017][24717] Num frames 4000...
618
+ [2023-02-22 21:32:36,125][24717] Num frames 4100...
619
+ [2023-02-22 21:32:36,232][24717] Num frames 4200...
620
+ [2023-02-22 21:32:36,342][24717] Num frames 4300...
621
+ [2023-02-22 21:32:36,445][24717] Num frames 4400...
622
+ [2023-02-22 21:32:36,553][24717] Num frames 4500...
623
+ [2023-02-22 21:32:36,664][24717] Num frames 4600...
624
+ [2023-02-22 21:32:36,734][24717] Avg episode rewards: #0: 28.032, true rewards: #0: 11.532
625
+ [2023-02-22 21:32:36,735][24717] Avg episode reward: 28.032, avg true_objective: 11.532
626
+ [2023-02-22 21:32:36,823][24717] Num frames 4700...
627
+ [2023-02-22 21:32:36,929][24717] Num frames 4800...
628
+ [2023-02-22 21:32:37,027][24717] Num frames 4900...
629
+ [2023-02-22 21:32:37,131][24717] Num frames 5000...
630
+ [2023-02-22 21:32:37,231][24717] Num frames 5100...
631
+ [2023-02-22 21:32:37,331][24717] Num frames 5200...
632
+ [2023-02-22 21:32:37,428][24717] Num frames 5300...
633
+ [2023-02-22 21:32:37,530][24717] Num frames 5400...
634
+ [2023-02-22 21:32:37,643][24717] Num frames 5500...
635
+ [2023-02-22 21:32:37,747][24717] Num frames 5600...
636
+ [2023-02-22 21:32:37,817][24717] Avg episode rewards: #0: 27.428, true rewards: #0: 11.228
637
+ [2023-02-22 21:32:37,818][24717] Avg episode reward: 27.428, avg true_objective: 11.228
638
+ [2023-02-22 21:32:37,907][24717] Num frames 5700...
639
+ [2023-02-22 21:32:38,007][24717] Num frames 5800...
640
+ [2023-02-22 21:32:38,106][24717] Num frames 5900...
641
+ [2023-02-22 21:32:38,202][24717] Num frames 6000...
642
+ [2023-02-22 21:32:38,296][24717] Num frames 6100...
643
+ [2023-02-22 21:32:38,398][24717] Num frames 6200...
644
+ [2023-02-22 21:32:38,494][24717] Num frames 6300...
645
+ [2023-02-22 21:32:38,593][24717] Num frames 6400...
646
+ [2023-02-22 21:32:38,689][24717] Num frames 6500...
647
+ [2023-02-22 21:32:38,755][24717] Avg episode rewards: #0: 25.850, true rewards: #0: 10.850
648
+ [2023-02-22 21:32:38,757][24717] Avg episode reward: 25.850, avg true_objective: 10.850
649
+ [2023-02-22 21:32:38,845][24717] Num frames 6600...
650
+ [2023-02-22 21:32:38,943][24717] Num frames 6700...
651
+ [2023-02-22 21:32:39,043][24717] Num frames 6800...
652
+ [2023-02-22 21:32:39,187][24717] Avg episode rewards: #0: 23.134, true rewards: #0: 9.849
653
+ [2023-02-22 21:32:39,188][24717] Avg episode reward: 23.134, avg true_objective: 9.849
654
+ [2023-02-22 21:32:39,195][24717] Num frames 6900...
655
+ [2023-02-22 21:32:39,302][24717] Num frames 7000...
656
+ [2023-02-22 21:32:39,399][24717] Num frames 7100...
657
+ [2023-02-22 21:32:39,501][24717] Num frames 7200...
658
+ [2023-02-22 21:32:39,600][24717] Num frames 7300...
659
+ [2023-02-22 21:32:39,696][24717] Num frames 7400...
660
+ [2023-02-22 21:32:39,790][24717] Num frames 7500...
661
+ [2023-02-22 21:32:39,884][24717] Num frames 7600...
662
+ [2023-02-22 21:32:39,985][24717] Num frames 7700...
663
+ [2023-02-22 21:32:40,084][24717] Num frames 7800...
664
+ [2023-02-22 21:32:40,187][24717] Num frames 7900...
665
+ [2023-02-22 21:32:40,292][24717] Avg episode rewards: #0: 22.937, true rewards: #0: 9.937
666
+ [2023-02-22 21:32:40,294][24717] Avg episode reward: 22.937, avg true_objective: 9.937
667
+ [2023-02-22 21:32:40,349][24717] Num frames 8000...
668
+ [2023-02-22 21:32:40,445][24717] Num frames 8100...
669
+ [2023-02-22 21:32:40,550][24717] Num frames 8200...
670
+ [2023-02-22 21:32:40,657][24717] Num frames 8300...
671
+ [2023-02-22 21:32:40,805][24717] Avg episode rewards: #0: 20.998, true rewards: #0: 9.331
672
+ [2023-02-22 21:32:40,806][24717] Avg episode reward: 20.998, avg true_objective: 9.331
673
+ [2023-02-22 21:32:40,809][24717] Num frames 8400...
674
+ [2023-02-22 21:32:40,907][24717] Num frames 8500...
675
+ [2023-02-22 21:32:41,012][24717] Num frames 8600...
676
+ [2023-02-22 21:32:41,114][24717] Num frames 8700...
677
+ [2023-02-22 21:32:41,255][24717] Avg episode rewards: #0: 19.282, true rewards: #0: 8.782
678
+ [2023-02-22 21:32:41,256][24717] Avg episode reward: 19.282, avg true_objective: 8.782
679
+ [2023-02-22 21:32:57,417][24717] Replay video saved to /home/flahoud/studies/collab/train_dir/default_experiment/replay.mp4!