nguyenduchuyiu
commited on
Commit
•
4106ecc
1
Parent(s):
7c636aa
Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .summary/0/events.out.tfevents.1723795229.nguyen-duc-huy-G5-GD +3 -0
- README.md +56 -0
- checkpoint_p0/best_000000766_3137536_reward_25.046.pth +3 -0
- checkpoint_p0/checkpoint_000000943_3862528.pth +3 -0
- checkpoint_p0/checkpoint_000000978_4005888.pth +3 -0
- config.json +142 -0
- replay.mp4 +3 -0
- sf_log.txt +643 -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.1723795229.nguyen-duc-huy-G5-GD
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:289d1e6b9be54b169af1b241afa776ce78652aca2fca96b23820427056a88010
|
3 |
+
size 236016
|
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: 9.95 +/- 4.64
|
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 nguyenduchuyiu/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_000000766_3137536_reward_25.046.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:dabad795431324f790b46d76743f359b3e6eb8bfd34be2f978cd8d9f735ab9fe
|
3 |
+
size 34929051
|
checkpoint_p0/checkpoint_000000943_3862528.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:1472f59bd8b7b19c944b44e583593d9a00d93daf093267b8cf2b2edb54fececc
|
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:afc8265d51f3c19fba60076e0fe69160d9e5b26ecfb214094f525781b7d282db
|
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": "/media/nguyen-duc-huy/E/Code/Deep_RL/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 sha256:497c3b529b4e1d8d65f5947de2b553139464c9c19c812fcb976ad1aa3c78cbab
|
3 |
+
size 19038547
|
sf_log.txt
ADDED
@@ -0,0 +1,643 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
[2024-08-16 15:00:33,731][09795] Saving configuration to /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/config.json...
|
2 |
+
[2024-08-16 15:00:33,732][09795] Rollout worker 0 uses device cpu
|
3 |
+
[2024-08-16 15:00:33,732][09795] Rollout worker 1 uses device cpu
|
4 |
+
[2024-08-16 15:00:33,732][09795] Rollout worker 2 uses device cpu
|
5 |
+
[2024-08-16 15:00:33,733][09795] Rollout worker 3 uses device cpu
|
6 |
+
[2024-08-16 15:00:33,733][09795] Rollout worker 4 uses device cpu
|
7 |
+
[2024-08-16 15:00:33,733][09795] Rollout worker 5 uses device cpu
|
8 |
+
[2024-08-16 15:00:33,733][09795] Rollout worker 6 uses device cpu
|
9 |
+
[2024-08-16 15:00:33,733][09795] Rollout worker 7 uses device cpu
|
10 |
+
[2024-08-16 15:00:33,773][09795] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
11 |
+
[2024-08-16 15:00:33,774][09795] InferenceWorker_p0-w0: min num requests: 2
|
12 |
+
[2024-08-16 15:00:33,804][09795] Starting all processes...
|
13 |
+
[2024-08-16 15:00:33,805][09795] Starting process learner_proc0
|
14 |
+
[2024-08-16 15:00:34,179][09795] Starting all processes...
|
15 |
+
[2024-08-16 15:00:34,183][09795] Starting process inference_proc0-0
|
16 |
+
[2024-08-16 15:00:34,183][09795] Starting process rollout_proc0
|
17 |
+
[2024-08-16 15:00:34,183][09795] Starting process rollout_proc1
|
18 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc2
|
19 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc3
|
20 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc4
|
21 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc5
|
22 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc6
|
23 |
+
[2024-08-16 15:00:34,184][09795] Starting process rollout_proc7
|
24 |
+
[2024-08-16 15:00:36,347][19834] Worker 4 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
25 |
+
[2024-08-16 15:00:36,389][19831] Worker 0 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
26 |
+
[2024-08-16 15:00:36,463][19836] Worker 6 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
27 |
+
[2024-08-16 15:00:36,485][19830] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
28 |
+
[2024-08-16 15:00:36,485][19830] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for inference process 0
|
29 |
+
[2024-08-16 15:00:36,500][19830] Num visible devices: 1
|
30 |
+
[2024-08-16 15:00:36,512][19832] Worker 3 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
31 |
+
[2024-08-16 15:00:36,512][19835] Worker 2 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
32 |
+
[2024-08-16 15:00:36,522][19817] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
33 |
+
[2024-08-16 15:00:36,522][19817] Set environment var CUDA_VISIBLE_DEVICES to '0' (GPU indices [0]) for learning process 0
|
34 |
+
[2024-08-16 15:00:36,535][19817] Num visible devices: 1
|
35 |
+
[2024-08-16 15:00:36,539][19817] Starting seed is not provided
|
36 |
+
[2024-08-16 15:00:36,539][19817] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
37 |
+
[2024-08-16 15:00:36,539][19817] Initializing actor-critic model on device cuda:0
|
38 |
+
[2024-08-16 15:00:36,539][19817] RunningMeanStd input shape: (3, 72, 128)
|
39 |
+
[2024-08-16 15:00:36,544][19817] RunningMeanStd input shape: (1,)
|
40 |
+
[2024-08-16 15:00:36,550][19833] Worker 1 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
41 |
+
[2024-08-16 15:00:36,553][19817] ConvEncoder: input_channels=3
|
42 |
+
[2024-08-16 15:00:36,561][19838] Worker 5 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
43 |
+
[2024-08-16 15:00:36,584][19837] Worker 7 uses CPU cores [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
|
44 |
+
[2024-08-16 15:00:36,653][19817] Conv encoder output size: 512
|
45 |
+
[2024-08-16 15:00:36,653][19817] Policy head output size: 512
|
46 |
+
[2024-08-16 15:00:36,671][19817] Created Actor Critic model with architecture:
|
47 |
+
[2024-08-16 15:00:36,671][19817] ActorCriticSharedWeights(
|
48 |
+
(obs_normalizer): ObservationNormalizer(
|
49 |
+
(running_mean_std): RunningMeanStdDictInPlace(
|
50 |
+
(running_mean_std): ModuleDict(
|
51 |
+
(obs): RunningMeanStdInPlace()
|
52 |
+
)
|
53 |
+
)
|
54 |
+
)
|
55 |
+
(returns_normalizer): RecursiveScriptModule(original_name=RunningMeanStdInPlace)
|
56 |
+
(encoder): VizdoomEncoder(
|
57 |
+
(basic_encoder): ConvEncoder(
|
58 |
+
(enc): RecursiveScriptModule(
|
59 |
+
original_name=ConvEncoderImpl
|
60 |
+
(conv_head): RecursiveScriptModule(
|
61 |
+
original_name=Sequential
|
62 |
+
(0): RecursiveScriptModule(original_name=Conv2d)
|
63 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
64 |
+
(2): RecursiveScriptModule(original_name=Conv2d)
|
65 |
+
(3): RecursiveScriptModule(original_name=ELU)
|
66 |
+
(4): RecursiveScriptModule(original_name=Conv2d)
|
67 |
+
(5): RecursiveScriptModule(original_name=ELU)
|
68 |
+
)
|
69 |
+
(mlp_layers): RecursiveScriptModule(
|
70 |
+
original_name=Sequential
|
71 |
+
(0): RecursiveScriptModule(original_name=Linear)
|
72 |
+
(1): RecursiveScriptModule(original_name=ELU)
|
73 |
+
)
|
74 |
+
)
|
75 |
+
)
|
76 |
+
)
|
77 |
+
(core): ModelCoreRNN(
|
78 |
+
(core): GRU(512, 512)
|
79 |
+
)
|
80 |
+
(decoder): MlpDecoder(
|
81 |
+
(mlp): Identity()
|
82 |
+
)
|
83 |
+
(critic_linear): Linear(in_features=512, out_features=1, bias=True)
|
84 |
+
(action_parameterization): ActionParameterizationDefault(
|
85 |
+
(distribution_linear): Linear(in_features=512, out_features=5, bias=True)
|
86 |
+
)
|
87 |
+
)
|
88 |
+
[2024-08-16 15:00:36,886][19817] Using optimizer <class 'torch.optim.adam.Adam'>
|
89 |
+
[2024-08-16 15:00:37,506][19817] No checkpoints found
|
90 |
+
[2024-08-16 15:00:37,506][19817] Did not load from checkpoint, starting from scratch!
|
91 |
+
[2024-08-16 15:00:37,506][19817] Initialized policy 0 weights for model version 0
|
92 |
+
[2024-08-16 15:00:37,509][19817] LearnerWorker_p0 finished initialization!
|
93 |
+
[2024-08-16 15:00:37,509][19817] Using GPUs [0] for process 0 (actually maps to GPUs [0])
|
94 |
+
[2024-08-16 15:00:37,655][19830] RunningMeanStd input shape: (3, 72, 128)
|
95 |
+
[2024-08-16 15:00:37,656][19830] RunningMeanStd input shape: (1,)
|
96 |
+
[2024-08-16 15:00:37,664][19830] ConvEncoder: input_channels=3
|
97 |
+
[2024-08-16 15:00:37,732][19830] Conv encoder output size: 512
|
98 |
+
[2024-08-16 15:00:37,732][19830] Policy head output size: 512
|
99 |
+
[2024-08-16 15:00:37,760][09795] Inference worker 0-0 is ready!
|
100 |
+
[2024-08-16 15:00:37,760][09795] All inference workers are ready! Signal rollout workers to start!
|
101 |
+
[2024-08-16 15:00:37,795][19834] Doom resolution: 160x120, resize resolution: (128, 72)
|
102 |
+
[2024-08-16 15:00:37,796][19838] Doom resolution: 160x120, resize resolution: (128, 72)
|
103 |
+
[2024-08-16 15:00:37,796][19831] Doom resolution: 160x120, resize resolution: (128, 72)
|
104 |
+
[2024-08-16 15:00:37,796][19832] Doom resolution: 160x120, resize resolution: (128, 72)
|
105 |
+
[2024-08-16 15:00:37,807][19833] Doom resolution: 160x120, resize resolution: (128, 72)
|
106 |
+
[2024-08-16 15:00:37,807][19836] Doom resolution: 160x120, resize resolution: (128, 72)
|
107 |
+
[2024-08-16 15:00:37,807][19835] Doom resolution: 160x120, resize resolution: (128, 72)
|
108 |
+
[2024-08-16 15:00:37,810][19837] Doom resolution: 160x120, resize resolution: (128, 72)
|
109 |
+
[2024-08-16 15:00:37,865][19832] VizDoom game.init() threw an exception ViZDoomUnexpectedExitException('Controlled ViZDoom instance exited unexpectedly.'). Terminate process...
|
110 |
+
[2024-08-16 15:00:37,865][19832] EvtLoop [rollout_proc3_evt_loop, process=rollout_proc3] unhandled exception in slot='init' connected to emitter=Emitter(object_id='Sampler', signal_name='_inference_workers_initialized'), args=()
|
111 |
+
Traceback (most recent call last):
|
112 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 228, in _game_init
|
113 |
+
self.game.init()
|
114 |
+
vizdoom.vizdoom.ViZDoomUnexpectedExitException: Controlled ViZDoom instance exited unexpectedly.
|
115 |
+
|
116 |
+
During handling of the above exception, another exception occurred:
|
117 |
+
|
118 |
+
Traceback (most recent call last):
|
119 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/signal_slot/signal_slot.py", line 355, in _process_signal
|
120 |
+
slot_callable(*args)
|
121 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/algo/sampling/rollout_worker.py", line 150, in init
|
122 |
+
env_runner.init(self.timing)
|
123 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 418, in init
|
124 |
+
self._reset()
|
125 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/algo/sampling/non_batched_sampling.py", line 430, in _reset
|
126 |
+
observations, info = e.reset(seed=seed) # new way of doing seeding since Gym 0.26.0
|
127 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/gymnasium/core.py", line 467, in reset
|
128 |
+
return self.env.reset(seed=seed, options=options)
|
129 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 125, in reset
|
130 |
+
obs, info = self.env.reset(**kwargs)
|
131 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/algo/utils/make_env.py", line 110, in reset
|
132 |
+
obs, info = self.env.reset(**kwargs)
|
133 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/scenario_wrappers/gathering_reward_shaping.py", line 30, in reset
|
134 |
+
return self.env.reset(**kwargs)
|
135 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/gymnasium/core.py", line 515, in reset
|
136 |
+
obs, info = self.env.reset(seed=seed, options=options)
|
137 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sample_factory/envs/env_wrappers.py", line 82, in reset
|
138 |
+
obs, info = self.env.reset(**kwargs)
|
139 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/gymnasium/core.py", line 467, in reset
|
140 |
+
return self.env.reset(seed=seed, options=options)
|
141 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/wrappers/multiplayer_stats.py", line 51, in reset
|
142 |
+
return self.env.reset(**kwargs)
|
143 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 323, in reset
|
144 |
+
self._ensure_initialized()
|
145 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 274, in _ensure_initialized
|
146 |
+
self.initialize()
|
147 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 269, in initialize
|
148 |
+
self._game_init()
|
149 |
+
File "/media/nguyen-duc-huy/E/anaconda3/envs/rl-project/lib/python3.10/site-packages/sf_examples/vizdoom/doom/doom_gym.py", line 244, in _game_init
|
150 |
+
raise EnvCriticalError()
|
151 |
+
sample_factory.envs.env_utils.EnvCriticalError
|
152 |
+
[2024-08-16 15:00:37,866][19832] Unhandled exception in evt loop rollout_proc3_evt_loop
|
153 |
+
[2024-08-16 15:00:38,007][19831] Decorrelating experience for 0 frames...
|
154 |
+
[2024-08-16 15:00:38,011][19836] Decorrelating experience for 0 frames...
|
155 |
+
[2024-08-16 15:00:38,013][19837] Decorrelating experience for 0 frames...
|
156 |
+
[2024-08-16 15:00:38,073][19838] Decorrelating experience for 0 frames...
|
157 |
+
[2024-08-16 15:00:38,076][19834] Decorrelating experience for 0 frames...
|
158 |
+
[2024-08-16 15:00:38,179][19836] Decorrelating experience for 32 frames...
|
159 |
+
[2024-08-16 15:00:38,180][19837] Decorrelating experience for 32 frames...
|
160 |
+
[2024-08-16 15:00:38,224][19831] Decorrelating experience for 32 frames...
|
161 |
+
[2024-08-16 15:00:38,226][19835] Decorrelating experience for 0 frames...
|
162 |
+
[2024-08-16 15:00:38,270][19833] Decorrelating experience for 0 frames...
|
163 |
+
[2024-08-16 15:00:38,393][19838] Decorrelating experience for 32 frames...
|
164 |
+
[2024-08-16 15:00:38,396][19835] Decorrelating experience for 32 frames...
|
165 |
+
[2024-08-16 15:00:38,423][19836] Decorrelating experience for 64 frames...
|
166 |
+
[2024-08-16 15:00:38,423][19834] Decorrelating experience for 32 frames...
|
167 |
+
[2024-08-16 15:00:38,437][19833] Decorrelating experience for 32 frames...
|
168 |
+
[2024-08-16 15:00:38,634][19836] Decorrelating experience for 96 frames...
|
169 |
+
[2024-08-16 15:00:38,643][19838] Decorrelating experience for 64 frames...
|
170 |
+
[2024-08-16 15:00:38,652][19831] Decorrelating experience for 64 frames...
|
171 |
+
[2024-08-16 15:00:38,682][19833] Decorrelating experience for 64 frames...
|
172 |
+
[2024-08-16 15:00:38,682][19835] Decorrelating experience for 64 frames...
|
173 |
+
[2024-08-16 15:00:38,811][19834] Decorrelating experience for 64 frames...
|
174 |
+
[2024-08-16 15:00:38,870][19831] Decorrelating experience for 96 frames...
|
175 |
+
[2024-08-16 15:00:38,871][19833] Decorrelating experience for 96 frames...
|
176 |
+
[2024-08-16 15:00:38,880][19835] Decorrelating experience for 96 frames...
|
177 |
+
[2024-08-16 15:00:38,898][19837] Decorrelating experience for 64 frames...
|
178 |
+
[2024-08-16 15:00:38,999][19834] Decorrelating experience for 96 frames...
|
179 |
+
[2024-08-16 15:00:39,034][19838] Decorrelating experience for 96 frames...
|
180 |
+
[2024-08-16 15:00:39,229][19837] Decorrelating experience for 96 frames...
|
181 |
+
[2024-08-16 15:00:39,423][09795] 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)
|
182 |
+
[2024-08-16 15:00:39,424][09795] Avg episode reward: [(0, '1.092')]
|
183 |
+
[2024-08-16 15:00:39,814][19817] Signal inference workers to stop experience collection...
|
184 |
+
[2024-08-16 15:00:39,818][19830] InferenceWorker_p0-w0: stopping experience collection
|
185 |
+
[2024-08-16 15:00:41,087][19817] Signal inference workers to resume experience collection...
|
186 |
+
[2024-08-16 15:00:41,088][19830] InferenceWorker_p0-w0: resuming experience collection
|
187 |
+
[2024-08-16 15:00:43,180][19830] Updated weights for policy 0, policy_version 10 (0.0113)
|
188 |
+
[2024-08-16 15:00:44,423][09795] Fps is (10 sec: 12287.7, 60 sec: 12287.7, 300 sec: 12287.7). Total num frames: 61440. Throughput: 0: 2707.1. Samples: 13536. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
189 |
+
[2024-08-16 15:00:44,424][09795] Avg episode reward: [(0, '4.447')]
|
190 |
+
[2024-08-16 15:00:45,464][19830] Updated weights for policy 0, policy_version 20 (0.0008)
|
191 |
+
[2024-08-16 15:00:47,818][19830] Updated weights for policy 0, policy_version 30 (0.0009)
|
192 |
+
[2024-08-16 15:00:49,423][09795] Fps is (10 sec: 15155.2, 60 sec: 15155.2, 300 sec: 15155.2). Total num frames: 151552. Throughput: 0: 2645.4. Samples: 26454. Policy #0 lag: (min: 0.0, avg: 0.3, max: 2.0)
|
193 |
+
[2024-08-16 15:00:49,424][09795] Avg episode reward: [(0, '4.560')]
|
194 |
+
[2024-08-16 15:00:49,427][19817] Saving new best policy, reward=4.560!
|
195 |
+
[2024-08-16 15:00:49,917][19830] Updated weights for policy 0, policy_version 40 (0.0008)
|
196 |
+
[2024-08-16 15:00:52,105][19830] Updated weights for policy 0, policy_version 50 (0.0008)
|
197 |
+
[2024-08-16 15:00:53,769][09795] Heartbeat connected on Batcher_0
|
198 |
+
[2024-08-16 15:00:53,779][09795] Heartbeat connected on LearnerWorker_p0
|
199 |
+
[2024-08-16 15:00:53,781][09795] Heartbeat connected on RolloutWorker_w0
|
200 |
+
[2024-08-16 15:00:53,781][09795] Heartbeat connected on RolloutWorker_w1
|
201 |
+
[2024-08-16 15:00:53,782][09795] Heartbeat connected on InferenceWorker_p0-w0
|
202 |
+
[2024-08-16 15:00:53,782][09795] Heartbeat connected on RolloutWorker_w2
|
203 |
+
[2024-08-16 15:00:53,787][09795] Heartbeat connected on RolloutWorker_w4
|
204 |
+
[2024-08-16 15:00:53,789][09795] Heartbeat connected on RolloutWorker_w5
|
205 |
+
[2024-08-16 15:00:53,792][09795] Heartbeat connected on RolloutWorker_w6
|
206 |
+
[2024-08-16 15:00:53,804][09795] Heartbeat connected on RolloutWorker_w7
|
207 |
+
[2024-08-16 15:00:54,170][19830] Updated weights for policy 0, policy_version 60 (0.0007)
|
208 |
+
[2024-08-16 15:00:54,423][09795] Fps is (10 sec: 18841.8, 60 sec: 16657.1, 300 sec: 16657.1). Total num frames: 249856. Throughput: 0: 3682.7. Samples: 55240. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
|
209 |
+
[2024-08-16 15:00:54,424][09795] Avg episode reward: [(0, '4.325')]
|
210 |
+
[2024-08-16 15:00:56,365][19830] Updated weights for policy 0, policy_version 70 (0.0007)
|
211 |
+
[2024-08-16 15:00:58,557][19830] Updated weights for policy 0, policy_version 80 (0.0008)
|
212 |
+
[2024-08-16 15:00:59,423][09795] Fps is (10 sec: 19251.3, 60 sec: 17203.2, 300 sec: 17203.2). Total num frames: 344064. Throughput: 0: 4178.0. Samples: 83560. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
213 |
+
[2024-08-16 15:00:59,424][09795] Avg episode reward: [(0, '4.428')]
|
214 |
+
[2024-08-16 15:01:00,612][19830] Updated weights for policy 0, policy_version 90 (0.0008)
|
215 |
+
[2024-08-16 15:01:02,841][19830] Updated weights for policy 0, policy_version 100 (0.0008)
|
216 |
+
[2024-08-16 15:01:04,423][09795] Fps is (10 sec: 18841.4, 60 sec: 17530.8, 300 sec: 17530.8). Total num frames: 438272. Throughput: 0: 3926.3. Samples: 98158. Policy #0 lag: (min: 0.0, avg: 0.8, max: 1.0)
|
217 |
+
[2024-08-16 15:01:04,424][09795] Avg episode reward: [(0, '4.555')]
|
218 |
+
[2024-08-16 15:01:05,072][19830] Updated weights for policy 0, policy_version 110 (0.0009)
|
219 |
+
[2024-08-16 15:01:07,573][19830] Updated weights for policy 0, policy_version 120 (0.0009)
|
220 |
+
[2024-08-16 15:01:09,423][09795] Fps is (10 sec: 17612.6, 60 sec: 17339.7, 300 sec: 17339.7). Total num frames: 520192. Throughput: 0: 4151.1. Samples: 124534. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
221 |
+
[2024-08-16 15:01:09,424][09795] Avg episode reward: [(0, '4.401')]
|
222 |
+
[2024-08-16 15:01:09,911][19830] Updated weights for policy 0, policy_version 130 (0.0009)
|
223 |
+
[2024-08-16 15:01:12,264][19830] Updated weights for policy 0, policy_version 140 (0.0009)
|
224 |
+
[2024-08-16 15:01:14,423][09795] Fps is (10 sec: 16793.6, 60 sec: 17320.2, 300 sec: 17320.2). Total num frames: 606208. Throughput: 0: 4290.8. Samples: 150180. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
225 |
+
[2024-08-16 15:01:14,424][09795] Avg episode reward: [(0, '4.590')]
|
226 |
+
[2024-08-16 15:01:14,426][19817] Saving new best policy, reward=4.590!
|
227 |
+
[2024-08-16 15:01:14,726][19830] Updated weights for policy 0, policy_version 150 (0.0009)
|
228 |
+
[2024-08-16 15:01:17,050][19830] Updated weights for policy 0, policy_version 160 (0.0009)
|
229 |
+
[2024-08-16 15:01:19,279][19830] Updated weights for policy 0, policy_version 170 (0.0009)
|
230 |
+
[2024-08-16 15:01:19,423][09795] Fps is (10 sec: 17612.8, 60 sec: 17408.0, 300 sec: 17408.0). Total num frames: 696320. Throughput: 0: 4074.9. Samples: 162998. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
231 |
+
[2024-08-16 15:01:19,424][09795] Avg episode reward: [(0, '4.887')]
|
232 |
+
[2024-08-16 15:01:19,428][19817] Saving new best policy, reward=4.887!
|
233 |
+
[2024-08-16 15:01:21,441][19830] Updated weights for policy 0, policy_version 180 (0.0008)
|
234 |
+
[2024-08-16 15:01:23,683][19830] Updated weights for policy 0, policy_version 190 (0.0008)
|
235 |
+
[2024-08-16 15:01:24,423][09795] Fps is (10 sec: 18432.1, 60 sec: 17567.3, 300 sec: 17567.3). Total num frames: 790528. Throughput: 0: 4244.1. Samples: 190986. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
236 |
+
[2024-08-16 15:01:24,424][09795] Avg episode reward: [(0, '4.891')]
|
237 |
+
[2024-08-16 15:01:24,425][19817] Saving new best policy, reward=4.891!
|
238 |
+
[2024-08-16 15:01:25,941][19830] Updated weights for policy 0, policy_version 200 (0.0009)
|
239 |
+
[2024-08-16 15:01:28,119][19830] Updated weights for policy 0, policy_version 210 (0.0009)
|
240 |
+
[2024-08-16 15:01:29,423][09795] Fps is (10 sec: 18432.1, 60 sec: 17612.8, 300 sec: 17612.8). Total num frames: 880640. Throughput: 0: 4556.1. Samples: 218558. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
241 |
+
[2024-08-16 15:01:29,424][09795] Avg episode reward: [(0, '5.945')]
|
242 |
+
[2024-08-16 15:01:29,457][19817] Saving new best policy, reward=5.945!
|
243 |
+
[2024-08-16 15:01:30,374][19830] Updated weights for policy 0, policy_version 220 (0.0009)
|
244 |
+
[2024-08-16 15:01:32,570][19830] Updated weights for policy 0, policy_version 230 (0.0009)
|
245 |
+
[2024-08-16 15:01:34,423][09795] Fps is (10 sec: 18432.0, 60 sec: 17724.5, 300 sec: 17724.5). Total num frames: 974848. Throughput: 0: 4574.5. Samples: 232306. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
246 |
+
[2024-08-16 15:01:34,425][09795] Avg episode reward: [(0, '7.048')]
|
247 |
+
[2024-08-16 15:01:34,425][19817] Saving new best policy, reward=7.048!
|
248 |
+
[2024-08-16 15:01:34,853][19830] Updated weights for policy 0, policy_version 240 (0.0009)
|
249 |
+
[2024-08-16 15:01:37,021][19830] Updated weights for policy 0, policy_version 250 (0.0008)
|
250 |
+
[2024-08-16 15:01:39,262][19830] Updated weights for policy 0, policy_version 260 (0.0008)
|
251 |
+
[2024-08-16 15:01:39,423][09795] Fps is (10 sec: 18431.9, 60 sec: 17749.3, 300 sec: 17749.3). Total num frames: 1064960. Throughput: 0: 4550.3. Samples: 260002. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
252 |
+
[2024-08-16 15:01:39,424][09795] Avg episode reward: [(0, '6.964')]
|
253 |
+
[2024-08-16 15:01:41,457][19830] Updated weights for policy 0, policy_version 270 (0.0008)
|
254 |
+
[2024-08-16 15:01:43,637][19830] Updated weights for policy 0, policy_version 280 (0.0009)
|
255 |
+
[2024-08-16 15:01:44,423][09795] Fps is (10 sec: 18431.9, 60 sec: 18295.5, 300 sec: 17833.3). Total num frames: 1159168. Throughput: 0: 4537.0. Samples: 287726. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
256 |
+
[2024-08-16 15:01:44,424][09795] Avg episode reward: [(0, '9.357')]
|
257 |
+
[2024-08-16 15:01:44,425][19817] Saving new best policy, reward=9.357!
|
258 |
+
[2024-08-16 15:01:45,922][19830] Updated weights for policy 0, policy_version 290 (0.0009)
|
259 |
+
[2024-08-16 15:01:48,081][19830] Updated weights for policy 0, policy_version 300 (0.0008)
|
260 |
+
[2024-08-16 15:01:49,423][09795] Fps is (10 sec: 18432.1, 60 sec: 18295.5, 300 sec: 17846.9). Total num frames: 1249280. Throughput: 0: 4518.2. Samples: 301476. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
261 |
+
[2024-08-16 15:01:49,424][09795] Avg episode reward: [(0, '7.852')]
|
262 |
+
[2024-08-16 15:01:50,349][19830] Updated weights for policy 0, policy_version 310 (0.0008)
|
263 |
+
[2024-08-16 15:01:52,544][19830] Updated weights for policy 0, policy_version 320 (0.0008)
|
264 |
+
[2024-08-16 15:01:54,423][09795] Fps is (10 sec: 18432.0, 60 sec: 18227.2, 300 sec: 17913.2). Total num frames: 1343488. Throughput: 0: 4549.2. Samples: 329246. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
265 |
+
[2024-08-16 15:01:54,424][09795] Avg episode reward: [(0, '9.561')]
|
266 |
+
[2024-08-16 15:01:54,425][19817] Saving new best policy, reward=9.561!
|
267 |
+
[2024-08-16 15:01:54,789][19830] Updated weights for policy 0, policy_version 330 (0.0008)
|
268 |
+
[2024-08-16 15:01:56,970][19830] Updated weights for policy 0, policy_version 340 (0.0009)
|
269 |
+
[2024-08-16 15:01:59,148][19830] Updated weights for policy 0, policy_version 350 (0.0009)
|
270 |
+
[2024-08-16 15:01:59,423][09795] Fps is (10 sec: 18432.0, 60 sec: 18158.9, 300 sec: 17920.0). Total num frames: 1433600. Throughput: 0: 4596.9. Samples: 357040. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
271 |
+
[2024-08-16 15:01:59,424][09795] Avg episode reward: [(0, '10.780')]
|
272 |
+
[2024-08-16 15:01:59,428][19817] Saving new best policy, reward=10.780!
|
273 |
+
[2024-08-16 15:02:01,442][19830] Updated weights for policy 0, policy_version 360 (0.0008)
|
274 |
+
[2024-08-16 15:02:03,728][19830] Updated weights for policy 0, policy_version 370 (0.0009)
|
275 |
+
[2024-08-16 15:02:04,423][09795] Fps is (10 sec: 18021.9, 60 sec: 18090.6, 300 sec: 17926.0). Total num frames: 1523712. Throughput: 0: 4618.8. Samples: 370844. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
276 |
+
[2024-08-16 15:02:04,424][09795] Avg episode reward: [(0, '10.450')]
|
277 |
+
[2024-08-16 15:02:06,271][19830] Updated weights for policy 0, policy_version 380 (0.0009)
|
278 |
+
[2024-08-16 15:02:08,626][19830] Updated weights for policy 0, policy_version 390 (0.0009)
|
279 |
+
[2024-08-16 15:02:09,423][09795] Fps is (10 sec: 17612.7, 60 sec: 18158.9, 300 sec: 17885.9). Total num frames: 1609728. Throughput: 0: 4559.1. Samples: 396144. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
280 |
+
[2024-08-16 15:02:09,424][09795] Avg episode reward: [(0, '11.546')]
|
281 |
+
[2024-08-16 15:02:09,427][19817] Saving new best policy, reward=11.546!
|
282 |
+
[2024-08-16 15:02:11,006][19830] Updated weights for policy 0, policy_version 400 (0.0009)
|
283 |
+
[2024-08-16 15:02:13,467][19830] Updated weights for policy 0, policy_version 410 (0.0009)
|
284 |
+
[2024-08-16 15:02:14,423][09795] Fps is (10 sec: 16794.0, 60 sec: 18090.7, 300 sec: 17806.8). Total num frames: 1691648. Throughput: 0: 4514.2. Samples: 421696. Policy #0 lag: (min: 0.0, avg: 0.3, max: 1.0)
|
285 |
+
[2024-08-16 15:02:14,424][09795] Avg episode reward: [(0, '13.300')]
|
286 |
+
[2024-08-16 15:02:14,425][19817] Saving new best policy, reward=13.300!
|
287 |
+
[2024-08-16 15:02:16,030][19830] Updated weights for policy 0, policy_version 420 (0.0010)
|
288 |
+
[2024-08-16 15:02:18,673][19830] Updated weights for policy 0, policy_version 430 (0.0009)
|
289 |
+
[2024-08-16 15:02:19,423][09795] Fps is (10 sec: 16384.2, 60 sec: 17954.2, 300 sec: 17735.7). Total num frames: 1773568. Throughput: 0: 4463.8. Samples: 433178. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
290 |
+
[2024-08-16 15:02:19,424][09795] Avg episode reward: [(0, '10.660')]
|
291 |
+
[2024-08-16 15:02:21,021][19830] Updated weights for policy 0, policy_version 440 (0.0009)
|
292 |
+
[2024-08-16 15:02:23,368][19830] Updated weights for policy 0, policy_version 450 (0.0008)
|
293 |
+
[2024-08-16 15:02:24,423][09795] Fps is (10 sec: 16793.6, 60 sec: 17817.6, 300 sec: 17710.3). Total num frames: 1859584. Throughput: 0: 4417.4. Samples: 458786. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
294 |
+
[2024-08-16 15:02:24,424][09795] Avg episode reward: [(0, '15.219')]
|
295 |
+
[2024-08-16 15:02:24,465][19817] Saving new best policy, reward=15.219!
|
296 |
+
[2024-08-16 15:02:25,656][19830] Updated weights for policy 0, policy_version 460 (0.0010)
|
297 |
+
[2024-08-16 15:02:28,006][19830] Updated weights for policy 0, policy_version 470 (0.0009)
|
298 |
+
[2024-08-16 15:02:29,423][09795] Fps is (10 sec: 17612.6, 60 sec: 17817.6, 300 sec: 17724.5). Total num frames: 1949696. Throughput: 0: 4392.5. Samples: 485388. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
299 |
+
[2024-08-16 15:02:29,424][09795] Avg episode reward: [(0, '15.121')]
|
300 |
+
[2024-08-16 15:02:29,428][19817] Saving /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000476_1949696.pth...
|
301 |
+
[2024-08-16 15:02:30,305][19830] Updated weights for policy 0, policy_version 480 (0.0009)
|
302 |
+
[2024-08-16 15:02:32,595][19830] Updated weights for policy 0, policy_version 490 (0.0009)
|
303 |
+
[2024-08-16 15:02:34,423][09795] Fps is (10 sec: 17613.0, 60 sec: 17681.1, 300 sec: 17701.9). Total num frames: 2035712. Throughput: 0: 4380.4. Samples: 498594. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
304 |
+
[2024-08-16 15:02:34,424][09795] Avg episode reward: [(0, '17.719')]
|
305 |
+
[2024-08-16 15:02:34,425][19817] Saving new best policy, reward=17.719!
|
306 |
+
[2024-08-16 15:02:34,965][19830] Updated weights for policy 0, policy_version 500 (0.0009)
|
307 |
+
[2024-08-16 15:02:37,288][19830] Updated weights for policy 0, policy_version 510 (0.0009)
|
308 |
+
[2024-08-16 15:02:39,423][09795] Fps is (10 sec: 17203.4, 60 sec: 17612.8, 300 sec: 17681.1). Total num frames: 2121728. Throughput: 0: 4347.0. Samples: 524862. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
309 |
+
[2024-08-16 15:02:39,424][09795] Avg episode reward: [(0, '16.486')]
|
310 |
+
[2024-08-16 15:02:39,678][19830] Updated weights for policy 0, policy_version 520 (0.0009)
|
311 |
+
[2024-08-16 15:02:41,968][19830] Updated weights for policy 0, policy_version 530 (0.0009)
|
312 |
+
[2024-08-16 15:02:44,337][19830] Updated weights for policy 0, policy_version 540 (0.0009)
|
313 |
+
[2024-08-16 15:02:44,423][09795] Fps is (10 sec: 17612.7, 60 sec: 17544.5, 300 sec: 17694.7). Total num frames: 2211840. Throughput: 0: 4313.9. Samples: 551164. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
314 |
+
[2024-08-16 15:02:44,424][09795] Avg episode reward: [(0, '15.403')]
|
315 |
+
[2024-08-16 15:02:46,708][19830] Updated weights for policy 0, policy_version 550 (0.0009)
|
316 |
+
[2024-08-16 15:02:49,383][19830] Updated weights for policy 0, policy_version 560 (0.0010)
|
317 |
+
[2024-08-16 15:02:49,423][09795] Fps is (10 sec: 17203.1, 60 sec: 17408.0, 300 sec: 17644.3). Total num frames: 2293760. Throughput: 0: 4293.9. Samples: 564066. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
318 |
+
[2024-08-16 15:02:49,424][09795] Avg episode reward: [(0, '15.907')]
|
319 |
+
[2024-08-16 15:02:52,067][19830] Updated weights for policy 0, policy_version 570 (0.0010)
|
320 |
+
[2024-08-16 15:02:54,365][19830] Updated weights for policy 0, policy_version 580 (0.0008)
|
321 |
+
[2024-08-16 15:02:54,423][09795] Fps is (10 sec: 16384.0, 60 sec: 17203.2, 300 sec: 17597.6). Total num frames: 2375680. Throughput: 0: 4246.0. Samples: 587212. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
322 |
+
[2024-08-16 15:02:54,424][09795] Avg episode reward: [(0, '19.519')]
|
323 |
+
[2024-08-16 15:02:54,425][19817] Saving new best policy, reward=19.519!
|
324 |
+
[2024-08-16 15:02:56,821][19830] Updated weights for policy 0, policy_version 590 (0.0009)
|
325 |
+
[2024-08-16 15:02:59,423][09795] Fps is (10 sec: 15974.3, 60 sec: 16998.4, 300 sec: 17525.0). Total num frames: 2453504. Throughput: 0: 4218.4. Samples: 611524. Policy #0 lag: (min: 0.0, avg: 0.7, max: 1.0)
|
326 |
+
[2024-08-16 15:02:59,424][09795] Avg episode reward: [(0, '18.098')]
|
327 |
+
[2024-08-16 15:02:59,662][19830] Updated weights for policy 0, policy_version 600 (0.0010)
|
328 |
+
[2024-08-16 15:03:02,145][19830] Updated weights for policy 0, policy_version 610 (0.0009)
|
329 |
+
[2024-08-16 15:03:04,423][09795] Fps is (10 sec: 15564.5, 60 sec: 16793.6, 300 sec: 17457.4). Total num frames: 2531328. Throughput: 0: 4236.4. Samples: 623818. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
330 |
+
[2024-08-16 15:03:04,424][09795] Avg episode reward: [(0, '16.211')]
|
331 |
+
[2024-08-16 15:03:04,946][19830] Updated weights for policy 0, policy_version 620 (0.0010)
|
332 |
+
[2024-08-16 15:03:07,359][19830] Updated weights for policy 0, policy_version 630 (0.0010)
|
333 |
+
[2024-08-16 15:03:09,423][09795] Fps is (10 sec: 15564.8, 60 sec: 16657.1, 300 sec: 17394.3). Total num frames: 2609152. Throughput: 0: 4190.5. Samples: 647360. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
334 |
+
[2024-08-16 15:03:09,424][09795] Avg episode reward: [(0, '16.607')]
|
335 |
+
[2024-08-16 15:03:09,991][19830] Updated weights for policy 0, policy_version 640 (0.0010)
|
336 |
+
[2024-08-16 15:03:13,072][19830] Updated weights for policy 0, policy_version 650 (0.0011)
|
337 |
+
[2024-08-16 15:03:14,423][09795] Fps is (10 sec: 15155.6, 60 sec: 16520.6, 300 sec: 17308.9). Total num frames: 2682880. Throughput: 0: 4073.9. Samples: 668714. Policy #0 lag: (min: 0.0, avg: 0.7, max: 2.0)
|
338 |
+
[2024-08-16 15:03:14,424][09795] Avg episode reward: [(0, '18.533')]
|
339 |
+
[2024-08-16 15:03:15,651][19830] Updated weights for policy 0, policy_version 660 (0.0010)
|
340 |
+
[2024-08-16 15:03:18,195][19830] Updated weights for policy 0, policy_version 670 (0.0010)
|
341 |
+
[2024-08-16 15:03:19,423][09795] Fps is (10 sec: 15155.2, 60 sec: 16452.2, 300 sec: 17254.4). Total num frames: 2760704. Throughput: 0: 4053.6. Samples: 681006. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
342 |
+
[2024-08-16 15:03:19,424][09795] Avg episode reward: [(0, '20.754')]
|
343 |
+
[2024-08-16 15:03:19,429][19817] Saving new best policy, reward=20.754!
|
344 |
+
[2024-08-16 15:03:21,009][19830] Updated weights for policy 0, policy_version 680 (0.0010)
|
345 |
+
[2024-08-16 15:03:23,683][19830] Updated weights for policy 0, policy_version 690 (0.0011)
|
346 |
+
[2024-08-16 15:03:24,423][09795] Fps is (10 sec: 15154.9, 60 sec: 16247.4, 300 sec: 17178.4). Total num frames: 2834432. Throughput: 0: 3975.9. Samples: 703780. Policy #0 lag: (min: 0.0, avg: 0.4, max: 2.0)
|
347 |
+
[2024-08-16 15:03:24,425][09795] Avg episode reward: [(0, '22.080')]
|
348 |
+
[2024-08-16 15:03:24,426][19817] Saving new best policy, reward=22.080!
|
349 |
+
[2024-08-16 15:03:26,418][19830] Updated weights for policy 0, policy_version 700 (0.0010)
|
350 |
+
[2024-08-16 15:03:29,121][19830] Updated weights for policy 0, policy_version 710 (0.0009)
|
351 |
+
[2024-08-16 15:03:29,423][09795] Fps is (10 sec: 15154.8, 60 sec: 16042.6, 300 sec: 17130.9). Total num frames: 2912256. Throughput: 0: 3893.7. Samples: 726382. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
352 |
+
[2024-08-16 15:03:29,425][09795] Avg episode reward: [(0, '20.974')]
|
353 |
+
[2024-08-16 15:03:31,752][19830] Updated weights for policy 0, policy_version 720 (0.0009)
|
354 |
+
[2024-08-16 15:03:34,424][09795] Fps is (10 sec: 15153.4, 60 sec: 15837.5, 300 sec: 17062.6). Total num frames: 2985984. Throughput: 0: 3860.5. Samples: 737792. Policy #0 lag: (min: 0.0, avg: 0.4, max: 1.0)
|
355 |
+
[2024-08-16 15:03:34,426][09795] Avg episode reward: [(0, '21.284')]
|
356 |
+
[2024-08-16 15:03:34,553][19830] Updated weights for policy 0, policy_version 730 (0.0010)
|
357 |
+
[2024-08-16 15:03:37,150][19830] Updated weights for policy 0, policy_version 740 (0.0010)
|
358 |
+
[2024-08-16 15:03:39,423][09795] Fps is (10 sec: 15154.8, 60 sec: 15701.2, 300 sec: 17021.1). Total num frames: 3063808. Throughput: 0: 3855.2. Samples: 760696. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
359 |
+
[2024-08-16 15:03:39,425][09795] Avg episode reward: [(0, '21.944')]
|
360 |
+
[2024-08-16 15:03:39,844][19830] Updated weights for policy 0, policy_version 750 (0.0010)
|
361 |
+
[2024-08-16 15:03:42,687][19830] Updated weights for policy 0, policy_version 760 (0.0011)
|
362 |
+
[2024-08-16 15:03:44,423][09795] Fps is (10 sec: 15157.1, 60 sec: 15428.2, 300 sec: 16959.6). Total num frames: 3137536. Throughput: 0: 3809.6. Samples: 782956. Policy #0 lag: (min: 0.0, avg: 0.6, max: 2.0)
|
363 |
+
[2024-08-16 15:03:44,424][09795] Avg episode reward: [(0, '25.046')]
|
364 |
+
[2024-08-16 15:03:44,425][19817] Saving new best policy, reward=25.046!
|
365 |
+
[2024-08-16 15:03:45,540][19830] Updated weights for policy 0, policy_version 770 (0.0010)
|
366 |
+
[2024-08-16 15:03:48,303][19830] Updated weights for policy 0, policy_version 780 (0.0010)
|
367 |
+
[2024-08-16 15:03:49,423][09795] Fps is (10 sec: 14746.4, 60 sec: 15291.7, 300 sec: 16901.4). Total num frames: 3211264. Throughput: 0: 3763.1. Samples: 793156. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
368 |
+
[2024-08-16 15:03:49,424][09795] Avg episode reward: [(0, '23.080')]
|
369 |
+
[2024-08-16 15:03:50,601][19830] Updated weights for policy 0, policy_version 790 (0.0009)
|
370 |
+
[2024-08-16 15:03:52,885][19830] Updated weights for policy 0, policy_version 800 (0.0009)
|
371 |
+
[2024-08-16 15:03:54,423][09795] Fps is (10 sec: 16384.0, 60 sec: 15428.2, 300 sec: 16930.1). Total num frames: 3301376. Throughput: 0: 3822.4. Samples: 819368. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
372 |
+
[2024-08-16 15:03:54,424][09795] Avg episode reward: [(0, '24.139')]
|
373 |
+
[2024-08-16 15:03:55,423][19830] Updated weights for policy 0, policy_version 810 (0.0010)
|
374 |
+
[2024-08-16 15:03:58,170][19830] Updated weights for policy 0, policy_version 820 (0.0011)
|
375 |
+
[2024-08-16 15:03:59,423][09795] Fps is (10 sec: 16793.2, 60 sec: 15428.2, 300 sec: 16896.0). Total num frames: 3379200. Throughput: 0: 3869.4. Samples: 842838. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
376 |
+
[2024-08-16 15:03:59,425][09795] Avg episode reward: [(0, '20.764')]
|
377 |
+
[2024-08-16 15:04:00,629][19830] Updated weights for policy 0, policy_version 830 (0.0010)
|
378 |
+
[2024-08-16 15:04:02,983][19830] Updated weights for policy 0, policy_version 840 (0.0009)
|
379 |
+
[2024-08-16 15:04:04,423][09795] Fps is (10 sec: 15974.5, 60 sec: 15496.6, 300 sec: 16883.5). Total num frames: 3461120. Throughput: 0: 3880.0. Samples: 855606. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
380 |
+
[2024-08-16 15:04:04,424][09795] Avg episode reward: [(0, '19.982')]
|
381 |
+
[2024-08-16 15:04:05,383][19830] Updated weights for policy 0, policy_version 850 (0.0009)
|
382 |
+
[2024-08-16 15:04:07,772][19830] Updated weights for policy 0, policy_version 860 (0.0009)
|
383 |
+
[2024-08-16 15:04:09,423][09795] Fps is (10 sec: 16793.2, 60 sec: 15632.9, 300 sec: 16891.1). Total num frames: 3547136. Throughput: 0: 3942.0. Samples: 881170. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
384 |
+
[2024-08-16 15:04:09,425][09795] Avg episode reward: [(0, '22.320')]
|
385 |
+
[2024-08-16 15:04:10,261][19830] Updated weights for policy 0, policy_version 870 (0.0010)
|
386 |
+
[2024-08-16 15:04:12,692][19830] Updated weights for policy 0, policy_version 880 (0.0009)
|
387 |
+
[2024-08-16 15:04:14,423][09795] Fps is (10 sec: 16793.5, 60 sec: 15769.5, 300 sec: 16879.3). Total num frames: 3629056. Throughput: 0: 3994.8. Samples: 906146. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
388 |
+
[2024-08-16 15:04:14,425][09795] Avg episode reward: [(0, '21.940')]
|
389 |
+
[2024-08-16 15:04:15,376][19830] Updated weights for policy 0, policy_version 890 (0.0010)
|
390 |
+
[2024-08-16 15:04:18,126][19830] Updated weights for policy 0, policy_version 900 (0.0010)
|
391 |
+
[2024-08-16 15:04:19,423][09795] Fps is (10 sec: 15975.2, 60 sec: 15769.6, 300 sec: 16849.5). Total num frames: 3706880. Throughput: 0: 3986.6. Samples: 917182. Policy #0 lag: (min: 0.0, avg: 0.6, max: 1.0)
|
392 |
+
[2024-08-16 15:04:19,424][09795] Avg episode reward: [(0, '23.776')]
|
393 |
+
[2024-08-16 15:04:20,599][19830] Updated weights for policy 0, policy_version 910 (0.0010)
|
394 |
+
[2024-08-16 15:04:23,316][19830] Updated weights for policy 0, policy_version 920 (0.0010)
|
395 |
+
[2024-08-16 15:04:24,423][09795] Fps is (10 sec: 15565.0, 60 sec: 15837.9, 300 sec: 16820.9). Total num frames: 3784704. Throughput: 0: 3997.4. Samples: 940576. Policy #0 lag: (min: 0.0, avg: 0.5, max: 2.0)
|
396 |
+
[2024-08-16 15:04:24,424][09795] Avg episode reward: [(0, '23.407')]
|
397 |
+
[2024-08-16 15:04:25,887][19830] Updated weights for policy 0, policy_version 930 (0.0010)
|
398 |
+
[2024-08-16 15:04:28,613][19830] Updated weights for policy 0, policy_version 940 (0.0009)
|
399 |
+
[2024-08-16 15:04:29,423][09795] Fps is (10 sec: 15564.8, 60 sec: 15838.0, 300 sec: 16793.6). Total num frames: 3862528. Throughput: 0: 4019.9. Samples: 963852. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
400 |
+
[2024-08-16 15:04:29,424][09795] Avg episode reward: [(0, '19.884')]
|
401 |
+
[2024-08-16 15:04:29,429][19817] Saving /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000943_3862528.pth...
|
402 |
+
[2024-08-16 15:04:31,179][19830] Updated weights for policy 0, policy_version 950 (0.0010)
|
403 |
+
[2024-08-16 15:04:33,747][19830] Updated weights for policy 0, policy_version 960 (0.0010)
|
404 |
+
[2024-08-16 15:04:34,423][09795] Fps is (10 sec: 15564.9, 60 sec: 15906.5, 300 sec: 16767.5). Total num frames: 3940352. Throughput: 0: 4055.8. Samples: 975668. Policy #0 lag: (min: 0.0, avg: 0.5, max: 1.0)
|
405 |
+
[2024-08-16 15:04:34,424][09795] Avg episode reward: [(0, '20.892')]
|
406 |
+
[2024-08-16 15:04:36,281][19830] Updated weights for policy 0, policy_version 970 (0.0009)
|
407 |
+
[2024-08-16 15:04:38,262][19817] Stopping Batcher_0...
|
408 |
+
[2024-08-16 15:04:38,263][19817] Loop batcher_evt_loop terminating...
|
409 |
+
[2024-08-16 15:04:38,263][19817] Saving /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
410 |
+
[2024-08-16 15:04:38,267][09795] Component Batcher_0 stopped!
|
411 |
+
[2024-08-16 15:04:38,270][09795] Component RolloutWorker_w3 process died already! Don't wait for it.
|
412 |
+
[2024-08-16 15:04:38,276][19835] Stopping RolloutWorker_w2...
|
413 |
+
[2024-08-16 15:04:38,276][19836] Stopping RolloutWorker_w6...
|
414 |
+
[2024-08-16 15:04:38,276][19831] Stopping RolloutWorker_w0...
|
415 |
+
[2024-08-16 15:04:38,276][19836] Loop rollout_proc6_evt_loop terminating...
|
416 |
+
[2024-08-16 15:04:38,277][19838] Stopping RolloutWorker_w5...
|
417 |
+
[2024-08-16 15:04:38,277][19831] Loop rollout_proc0_evt_loop terminating...
|
418 |
+
[2024-08-16 15:04:38,277][19835] Loop rollout_proc2_evt_loop terminating...
|
419 |
+
[2024-08-16 15:04:38,277][19838] Loop rollout_proc5_evt_loop terminating...
|
420 |
+
[2024-08-16 15:04:38,277][19837] Stopping RolloutWorker_w7...
|
421 |
+
[2024-08-16 15:04:38,278][19837] Loop rollout_proc7_evt_loop terminating...
|
422 |
+
[2024-08-16 15:04:38,276][09795] Component RolloutWorker_w2 stopped!
|
423 |
+
[2024-08-16 15:04:38,280][19834] Stopping RolloutWorker_w4...
|
424 |
+
[2024-08-16 15:04:38,282][19833] Stopping RolloutWorker_w1...
|
425 |
+
[2024-08-16 15:04:38,282][19834] Loop rollout_proc4_evt_loop terminating...
|
426 |
+
[2024-08-16 15:04:38,282][19833] Loop rollout_proc1_evt_loop terminating...
|
427 |
+
[2024-08-16 15:04:38,280][09795] Component RolloutWorker_w6 stopped!
|
428 |
+
[2024-08-16 15:04:38,284][19830] Weights refcount: 2 0
|
429 |
+
[2024-08-16 15:04:38,284][09795] Component RolloutWorker_w0 stopped!
|
430 |
+
[2024-08-16 15:04:38,285][19830] Stopping InferenceWorker_p0-w0...
|
431 |
+
[2024-08-16 15:04:38,286][19830] Loop inference_proc0-0_evt_loop terminating...
|
432 |
+
[2024-08-16 15:04:38,285][09795] Component RolloutWorker_w5 stopped!
|
433 |
+
[2024-08-16 15:04:38,288][09795] Component RolloutWorker_w7 stopped!
|
434 |
+
[2024-08-16 15:04:38,290][09795] Component RolloutWorker_w4 stopped!
|
435 |
+
[2024-08-16 15:04:38,293][09795] Component RolloutWorker_w1 stopped!
|
436 |
+
[2024-08-16 15:04:38,295][09795] Component InferenceWorker_p0-w0 stopped!
|
437 |
+
[2024-08-16 15:04:38,333][19817] Removing /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000476_1949696.pth
|
438 |
+
[2024-08-16 15:04:38,341][19817] Saving /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
439 |
+
[2024-08-16 15:04:38,422][19817] Stopping LearnerWorker_p0...
|
440 |
+
[2024-08-16 15:04:38,423][19817] Loop learner_proc0_evt_loop terminating...
|
441 |
+
[2024-08-16 15:04:38,423][09795] Component LearnerWorker_p0 stopped!
|
442 |
+
[2024-08-16 15:04:38,425][09795] Waiting for process learner_proc0 to stop...
|
443 |
+
[2024-08-16 15:04:39,321][09795] Waiting for process inference_proc0-0 to join...
|
444 |
+
[2024-08-16 15:04:39,322][09795] Waiting for process rollout_proc0 to join...
|
445 |
+
[2024-08-16 15:04:39,322][09795] Waiting for process rollout_proc1 to join...
|
446 |
+
[2024-08-16 15:04:39,323][09795] Waiting for process rollout_proc2 to join...
|
447 |
+
[2024-08-16 15:04:39,323][09795] Waiting for process rollout_proc3 to join...
|
448 |
+
[2024-08-16 15:04:39,324][09795] Waiting for process rollout_proc4 to join...
|
449 |
+
[2024-08-16 15:04:39,324][09795] Waiting for process rollout_proc5 to join...
|
450 |
+
[2024-08-16 15:04:39,324][09795] Waiting for process rollout_proc6 to join...
|
451 |
+
[2024-08-16 15:04:39,325][09795] Waiting for process rollout_proc7 to join...
|
452 |
+
[2024-08-16 15:04:39,325][09795] Batcher 0 profile tree view:
|
453 |
+
batching: 12.0359, releasing_batches: 0.0294
|
454 |
+
[2024-08-16 15:04:39,325][09795] InferenceWorker_p0-w0 profile tree view:
|
455 |
+
wait_policy: 0.0000
|
456 |
+
wait_policy_total: 3.0779
|
457 |
+
update_model: 3.7110
|
458 |
+
weight_update: 0.0010
|
459 |
+
one_step: 0.0030
|
460 |
+
handle_policy_step: 222.3845
|
461 |
+
deserialize: 8.3652, stack: 1.3086, obs_to_device_normalize: 54.2507, forward: 114.7561, send_messages: 10.5792
|
462 |
+
prepare_outputs: 24.1736
|
463 |
+
to_cpu: 14.5914
|
464 |
+
[2024-08-16 15:04:39,326][09795] Learner 0 profile tree view:
|
465 |
+
misc: 0.0043, prepare_batch: 12.4152
|
466 |
+
train: 39.1134
|
467 |
+
epoch_init: 0.0042, minibatch_init: 0.0059, losses_postprocess: 0.2538, kl_divergence: 0.2299, after_optimizer: 19.6184
|
468 |
+
calculate_losses: 13.0556
|
469 |
+
losses_init: 0.0022, forward_head: 0.8085, bptt_initial: 9.7676, tail: 0.5032, advantages_returns: 0.1281, losses: 0.8480
|
470 |
+
bptt: 0.8324
|
471 |
+
bptt_forward_core: 0.7901
|
472 |
+
update: 5.5965
|
473 |
+
clip: 0.6016
|
474 |
+
[2024-08-16 15:04:39,326][09795] RolloutWorker_w0 profile tree view:
|
475 |
+
wait_for_trajectories: 0.1335, enqueue_policy_requests: 8.5325, env_step: 100.0188, overhead: 11.2157, complete_rollouts: 0.2483
|
476 |
+
save_policy_outputs: 8.6007
|
477 |
+
split_output_tensors: 4.1162
|
478 |
+
[2024-08-16 15:04:39,326][09795] RolloutWorker_w7 profile tree view:
|
479 |
+
wait_for_trajectories: 0.1288, enqueue_policy_requests: 8.5215, env_step: 100.0412, overhead: 11.4728, complete_rollouts: 0.2583
|
480 |
+
save_policy_outputs: 8.5721
|
481 |
+
split_output_tensors: 4.0914
|
482 |
+
[2024-08-16 15:04:39,327][09795] Loop Runner_EvtLoop terminating...
|
483 |
+
[2024-08-16 15:04:39,327][09795] Runner profile tree view:
|
484 |
+
main_loop: 245.5234
|
485 |
+
[2024-08-16 15:04:39,327][09795] Collected {0: 4005888}, FPS: 16315.7
|
486 |
+
[2024-08-16 15:07:42,139][09795] Loading existing experiment configuration from /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/config.json
|
487 |
+
[2024-08-16 15:07:42,140][09795] Overriding arg 'num_workers' with value 1 passed from command line
|
488 |
+
[2024-08-16 15:07:42,140][09795] Adding new argument 'no_render'=True that is not in the saved config file!
|
489 |
+
[2024-08-16 15:07:42,141][09795] Adding new argument 'save_video'=True that is not in the saved config file!
|
490 |
+
[2024-08-16 15:07:42,141][09795] Adding new argument 'video_frames'=1000000000.0 that is not in the saved config file!
|
491 |
+
[2024-08-16 15:07:42,141][09795] Adding new argument 'video_name'=None that is not in the saved config file!
|
492 |
+
[2024-08-16 15:07:42,141][09795] Adding new argument 'max_num_frames'=1000000000.0 that is not in the saved config file!
|
493 |
+
[2024-08-16 15:07:42,142][09795] Adding new argument 'max_num_episodes'=10 that is not in the saved config file!
|
494 |
+
[2024-08-16 15:07:42,142][09795] Adding new argument 'push_to_hub'=False that is not in the saved config file!
|
495 |
+
[2024-08-16 15:07:42,142][09795] Adding new argument 'hf_repository'=None that is not in the saved config file!
|
496 |
+
[2024-08-16 15:07:42,143][09795] Adding new argument 'policy_index'=0 that is not in the saved config file!
|
497 |
+
[2024-08-16 15:07:42,143][09795] Adding new argument 'eval_deterministic'=False that is not in the saved config file!
|
498 |
+
[2024-08-16 15:07:42,144][09795] Adding new argument 'train_script'=None that is not in the saved config file!
|
499 |
+
[2024-08-16 15:07:42,144][09795] Adding new argument 'enjoy_script'=None that is not in the saved config file!
|
500 |
+
[2024-08-16 15:07:42,144][09795] Using frameskip 1 and render_action_repeat=4 for evaluation
|
501 |
+
[2024-08-16 15:07:42,162][09795] Doom resolution: 160x120, resize resolution: (128, 72)
|
502 |
+
[2024-08-16 15:07:42,164][09795] RunningMeanStd input shape: (3, 72, 128)
|
503 |
+
[2024-08-16 15:07:42,165][09795] RunningMeanStd input shape: (1,)
|
504 |
+
[2024-08-16 15:07:42,175][09795] ConvEncoder: input_channels=3
|
505 |
+
[2024-08-16 15:07:42,252][09795] Conv encoder output size: 512
|
506 |
+
[2024-08-16 15:07:42,253][09795] Policy head output size: 512
|
507 |
+
[2024-08-16 15:07:43,859][09795] Loading state from checkpoint /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/checkpoint_p0/checkpoint_000000978_4005888.pth...
|
508 |
+
[2024-08-16 15:07:44,321][09795] Num frames 100...
|
509 |
+
[2024-08-16 15:07:44,402][09795] Num frames 200...
|
510 |
+
[2024-08-16 15:07:44,485][09795] Num frames 300...
|
511 |
+
[2024-08-16 15:07:44,564][09795] Num frames 400...
|
512 |
+
[2024-08-16 15:07:44,642][09795] Num frames 500...
|
513 |
+
[2024-08-16 15:07:44,720][09795] Num frames 600...
|
514 |
+
[2024-08-16 15:07:44,820][09795] Num frames 700...
|
515 |
+
[2024-08-16 15:07:44,906][09795] Num frames 800...
|
516 |
+
[2024-08-16 15:07:44,991][09795] Num frames 900...
|
517 |
+
[2024-08-16 15:07:45,073][09795] Num frames 1000...
|
518 |
+
[2024-08-16 15:07:45,157][09795] Num frames 1100...
|
519 |
+
[2024-08-16 15:07:45,242][09795] Num frames 1200...
|
520 |
+
[2024-08-16 15:07:45,343][09795] Avg episode rewards: #0: 26.480, true rewards: #0: 12.480
|
521 |
+
[2024-08-16 15:07:45,344][09795] Avg episode reward: 26.480, avg true_objective: 12.480
|
522 |
+
[2024-08-16 15:07:45,388][09795] Num frames 1300...
|
523 |
+
[2024-08-16 15:07:45,468][09795] Num frames 1400...
|
524 |
+
[2024-08-16 15:07:45,549][09795] Num frames 1500...
|
525 |
+
[2024-08-16 15:07:45,630][09795] Num frames 1600...
|
526 |
+
[2024-08-16 15:07:45,707][09795] Num frames 1700...
|
527 |
+
[2024-08-16 15:07:45,786][09795] Num frames 1800...
|
528 |
+
[2024-08-16 15:07:45,866][09795] Num frames 1900...
|
529 |
+
[2024-08-16 15:07:45,948][09795] Num frames 2000...
|
530 |
+
[2024-08-16 15:07:46,029][09795] Num frames 2100...
|
531 |
+
[2024-08-16 15:07:46,109][09795] Num frames 2200...
|
532 |
+
[2024-08-16 15:07:46,185][09795] Num frames 2300...
|
533 |
+
[2024-08-16 15:07:46,264][09795] Num frames 2400...
|
534 |
+
[2024-08-16 15:07:46,345][09795] Num frames 2500...
|
535 |
+
[2024-08-16 15:07:46,426][09795] Num frames 2600...
|
536 |
+
[2024-08-16 15:07:46,507][09795] Num frames 2700...
|
537 |
+
[2024-08-16 15:07:46,586][09795] Num frames 2800...
|
538 |
+
[2024-08-16 15:07:46,665][09795] Num frames 2900...
|
539 |
+
[2024-08-16 15:07:46,756][09795] Avg episode rewards: #0: 30.720, true rewards: #0: 14.720
|
540 |
+
[2024-08-16 15:07:46,757][09795] Avg episode reward: 30.720, avg true_objective: 14.720
|
541 |
+
[2024-08-16 15:07:46,807][09795] Num frames 3000...
|
542 |
+
[2024-08-16 15:07:46,885][09795] Num frames 3100...
|
543 |
+
[2024-08-16 15:07:46,963][09795] Num frames 3200...
|
544 |
+
[2024-08-16 15:07:47,037][09795] Num frames 3300...
|
545 |
+
[2024-08-16 15:07:47,115][09795] Num frames 3400...
|
546 |
+
[2024-08-16 15:07:47,193][09795] Num frames 3500...
|
547 |
+
[2024-08-16 15:07:47,271][09795] Num frames 3600...
|
548 |
+
[2024-08-16 15:07:47,336][09795] Avg episode rewards: #0: 24.053, true rewards: #0: 12.053
|
549 |
+
[2024-08-16 15:07:47,337][09795] Avg episode reward: 24.053, avg true_objective: 12.053
|
550 |
+
[2024-08-16 15:07:47,400][09795] Num frames 3700...
|
551 |
+
[2024-08-16 15:07:47,476][09795] Num frames 3800...
|
552 |
+
[2024-08-16 15:07:47,551][09795] Num frames 3900...
|
553 |
+
[2024-08-16 15:07:47,632][09795] Num frames 4000...
|
554 |
+
[2024-08-16 15:07:47,708][09795] Num frames 4100...
|
555 |
+
[2024-08-16 15:07:47,783][09795] Num frames 4200...
|
556 |
+
[2024-08-16 15:07:47,859][09795] Num frames 4300...
|
557 |
+
[2024-08-16 15:07:47,938][09795] Num frames 4400...
|
558 |
+
[2024-08-16 15:07:48,017][09795] Num frames 4500...
|
559 |
+
[2024-08-16 15:07:48,094][09795] Num frames 4600...
|
560 |
+
[2024-08-16 15:07:48,168][09795] Num frames 4700...
|
561 |
+
[2024-08-16 15:07:48,244][09795] Num frames 4800...
|
562 |
+
[2024-08-16 15:07:48,319][09795] Num frames 4900...
|
563 |
+
[2024-08-16 15:07:48,395][09795] Num frames 5000...
|
564 |
+
[2024-08-16 15:07:48,515][09795] Avg episode rewards: #0: 27.220, true rewards: #0: 12.720
|
565 |
+
[2024-08-16 15:07:48,516][09795] Avg episode reward: 27.220, avg true_objective: 12.720
|
566 |
+
[2024-08-16 15:07:48,526][09795] Num frames 5100...
|
567 |
+
[2024-08-16 15:07:48,600][09795] Num frames 5200...
|
568 |
+
[2024-08-16 15:07:48,675][09795] Num frames 5300...
|
569 |
+
[2024-08-16 15:07:48,751][09795] Num frames 5400...
|
570 |
+
[2024-08-16 15:07:48,830][09795] Num frames 5500...
|
571 |
+
[2024-08-16 15:07:48,911][09795] Num frames 5600...
|
572 |
+
[2024-08-16 15:07:48,988][09795] Num frames 5700...
|
573 |
+
[2024-08-16 15:07:49,067][09795] Num frames 5800...
|
574 |
+
[2024-08-16 15:07:49,142][09795] Num frames 5900...
|
575 |
+
[2024-08-16 15:07:49,221][09795] Num frames 6000...
|
576 |
+
[2024-08-16 15:07:49,300][09795] Num frames 6100...
|
577 |
+
[2024-08-16 15:07:49,380][09795] Num frames 6200...
|
578 |
+
[2024-08-16 15:07:49,459][09795] Num frames 6300...
|
579 |
+
[2024-08-16 15:07:49,541][09795] Num frames 6400...
|
580 |
+
[2024-08-16 15:07:49,621][09795] Num frames 6500...
|
581 |
+
[2024-08-16 15:07:49,700][09795] Num frames 6600...
|
582 |
+
[2024-08-16 15:07:49,779][09795] Num frames 6700...
|
583 |
+
[2024-08-16 15:07:49,860][09795] Num frames 6800...
|
584 |
+
[2024-08-16 15:07:49,939][09795] Num frames 6900...
|
585 |
+
[2024-08-16 15:07:50,018][09795] Num frames 7000...
|
586 |
+
[2024-08-16 15:07:50,095][09795] Num frames 7100...
|
587 |
+
[2024-08-16 15:07:50,233][09795] Avg episode rewards: #0: 33.176, true rewards: #0: 14.376
|
588 |
+
[2024-08-16 15:07:50,234][09795] Avg episode reward: 33.176, avg true_objective: 14.376
|
589 |
+
[2024-08-16 15:07:50,245][09795] Num frames 7200...
|
590 |
+
[2024-08-16 15:07:50,332][09795] Num frames 7300...
|
591 |
+
[2024-08-16 15:07:50,415][09795] Num frames 7400...
|
592 |
+
[2024-08-16 15:07:50,501][09795] Num frames 7500...
|
593 |
+
[2024-08-16 15:07:50,594][09795] Num frames 7600...
|
594 |
+
[2024-08-16 15:07:50,651][09795] Avg episode rewards: #0: 28.673, true rewards: #0: 12.673
|
595 |
+
[2024-08-16 15:07:50,651][09795] Avg episode reward: 28.673, avg true_objective: 12.673
|
596 |
+
[2024-08-16 15:07:50,736][09795] Num frames 7700...
|
597 |
+
[2024-08-16 15:07:50,826][09795] Num frames 7800...
|
598 |
+
[2024-08-16 15:07:50,904][09795] Num frames 7900...
|
599 |
+
[2024-08-16 15:07:50,997][09795] Num frames 8000...
|
600 |
+
[2024-08-16 15:07:51,078][09795] Num frames 8100...
|
601 |
+
[2024-08-16 15:07:51,162][09795] Num frames 8200...
|
602 |
+
[2024-08-16 15:07:51,248][09795] Num frames 8300...
|
603 |
+
[2024-08-16 15:07:51,328][09795] Num frames 8400...
|
604 |
+
[2024-08-16 15:07:51,413][09795] Num frames 8500...
|
605 |
+
[2024-08-16 15:07:51,464][09795] Avg episode rewards: #0: 27.000, true rewards: #0: 12.143
|
606 |
+
[2024-08-16 15:07:51,465][09795] Avg episode reward: 27.000, avg true_objective: 12.143
|
607 |
+
[2024-08-16 15:07:51,555][09795] Num frames 8600...
|
608 |
+
[2024-08-16 15:07:51,644][09795] Num frames 8700...
|
609 |
+
[2024-08-16 15:07:51,723][09795] Num frames 8800...
|
610 |
+
[2024-08-16 15:07:51,802][09795] Num frames 8900...
|
611 |
+
[2024-08-16 15:07:51,885][09795] Num frames 9000...
|
612 |
+
[2024-08-16 15:07:51,965][09795] Num frames 9100...
|
613 |
+
[2024-08-16 15:07:52,080][09795] Avg episode rewards: #0: 25.466, true rewards: #0: 11.466
|
614 |
+
[2024-08-16 15:07:52,080][09795] Avg episode reward: 25.466, avg true_objective: 11.466
|
615 |
+
[2024-08-16 15:07:52,103][09795] Num frames 9200...
|
616 |
+
[2024-08-16 15:07:52,183][09795] Num frames 9300...
|
617 |
+
[2024-08-16 15:07:52,263][09795] Num frames 9400...
|
618 |
+
[2024-08-16 15:07:52,388][09795] Avg episode rewards: #0: 23.210, true rewards: #0: 10.543
|
619 |
+
[2024-08-16 15:07:52,389][09795] Avg episode reward: 23.210, avg true_objective: 10.543
|
620 |
+
[2024-08-16 15:07:52,398][09795] Num frames 9500...
|
621 |
+
[2024-08-16 15:07:52,472][09795] Num frames 9600...
|
622 |
+
[2024-08-16 15:07:52,549][09795] Num frames 9700...
|
623 |
+
[2024-08-16 15:07:52,626][09795] Num frames 9800...
|
624 |
+
[2024-08-16 15:07:52,708][09795] Num frames 9900...
|
625 |
+
[2024-08-16 15:07:52,794][09795] Num frames 10000...
|
626 |
+
[2024-08-16 15:07:52,883][09795] Num frames 10100...
|
627 |
+
[2024-08-16 15:07:52,966][09795] Num frames 10200...
|
628 |
+
[2024-08-16 15:07:53,040][09795] Num frames 10300...
|
629 |
+
[2024-08-16 15:07:53,118][09795] Num frames 10400...
|
630 |
+
[2024-08-16 15:07:53,200][09795] Num frames 10500...
|
631 |
+
[2024-08-16 15:07:53,275][09795] Num frames 10600...
|
632 |
+
[2024-08-16 15:07:53,349][09795] Num frames 10700...
|
633 |
+
[2024-08-16 15:07:53,426][09795] Num frames 10800...
|
634 |
+
[2024-08-16 15:07:53,502][09795] Num frames 10900...
|
635 |
+
[2024-08-16 15:07:53,580][09795] Num frames 11000...
|
636 |
+
[2024-08-16 15:07:53,659][09795] Num frames 11100...
|
637 |
+
[2024-08-16 15:07:53,735][09795] Num frames 11200...
|
638 |
+
[2024-08-16 15:07:53,813][09795] Num frames 11300...
|
639 |
+
[2024-08-16 15:07:53,890][09795] Num frames 11400...
|
640 |
+
[2024-08-16 15:07:53,964][09795] Num frames 11500...
|
641 |
+
[2024-08-16 15:07:54,024][09795] Avg episode rewards: #0: 25.908, true rewards: #0: 11.508
|
642 |
+
[2024-08-16 15:07:54,024][09795] Avg episode reward: 25.908, avg true_objective: 11.508
|
643 |
+
[2024-08-16 15:08:10,415][09795] Replay video saved to /media/nguyen-duc-huy/E/Code/Deep_RL/train_dir/default_experiment/replay.mp4!
|