Quentin Gallouédec commited on
Commit
781ae44
1 Parent(s): 2dbf410

Initial commit

Browse files
.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
+ *.mp4 filter=lfs diff=lfs merge=lfs -text
README.md ADDED
@@ -0,0 +1,79 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ library_name: stable-baselines3
3
+ tags:
4
+ - PongNoFrameskip-v4
5
+ - deep-reinforcement-learning
6
+ - reinforcement-learning
7
+ - stable-baselines3
8
+ model-index:
9
+ - name: PPO
10
+ results:
11
+ - task:
12
+ type: reinforcement-learning
13
+ name: reinforcement-learning
14
+ dataset:
15
+ name: PongNoFrameskip-v4
16
+ type: PongNoFrameskip-v4
17
+ metrics:
18
+ - type: mean_reward
19
+ value: 20.80 +/- 0.40
20
+ name: mean_reward
21
+ verified: false
22
+ ---
23
+
24
+ # **PPO** Agent playing **PongNoFrameskip-v4**
25
+ This is a trained model of a **PPO** agent playing **PongNoFrameskip-v4**
26
+ using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3)
27
+ and the [RL Zoo](https://github.com/DLR-RM/rl-baselines3-zoo).
28
+
29
+ The RL Zoo is a training framework for Stable Baselines3
30
+ reinforcement learning agents,
31
+ with hyperparameter optimization and pre-trained agents included.
32
+
33
+ ## Usage (with SB3 RL Zoo)
34
+
35
+ RL Zoo: https://github.com/DLR-RM/rl-baselines3-zoo<br/>
36
+ SB3: https://github.com/DLR-RM/stable-baselines3<br/>
37
+ SB3 Contrib: https://github.com/Stable-Baselines-Team/stable-baselines3-contrib
38
+
39
+ Install the RL Zoo (with SB3 and SB3-Contrib):
40
+ ```bash
41
+ pip install rl_zoo3
42
+ ```
43
+
44
+ ```
45
+ # Download model and save it into the logs/ folder
46
+ python -m rl_zoo3.load_from_hub --algo ppo --env PongNoFrameskip-v4 -orga qgallouedec -f logs/
47
+ python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-v4 -f logs/
48
+ ```
49
+
50
+ If you installed the RL Zoo3 via pip (`pip install rl_zoo3`), from anywhere you can do:
51
+ ```
52
+ python -m rl_zoo3.load_from_hub --algo ppo --env PongNoFrameskip-v4 -orga qgallouedec -f logs/
53
+ python -m rl_zoo3.enjoy --algo ppo --env PongNoFrameskip-v4 -f logs/
54
+ ```
55
+
56
+ ## Training (with the RL Zoo)
57
+ ```
58
+ python -m rl_zoo3.train --algo ppo --env PongNoFrameskip-v4 -f logs/
59
+ # Upload the model and generate video (when possible)
60
+ python -m rl_zoo3.push_to_hub --algo ppo --env PongNoFrameskip-v4 -f logs/ -orga qgallouedec
61
+ ```
62
+
63
+ ## Hyperparameters
64
+ ```python
65
+ OrderedDict([('batch_size', 256),
66
+ ('clip_range', 'lin_0.1'),
67
+ ('ent_coef', 0.01),
68
+ ('env_wrapper',
69
+ ['stable_baselines3.common.atari_wrappers.AtariWrapper']),
70
+ ('frame_stack', 4),
71
+ ('learning_rate', 'lin_2.5e-4'),
72
+ ('n_envs', 8),
73
+ ('n_epochs', 4),
74
+ ('n_steps', 128),
75
+ ('n_timesteps', 10000000.0),
76
+ ('policy', 'CnnPolicy'),
77
+ ('vf_coef', 0.5),
78
+ ('normalize', False)])
79
+ ```
args.yml ADDED
@@ -0,0 +1,83 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - algo
3
+ - ppo
4
+ - - conf_file
5
+ - null
6
+ - - device
7
+ - auto
8
+ - - env
9
+ - PongNoFrameskip-v4
10
+ - - env_kwargs
11
+ - null
12
+ - - eval_episodes
13
+ - 20
14
+ - - eval_freq
15
+ - 25000
16
+ - - gym_packages
17
+ - []
18
+ - - hyperparams
19
+ - null
20
+ - - log_folder
21
+ - logs
22
+ - - log_interval
23
+ - -1
24
+ - - max_total_trials
25
+ - null
26
+ - - n_eval_envs
27
+ - 5
28
+ - - n_evaluations
29
+ - null
30
+ - - n_jobs
31
+ - 1
32
+ - - n_startup_trials
33
+ - 10
34
+ - - n_timesteps
35
+ - -1
36
+ - - n_trials
37
+ - 500
38
+ - - no_optim_plots
39
+ - false
40
+ - - num_threads
41
+ - -1
42
+ - - optimization_log_path
43
+ - null
44
+ - - optimize_hyperparameters
45
+ - false
46
+ - - progress
47
+ - false
48
+ - - pruner
49
+ - median
50
+ - - sampler
51
+ - tpe
52
+ - - save_freq
53
+ - -1
54
+ - - save_replay_buffer
55
+ - false
56
+ - - seed
57
+ - 511610459
58
+ - - storage
59
+ - null
60
+ - - study_name
61
+ - null
62
+ - - tensorboard_log
63
+ - runs/PongNoFrameskip-v4__ppo__511610459__1675437974
64
+ - - track
65
+ - true
66
+ - - trained_agent
67
+ - ''
68
+ - - truncate_last_trajectory
69
+ - true
70
+ - - uuid
71
+ - false
72
+ - - vec_env
73
+ - dummy
74
+ - - verbose
75
+ - 1
76
+ - - wandb_entity
77
+ - qgallouedec
78
+ - - wandb_project_name
79
+ - sb3-iqn
80
+ - - wandb_tags
81
+ - []
82
+ - - yaml_file
83
+ - null
config.yml ADDED
@@ -0,0 +1,25 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ !!python/object/apply:collections.OrderedDict
2
+ - - - batch_size
3
+ - 256
4
+ - - clip_range
5
+ - lin_0.1
6
+ - - ent_coef
7
+ - 0.01
8
+ - - env_wrapper
9
+ - - stable_baselines3.common.atari_wrappers.AtariWrapper
10
+ - - frame_stack
11
+ - 4
12
+ - - learning_rate
13
+ - lin_2.5e-4
14
+ - - n_envs
15
+ - 8
16
+ - - n_epochs
17
+ - 4
18
+ - - n_steps
19
+ - 128
20
+ - - n_timesteps
21
+ - 10000000.0
22
+ - - policy
23
+ - CnnPolicy
24
+ - - vf_coef
25
+ - 0.5
env_kwargs.yml ADDED
@@ -0,0 +1 @@
 
 
1
+ {}
ppo-PongNoFrameskip-v4.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f84be5559c3727d6dc685d2ec354b53ccc9695722046b58844b374fc14cbda2d
3
+ size 20445206
ppo-PongNoFrameskip-v4/_stable_baselines3_version ADDED
@@ -0,0 +1 @@
 
 
1
+ 1.8.0a6
ppo-PongNoFrameskip-v4/data ADDED
The diff for this file is too large to render. See raw diff
 
ppo-PongNoFrameskip-v4/policy.optimizer.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:efea4e7145a5587f16cfa2abdbd0c96d04322198eb973a4197e36689efd8b4b4
3
+ size 13511481
ppo-PongNoFrameskip-v4/policy.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:51c0492813567beb431785180d616f019751bd85c33767369fc655f23e4c01d8
3
+ size 6757825
ppo-PongNoFrameskip-v4/pytorch_variables.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d030ad8db708280fcae77d87e973102039acd23a11bdecc3db8eb6c0ac940ee1
3
+ size 431
ppo-PongNoFrameskip-v4/system_info.txt ADDED
@@ -0,0 +1,7 @@
 
 
 
 
 
 
 
 
1
+ - OS: Linux-5.19.0-32-generic-x86_64-with-glibc2.35 # 33~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Mon Jan 30 17:03:34 UTC 2
2
+ - Python: 3.9.12
3
+ - Stable-Baselines3: 1.8.0a6
4
+ - PyTorch: 1.13.1+cu117
5
+ - GPU Enabled: True
6
+ - Numpy: 1.24.1
7
+ - Gym: 0.21.0
replay.mp4 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:05470fa931ca43a60a77b23cfe61eb405760520a14bdbbbccca67f98c190c2de
3
+ size 68968
results.json ADDED
@@ -0,0 +1 @@
 
 
1
+ {"mean_reward": 20.8, "std_reward": 0.4, "is_deterministic": false, "n_eval_episodes": 10, "eval_datetime": "2023-02-27T19:49:04.415387"}
train_eval_metrics.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:53ab124bf996010bdbae1765f49bccd4e53f0a33fa4c01e43c57a850922bebd5
3
+ size 235138