Quentin Gallouédec
commited on
Commit
•
119a70b
1
Parent(s):
6cca948
Initial commit
Browse files- .gitattributes +1 -0
- README.md +90 -0
- args.yml +83 -0
- config.yml +45 -0
- env_kwargs.yml +1 -0
- ppo-CarRacing-v0.zip +3 -0
- ppo-CarRacing-v0/_stable_baselines3_version +1 -0
- ppo-CarRacing-v0/data +0 -0
- ppo-CarRacing-v0/policy.optimizer.pth +3 -0
- ppo-CarRacing-v0/policy.pth +3 -0
- ppo-CarRacing-v0/pytorch_variables.pth +3 -0
- ppo-CarRacing-v0/system_info.txt +7 -0
- replay.mp4 +3 -0
- results.json +1 -0
- train_eval_metrics.zip +3 -0
- vec_normalize.pkl +3 -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 |
+
*.mp4 filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: stable-baselines3
|
3 |
+
tags:
|
4 |
+
- CarRacing-v0
|
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: CarRacing-v0
|
16 |
+
type: CarRacing-v0
|
17 |
+
metrics:
|
18 |
+
- type: mean_reward
|
19 |
+
value: 174.99 +/- 100.17
|
20 |
+
name: mean_reward
|
21 |
+
verified: false
|
22 |
+
---
|
23 |
+
|
24 |
+
# **PPO** Agent playing **CarRacing-v0**
|
25 |
+
This is a trained model of a **PPO** agent playing **CarRacing-v0**
|
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 CarRacing-v0 -orga sb3 -f logs/
|
47 |
+
python -m rl_zoo3.enjoy --algo ppo --env CarRacing-v0 -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 CarRacing-v0 -orga sb3 -f logs/
|
53 |
+
python -m rl_zoo3.enjoy --algo ppo --env CarRacing-v0 -f logs/
|
54 |
+
```
|
55 |
+
|
56 |
+
## Training (with the RL Zoo)
|
57 |
+
```
|
58 |
+
python -m rl_zoo3.train --algo ppo --env CarRacing-v0 -f logs/
|
59 |
+
# Upload the model and generate video (when possible)
|
60 |
+
python -m rl_zoo3.push_to_hub --algo ppo --env CarRacing-v0 -f logs/ -orga sb3
|
61 |
+
```
|
62 |
+
|
63 |
+
## Hyperparameters
|
64 |
+
```python
|
65 |
+
OrderedDict([('batch_size', 128),
|
66 |
+
('clip_range', 0.2),
|
67 |
+
('ent_coef', 0.0),
|
68 |
+
('env_wrapper',
|
69 |
+
[{'rl_zoo3.wrappers.FrameSkip': {'skip': 2}},
|
70 |
+
{'gym.wrappers.resize_observation.ResizeObservation': {'shape': 64}},
|
71 |
+
{'gym.wrappers.gray_scale_observation.GrayScaleObservation': {'keep_dim': True}}]),
|
72 |
+
('frame_stack', 2),
|
73 |
+
('gae_lambda', 0.95),
|
74 |
+
('gamma', 0.99),
|
75 |
+
('learning_rate', 'lin_1e-4'),
|
76 |
+
('max_grad_norm', 0.5),
|
77 |
+
('n_envs', 8),
|
78 |
+
('n_epochs', 10),
|
79 |
+
('n_steps', 512),
|
80 |
+
('n_timesteps', 4000000.0),
|
81 |
+
('normalize', "{'norm_obs': False, 'norm_reward': True}"),
|
82 |
+
('policy', 'CnnPolicy'),
|
83 |
+
('policy_kwargs',
|
84 |
+
'dict(log_std_init=-2, ortho_init=False, activation_fn=nn.GELU, '
|
85 |
+
'net_arch=dict(pi=[256], vf=[256]), )'),
|
86 |
+
('sde_sample_freq', 4),
|
87 |
+
('use_sde', True),
|
88 |
+
('vf_coef', 0.5),
|
89 |
+
('normalize_kwargs', {'norm_obs': False, 'norm_reward': False})])
|
90 |
+
```
|
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 |
+
- CarRacing-v0
|
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 |
+
- 1260176553
|
58 |
+
- - storage
|
59 |
+
- null
|
60 |
+
- - study_name
|
61 |
+
- null
|
62 |
+
- - tensorboard_log
|
63 |
+
- runs/CarRacing-v0__ppo__1260176553__1675763928
|
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 |
+
- openrlbenchmark
|
78 |
+
- - wandb_project_name
|
79 |
+
- sb3
|
80 |
+
- - wandb_tags
|
81 |
+
- []
|
82 |
+
- - yaml_file
|
83 |
+
- null
|
config.yml
ADDED
@@ -0,0 +1,45 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
!!python/object/apply:collections.OrderedDict
|
2 |
+
- - - batch_size
|
3 |
+
- 128
|
4 |
+
- - clip_range
|
5 |
+
- 0.2
|
6 |
+
- - ent_coef
|
7 |
+
- 0.0
|
8 |
+
- - env_wrapper
|
9 |
+
- - rl_zoo3.wrappers.FrameSkip:
|
10 |
+
skip: 2
|
11 |
+
- gym.wrappers.resize_observation.ResizeObservation:
|
12 |
+
shape: 64
|
13 |
+
- gym.wrappers.gray_scale_observation.GrayScaleObservation:
|
14 |
+
keep_dim: true
|
15 |
+
- - frame_stack
|
16 |
+
- 2
|
17 |
+
- - gae_lambda
|
18 |
+
- 0.95
|
19 |
+
- - gamma
|
20 |
+
- 0.99
|
21 |
+
- - learning_rate
|
22 |
+
- lin_1e-4
|
23 |
+
- - max_grad_norm
|
24 |
+
- 0.5
|
25 |
+
- - n_envs
|
26 |
+
- 8
|
27 |
+
- - n_epochs
|
28 |
+
- 10
|
29 |
+
- - n_steps
|
30 |
+
- 512
|
31 |
+
- - n_timesteps
|
32 |
+
- 4000000.0
|
33 |
+
- - normalize
|
34 |
+
- '{''norm_obs'': False, ''norm_reward'': True}'
|
35 |
+
- - policy
|
36 |
+
- CnnPolicy
|
37 |
+
- - policy_kwargs
|
38 |
+
- dict(log_std_init=-2, ortho_init=False, activation_fn=nn.GELU, net_arch=dict(pi=[256],
|
39 |
+
vf=[256]), )
|
40 |
+
- - sde_sample_freq
|
41 |
+
- 4
|
42 |
+
- - use_sde
|
43 |
+
- true
|
44 |
+
- - vf_coef
|
45 |
+
- 0.5
|
env_kwargs.yml
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{}
|
ppo-CarRacing-v0.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8d72b7e2cf85fa69d9ae3895dc76669382014f7d070b9c221eb6d16872ca584d
|
3 |
+
size 10492462
|
ppo-CarRacing-v0/_stable_baselines3_version
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
1.8.0a4
|
ppo-CarRacing-v0/data
ADDED
The diff for this file is too large to render.
See raw diff
|
|
ppo-CarRacing-v0/policy.optimizer.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:99eaeeb34d7b644c10f43942e2624e2dccdd0df040987b769edca739531e57cd
|
3 |
+
size 6919180
|
ppo-CarRacing-v0/policy.pth
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e5ed63ee2d4b74f33ec0082f7aff44c63e08a7626a2a037492d674999a2256f4
|
3 |
+
size 3461426
|
ppo-CarRacing-v0/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-CarRacing-v0/system_info.txt
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
- OS: Linux-5.15.0-58-generic-x86_64-with-glibc2.35 # 64-Ubuntu SMP Thu Jan 5 11:43:13 UTC 2023
|
2 |
+
- Python: 3.9.12
|
3 |
+
- Stable-Baselines3: 1.8.0a4
|
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:e92127e976c87dd8e84ac8d176cc097616e9ed6a1b9c50910658a28f7514382a
|
3 |
+
size 677236
|
results.json
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
{"mean_reward": 174.986126, "std_reward": 100.17189983874893, "is_deterministic": true, "n_eval_episodes": 10, "eval_datetime": "2023-02-07T19:27:04.025073"}
|
train_eval_metrics.zip
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e092db6d4e19b9234fb09939312a884875832bbc0860102cfd5108a8835f9314
|
3 |
+
size 287099
|
vec_normalize.pkl
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:cb8d900a297fc937703eb15f89d57b88f188f4cd4cfe92a23d50728456937ebd
|
3 |
+
size 53096
|