Commit
•
d648121
1
Parent(s):
4868d89
Update README.md
Browse files
README.md
CHANGED
@@ -26,12 +26,38 @@ This is a trained model of a **A2C** agent playing **PandaReachDense-v3**
|
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
29 |
-
TODO: Add your code
|
30 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
31 |
|
32 |
```python
|
33 |
-
|
34 |
-
from huggingface_sb3 import load_from_hub
|
35 |
|
36 |
-
|
|
|
37 |
```
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
|
|
29 |
|
30 |
+
```python
|
31 |
+
import os
|
32 |
+
|
33 |
+
import gymnasium as gym
|
34 |
+
import panda_gym
|
35 |
+
|
36 |
+
from huggingface_sb3 import load_from_hub, package_to_hub
|
37 |
+
|
38 |
+
from stable_baselines3 import A2C
|
39 |
+
from stable_baselines3.common.evaluation import evaluate_policy
|
40 |
+
from stable_baselines3.common.vec_env import DummyVecEnv, VecNormalize
|
41 |
+
from stable_baselines3.common.env_util import make_vec_env
|
42 |
+
|
43 |
+
from huggingface_hub import notebook_login
|
44 |
+
```
|
45 |
+
|
46 |
+
**Environment**
|
47 |
|
48 |
```python
|
49 |
+
env_id = "PandaReachDense-v3"
|
|
|
50 |
|
51 |
+
# Create the env
|
52 |
+
env = gym.make(env_id)
|
53 |
```
|
54 |
+
|
55 |
+
**Model**
|
56 |
+
|
57 |
+
```python
|
58 |
+
model = A2C(policy = "MultiInputPolicy",
|
59 |
+
env = env,
|
60 |
+
learning_rate = 0.0001,
|
61 |
+
n_steps = 10,
|
62 |
+
verbose=1)
|
63 |
+
```
|