Commit
•
4e7d40d
1
Parent(s):
5590689
Update README.md
Browse files
README.md
CHANGED
@@ -26,16 +26,12 @@ This is a trained model of a **SAC** agent playing **PandaReachDense-v3**
|
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
29 |
-
```
|
30 |
-
from stable_baselines3 import SAC
|
31 |
|
32 |
-
|
33 |
-
model.learn(5_000)
|
34 |
-
```
|
35 |
|
36 |
```python
|
37 |
-
from stable_baselines3 import
|
38 |
-
from huggingface_sb3 import load_from_hub
|
39 |
|
40 |
-
|
|
|
41 |
```
|
|
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
## Usage (with Stable-baselines3)
|
|
|
|
|
29 |
|
30 |
+
Copy the code:
|
|
|
|
|
31 |
|
32 |
```python
|
33 |
+
from stable_baselines3 import SAC
|
|
|
34 |
|
35 |
+
model = SAC("MultiInputPolicy", env, learning_rate = 0.00073, gamma = 0.98, gradient_steps = 64, verbose=1)
|
36 |
+
model.learn(5_000)
|
37 |
```
|