Commit
•
1212adb
1
Parent(s):
d53186c
Update README.md
Browse files
README.md
CHANGED
@@ -9,23 +9,24 @@ This is a trained model of a PPO agent playing PongNoFrameskip-v4 using the stab
|
|
9 |
|
10 |
<video src="https://huggingface.co/ThomasSimonini/ppo-PongNoFrameskip-v4/resolve/main/output.mp4" controls autoplay loop></video>
|
11 |
|
12 |
-
# Usage (with Stable-baselines3)
|
13 |
-
|
14 |
-
|
15 |
## Evaluation Results
|
16 |
Mean_reward = 21.00 +/- 0.0
|
17 |
|
18 |
-
|
|
|
19 |
- You need to use `gym==0.19` since it **includes Atari Roms**.
|
20 |
- The Actor Space is 6 since we use only **legit actions**.
|
21 |
|
22 |
```python
|
23 |
-
# Install these libraries (don't forget to restart the runtime after installing the librairies)
|
24 |
!pip install stable-baselines3[extra]
|
25 |
!pip install huggingface_sb3
|
26 |
!pip install huggingface_hub
|
27 |
!pip install pickle5
|
|
|
28 |
|
|
|
|
|
29 |
# Import the libraries
|
30 |
import os
|
31 |
|
|
|
9 |
|
10 |
<video src="https://huggingface.co/ThomasSimonini/ppo-PongNoFrameskip-v4/resolve/main/output.mp4" controls autoplay loop></video>
|
11 |
|
|
|
|
|
|
|
12 |
## Evaluation Results
|
13 |
Mean_reward = 21.00 +/- 0.0
|
14 |
|
15 |
+
# Usage (with Stable-baselines3)
|
16 |
+
## Watch your agent interacts (in Google Colab)
|
17 |
- You need to use `gym==0.19` since it **includes Atari Roms**.
|
18 |
- The Actor Space is 6 since we use only **legit actions**.
|
19 |
|
20 |
```python
|
21 |
+
# Install these libraries in one cell (don't forget to restart the runtime after installing the librairies)
|
22 |
!pip install stable-baselines3[extra]
|
23 |
!pip install huggingface_sb3
|
24 |
!pip install huggingface_hub
|
25 |
!pip install pickle5
|
26 |
+
```
|
27 |
|
28 |
+
Don't forget to restart the runtime before running the code below:
|
29 |
+
```python
|
30 |
# Import the libraries
|
31 |
import os
|
32 |
|