Commit
·
61343e6
1
Parent(s):
4551cb9
Update README.md
Browse files
README.md
CHANGED
@@ -26,12 +26,31 @@ 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 |
-
from stable_baselines3 import
|
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 |
+
from stable_baselines3 import A2C
|
32 |
from huggingface_sb3 import load_from_hub
|
33 |
|
34 |
+
model = load_from_hub(repo_id='Francesco-A/a2c-PandaReachDense-v3',
|
35 |
+
filename= 'a2c-PandaReachDense-v3.zip')
|
36 |
```
|
37 |
+
|
38 |
+
## Training details (last output)
|
39 |
+
------------------------------------
|
40 |
+
| rollout/ | |
|
41 |
+
| ep_len_mean | 4.05 |
|
42 |
+
| ep_rew_mean | -0.317 |
|
43 |
+
| time/ | |
|
44 |
+
| fps | 378 |
|
45 |
+
| iterations | 50000 |
|
46 |
+
| time_elapsed | 2641 |
|
47 |
+
| total_timesteps | 1000000 |
|
48 |
+
| train/ | |
|
49 |
+
| entropy_loss | 1.25 |
|
50 |
+
| explained_variance | 0.975 |
|
51 |
+
| learning_rate | 0.0007 |
|
52 |
+
| n_updates | 49999 |
|
53 |
+
| policy_loss | -0.0935 |
|
54 |
+
| std | 0.185 |
|
55 |
+
| value_loss | 0.0306 |
|
56 |
+
------------------------------------
|