Update README.md
Browse files
README.md
CHANGED
@@ -25,13 +25,19 @@ model-index:
|
|
25 |
This is a trained model of a **PPO** agent playing **BipedalWalker-v3**
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
-
##
|
29 |
-
TODO: Add your code
|
30 |
-
|
31 |
-
|
32 |
```python
|
33 |
-
|
34 |
-
|
35 |
-
|
36 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
37 |
```
|
|
|
|
|
|
|
|
25 |
This is a trained model of a **PPO** agent playing **BipedalWalker-v3**
|
26 |
using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
27 |
|
28 |
+
## Hyperparameters
|
|
|
|
|
|
|
29 |
```python
|
30 |
+
model = PPO(
|
31 |
+
policy = 'MlpPolicy',
|
32 |
+
env = env,
|
33 |
+
n_steps = 1024,
|
34 |
+
batch_size = 64,
|
35 |
+
n_epochs = 4,
|
36 |
+
gamma = 0.99,
|
37 |
+
gae_lambda = 0.98,
|
38 |
+
ent_coef = 0.01,
|
39 |
+
verbose=1)
|
40 |
```
|
41 |
+
|
42 |
+
## Train Time
|
43 |
+
Trained for 3 000 000 timesteps. Training took 1 hour and 8 minutes on Nvidia RTX A2000 Laptop.
|