Commit
•
bdd9a9f
1
Parent(s):
6a64e8c
Update README.md
Browse files
README.md
CHANGED
@@ -24,5 +24,16 @@ model-index:
|
|
24 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
|
26 |
## Usage (with Stable-baselines3)
|
27 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
28 |
|
|
|
24 |
This is a trained model of a **PPO** agent playing **LunarLander-v2** using the [stable-baselines3 library](https://github.com/DLR-RM/stable-baselines3).
|
25 |
|
26 |
## Usage (with Stable-baselines3)
|
27 |
+
model = PPO(
|
28 |
+
policy = 'MlpPolicy',
|
29 |
+
env = env,
|
30 |
+
n_steps = 1024,
|
31 |
+
batch_size = 32,
|
32 |
+
n_epochs = 4,
|
33 |
+
gamma = 0.9990,
|
34 |
+
gae_lambda = 0.995,
|
35 |
+
ent_coef = 0.005,
|
36 |
+
verbose=1)
|
37 |
+
|
38 |
+
model.learn(total_timesteps=2000000)
|
39 |
|