Commit ·
ff9c18a
1
Parent(s): f2e0e4f
Update README.md
Browse filesexplained the journey
README.md
CHANGED
|
@@ -27,4 +27,6 @@ model-index:
|
|
| 27 |
This is a trained model of a PPO agent playing CartPole-v1.
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
-
|
|
|
|
|
|
|
|
|
| 27 |
This is a trained model of a PPO agent playing CartPole-v1.
|
| 28 |
|
| 29 |
# Hyperparameters
|
| 30 |
+
This was trained with a decaying learning rate of 25e-5, clip-coef of 0.1 and 1 million timesteps.
|
| 31 |
+
|
| 32 |
+
Still not perfect but that was not the point. You can follow the full journey here for more info: https://github.com/MattStammers/PPO_Lander_Implementation
|