Update README.md
Browse files
README.md
CHANGED
|
@@ -1,3 +1,18 @@
|
|
| 1 |
-
---
|
| 2 |
-
license: mit
|
| 3 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: mit
|
| 3 |
+
tags:
|
| 4 |
+
- reinforcement-learning
|
| 5 |
+
- agent
|
| 6 |
+
- ppo
|
| 7 |
+
- pytorch
|
| 8 |
+
- gymnasium
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
# Reinforcement Learning in Robotic and Simulated Environments
|
| 12 |
+
- Environment: Hopper-v5
|
| 13 |
+
- Algorithm: PPO
|
| 14 |
+
- Steps: 1M
|
| 15 |
+
- Average reward: 2200
|
| 16 |
+
- Network layer size: 256
|
| 17 |
+
|
| 18 |
+
Both .pth (for neural network) and .npz (for observation preprocessing) files need to be loaded in order to work correctly.
|