Create README.md
Browse files
README.md
ADDED
|
@@ -0,0 +1,32 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- reinforcement-learning
|
| 4 |
+
- ml-agents
|
| 5 |
+
- unity
|
| 6 |
+
- ppo
|
| 7 |
+
- ML-Agents-PushBlock
|
| 8 |
+
license: mit
|
| 9 |
+
---
|
| 10 |
+
|
| 11 |
+
%%writefile README.md
|
| 12 |
+
|
| 13 |
+
# PPO PushBlock Agent
|
| 14 |
+
|
| 15 |
+
This model was trained using PPO with Unity ML-Agents in the PushBlock environment.
|
| 16 |
+
|
| 17 |
+
## Environment
|
| 18 |
+
PushBlock
|
| 19 |
+
|
| 20 |
+
## Algorithm
|
| 21 |
+
PPO (Proximal Policy Optimization)
|
| 22 |
+
|
| 23 |
+
## Files
|
| 24 |
+
- `PushBlock.onnx` — trained policy network
|
| 25 |
+
|
| 26 |
+
## View
|
| 27 |
+
1. https://huggingface.co/spaces/unity/ML-Agents-PushBlock
|
| 28 |
+
2. RyanAA
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
## Author
|
| 32 |
+
Ryan Aparicio
|