Zybg/ppo-Huggy
By Zybg · ↓ 0 · ♥ 0 · Updated 2025-10-12
What's in this repo
This page lists the files in Zybg/ppo-Huggy, including Huggy.onnx, Huggy-1199942.onnx, Huggy-1399939.onnx and more.
- 12 ONNX models (.onnx files)
- 31 files, including 12 .onnx, 12 .pt, 2 .json, 1 .0, 1 .md, 1 .yaml
- Last updated 2025-10-12
ONNX files
| File | Size | Download |
|---|---|---|
| Huggy.onnx | — | Download |
| Huggy/Huggy-1199942.onnx | — | Download |
| Huggy/Huggy-1399939.onnx | — | Download |
| Huggy/Huggy-1599900.onnx | — | Download |
| Huggy/Huggy-1799998.onnx | — | Download |
| Huggy/Huggy-199919.onnx | — | Download |
| Huggy/Huggy-1999700.onnx | — | Download |
| Huggy/Huggy-2000450.onnx | — | Download |
| Huggy/Huggy-399997.onnx | — | Download |
| Huggy/Huggy-599678.onnx | — | Download |
Showing 10 of 12 .onnx files — see the full file list on the right.
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
🐶 PPO-Trained Huggy Agent
This model was trained using Unity ML-Agents (PPO) to teach Huggy the Dog to fetch a stick.
➡️ Play with it here:
👉 https://huggingface.co/spaces/ThomasSimonini/Huggy
🧠 Training Details
- Algorithm: PPO
- Environment: Huggy (fetch-the-stick dog game)
- Framework: Unity ML-Agents v1.2.0
- Reward Design: +orientation bonus −time penalty −rotation penalty
- Max Steps: 2 × 10⁶
- Checkpoint interval: 200 000
You can replay this model in the Huggy Space by entering:
Model info
Created: 2025-10-12
Updated: 2025-10-12
View on Hugging FaceFiles (31)
Related models
More from Zybg
No other models by this author.
More models
No task type declared.