ShahzebKhoso/ppo-Huggy

ppo Agent playing Huggy

This is a trained model of a ppo agent playing Huggy using the Unity ML-Agents Library.

📈 Training Performance

• Mean Reward: 4.0+
• Training Steps: 2,000,000

Improvements

• Added more Hidden Units (hidden_units: 2048)

Usage (with ML-Agents)

The Documentation: https://unity-technologies.github.io/ml-agents/ML-Agents-Toolkit-Documentation/

Follow the Huggingface tutorial to learn to train agent using ML-Agents:

• A short tutorial where you teach Huggy the Dog 🐶 to fetch the stick and then play with him directly in your browser: https://huggingface.co/learn/deep-rl-course/unitbonus1/introduction
• A longer tutorial to understand how works ML-Agents: https://huggingface.co/learn/deep-rl-course/unit5/introduction

Resume the training

mlagents-learn <your_configuration_file_path.yaml> --run-id=<run_id> --resume

Play With My Trained Huggy 🐕

• Open the Huggy game in your browser: https://huggingface.co/spaces/ThomasSimonini/Huggy
• Click on Play with my Huggy model
• In Username type ShahzebKhoso
• Select reporitory 'ppo-Huggy' from dropdown
• Select Model (e.g.Huggy.onnx)
• Enjoy!