README.md

metadata

tags:
  - reinforcement-learning
  - ml-agents
  - ppo
  - unity
  - SnowballTarget
  - ML-Agents-SnowballTarget
license: mit

PPO SnowballTarget

This is a trained PPO agent playing SnowballTarget using Unity ML-Agents.

Environment

SnowballTarget

Algorithm

PPO (Proximal Policy Optimization)

Training Results

Final mean reward: ~23.2 after 200k training steps.

Usage

You can watch the agent play directly in your browser:

1. Go to: https://huggingface.co/spaces/ThomasSimonini/ML-Agents-SnowballTarget

2. Search for "RyanAA"

3. Select SnowballTarget.onnx

4. Click "Watch the agent play"

Files

• SnowballTarget.onnx — trained policy network