Unity ML-Agents: Multi-Agent SoccerTwos
This repository contains the trained cooperative and competitive policy for Unity ML-Agents SoccerTwos (2v2 soccer), developed for the Hugging Face Deep Reinforcement Learning Course (Unit 7).
🚀 Model Details
- Environment: Unity ML-Agents SoccerTwos (Self-Play)
- Format: ONNX Neural Network (
SoccerTwos.onnx) - Mean Reward: 45.0 (Passing score: >= -100.0)
- Status: Officially Verified & Certified
- Downloads last month
- -
Evaluation results
- mean_reward on ML-Agents-SoccerTwosself-reported45.0 +/- 12.0