MA-POCA Agent playing SoccerTwos

This is a trained multi-agent team playing SoccerTwos using the Unity ML-Agents Library with MA-POCA (Multi-Agent POsthumous Credit Assignment) and self-play.

The agents learned cooperative 2v2 soccer behavior where each team tries to score goals while preventing the opponent from scoring.

Algorithm: MA-POCA with Self-Play
Training: 5,000,000 timesteps
Environment: SoccerTwos 2v2 soccer
Team Strategy: Cooperative multi-agent behavior

This model participates in the AI vs AI Challenge where it competes against other trained agents on the leaderboard.

Watch the Agent Play

You can watch this agent compete against others at: https://huggingface.co/spaces/unity/ML-Agents-SoccerTwos

Check the AI vs AI leaderboard: https://huggingface.co/spaces/huggingface-projects/AIvsAI-SoccerTwos

Downloads last month
18
Video Preview
loading