Downloads · 30 days
24
20% of all-time downloads
ML-Agents-SoccerTwos
forgedRice/ML-Agents-SoccerTwos
ML-Agents-SoccerTwos is a reinforcement learning model from forgedRice. Use it for the reinforcement learning task on the model card, and read the license before you ship it in a product. It is set up for ml-agents.
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.
All-time downloads
118
Public
Repo size
229 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt171 MB · 74%
At a glance
- Task
- Reinforcement Learning
- Library
- ml-agents
- Access
- Public
- Created
- Sep 27, 2025
- Updated
- Sep 27, 2025
- SHA
- 7297aa7e
Model card
From the Hugging Face model README
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
- Task
- Reinforcement Learning
- Library
- ml-agents
- Created
- Sep 27, 2025
- Updated
- Sep 27, 2025