legalaspro/unity_multiagent_rl

Multi-agent reinforcement learning framework for Unity environments. Implements MAPPO, MASAC, MATD3, and MADDPG with comprehensive evaluation tools. Features sample-efficient training, competitive analysis, and pre-trained models achieving great performance in Tennis and Soccer environments.

28
/ 100
Experimental

This framework helps AI researchers and game developers train and evaluate groups of AI agents in simulated Unity environments. You input a Unity environment (like a tennis or soccer game) and configuration settings for the AI, and it outputs trained AI models capable of complex cooperative or competitive behaviors. It's designed for those working with multi-agent reinforcement learning in gaming or simulation.

No commits in the last 6 months.

Use this if you need to develop and test advanced AI behaviors for multiple agents interacting in Unity-based simulations or games.

Not ideal if you are looking to develop single-agent AI or if your simulation environment is not built with Unity.

game-ai-development multi-agent-systems ai-simulation reinforcement-learning-research robotics-simulation
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 15 / 25
Community 6 / 25

How are scores calculated?

Stars

12

Forks

1

Language

Python

License

MIT

Last pushed

May 30, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/legalaspro/unity_multiagent_rl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.