marlbenchmark/on-policy

This is the official implementation of Multi-Agent PPO (MAPPO).

51
/ 100
Established

This project helps researchers and practitioners in multi-agent systems develop and evaluate advanced artificial intelligence for cooperative scenarios. It takes multi-agent environment data from simulations like StarCraft II, Hanabi, or Google Research Football and outputs optimized policies for agents to collaborate effectively. Anyone working on AI for teams, autonomous systems, or complex game environments would find this useful.

1,914 stars. No commits in the last 6 months.

Use this if you are developing or studying AI agents that need to learn cooperative behaviors in multi-agent simulation environments.

Not ideal if you are looking for a simple, out-of-the-box solution for single-agent tasks or real-world robotics deployment without simulation.

multi-agent-systems cooperative-ai reinforcement-learning-research game-ai autonomous-teams
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

1,914

Forks

371

Language

Python

License

MIT

Last pushed

Jul 18, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/marlbenchmark/on-policy"

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