LAMDA-RL/ODIS

The implementation of ICLR 2023 paper "Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data".

37
/ 100
Emerging

This project helps AI researchers and developers working on multi-agent reinforcement learning (MARL) to discover and learn generalizable coordination skills for AI teams. It takes in large datasets of offline multi-agent interactions, like those from StarCraft II or cooperative navigation tasks, and outputs trained models that demonstrate effective teamwork and coordination. The primary users are researchers focused on developing advanced AI systems capable of complex cooperative behaviors.

No commits in the last 6 months.

Use this if you need to train AI agents to coordinate effectively across multiple, similar tasks using pre-recorded data, rather than through real-time interaction.

Not ideal if you are looking for a real-time, online reinforcement learning system or a tool for single-agent tasks.

Multi-agent AI Reinforcement Learning Research AI Team Coordination Offline Learning Strategic Gaming AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

46

Forks

6

Language

Python

License

Apache-2.0

Last pushed

Oct 31, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/LAMDA-RL/ODIS"

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