opendilab/ACE

[AAAI 2023] Official PyTorch implementation of paper "ACE: Cooperative Multi-agent Q-learning with Bidirectional Action-Dependency".

37
/ 100
Emerging

This project helps AI researchers and developers working on multi-agent systems to train AI agents that collaborate more effectively. It provides code that takes in scenarios from environments like StarCraft II or Google Research Football and outputs improved training strategies for AI agents to work together and achieve common goals. This is designed for researchers and practitioners in reinforcement learning.

238 stars. No commits in the last 6 months.

Use this if you are developing or researching cooperative AI systems where multiple agents need to coordinate their actions to solve complex problems.

Not ideal if you are looking for a pre-trained, ready-to-deploy AI solution for a specific game or real-world application, or if your problem involves single-agent learning.

AI research multi-agent systems reinforcement learning AI collaboration game AI
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

238

Forks

12

Language

Python

License

Apache-2.0

Last pushed

Dec 07, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/opendilab/ACE"

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