opendilab/ACE

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

37
/ 100
Emerging

Introduces bidirectional action-dependency modeling to capture inter-agent coordination patterns, enabling agents to reason about both how their actions affect teammates and how teammate actions constrain their own decisions. Integrates with SMAC (StarCraft Multi-Agent Challenge) and Google Research Football environments, providing end-to-end training pipelines with PyTorch-based Q-learning optimized for cooperative scenarios with explicit action dependency graphs.

238 stars. No commits in the last 6 months.

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.