No official code found. Best implementation: zyfsjycc/GoMARL (31 stars, Apache-2.0, last commit 2024-08-14).
Codes of GoMARL accompanying the paper "Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning"(NeurIPS 2023). GoMARL is a domain-agnostic MARL method that learns automatic grouping for efficient cooperation by promoting intra- and inter-group coordination.
@article{zang2026automatic,
title = {Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning},
author = {Yifan Zang and Jinmin He and Kai Li and Haobo Fu and Qiang Fu and Junliang Xing and Jian Cheng},
year = {2026},
url = {https://api.semanticscholar.org/CorpusID:c7ee28709156f074cbbd6355104d2bb9eb6cae96},
journal = {NEURIPS 2023 2023}
}