English

Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution

Neural and Evolutionary Computing 2025-01-03 v3 Artificial Intelligence Machine Learning Multiagent Systems

Abstract

Generating agents that can achieve zero-shot coordination (ZSC) with unseen partners is a new challenge in cooperative multi-agent reinforcement learning (MARL). Recently, some studies have made progress in ZSC by exposing the agents to diverse partners during the training process. They usually involve self-play when training the partners, implicitly assuming that the tasks are homogeneous. However, many real-world tasks are heterogeneous, and hence previous methods may be inefficient. In this paper, we study the heterogeneous ZSC problem for the first time and propose a general method based on coevolution, which coevolves two populations of agents and partners through three sub-processes: pairing, updating and selection. Experimental results on various heterogeneous tasks highlight the necessity of considering the heterogeneous setting and demonstrate that our proposed method is a promising solution for heterogeneous ZSC tasks.

Keywords

Cite

@article{arxiv.2208.04957,
  title  = {Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution},
  author = {Ke Xue and Yutong Wang and Cong Guan and Lei Yuan and Haobo Fu and Qiang Fu and Chao Qian and Yang Yu},
  journal= {arXiv preprint arXiv:2208.04957},
  year   = {2025}
}

Comments

IEEE TEvC

R2 v1 2026-06-25T01:36:24.937Z