Heterogeneous Multi-agent Zero-Shot Coordination by Coevolution

2022-08-09 · Ke Xue, Yutong Wang, Cong Guan, Lei Yuan, Haobo Fu, Qiang Fu, Chao Qian, Yang Yu

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.

📄 PDF Abstract BibTeX arXiv:2208.04957

Code (1)

lamda-bbo/maze 공식 구현 tf

Tasks

Multi-agent Reinforcement Learning

Automatic Curriculum Design for Zero-Shot Human-AI Coordination

2025-03-10 · Won-Sang You, Tae-Gwan Ha, Seo-Young Lee, Kyung-Joong Kim

Zero-shot human-AI coordination is the training of an ego-agent to coordinate with humans without using human data. Most studies on zero-shot human-AI coordination have focused on enhancing the ego-agent's coordination a…

Shaping Zero-Shot Coordination via State Blocking

2026-05-12 · Mingu Kang, Sunwoo Lee, Yonghyeon Jo, Seungyul Han arxiv

Zero-shot coordination (ZSC) aims to enable agents to cooperate with independently trained partners without prior interaction, a key requirement for real-world multi-agent systems and human-AI collaboration. Existing app…

“Other-Play” for Zero-Shot Coordination

2020-01-01 · ICML 2020 1 · Hengyuan Hu, Alexander Peysakhovich, Adam Lerer, Jakob Foerster

We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g.humans). Standard Multi-Agent Reinforcement Learning (MARL) methods typica…

Multi-agent Reinforcement Learning Reinforcement Learning (RL)

Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework

2025-06-21 · Ava Abderezaei, Chi-Hui Lin, Joseph Miceli, Naren Sivagnanadasan 외

Zero-shot coordination (ZSC) -- the ability to collaborate with unfamiliar partners -- is essential to making autonomous agents effective teammates. Existing ZSC methods evaluate coordination capabilities between two age…

"Other-Play" for Zero-Shot Coordination

2020-03-06 · Hengyuan Hu, Adam Lerer, Alex Peysakhovich, Jakob Foerster

We consider the problem of zero-shot coordination - constructing AI agents that can coordinate with novel partners they have not seen before (e.g. humans). Standard Multi-Agent Reinforcement Learning (MARL) methods typic…

Multi-agent Reinforcement Learning Reinforcement Learning