Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games
Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (26) · 22110-22118
DOI: 10.1609/aaai.v40i26.39366 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Bingyu Hui und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Zero-shot coordination(ZSC), a key challenge in multi-agent game theory, has become a hot topic in reinforcement learning (RL) research recently, especially in complex evolving games. It focuses on the generalization ability of agents, requiring them to coordinate well with collaborators from a diverse, potentially evolving, pool of partners that are not seen before without any fine-tuning. Population-based training, which approximates such an evolving partner pool, has been proven to provide good zero-shot coordination performance; nevertheless, existing methods are limited by computational resources, mainly focusing on optimizing diversity in small populations while neglecting the potential performance gains from scaling population size. To address this issue, this paper proposes the Scalable Population Training (ScaPT), an efficient RL training framework comprising two key components: a meta-agent that efficiently realizes a population by selectively sharing parameters across agents, and a mutual information regularizer that guarantees population diversity. To empirically validate the effectiveness of ScaPT, this paper evaluates it along with representational frameworks in Hanabi cooperative game and confirms its superiority.
Zitieren
APA
Hui, B., Yu, L., Yao, Q., Qu, Y., Zhang, X., & Wang, J. (2026). Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games. Proceedings of the AAAI Conference on Artificial Intelligence, 40(26), 22110-22118. https://doi.org/10.1609/aaai.v40i26.39366
Vancouver
Hui B, Yu L, Yao Q, Qu Y, Zhang X, Wang J. Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(26):22110-22118. doi:10.1609/aaai.v40i26.39366
BibTeX
@article{Hui2026,
author = {Hui, Bingyu and Yu, Lebin and Yao, Quanming and Qu, Yunpeng and Zhang, Xudong and Wang, Jian},
title = {Efficient Reinforcement Learning for Zero-Shot Coordination in Evolving Games},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2026},
volume = {40},
number = {26},
pages = {22110--22118},
doi = {10.1609/aaai.v40i26.39366}
}
EUVIMED