English

JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games

Artificial Intelligence 2023-08-10 v1

Abstract

This paper presents an empirical exploration of non-transitivity in perfect-information games, specifically focusing on Xiangqi, a traditional Chinese board game comparable in game-tree complexity to chess and shogi. By analyzing over 10,000 records of human Xiangqi play, we highlight the existence of both transitive and non-transitive elements within the game's strategic structure. To address non-transitivity, we introduce the JiangJun algorithm, an innovative combination of Monte-Carlo Tree Search (MCTS) and Policy Space Response Oracles (PSRO) designed to approximate a Nash equilibrium. We evaluate the algorithm empirically using a WeChat mini program and achieve a Master level with a 99.41\% win rate against human players. The algorithm's effectiveness in overcoming non-transitivity is confirmed by a plethora of metrics, such as relative population performance and visualization results. Our project site is available at \url{https://sites.google.com/view/jiangjun-site/}.

Keywords

Cite

@article{arxiv.2308.04719,
  title  = {JiangJun: Mastering Xiangqi by Tackling Non-Transitivity in Two-Player Zero-Sum Games},
  author = {Yang Li and Kun Xiong and Yingping Zhang and Jiangcheng Zhu and Stephen Mcaleer and Wei Pan and Jun Wang and Zonghong Dai and Yaodong Yang},
  journal= {arXiv preprint arXiv:2308.04719},
  year   = {2023}
}

Comments

28 pages, accepted by Transactions on Machine Learning Research (TMLR)