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

TL;DR

This paper investigates non-transitivity in Xiangqi, introduces the JiangJun algorithm combining MCTS and PSRO to address it, and demonstrates its effectiveness by achieving Master level performance against humans.

Contribution

The paper presents JiangJun, a novel algorithm that tackles non-transitivity in Xiangqi using a combination of MCTS and PSRO, advancing AI strategies in complex board games.

Findings

JiangJun achieves 99.41% win rate against human players.

The algorithm effectively overcomes non-transitivity in Xiangqi.

Empirical evaluation confirms JiangJun's superiority in strategic performance.

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/}.