麻将博弈AI构建方法综述  

Survey of Mahjong game AI construction methods

作　　者：李霞丽[1,2] 王昭琦 刘博 吴立成[1,2] LI Xiai;WANG Zhaoqi;LIU Bo;WU Licheng(School of Information Engineering,Minzu University of China,Beijing 100081,China;Key Laboratory of Ethnic Language In-telligent Analysis and Security Governance of MOE,Minzu University of China,Beijing 100081,China)

机构地区：[1]中央民族大学信息工程学院,北京100081 [2]中央民族大学民族语言智能分析与安全治理教育部重点实验室,北京100081

出　　处：《智能系统学报》2023年第6期1143-1155,共13页CAAI Transactions on Intelligent Systems

基　　金：国家自然科学基金项目(61873291,62276285).

摘　　要：麻将及其不同变体的规则复杂,构建高水平的麻将博弈AI(artificial intelligence)算法及其测试环境等面临巨大挑战。本文分析了麻将博弈的相关研究文献,梳理出基于知识和基于数据的两大类麻将AI构建方法,分析了每种类型的构建方法的优势和局限性,重点分析了Suphx构建方法。指出了麻将AI构建面临的问题和挑战;提出将经验回放、分层强化学习、好奇心模型、对手模型、元学习、迁移学习、课程学习等应用到麻将博弈AI算法优化中,构建多元化的麻将AI评估指标、通用对抗平台和高质量的数据集等未来的研究重点。Mahjong and its different variants have complex rules.Therefore,building a high-level Mahjong game artifi-cial intelligence(AI)algorithm and its test environment is challenging.Through the analysis of relevant research literat-ure on Mahjong game,this paper identified two types of Mahjong AI construction methods based on knowledge and data.Moreover,the advantages and disadvantages of each typical method are analyzed,emphasizing the construction method of Suphx.The problems and challenges encountered in constructing Mahjong AI are identified,suggesting the need to apply experience replay,hierarchical reinforcement learning,curiosity model,opponent model,metalearning,transfer learning,and curriculum learning to the AI algorithm optimization of Mahjong game and construct diversified Mahjong AI evaluation indicators,general confrontation platforms,and high-quality data sets.These problems are all promising research directions for the future.

关 键 词：机器博弈 非完备信息博弈 麻将 Suphx 知识 对手建模 深度学习 强化学习 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]