面向麻将多人博弈中马尔可夫决策过程抽象的人工智能玩家构建方法
人工智能
2019-04-17 v1
摘要
我们提出一种构建麻将人工智能（AI）的方法，麻将是一种多人不完美信息博弈。由于博弈树规模巨大，构建专家级麻将 AI 玩家具有挑战性。我们定义多个马尔可夫决策过程（MDPs）作为麻将的抽象以构建有效搜索树。我们还引入两种利用这些 MDP 推断原始麻将状态值的方法。我们通过与当前最强 AI 玩家的对局评估了方法的有效性。
引用
@article{arxiv.1904.07491,
title = {Method for Constructing Artificial Intelligence Player with Abstraction to Markov Decision Processes in Multiplayer Game of Mahjong},
author = {Moyuru Kurita and Kunihito Hoki},
journal= {arXiv preprint arXiv:1904.07491},
year = {2019}
}
备注
Copyright 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works