正在加载图片...
第15卷第2期 智能系统学报 Vol.15 No.2 2020年3月 CAAI Transactions on Intelligent Systems Mar.2020 D0:10.11992/tis.201812012 网络出版地址:http:/kns.cnki.net/kcms/detail/23.1538.TP.20200323.1314.004html 一种军棋机器博弈的多棋子协同博弈方法 张小川,王宛宛2,彭丽蓉3 (1.重庆理工大学两江人工智能学院,重庆400054;2.重庆理工大学计算机科学与工程学院,重庆400054: 3.重庆工业职业技术学院信息工程学院,重庆401120) 摘要:针对在军棋博弈不完全信息对弈中,面对棋子不同价值、不同位置、不同搭配所产生的不同棋力,传统 的单子意图搜索算法,不能满足棋子之间的协同性与沟通性,同时也缺乏对敌方的引诱与欺骗等高级对抗能 力。本文提出一种结合UCT搜索策略的高价值棋子博弈方法,实现高价值棋子协同博弈的策略。实战经验表 明:高价值多棋子军棋协同博弈策略优于单棋子军棋博弈策略。 关键词:机器博弈;军棋;协同博弈;Q学习算法:攻守平衡:维度灾难:UCT:高价值棋子 中图分类号:TP311.5文献标志码:A文章编号:1673-4785(2020)02-0399-06 中文引用格式:张小川,王宛宛,彭丽蓉.一种军棋机器博弈的多棋子协同博弈方法J川.智能系统学报,2020,15(2): 399-404. 英文引用格式:ZHANG Xiaochuan,,WANG Wanwan,PENG Lirong.A multi--chess collaborative game method for military chess game machine[J].CAAI transactions on intelligent systems,2020,15(2):399-404. A multi-chess collaborative game method for military chess game machine ZHANG Xiaochuan',WANG Wanwan',PENG Lirong (1.Liangjiang Institute of Artificial Intelligence,Chongqing University of Technology,Chongqing 400054,China;2.School of Com- puter Science and Engineering,Chongqing University of Technology,Chongqing 400054,China;3.Faculty Information Engineering, Chongqing Industry Polytechnic College,Chongqing 401120,China) Abstract:Owing to incomplete information on the military chess and the different strengths of chess pieces with differ- ent values,positions,and combinations,the traditional single-intention search algorithm cannot satisfy the coordination and communication requirements of chess pieces and lacks advanced confrontation capabilities,such as temptation and deception of the enemy.This study proposes the combination of the high-value chess piece game method and the UCT search strategy to achieve a high-value chess piece cooperative game strategy that can be used to solve the problems of the military chess game.Practical experience shows that the high-value multipiece military chess game strategy is better than the high-value single-piece military chess game strategy. Keywords:computer game;military;collaborative game;Q learning algorithm;balance of attack and defend UCT;di- mension disaster;high value chess piece; 机器博弈是人工智能领域重要的研究方向, Alpha Go战胜韩国围棋大师李世石使得人机博弈 通过训练计算机下棋来衡量机器的智能程度,具 变得家喻户晓,紧接着网络注册名Master线上 有人-机、机-机对弈2种形式,2016年Google的 挑战中日韩围棋高手,以及升级版Alpha Go Zero 收稿日期:2018-12-11.网络出版日期:2020-03-23. 以4:0战胜世界围棋第一人柯洁等标志性事件, 基金项目:国家自然科学基金项目(61702063):重庆理工大学 掀开了人机博弈中机器取胜的新篇章四。但是机- 研究生创新基金项目(ycx2018244). 通信作者:王宛宛.E-mail:1033104010@qq.com, 机博弈依然是人类在人工智能领域不断探索的新DOI: 10.11992/tis.201812012 网络出版地址: http://kns.cnki.net/kcms/detail/23.1538.TP.20200323.1314.004.html 一种军棋机器博弈的多棋子协同博弈方法 张小川1 ,王宛宛2 ,彭丽蓉3 (1. 重庆理工大学 两江人工智能学院,重庆 400054; 2. 重庆理工大学 计算机科学与工程学院,重庆 400054; 3. 重庆工业职业技术学院 信息工程学院,重庆 401120) 摘 要:针对在军棋博弈不完全信息对弈中,面对棋子不同价值、不同位置、不同搭配所产生的不同棋力,传统 的单子意图搜索算法,不能满足棋子之间的协同性与沟通性,同时也缺乏对敌方的引诱与欺骗等高级对抗能 力。本文提出一种结合 UCT 搜索策略的高价值棋子博弈方法,实现高价值棋子协同博弈的策略。实战经验表 明:高价值多棋子军棋协同博弈策略优于单棋子军棋博弈策略。 关键词:机器博弈;军棋;协同博弈;Q 学习算法;攻守平衡;维度灾难;UCT;高价值棋子 中图分类号:TP311.5 文献标志码:A 文章编号:1673−4785(2020)02−0399−06 中文引用格式:张小川, 王宛宛, 彭丽蓉. 一种军棋机器博弈的多棋子协同博弈方法 [J]. 智能系统学报, 2020, 15(2): 399–404. 英文引用格式:ZHANG Xiaochuan, WANG Wanwan, PENG Lirong. A multi-chess collaborative game method for military chess game machine[J]. CAAI transactions on intelligent systems, 2020, 15(2): 399–404. A multi-chess collaborative game method for military chess game machine ZHANG Xiaochuan1 ,WANG Wanwan2 ,PENG Lirong3 (1. Liangjiang Institute of Artificial Intelligence, Chongqing University of Technology, Chongqing 400054, China; 2. School of Com￾puter Science and Engineering, Chongqing University of Technology, Chongqing 400054, China; 3. Faculty Information Engineering, Chongqing Industry Polytechnic College,Chongqing 401120, China) Abstract: Owing to incomplete information on the military chess and the different strengths of chess pieces with differ￾ent values, positions, and combinations, the traditional single-intention search algorithm cannot satisfy the coordination and communication requirements of chess pieces and lacks advanced confrontation capabilities, such as temptation and deception of the enemy. This study proposes the combination of the high-value chess piece game method and the UCT search strategy to achieve a high-value chess piece cooperative game strategy that can be used to solve the problems of the military chess game. Practical experience shows that the high-value multipiece military chess game strategy is better than the high-value single-piece military chess game strategy. Keywords: computer game; military; collaborative game; Q learning algorithm; balance of attack and defend UCT; di￾mension disaster; high value chess piece; 机器博弈是人工智能领域重要的研究方向, 通过训练计算机下棋来衡量机器的智能程度,具 有人−机、机−机对弈 2 种形式,2016 年 Google 的 Alpha Go 战胜韩国围棋大师李世石使得人机博弈 变得家喻户晓[1] ,紧接着网络注册名 Master 线上 挑战中日韩围棋高手,以及升级版 Alpha Go Zero 以 4∶0 战胜世界围棋第一人柯洁等标志性事件, 掀开了人机博弈中机器取胜的新篇章[2]。但是机− 机博弈依然是人类在人工智能领域不断探索的新 收稿日期:2018−12−11. 网络出版日期:2020−03−23. 基金项目:国家自然科学基金项目 (61702063);重庆理工大学 研究生创新基金项目 (ycx2018244). 通信作者:王宛宛. E-mail:1033104010@qq.com. 第 15 卷第 2 期 智 能 系 统 学 报 Vol.15 No.2 2020 年 3 月 CAAI Transactions on Intelligent Systems Mar. 2020
向下翻页>>
©2008-现在 cucdc.com 高等教育资讯网 版权所有