摘要
"久"棋是藏族人民的传统棋类游戏,游戏过程分为布局阶段和战斗阶段,布局的质量对弈棋结果影响很大。与围棋博弈智能软件战胜人类高手的情况比较,"久"棋博弈研究几乎空白。为了拓宽机器博弈研究的游戏范围,开发具有较高棋力的"久"棋软件,作者开展了基于棋型的"久"棋计算机博弈研究。通过实地考察,在四川阿坝地区采集了约300局有效的"久"棋对弈数据,提取了常见棋型,分别为棋型命名为三角、三子、二子、对角、四子等。在布局阶段,采用模式匹配算法提高棋型的匹配速度。在布局和战斗阶段,基于棋型,设计了具有优先级别的防守、攻击、连子策略。采用C语言开发了"久"棋博弈软件,该软件具有人人对弈、人机对弈、自动录制棋谱等功能。该软件在2016年四川省阿坝县第七届"体彩杯"藏棋比赛中成功开展了人机对弈,但是棋力有待提高。结果表明,基于棋型的攻防策略能够有效地应用于"久"棋计算机博弈。
JIU is a traditional Tibetan board game that is divided into two sequential stages—embattle(or prepare for battle) and battle. The embattle stage has a critical effect on the subsequent battle. Compared with Alpha Go and Alpha Go Zero computer programs, which have defeated top human players, research on the game of JIU is almost nonexistent. To broaden the scope of computer game research and work toward the development of a sophisticated JIU chess game, we conducted a computer game study of the formations used in chess. Specifically, we collected about 300 JIU play records in an on-the-spot investigation in the Aba Autonomous Prefecture of Sichuan Province. In our analysis of these play records, we identified several common chess formations, which we refer to as the triangle, trinity, twain, contrast, and square formations. To increase the speed of the character string matching process, we used a pattern matching algorithm in the embattle stage. We also designed defensive, attack, and collaboration strategies for the embattle and battle stages based on these chess formations. The defensive, attack, and collaboration strategies have decreasing priority. Then, we developed JIU chess software using C language, with functions including the man–man VS mode,human–computer VS AI mode, and automatic recording of the play process. This software performed consistently in the man–machine game play exhibition at the 2016 Seventh "Sports Lottery Cup" Tibetan Chess Contest held in the Aba Autonomous Prefecture of Sichuan Province. However, the chess level realized by the software must be improved. The results show that attack and defense strategies based on chess formations can be effectively applied to JIU chess computer games.
引文
[1]刘强.藏族传统棋艺现状及推广价值[J].当代体育科技,2012,2(27):83-84.LIU Qiang.The status and promotion value of traditional Tibetan chess[J].Contemporary sports technology,2012,2(27):83-84.
[2]张月娟,苟小江.西藏高校引入藏族传统体育项目注意的问题[J].当代体育科技,2014,4(23):130-132.ZHANG Yuejuan,GOU Xiaojiang.The attention of tibetan traditional sports introduced in Tibet college[J].Contemporary sports technology,2014,4(23):130-132.
[3]德康·索朗曲杰译,约翰·帕日柏林著.围棋在世界屋脊[J].西藏研究,1994,3:153-157.
[4]更堆.浅淡西藏“密芒”围棋的发现和相关传统藏棋种类[J].西藏大学学报:汉文版,2003,18(3):44-48.GENG Dui.On the discovery of Tibetan Chess(Mimang)and related traditional Tibetan chesses[J].Journal of Tibet university:chinese edition,2003,18(3):44-48.
[5]徐心和,邓志立,王骄,等.机器博弈研究面临的各种挑战[J].智能系统学报,2008,3(4):288-293.XU Xinhe,DENG Zhili,WANG Jiao,et al.Various challenging issues faced to computer game research[J].CAAItransactions on intelligent systems,2008,3(4):288-293.
[6]MNIH V,KAVUKCUOGLU K,SILVER D,et al.Humanlevel control through deep reinforcement learning[J].Nature,2016,518:529-533.
[7]MNIH V,KAVUKCUOGLU K,SILVER D,et al.Mastering the game of Go with deep neural networks and tree search[J].Nature,2016,529:484-489.
[8]TIAN Yuandong,ZHU Yan.Better computer goplayer with neural network and long-term prediction[EB/OL].https://arxiv.org/abs/1511.0641.
[9]SILVER D,SCHRITTWIESER Julian,SIMONYAN K,et al.Mastering the game of Go without human knowledge[J].Nature,2017,550:354-358.
[10]LI Xiali,DENG Songting.Review of research on computer games for Tibetan chess[C]//IEEE 14th Intl Conf on Dependable,Autonomic and Secure Computing.Auckland,New Zealand,2016:97-99.
[11]李达伟,关欣.藏族传统体育项目探究[J].沈阳体育学院学报,2011,06:130-132,142.LI Dawei,GUAN Xin.Exploration on Tibetan traditional sports[J].Journal of Shenyang sport university,2011,06:130-132,142.
[12]角巴东主.对藏族民间棋艺抢救保护的思考[J].西藏艺术研究,2007,02:78-82.JOPA Dondrub.Considerations on the rescuing and protecting Tibetan folk chess art[J].Tibetan art studies,2007,02:78-82.
[13]陈斌.文化哲学视域中的围棋与藏围棋[J].云南师范大学学报:哲学社会科学版,2006,38(2):1-5.CHEN Bin.A comparison of the i-go cultures between the han and the Tibetan from the perspective of cultural philosophy[J].Journal of Yunnan normal university:philosophy and social sciences edition,2006,38(2):1-5.
[14]尖扎夏贝.藏族围棋软件的设计与实现[D].西宁:青海民族大学毕业论文,2011.
[15]裴生雷.王宫双门棋博弈系统中的关键问题研究[J].微计算机信息,2012,10:461-462.PEI Shenglei.Study of key issues in the palace two-door chess game system[J].Microcomputer information,2012,10:461-462.
[16]仁增多杰,安见才让.“褡裢”藏棋的设计与实现[J].信息与电脑(理论版),2014,08:106-107.
[17]范忠雄.对弈熵率在藏棋“杰布杰曾”上的应用[J].西藏大学学报:自然科学版,2014,01:67-70.FAN Zhongxiong.Entropy rate of chess game-Tibetan Jiebujiezeng[J].Journal of Tibet university:natural science,2014,01:67-70.
[18]王昕杨.藏式围棋博弈软件及其教育应用技术研究[D].北京:中央民族大学硕士生毕业论文,2016.
[19]洪晓蕾.模糊有限自动机及其最小化问题[D].成都:四川师范大学,2007:1-15.HONG Xiaolei.Fuzzy finite automata and their minimizations[D].Chengdu:Sichuan Normal University,2007:1-15.
[20]张红梅,范明钰.棋型匹配BM算法改进[J].计算机应用研究,2009,09:3249-3252.ZHANG Hongmei,FAN Mingyu.Improved algorithm for BM string matching[J].Application research of computers,2009,09:3249-3252.