融合先后手优势的竞技水平估计算法

doi:10.11772/j.issn.1001-9081.2014.11.3264

计算机应用 ›› 2014, Vol. 34 ›› Issue (11): 3264-3267.DOI: 10.11772/j.issn.1001-9081.2014.11.3264

融合先后手优势的竞技水平估计算法

吴霖,陈磊,袁梅宇,江虹

昆明理工大学信息工程与自动化学院, 昆明 650500

收稿日期:2014-05-14 修回日期:2014-07-03 发布日期:2014-12-01 出版日期:2014-11-01
通讯作者: 吴霖
作者简介:吴霖(1976-),男,云南昆明人,讲师,博士,主要研究方向:计算机围棋、机器学习;陈磊(1987-),男,安徽安庆人,硕士研究生,主要研究方向:计算机围棋、机器学习;袁梅宇(1967-),男,云南昆明人,副教授,博士,主要研究方向:基于Java EE的分布式计算;江虹(1965-),男,云南昆明人,讲师,主要研究方向:嵌入式系统。
基金资助:
江苏高校优势学科建设工程项目;云南省应用基础研究计划项目

Improved player skill estimation algorithm by modeling first-move advantage

WU Lin,CHEN Lei,YUAN Meiyu,JIANG Hong

Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming Yunan 650500, China

Received:2014-05-14 Revised:2014-07-03 Online:2014-12-01 Published:2014-11-01
Contact: WU Lin
Supported by:
;the Applied Basic Research Programs of Yunnan Province

摘要/Abstract

摘要：

针对传统的基于概率图模型的竞技水平估计算法忽略了先后手(主客场)优势从而影响估计精度的问题,提出一种融合先后手优势的竞技水平估计算法。该算法在竞技水平估计算法的图模型上,引入先后手节点,将先后手优势与选手真实竞技水平融合;然后利用比赛结果,采用贝叶斯学习的方法同时估计选手的真实竞技水平和先后手优势;最终根据估计结果对比赛进行预测。在两个真实比赛数据上的对比实验〖BP(〗原文“试验”〖BP)〗表明,相对于没有融合先后手优势的估计算法,该方法能够明显提高竞技水平估计的精度。

Abstract:

For the traditional player skill estimation algorithms based on probabilistic graphical model neglect the first-move advantage (or home play advantage) which affects estimation accuracy, a new method to model the first-move advantage was proposed. Based on the graphical model, the nodes of first-move advantage were introduced and added into player's skills. Then, according to the game results, true skills and first-move advantage of palyers were caculated by Bayesian learning method. Finally, predictions for the upcoming matches were made using those estimated results. Two real world datasets were used to compare the proposed method with the traditional model that neglect the first-move advantage. The result shows that the proposed method can improve average estimation accuracy noticeably.

中图分类号:

TP181

吴霖陈磊袁梅宇江虹. 融合先后手优势的竞技水平估计算法[J]. 计算机应用, 2014, 34(11): 3264-3267.

WU Lin CHEN Lei YUAN Meiyu JIANG Hong. Improved player skill estimation algorithm by modeling first-move advantage[J]. Journal of Computer Applications, 2014, 34(11): 3264-3267.

参考文献

[1]ELO A E. The rating of chess players, past and present [M]. New York: Arco Publishing, 1978.
[2]HERBRICH R, MINKA T, GRAEPEL T. TrueSkill: a Bayesian skill rating system [C]// Proceedings of Advances in Neural Information Processing Systems 19. Cambridge: MIT Press, 2007:569-576.
[3]STERN D, HERBRICH R, GRAEPEL T. Bayesian pattern ranking for move prediction in the game of Go [C]// Proceedings of the 23rd International Conference on Machine Learning. New York: ACM Press, 2006: 873-880.
[4]WISTUBA M, SCHAEFERS L, PLATZNER M. Comparison of Bayesian move prediction systems for Computer Go [C]// Proceedings of the 2012 IEEE Conference on Computational Intelligence and Games. Piscataway: IEEE Press, 2012: 91-99.
[5]GRAEPEL T, CANDELA J Q, BORCHERT T, et al. Web-scale Bayesian click-through rate prediction for sponsored search advertising in Microsoft's bing search engine [C]// Proceedings of the 27th International Conference on Machine Learning. Anderson: Omnipress, 2010:13-20.
[6]KIM S, QIN T, LIU T Y, et al. Advertiser-centric approach to understand user click behavior in sponsored search [J]. Information Sciences, 2014, 276: 242-254.
[7]ZHANG X, GRAEPEL T, HERBRICH R. Bayesian online learning for multi-label and multi-variate performance measures [C]// Proceedings of the 13th International Conference on Artificial Intelligence and Statistics. Redmond, Washington, USA: Microsoft Press, 2010:956-963.
[8]LEE J S. TrueSkill-based pairwise coupling for multi-class classification [C]// Proceedings of the 22nd International Conference on Artificial Neural Networks and Machine Learning, LNCS 7553. Berlin: Springer-Verlag, 2012: 213-220.
[9]WU L, CHEN L, DENG C, et al. A ranking approach of go players based on TrueSkill model with empirical evaluation [J]. Journal of Kunming University of Science and Technology: Natural Science, 2013, 38(3):47-55.(吴霖, 陈磊, 邓超, 等. 基于 TrueSkill 模型的围棋棋手排名方法及评估[J]. 昆明理工大学学报:自然科学版, 2013, 38(3):47-55.)
[10]HUANG J, ZIMMERMANN T, NAGAPAN N, et al. Mastering the art of war: how patterns of gameplay influence skill in Halo [C]// Proceedings of the 2013 International Conference on Human Factors in Computing Systems. New York: ACM Press, 2013: 695-704.
[11]DANGAUTHIER P, HERBRICH R, MINKA T, et al. TrueSkill through time: revisiting the history of chess [C]// Proceedings of Advances in Neural Information Processing Systems 20. Cambridge: MIT Press, 2008:337-344.
[12]GUO S, SANNER S, GRAEPEL T, et al. Score-based Bayesian skill learning [C]// Proceedings of the 2012 European Conference on Machine Learning and Knowledge Discovery in Databases, Part I. Berlin: Springer-Verlag, 2012:106-121.
[13]KSCHISCHANG F R, FREY B J, LOELIGER H A. Factor graphs and the sum-product algorithm [J]. IEEE Transactions on Information Theory, 2001,47(2): 498-519.
[14]MINKA T P. Expectation propagation for approximate Bayesian inference [C]// Proceedings of the 17th Conference in Uncertainty in Artificial Intelligence. San Francisco: Morgan Kaufmann Publishers, 2001:362-369.

[1]	宫智宇王士同. 面向重尾噪声图像分类的残差网络学习方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[2]	王虎王晓峰李可马云洁. 融合多头自注意力的标签语义嵌入联邦类增量学习方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[3]	刘晶鑫, 黄雯静, 徐亮胜, 黄冲, 吴建生. 字典学习与样本关联保持结合的无监督特征选择模型[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3766-3775.
[4]	宋逸飞, 柳毅. 基于数据增强和标签噪声的快速对抗训练方法[J]. 《计算机应用》唯一官方网站, 2024, 44(12): 3798-3807.
[5]	赵小阳许新征李仲年. 物联网应用中的可解释人工智能研究综述[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[6]	余家宸, 杨晔. 基于裁剪近端策略优化算法的软机械臂不规则物体抓取[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3629-3638.
[7]	黄雨鑫, 黄贻望, 黄辉. 基于浅层网络预测的元标签校正方法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3364-3370.
[8]	李志杰, 廖旭红, 李元香, 李青蓝. 基于基因关联分析的贝叶斯网络疾病样本分类算法[J]. 《计算机应用》唯一官方网站, 2024, 44(11): 3449-3458.
[9]	胡婕郑启扬孙军张龑. 基于多关系标签图和局部动态重构学习的多标签分类模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[10]	柴汶泽, 范菁, 孙书魁, 梁一鸣, 刘竟锋. 深度度量学习综述[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 2995-3010.
[11]	尹春勇, 周永成. 双端聚类的自动调整聚类联邦学习[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3011-3020.
[12]	曹锋, 杨小玲, 易见兵, 李俊. 矛盾体分离超演绎方法及应用[J]. 《计算机应用》唯一官方网站, 2024, 44(10): 3074-3080.
[13]	许鹏程何磊李川钱炜祺赵暾. 基于Transformer的深度符号回归方法[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[14]	颜文婧王瑞东左敏张青川. 基于风味嵌入异构图层次学习的食谱推荐模型[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.
[15]	郭书剑余节约尹学松. 图正则化弹性网子空间聚类[J]. 《计算机应用》唯一官方网站, 0, (): 0-0.

融合先后手优势的竞技水平估计算法

Improved player skill estimation algorithm by modeling first-move advantage

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics