Solving Winning Probability Problems in Go

摘要：

Positional analysis needs to be made in the Go game,and it is true for professional players or Go program.The present Go program regards the territory scores as a major standard in its positional analysis,which is a flawed approach.In this article,an approach is proposed to calculate the winning probability,and the model parameter is further optimized by genetic algorithm.Through this approach,various winning probability models based on different levels can be obtained.After the test,it is concluded that the precision of this model can be applied in the module of middle game and end game in the computer Go.

关键词： winning probability genetic algorithm Go

作者: Lei Yu Xiaojin Zhang Chunni Dai Jingao Liu

作者单位: Department of Electronic Science and Technology East China Normal University Shanghai,China

会议类型: 国际会议

会议名称: The 2nd IEEE International Conference on Advanced Computer Control(第二届先进计算机控制国际会议 ICACC 2010)

会议地点: 沈阳

会议语种:英文

页码: 477-480

在线出版日期: 2010-03-27（万方平台首次上网日期，不代表论文的发表时间）