Learning piece values using temporal differences

被引:23
作者
Beal, DF [1 ]
Smith, MC [1 ]
机构
[1] UNIV LONDON,UNIV LONDON QUEEN MARY & WESTFIELD COLL,DEPT COMP SCI,LONDON E1 4NS,ENGLAND
来源
ICCA JOURNAL | 1997年 / 20卷 / 03期
关键词
D O I
10.3233/ICG-1997-20302
中图分类号
TP31 [计算机软件];
学科分类号
081202 ; 0835 ;
摘要
This paper describes experiments where we attempt to learn the relative values of chess pieces by the use of temporal difference learning applied to minimax searches. We show that we are able to learn suitable piece values, and that these values perform at least as well as piece values widely quoted in elementary chess books.
引用
收藏
页码:147 / 151
页数:5
相关论文
共 3 条
[1]  
MARSLAND TA, 1992, ENCY ARTIFICIAL INTE
[2]  
Sutton R. S., 1988, Machine Learning, V3, P9, DOI 10.1023/A:1022633531479
[3]  
TESAURO G, 1992, MACH LEARN, V8, P257, DOI 10.1007/BF00992697