KnightCap: A chess program that learns by combining TD(lambda) with game-tree search

KnightCap: A chess program that learns by combining TD(lambda) with game-tree search
复制标题

KnightCap:一个通过将 TD(lambda) 与博弈树搜索相结合来学习的国际象棋程序

DOI:
--
复制
发表时间:
1999
期刊:
影响因子:
--
通讯作者:
Lex Weaver
Lex Weaver
中科院分区:
--
文献类型:
--
作者:
Jonathan Baxter;A. Tridgell;Lex Weaver

文献摘要

被引文献

相似文献

在本文中,我们提出了TDLeaf(lambda),TD(lambda)算法的一个变体,使其能够与游戏树搜索结合使用。我们提出了一些实验中,我们的国际象棋程序"骑士帽"使用TDLeaf(lambda)学习其评价功能,而发挥免费的互联网国际象棋服务器(FICS,www.example.com)。我们报告的主要成功是KnightCap在短短308场比赛和3天的比赛中从1650评级提高到2150评级。作为参考,1650的等级对应于大约水平B人类游戏(在从E(1000)到A(1800)的标度上),而2150是人类大师水平。我们讨论了这种成功的一些原因,其中的原则是使用在线,而不是自我发挥。
In this paper we present TDLeaf(lambda), a variation on the TD(lambda) algorithm that enables it to be used in conjunction with game-tree search. We present some experiments in which our chess program ``KnightCap' used TDLeaf(lambda) to learn its evaluation function while playing on the Free Internet Chess Server (FICS, fics.onenet.net). The main success we report is that KnightCap improved from a 1650 rating to a 2150 rating in just 308 games and 3 days of play. As a reference, a rating of 1650 corresponds to about level B human play (on a scale from E (1000) to A (1800)), while 2150 is human master level. We discuss some of the reasons for this success, principle among them being the use of on-line, rather than self-play.