Computer Science – Learning
Scientific paper
1999-01-10
MACHINE LEARNING Proceedings of the Fifteenth International Conference (ICML '98), ISBN 1-55860-556-8, ISSN 1049-1910, Madison
Computer Science
Learning
9 pages
Scientific paper
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.
Baxter Jonathan
Tridgell Andrew
Weaver Lex
No associations
LandOfFree
KnightCap: A chess program that learns by combining TD(lambda) with game-tree search does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with KnightCap: A chess program that learns by combining TD(lambda) with game-tree search, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and KnightCap: A chess program that learns by combining TD(lambda) with game-tree search will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-252797