KnightCap: A chess program that learns by combining TD(lambda) with game-tree search
| dc.creator | Baxter, Jonathan | |
| dc.creator | Tridgell, Andrew | |
| dc.creator | Weaver, Lex | |
| dc.date | 1999-01-10 | |
| dc.date.accessioned | 2026-07-07T03:23:54Z | |
| dc.date.available | 2026-07-07T03:23:54Z | |
| dc.description | 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. | |
| dc.description | 9 pages | |
| dc.identifier | https://arxiv.org/abs/cs/9901002 | |
| dc.identifier | http://arxiv.org/abs/cs/9901002 | |
| dc.identifier | MACHINE LEARNING Proceedings of the Fifteenth International Conference (ICML '98), ISBN 1-55860-556-8, ISSN 1049-1910, Madison WISCONSIN, July 24-27 1998, pages 28-36 | |
| dc.identifier.uri | http://salesiana.dossiersoluciones.com/handle/123456789/33123 | |
| dc.subject | Machine Learning | |
| dc.subject | Artificial Intelligence | |
| dc.subject | I.2.6 | |
| dc.title | KnightCap: A chess program that learns by combining TD(lambda) with game-tree search | |
| dc.type | text |