TU Darmstadt / ULB / TUbiblio

Learning of Piece Values for Chess Variants

Droste, Sacha ; Fürnkranz, Johannes (2008)
Learning of Piece Values for Chess Variants.
Report, Bibliographie

Kurzbeschreibung (Abstract)

In this paper we describe a set of experiments for learning a the values of chess pieces for the popular chess variants crazyhouse, suicide, and atomic chess. We follow an established methodology that relies on reinforcement learning from self-games to learn piece values and piece-square tables for these chess variants. The learned piece values are quite different from those of standard chess, and in several ways surprising, but they generally outperform those that have been previously used in the literature, and in implementations of computer players for these games. The results also underline the practical importance of piece-square value tables for tactical variants of the game.

Typ des Eintrags: Report
Erschienen: 2008
Autor(en): Droste, Sacha ; Fürnkranz, Johannes
Art des Eintrags: Bibliographie
Titel: Learning of Piece Values for Chess Variants
Sprache: Englisch
Publikationsjahr: 2008
URL / URN: http://www.ke.informatik.tu-darmstadt.de/publications/report...
Kurzbeschreibung (Abstract):

In this paper we describe a set of experiments for learning a the values of chess pieces for the popular chess variants crazyhouse, suicide, and atomic chess. We follow an established methodology that relies on reinforcement learning from self-games to learn piece values and piece-square tables for these chess variants. The learned piece values are quite different from those of standard chess, and in several ways surprising, but they generally outperform those that have been previously used in the literature, and in implementations of computer players for these games. The results also underline the practical importance of piece-square value tables for tactical variants of the game.

ID-Nummer: TUD-KE-2008-07
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik > Knowledge Engineering
20 Fachbereich Informatik
Hinterlegungsdatum: 24 Jun 2011 15:12
Letzte Änderung: 05 Mär 2013 09:49
PPN:
Export:
Suche nach Titel in: TUfind oder in Google
Frage zum Eintrag Frage zum Eintrag

Optionen (nur für Redakteure)
Redaktionelle Details anzeigen Redaktionelle Details anzeigen