Logo des Repositoriums
 
Zeitschriftenartikel

A GGP Feature Learning Algorithm

Vorschaubild nicht verfügbar

Volltext URI

Dokumententyp

Text/Journal Article

Zusatzinformation

Datum

2011

Autor:innen

Zeitschriftentitel

ISSN der Zeitschrift

Bandtitel

Quelle

KI - Künstliche Intelligenz: Vol. 25, No. 1

Verlag

Springer

Zusammenfassung

This paper presents a learning algorithm for two-player, alternating move GGP games. The Game Independent Feature Learning algorithm, GIFL, uses the differences in temporally-related states to learn patterns that are correlated with winning or losing a GGP game. These patterns are then used to inform the search. GIFL is simple, robust and improves the quality of play in the majority of games tested. GIFL has been successfully used in the GGP program Maligne.

Beschreibung

Kirci, Mesut; Sturtevant, Nathan; Schaeffer, Jonathan (2011): A GGP Feature Learning Algorithm. KI - Künstliche Intelligenz: Vol. 25, No. 1. Springer. PISSN: 1610-1987. pp. 35-42

Schlagwörter

Feature learning , General game playing

Zitierform

DOI

Tags

Sammlungen

Künstliche Intelligenz 25(1) - März 2011