A GGP Feature Learning Algorithm

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 infor...

Full description

Saved in:
Bibliographic Details
Published inKI. Künstliche Intelligenz (Oldenbourg) Vol. 25; no. 1; pp. 35 - 42
Main Authors Kirci, Mesut, Sturtevant, Nathan, Schaeffer, Jonathan
Format Magazine Article
LanguageEnglish
Published Berlin/Heidelberg Springer-Verlag 01.03.2011
Subjects
Artificial Intelligence
Computer Science
Fachbeitrag
Software Engineering/Programming and Operating Systems
Feature learning
General game playing
Online AccessGet full text
ISSN0933-1875
1610-1987
DOI10.1007/s13218-010-0081-8

Cover

More Information
Summary: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 .
ISSN:0933-1875
1610-1987
DOI:10.1007/s13218-010-0081-8