A GGP Feature Learning Algorithm
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.
- Vollständige Referenz
- BibTeX
Kirci, M., Sturtevant, N. & Schaeffer, J.,
(2011).
A GGP Feature Learning Algorithm.
KI - Künstliche Intelligenz: Vol. 25, No. 1.
Springer.
(S. 35-42).
DOI: 10.1007/s13218-010-0081-8
@article{mci/Kirci2011,
author = {Kirci, Mesut AND Sturtevant, Nathan AND Schaeffer, Jonathan},
title = {A GGP Feature Learning Algorithm},
journal = {KI - Künstliche Intelligenz},
volume = {25},
number = {1},
year = {2011},
,
pages = { 35-42 } ,
doi = { 10.1007/s13218-010-0081-8 }
}
author = {Kirci, Mesut AND Sturtevant, Nathan AND Schaeffer, Jonathan},
title = {A GGP Feature Learning Algorithm},
journal = {KI - Künstliche Intelligenz},
volume = {25},
number = {1},
year = {2011},
,
pages = { 35-42 } ,
doi = { 10.1007/s13218-010-0081-8 }
}
Sollte hier kein Volltext (PDF) verlinkt sein, dann kann es sein, dass dieser aus verschiedenen Gruenden (z.B. Lizenzen oder Copyright) nur in einer anderen Digital Library verfuegbar ist. Versuchen Sie in diesem Fall einen Zugriff ueber die verlinkte DOI: 10.1007/s13218-010-0081-8
Haben Sie fehlerhafte Angaben entdeckt? Sagen Sie uns Bescheid: Feedback abschicken
Mehr Information
ISSN: 1610-1987
Datum: 2011
Typ: Text/Journal Article