Domain-independent feature learning is a hard problem. This is reflected by lack of broad research in the area. The goal of General Game Playing (GGP) can be described as designing computer programs that can play a variety of games given only a logical game description. Any learning has to be domain-independent in the GGP framework. Learning algorithms have not been an essential part of all successful GGP programs. This thesis presents a feature learning approach, GIFL, for 2-player, alternating move games using state differences. The algorithm is simple, robust and improves the quality of play. GIFL is implemented in a GGP program, Maligne. The experiments show that GIFL outperforms standard UCT algorithm in nine out of fifteen games and loses performance only in one game.
Identifer | oai:union.ndltd.org:LACETR/oai:collectionscanada.gc.ca:AEU.10048/1011 |
Date | 06 1900 |
Creators | KIRCI, MESUT |
Contributors | Schaeffer, Jonathan (Computing Science), Sturtevant, Nathan (Computing Science), Buro, Michael (Computing Science), Gouglas, Sean (History and Classics) |
Source Sets | Library and Archives Canada ETDs Repository / Centre d'archives des thèses électroniques de Bibliothèque et Archives Canada |
Language | English |
Detected Language | English |
Type | Thesis |
Format | 448610 bytes, application/pdf |
Page generated in 0.0015 seconds