Feature learning using state differences

• Main Author: KIRCI, MESUT
• Other Authors: Schaeffer, Jonathan (Computing Science)
• Format: Others
• Language: en
• Published: 2010
• Subjects: feature learning; general game playing
• Online Access: http://hdl.handle.net/10048/1011

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.