A GGP Feature Learning Algorithm
| dc.contributor.author | Kirci, Mesut | |
| dc.contributor.author | Sturtevant, Nathan | |
| dc.contributor.author | Schaeffer, Jonathan | |
| dc.date.accessioned | 2018-01-08T09:14:53Z | |
| dc.date.available | 2018-01-08T09:14:53Z | |
| dc.date.issued | 2011 | |
| dc.description.abstract | 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. | |
| dc.identifier.pissn | 1610-1987 | |
| dc.identifier.uri | https://dl.gi.de/handle/20.500.12116/11193 | |
| dc.publisher | Springer | |
| dc.relation.ispartof | KI - Künstliche Intelligenz: Vol. 25, No. 1 | |
| dc.relation.ispartofseries | KI - Künstliche Intelligenz | |
| dc.subject | Feature learning | |
| dc.subject | General game playing | |
| dc.title | A GGP Feature Learning Algorithm | |
| dc.type | Text/Journal Article | |
| gi.citation.endPage | 42 | |
| gi.citation.startPage | 35 |