EUVIMEDEUVIMED entdecken
Crossref

A methodology for learning players' styles from game records

Mark Levene, Trevor Fenner

International Journal of Artificial Intelligence and Soft Computing · 2011 · 2 (4) · 272

DOI: 10.1504/ijaisc.2011.042711 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Artificial Intelligence and Soft Computing, 2011. Verfasst von Mark Levene und 1 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We describe a preliminary investigation into learning a Chess player|s style from game records. The method is based on attempting to learn features of a player|s individual evaluation function using the method of temporal differences, with the aid of a conventional Chess engine architecture. Some encouraging results were obtained in learning the styles of two Chess world champions, and we report on our attempt to use the learnt styles to discriminate between the players from game records, by trying to detect who was playing white and who was playing black. We also discuss some limitations of our approach.

Zitieren

APA

Levene, M., & Fenner, T. (2011). A methodology for learning players' styles from game records. International Journal of Artificial Intelligence and Soft Computing, 2(4), 272. https://doi.org/10.1504/ijaisc.2011.042711

Vancouver

Levene M, Fenner T. A methodology for learning players' styles from game records. International Journal of Artificial Intelligence and Soft Computing. 2011;2(4):272. doi:10.1504/ijaisc.2011.042711

BibTeX
@article{Levene2011,
  author = {Levene, Mark and Fenner, Trevor},
  title = {A methodology for learning players' styles from game records},
  journal = {International Journal of Artificial Intelligence and Soft Computing},
  year = {2011},
  volume = {2},
  number = {4},
  pages = {272},
  doi = {10.1504/ijaisc.2011.042711}
}
Kostenlos starten →