Game playing styles
Posted: Friday, 8 May 2009 12:34
Research carried out by Prof. Mark Levene and Dr. Trevor Fenner on A Methodology for Learning Players' Styles from Game Records recently featured in Wired and Technology Review.
The research was focused on a preliminary investigation into learning a Chess player's style from game records. The method used attempts to learn features that make up a player's 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 recent Chess world champions, and an 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 was carried out. The method used may also be applicable to other strategic games, and may even be generalisable to other domains where sequences of agents' actions are recorded.