A methodology for learning players
作者： Mark Levene , Trevor Fenner
DOI: 10.1504/IJAISC.2011.042711
关键词: Computer science 、 Temporal difference learning 、 Sequential game 、 White (horse) 、 Evaluation function 、 Artificial intelligence 、 Computer chess 、 Style (sociolinguistics)
摘要: We describe a preliminary investigation into learning Chess player|s style from game records. The method is based on attempting to learn features of individual evaluation function using the temporal differences, with aid conventional engine architecture. Some encouraging results were obtained in styles two world champions, and we report our attempt use learnt discriminate between players records, by trying detect who was playing white black. also discuss some limitations approach.
bbk.ac.uk
arxiv.org
sci-hub.se 参考文章(31)
Yngvi Björnsson, Tony Marsland, From minimax to Manhattan national conference on artificial intelligence. pp. 31- 36 ,(1997)
Stuart M. Cracraft, Bitmap Move Generation in Chess ICGA Journal. ,vol. 7, pp. 146- 153 ,(1984) , 10.3233/ICG-1984-7304
Yoshimasa Tsuruoka, Daisaku Yokoyama, Takashi Chikayama, Game-tree Search Algorithm based on Realization Probability ICGA Journal. ,vol. 25, pp. 145- 152 ,(2002) , 10.3233/ICG-2002-25304
Markian Hlynka, Vili Jussila, Jonathan Schaeffer, Temporal difference learning applied to a high-performance game-playing program international joint conference on artificial intelligence. pp. 529- 534 ,(2001)
Thong B. Trinh, Anwer S. Bashi, Nikhil Deshpande, Temporal Difference Learning in Chinese Chess industrial and engineering applications of artificial intelligence and expert systems. pp. 612- 618 ,(1998) , 10.1007/3-540-64574-8_447
Robert J. Marks, Russell D. Reed, Neural Smithing: Supervised Learning in Feedforward Artificial Neural Networks ,(1999)
Jonathan Schaeffer, One Jump Ahead: Challenging Human Supremacy in Checkers ,(1997)
Trevor Fenner, Mark Levene, MOVE GENERATION WITH PERFECT HASH FUNCTIONS ICGA Journal. ,vol. 31, pp. 3- 12 ,(2008) , 10.3233/ICG-2008-31102
Henk Mannen, MA Wiering, A Nowe, K Steenhout, Learning to Play Chess using TD(lambda)-learning with database games Benelearn'04: Proceedings of the Thirteenth Belgian-Dutch Conference on Machine Learning. pp. 72- 79 ,(2004)
John H. Holland, Emergence: From Chaos to Order ,(1998)