Associating domain-dependent knowledge and Monte Carlo approaches within a Go program

This paper underlines the association of two computer go approaches, a domain-dependent knowledge approach and Monte Carlo. First, the strengthes and weaknesses of the two existing approaches are related. Then, the association is described in two steps. A first step consists in using domain-dependent knowledge within the random games enabling the program to compute evaluations that are more significant than before. A second step simply lies in pre-processing the Monte Carlo process with a knowledge-based move generator in order to speed up the program and to eliminate tactically bad moves. We set up experiments demonstrating the relevance of this association, used by Indigo at the 8th computer olympiad as well.

[1]  Bernd Brügmann Max-Planck.  Monte Carlo Go , 1993 .

[2]  Peter Dayan,et al.  Technical Note: Q-Learning , 2004, Machine Learning.

[3]  Bruno Bouzy.  The Move-Decision Strategy of Indigo , 2003, J. Int. Comput. Games Assoc..

[4]  C. D. Gelatt,et al.  Optimization by Simulated Annealing , 1983, Science.

[5]  Omid Omidvar,et al.  Neural Networks and Pattern Recognition , 1997 .

[6]  Jonathan Schaeffer,et al.  The challenge of poker , 2002, Artif. Intell..

[7]  Gerald Tesauro,et al.  On-line Policy Improvement using Monte-Carlo Search , 1996, NIPS.

[8]  Richard S. Sutton,et al.  Reinforcement Learning: An Introduction , 1998, IEEE Trans. Neural Networks.

[9]  Bruce Abramson,et al.  Expected-Outcome: A General Model of Static Evaluation , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Richard S. Sutton,et al.  Introduction to Reinforcement Learning , 1998 .

[11]  Bruno Bouzy,et al.  Computer Go: An AI oriented survey , 2001, Artif. Intell..

[12]  Terrence J. Sejnowski,et al.  Temporal Difference Learning of Position Evaluation in the Game of Go , 1993, NIPS.

[13]  Peter Dayan,et al.  Q-learning , 1992, Machine Learning.

[14]  Bruno Bouzy.  Mathematical Morphology Applied to Computer Go , 2003, Int. J. Pattern Recognit. Artif. Intell..

[15]  Christopher M. Bishop,et al.  Neural networks for pattern recognition , 1995 .

[16]  Bruno Bouzy,et al.  Monte-Carlo Go Developments , 2003, ACG.

[17]  Ken Chen,et al.  GNU Go WINS 19x19 GO TOURNAMENT , 2006 .

[18]  E. van der Werf.  AYA WINS 9 x 9 GO TOURNAMENT , 2003 .

[19]  Richard E. Korf,et al.  Best-First Minimax Search , 1996, Artif. Intell..

[20]  Anil K. Jain,et al.  Neural networks and pattern recognition , 1994 .