Abstract
This paper presents a learning system for scoring final positions in the Game of Go. Our system learns to predict life and death from labelled game records. 98.9% of the positions are scored correctly and nearly all incorrectly scored positions are recognized. By providing reliable score information our system opens the large source of Go knowledge implicitly available in human game records, thus paving the way for a successful application of machine learning in Go.
Chapter PDF
Similar content being viewed by others
References
Bouzy, B. and Cazenave, T. (2001). Computer Go: An AI oriented survey. Artificial Intelligence, 132 (1): 39–102.
Chen, K. and Chen, Z. (1999). Static analysis of life and death in the game of Go. Information Sciences, 121: 113–134.
Dahl, F. (2001). Honte, a go-playing program using neural nets. In Fürnkranz, J. and Kubat, M., editors, Machines that Learn to Play Games, chapter 10, pages 205–223. Nova Science Publishers, Huntington, NY.
Duin, R. (2000). PRTools, a Matlab Toolbox for Pattern Recognition
Enderton, H. (1991). The Golem Go program. Technical Report CMU-CS-92–101, School of Computer Science, Carnegie-Mellon University.
Enzenberger, M. (1996). The integration of a priori knowledge into a Go playing neural network. Unpublished Manuscript.
Fotland, D. (2002). Static eye analysis in `THE MANY FACES OF Go’. ICGA Journal, 25 (4): 201–210.
Jain, A. K., Duin, R. P. W., and Mao, J. (2000). Statistical pattern recognition: A review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22 (1): 4–37.
Müller, M. (1997). Playing it safe: Recognizing secure territories in computer Go by using static rules and search. In Matsubara, H., editor, Proceedings of the Game Programming Workshop in Japan ‘87, pages 80–86. Computer Shogi Association, Tokyo, Japan.
Müller, M. (2002). Computer Go. Artificial Intelligence, 134 (1–2): 145–179.
Myers, B. (2002). The 21st century championship cup 2002. ICGA Journal, 25 (4): 245.
NNGS (2002). The no name go server game archive. http://nngs.cosmic.org/gamesearch.html.
Schraudolph, N., Dayan, P., and Sejnowski, T. (1994). Temporal difference learning of position evaluation in the game of Go. In Cowan, J. D., Tesauro, G., and Alspector, J., editors, Advances in Neural Information Processing 6, pages 817–824.
Morgan Kaufmann, San Francisco, CA. Tesauro, G. (1995). Temporal difference learning and TD-Gammon Communications of the ACM, 38 (3): 58–68.
van der Werf, E. C. D., Uiterwijk, J. W. H. M., Postma, E. O., and van den Herik, H. J. (2002). Local move prediction in Go. In Proceedings of the 3rd International Conference on Computers and Games (CG’02) (Edmonton, CA, July 25–27 To appear in LNCS, © Springer-Verlag.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 IFIP International Federation for Information Processing
About this chapter
Cite this chapter
van der Werf, E.C.D., van den Herik, H.J., Uiterwijk, J.W.H.M. (2004). Learning to Score Final Positions in the Game of Go. In: Van Den Herik, H.J., Iida, H., Heinz, E.A. (eds) Advances in Computer Games. IFIP — The International Federation for Information Processing, vol 135. Springer, Boston, MA. https://doi.org/10.1007/978-0-387-35706-5_10
Download citation
DOI: https://doi.org/10.1007/978-0-387-35706-5_10
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4757-4424-8
Online ISBN: 978-0-387-35706-5
eBook Packages: Springer Book Archive