Abstract
This paper investigates methods for estimating potential territory in the game of Go. We have tested the performance of direct methods known from the literature, which do not require a notion of life and death. Several enhancements are introduced which can improve the performance of the direct methods. New trainable methods are presented for learning to estimate potential territory from examples. The trainable methods can be used in combination with our previously developed method for predicting life and death [25]. Experiments show that all methods are greatly improved by adding knowledge of life and death.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
Bellman, R.E.: Adaptive Control Processes: A Guided Tour. Princeton University Press, Princeton (1961)
Benson, D.B.: Life in the game of Go. Information Sciences 10, 17–29 (1976); Levy, D.N.L. (ed.): Reprinted in Computer Games, vol. II, pp. 203–213. Springer, New York (1988) ISBN 0-387-96609-9
Bouzy, B.: Mathematical morphology applied to computer Go. International Journal of Pattern Recognition and Artificial Intelligence 17(2), 257–268 (2003)
Bouzy, B.: Personal communication (2004)
Bouzy, B., Cazenave, T.: Computer Go: An AI oriented survey. Artificial Intelligence 132(1), 39–102 (2001)
Brügmann, B.: Monte Carlo Go (March 1993), Available at, ftp://ftp.cse.cuhk.edu.hk/pub/neuro/GO/mcgo.tex
Chen, K.: Some practical techniques for global search in Go. ICGA Journal 23(2), 67–74 (2000)
Chen, K.: Computer Go: Knowledge, search, and move decision. ICGA Journal 24(4), 203–215 (2001)
Chen, Z.: Semi-empirical quantitative theory of Go part i: Estimation of the influence of a wall. ICGA Journal 25(4), 211–218 (2002)
Dahl, F.A.: Honte, a Go-playing program using neural nets. In: Fürnkranz, J., Kubat, M. (eds.) Machines that Learn to Play Games, ch.10, pp. 205–223. Nova Science Publishers, Huntington (2001)
Enzenberger, M.: The integration of a priori knowledge into a Go playing neural network (September 1996), Available at, http://www.markus-enzenberger.de/neurogo1996.html
Enzenberger, M.: Evaluation in Go by a neural network using soft segmentation. In: van den Herik, H.J., Iida, H., Heinz, E.A. (eds.) Advances in Computer Games: Many Games, Many Challenges, Boston, pp. 97–108. Kluwer Academic Publishers, Dordrecht (2003)
GnuGo (2003)
Jain, A., Chandrasekaran, B.: Dimensionality and sample size considerations in pattern recognition practice. In: Krishnaiah, P.R., Kanal, L.N. (eds.) Handbook of Statistics, vol. 2, pp. 835–855. North-Holland, Amsterdam (1982)
Müller, M.: Playing it safe: Recognizing secure territories in computer Go by using static rules and search. In: Matsubara, H. (ed.) Proceedings of the Game Programming Workshop in Japan 1997, pp. 80–86. Computer Shogi Association, Tokyo (1997)
Müller, M.: Computer Go. Artificial Intelligence 134(1-2), 145–179 (2002)
Müller, M.: Position evaluation in computer Go. ICGA Journal 25(4), 219–228 (2002)
NNGS, The no name Go server game archive (2002)
Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation: the RPROP algorithm. In: Rusini, H. (ed.) Proceedings of the IEEE Int. Conf. on Neural Networks (ICNN), pp. 586–591 (1993)
Ryder, J.L.: Heuristic analysis of large trees as generated in the game of Go. PhD thesis, Stanford University (1971)
Schraudolph, N.N., Dayan, P., Sejnowski, T.J.: Temporal difference learning of position evaluation in the game of Go. In: Cowan, J.D., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing, vol. 6, pp. 817–824. Morgan Kaufmann, San Francisco (1994)
van der Steen, J.: Gobase.org - Go games, Go information and Go study tools (2003)
van der Werf, E.C.D., van den Herik, H.J., Uiterwijk, J.W.H.M.: 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: Many Games, Many Challenges, Boston, pp. 143–158. Kluwer Academic Publishers, Dordrecht (2003)
van der Werf, E.C.D., van den Herik, H.J., Uiterwijk, J.W.H.M.: Solving Go on small boards. ICGA Journal 26(2), 92–107 (2003)
van der Werf, E.C.D., Winands, M.H.M., van den Herik, H.J., Uiterwijk, J.W.H.M.: Learning to predict life and death from Go game records. In: Chen, K., et al. (eds.) Proceedings of JCIS 2003 7th Joint Conference on Information Sciences, pp. 501–504. JCIS/Association for Intelligent Machinery, Inc. (2003)
Zobrist, A.L.: A model of visual organization for the game Go. In: Proceedings of AFIPS 1969 Spring Joint Computer Conference, vol. 34, pp. 103–112. AFIPS Press (1969)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
van der Werf, E.C.D., van den Herik, H.J., Uiterwijk, J.W.H.M. (2006). Learning to Estimate Potential Territory in the Game of Go. In: van den Herik, H.J., Björnsson, Y., Netanyahu, N.S. (eds) Computers and Games. CG 2004. Lecture Notes in Computer Science, vol 3846. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11674399_6
Download citation
DOI: https://doi.org/10.1007/11674399_6
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-32488-1
Online ISBN: 978-3-540-32489-8
eBook Packages: Computer ScienceComputer Science (R0)