Advertisement

Local Move Prediction in Go

  • Erik van der Werf
  • Jos W. H. M. Uiterwijk
  • Eric Postma
  • Jaap van den Herik
Part of the Lecture Notes in Computer Science book series (LNCS, volume 2883)

Abstract

The paper presents a system that learns to predict local strong expert moves in the game of Go at a level comparable to that of strong human kyu players. This performance is achieved by four techniques. First, our training algorithm is based on a relative-target approach that avoids needless weight adaptations characteristic of most neural-network classifiers. Second, we reduce dimensionality through state-of-the-art feature extraction, and present two new feature-extraction methods, the Move Pair Analysis and the Modified Eigenspace Separation Transform. Third, informed pre-processing is used to reduce state-space complexity and to focus the feature extraction on important features. Fourth, we introduce and apply second-phase training, i.e., the retraining of the trained network with an augmented input constituting all pre-processed features. Experiments suggest that local move prediction will be a significant factor in enhancing the strength of Go programs.

Keywords

Linear Discriminant Analysis Local Move Legal Move Multi Layer Perceptron Scatter Matrix 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Bouzy, B., Cazenave, T.: Computer Go: An AI oriented survey. Artificial Intelligence 132, 39–102 (2001)zbMATHCrossRefMathSciNetGoogle Scholar
  2. 2.
    Müller, M.: Computer Go. Artificial Intelligence 134, 145–179 (2002)zbMATHCrossRefGoogle Scholar
  3. 3.
    Enderton, H.: The Golem Go program. Technical Report CMU-CS-92-101, School of Computer Science, Carnegie-Mellon University (1991)Google Scholar
  4. 4.
    Dahl, F.: Honte, a Go-playing program using neural nets. In: 16th International Conference on Machine Learning (1999)Google Scholar
  5. 5.
    Schraudolph, N., Dayan, P., Sejnowski, T.: Temporal difference learning of position evaluation in the game of Go. In: Cowan, J., Tesauro, G., Alspector, J. (eds.) Advances in Neural Information Processing 6, pp. 817–824. Morgan Kaufmann, San Francisco (1994)Google Scholar
  6. 6.
    Tesauro, G.: Connectionist learning of expert preferences by comparison training. In: Touretzky, D. (ed.) Advances in Neural Information Processing Systems 1 (NIPS 1988), pp. 99–106. Morgan Kaufmann, San Francisco (1989)Google Scholar
  7. 7.
    Riedmiller, M., Braun, H.: A direct adaptive method for faster backpropagation: the RPROP algorithm. In: IEEE Int. Conf. on Neural Networks (ICNN), pp. 586–591 (1993)Google Scholar
  8. 8.
    Jain, A., Chandrasekaran, B.: Dimensionality and sample size considerations in pattern recognition practice. In: Krishnaiah, P., Kanal, L. (eds.) Handbook of Statistics, vol. 2, pp. 835–855. North-Holland, Amsterdam (1982)Google Scholar
  9. 9.
    Bellman, R.: Adaptive Control Processes: A Guided Tour. Princeton University Press, Princeton (1961)zbMATHGoogle Scholar
  10. 10.
    Bishop, C.: Neural Networks for Pattern Recognition. Clarendon Press, Oxford (1995)Google Scholar
  11. 11.
    Jollife, I.: Principal Component Analysis. Springer, Heidelberg (1986)Google Scholar
  12. 12.
    Fukunaga, K.: Introduction to Statistical Pattern Recognition, 2nd edn. Academic Press, London (1990)zbMATHGoogle Scholar
  13. 13.
    Karhunen, J., Oja, E., Wang, L., Vigario, R., Joutsensalo, J.: A class of neural networks for independant component analysis. IEEE Transactions on Neural Networks 8, 486–504 (1997)CrossRefGoogle Scholar
  14. 14.
    Kohonen, T.: Self-organising maps. Springer, Heidelberg (1995)Google Scholar
  15. 15.
    Sammon Jr., J.: A non-linear mapping for data structure analysis. IEEE Transactions on Computers 18, 401–409 (1969)CrossRefGoogle Scholar
  16. 16.
    van der Werf, E.: Non-linear target based feature extraction by diabolo networks. Master’s thesis, Pattern Recognition Group, Department of Applied Physics, Faculty of Applied Sciences, Delft University of Technology (1999)Google Scholar
  17. 17.
    Torrieri, D.: The eigenspace separation transform for neural-network classifiers. Neural Networks 12, 419–427 (1999)CrossRefGoogle Scholar
  18. 18.
    Müller, M.: Computer Go as a sum of local games: An application of combinatorial game theory. PhD thesis, ETH Zürich (1995) Diss. ETH No. 11.006Google Scholar
  19. 19.
    Chen, K., Chen, Z.: Static analysis of life and death in the game of Go. Information Sciences 121, 113–134 (1999)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2003

Authors and Affiliations

  • Erik van der Werf
    • 1
  • Jos W. H. M. Uiterwijk
    • 1
  • Eric Postma
    • 1
  • Jaap van den Herik
    • 1
  1. 1.Search and Games Group, IKAT, Department of Computer ScienceUniversiteit Maastricht 

Personalised recommendations