Advertisement

From Simple Features to Sophisticated Evaluation Functions

  • Michael Buro
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 1558)

Abstract

This paper discusses a practical framework for the semi-automatic construction of evaluation-functions for games. Based on a structured evaluation function representation, a procedure for exploring the feature space is presented that is able to discover new features in a computationally feasible way. Besides the theoretical aspects, related practical issues such as the generation of training positions, feature selection, and weight fitting in large linear systems are discussed. Finally, we present experimental results for Othello, which demonstrate the potential of the described approach.

Keywords

automatic feature construction GLEM Othello 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. [1]
    M. Buro. Experiments with Multi-Probcut and a new high-quality evaluation function for Othello. Workshop on Game-Tree Search, NEC Research Institute, 1997.Google Scholar
  2. [2]
    M. Buro. The Othello match of the year: Takeshi Murakami vs. Logistello. ICCA Journal, 20(3):189–193, 1997.Google Scholar
  3. [3]
    S.J. Hanson. Meiosis networks. Advances in Neural Information Processing Systems, pages 553–541, 1990.Google Scholar
  4. [4]
    F. Hsu, S. Anantharaman, M.S. Campbell, and A. Nowatzyk. Deep Thought. In T.A. Marsland and J. Schaeffer, editors, Computer, Chess, and Cognition, pages 55–78. Springer Verlag, 1990.Google Scholar
  5. [5]
    R.A. Levinson and R. Snyder. Adaptive pattern-oriented chess. In L. Birnbaum and G. Collins, editors, Proceedings of the 8th International Workshop on Machine Learning, pages 85–89, 1991.Google Scholar
  6. [6]
    W.H. Press, S.A. Teukolsky, W.T. Vetterling, and B.P. Flannery. Numerical Recipes, 2nd edition. Cambridge University Press, 1992.Google Scholar
  7. [7]
    A.L. Samuel. Some studies in machine learning using the game of checkers. IBM Journal of Research and Development, 3(3):211–229, 1959.MathSciNetCrossRefGoogle Scholar
  8. [8]
    G. Tesauro. TD-Gammon, a self-teaching backgammon program, reaches master-level play. Neural Computation, 6(2):215–219, 1994.CrossRefGoogle Scholar
  9. [9]
    G. Tesauro. Temporal difference learning and TD-Gammon. Communications of the ACM, 38(3):58–68, 1995.CrossRefGoogle Scholar
  10. [10]
    P.E. Utgoff. Constructive function approximation. Technical Report 97-4, Univ. of Mass., 1997.Google Scholar
  11. [11]
    M. Wynne-Jones. Node splitting: A constructive algorithm for feed-forward neural networks. Neural Computing and Applications, 1(1):17–22, 1993.CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1999

Authors and Affiliations

  • Michael Buro
    • 1
  1. 1.NEC Research InstitutePrincetonUSA

Personalised recommendations