Advertisement

Automated Discovery of Search-Extension Features

  • Pálmi Skowronski
  • Yngvi Björnsson
  • Mark H. M. Winands
Part of the Lecture Notes in Computer Science book series (LNCS, volume 6048)

Abstract

One of the main challenges with selective search extensions is designing effective move categories (features). Usually, it is a manual trial-and-error task, which requires both intuition and expert human knowledge. Automating this task potentially enables the discovery of both more complex and more effective move categories. The current work introduces Gradual Focus, an algorithm for automatically discovering interesting move categories for selective search extensions. The algorithm iteratively creates new more refined move categories by combining features from an atomic feature set. Empirical data is presented for the game Breakthrough showing that Gradual Focus looks at a number of combinations that is two orders of magnitude fewer than a brute-force method does, while preserving adequate precision and recall.

Keywords

Atomic Feature Pruning Method Move Category Interesting Combination Neutral Feature 
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.
    Anantharaman, T.S., Campbell, M.S., Hsu, F.: Singular extensions: adding selectivity to brute-force searching. Artificial Intelligence 43(1), 99–109 (1990)CrossRefGoogle Scholar
  2. 2.
    Beal, D.F., Smith, M.C.: Quantification of search extension benefits. ICCA Journal 8(4), 205–218 (1995)Google Scholar
  3. 3.
    Hyatt, R.M.: Crafty. A chess program (1996) (March 27, 2008), ftp://ftp.cis.uab.edu/pub/hyatt
  4. 4.
    Levy, D., Broughton, D., Taylor, M.: The SEX algorithm in computer chess. ICCA Journal 12(1), 10–21 (1989)Google Scholar
  5. 5.
    Tsuruoka, Y., Yokoyama, D., Chikayama, T.: Game-tree search algorithm based on realization probability. ICGA Journal 25(3), 146–153 (2002)Google Scholar
  6. 6.
    Winands, M.H.M., Björnsson, Y.: Enhanced realization probability search. New Mathematics and Natural Computation 4(3), 329–342 (2008)zbMATHCrossRefMathSciNetGoogle Scholar
  7. 7.
    Björnsson, Y.: Selective Depth-First Game-Tree Search. Phd dissertation, University of Alberta (2002)Google Scholar
  8. 8.
    Björnsson, Y., Marsland, T.A.: Learning extension parameters in game-tree search. Information Sciences 154(3-4), 95–118 (2003)CrossRefMathSciNetGoogle Scholar
  9. 9.
    Kocsis, L., Szepesvári, C., Winands, M.H.M.: RSPSA: Enhanced Parameter Optimization in Games. In: van den Herik, H.J., Hsu, S.-C., Hsu, T.-s., Donkers, H.H.L.M(J.) (eds.) CG 2005. LNCS, vol. 4250, pp. 39–56. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  10. 10.
    Fawcett, T.E., Utgoff, P.E.: Automatic feature generation for problem solving systems. In: Intern. Conf. on Machine Learning (ICML), pp. 144–153 (1992)Google Scholar
  11. 11.
    Kaneko, T., Yamaguchi, K., Kawai, S.: Automated identification of patterns in evaluation functions. In: Advances in Computer Games, vol. 10, pp. 279–298 (2003)Google Scholar
  12. 12.
    Buro, M.: From simple features to sophisticated evaluation functions. In: van den Herik, H.J., Iida, H. (eds.) CG 1998. LNCS, vol. 1558, pp. 126–145. Springer, Heidelberg (1999)CrossRefGoogle Scholar
  13. 13.
    Buro, M.: Experiments with Multi-ProbCut and a new high-quality evaluation function for Othello. In: Games in AI Research, pp. 77–96 (1999)Google Scholar
  14. 14.
    Sturtevant, N.R., White, A.M.: Feature construction for reinforcement learning in hearts. In: van den Herik, H.J., Ciancarini, P., Donkers, H.H.L.M(J.) (eds.) CG 2006. LNCS, vol. 4630, pp. 122–134. Springer, Heidelberg (2007)CrossRefGoogle Scholar
  15. 15.
    Finkelstein, L., Markovitch, S.: Learning to play chess selectively by acquiring move patterns. ICCA Journal 21(2), 100–119 (1998)Google Scholar
  16. 16.
    Handscomb, K.: 8×8 game design competition: The winning game: Breakthrough ... and two other favorites. Abstract Games Magazine 7 (2001)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2010

Authors and Affiliations

  • Pálmi Skowronski
    • 1
  • Yngvi Björnsson
    • 1
  • Mark H. M. Winands
    • 2
  1. 1.School of Computer ScienceReykjavík UniversityIcleand
  2. 2.Games and AI Group, Department of Knowledge EngineeringMaastricht UniversityMaastrichtThe Netherlands

Personalised recommendations