Advertisement

Optimistic Heuristics for MineSweeper

  • Olivier Buffet
  • Chang-Shing Lee
  • Woan-Tyng Lin
  • Olivier Teytuad
Part of the Smart Innovation, Systems and Technologies book series (SIST, volume 20)

Abstract

We present a combination of Upper Confidence Tree (UCT) and domain specific solvers, aimed at improving the behavior of UCT for long term aspects of a problem. Results improve the state of the art, combining top performance on small boards (where UCT is the state of the art) and on big boards (where variants of CSP rule).

Keywords

Constraint Satisfaction Problems Upper Confidence Tree Minesweeper 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Ben-Ari, M.M.: Minesweeper as an np-complete problem. SIGCSE Bull. 37, 39–40 (2005)CrossRefGoogle Scholar
  2. 2.
    Chaslot, G., Winands, M., Uiterwijk, J., van den Herik, H., Bouzy, B.: Progressive Strategies for Monte-Carlo Tree Search. In: Wang, P., et al. (eds.) Proceedings of the 10th Joint Conference on Information Sciences (JCIS 2007), pp. 655–661. World Scientific Publishing Co. Pte. Ltd. (2007)Google Scholar
  3. 3.
    Couetoux, A., Milone, M., Teytaud, O.: Consistent belief state estimation, with application to mines. In: Proceedings of the 2011 Conference on Technologies and Application of Artificial Intelligence (TAAI 2011), Taoyuan, Taiwan, November 11-13 (2011)Google Scholar
  4. 4.
    Coulom, R.: Computing elo ratings of move patterns in the game of Go. In: Computer Games Workshop 2007, Amsterdam, The Netherlands (2007)Google Scholar
  5. 5.
    Gelly, S.: Une contribution l’apprendissage par renforcement: application au Computer GO. PhD thesis, Université Paris-Sud (September 2007)Google Scholar
  6. 6.
    Gelly, S., Silver, D.: Combining online and offline knowledge in UCT. In. In: Proceedings of the 24th International Conference on Machine Learning (CML 2007), pp. 273–280. ACM Press, New York (2007)CrossRefGoogle Scholar
  7. 7.
    Hein, K.B., Weiss, R.: Minesweeper for sensor networks–making event detection in sensor networks dependable. In: Proceedings of the 2009 International Conference on Computational Science and Engineering (CSE 2009), vol. 1, pp. 388–393. IEEE Computer Society, Washington, DC (2009)CrossRefGoogle Scholar
  8. 8.
    Kaye, R.: Minesweeper is np-complete. Mathematical Intelligencer 22, 915 (2000)MathSciNetCrossRefGoogle Scholar
  9. 9.
    Kocsis, L., Szepesvari, C.: Bandit based Monte-Carlo planning. In: 15th European Conference on Machine Learning (ECML), pp. 282–293 (2006)Google Scholar
  10. 10.
    Lee, C.S., Wang, M.H., Chaslot, G., Hoock, J.B., Rimmel, A., Teytaud, O., Tsai, S.R., Hsu, S.C., Hong, T.P.: The Computational Intelligence of MoGo Revealed in Taiwan’s Computer Go Tournaments. IEEE Transactions on Computational Intelligence and AI in Games 1, 73–89 (2009)CrossRefGoogle Scholar
  11. 11.
    Legendre, M., Hollard, K., Buffet, O., Dutech, A.: Minesweeper: Where to probe? Technical Report RR-8041, INRIA (2012)Google Scholar
  12. 12.
    Nakov, P., Wei, Z.: Minesweeper, #minesweeper. Technical report, EECS, Berkeley (2003)Google Scholar
  13. 13.
    Sebag, M., Teytaud, O.: Combining Myopic Optimization and Tree Search: Application to MineSweeper. In: Learning and Intelligent Optimization Conference, LION6, Paris, France, January 16-20 (2012)Google Scholar
  14. 14.
    Studholme, C.: Minesweeper as a constraint satisfaction problem. Unpublished project report (2000)Google Scholar
  15. 15.
    Wang, Y., Audibert, J.Y., Munos, R.: Algorithms for infinitely many-armed bandits. In: Advances in Neural Information Processing Systems, vol. 21 (2008)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Olivier Buffet
    • 3
  • Chang-Shing Lee
    • 2
  • Woan-Tyng Lin
    • 2
  • Olivier Teytuad
    • 1
    • 2
    • 4
  1. 1.TAO-INRIA, LRI, CNRS UMR 8623Université Paris-SudOrsayFrance
  2. 2.National University of TainanTainanTaiwan
  3. 3.MAIA team, LORIA, INRIAUniversit de LorraineLorraineFrance
  4. 4.Montefiore InstituteUniversité de LiègeLiègeBelgium

Personalised recommendations