Advertisement

Solving the Double Dummy Bridge Problem with Shallow Autoencoders

  • Jacek MańdziukEmail author
  • Jakub Suchan
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11304)

Abstract

This paper presents a new approach to solving the Double Dummy Bridge Problem (DDBP). The DDBP is a hard classification task utilized by bridge playing programs which rely on Monte Carlo simulations. The proposed method employs shallow autoencoders (AEs) during an unsupervised pretraining phase and Multilayer Perceptron networks (MLPs) with three hidden layers, built on top of these trained AEs, in the final fine-tuning training. The results are compared with our previous study in which MLPs with similar architectures, but with no use of AEs and pretraining, were employed to solve this task. Several conclusions concerning efficient weight topologies and fine-tuning schemes of the proposed model, as well as interesting weight patterns discovered in the trained networks are presented and explained.

Keywords

Autoencoder Double Dummy Bridge Problem Classification 

Notes

Acknowledgments

This work was supported by the Polish National Science Centre grant 2017/25/B/ST6/02061.

References

  1. 1.
    DDBP Github repository. https://github.com/holgus103/DDBP/
  2. 2.
    Amit, A., Markovitch, S.: Learning to bid in bridge. Mach. Learn. 63(3), 287–327 (2006)CrossRefGoogle Scholar
  3. 3.
    Beling, P.: Partition search revisited. IEEE Trans. Comput. Intell. AI Games 9(1), 76–87 (2017)CrossRefGoogle Scholar
  4. 4.
    David, O.E., Netanyahu, N.S., Wolf, L.: DeepChess: end-to-end deep neural network for automatic learning in chess. In: Villa, A.E.P., Masulli, P., Pons Rivero, A.J. (eds.) ICANN 2016. LNCS, vol. 9887, pp. 88–96. Springer, Cham (2016).  https://doi.org/10.1007/978-3-319-44781-0_11CrossRefGoogle Scholar
  5. 5.
    Dharmalingam, M., Amalraj, R.: Articifial neural network architecture for solving the double dummy bridge problem in contract bridge. Int. J. Adv. Res. Comput. Commun. Eng. 2(12), 4683–4691 (2013)Google Scholar
  6. 6.
    Dharmalingam, M., Amalraj, R.: A solution to the double dummy contract bridge problem influenced by supervised learning module adapted by artificial neural network. ICTACT J. Soft Comput. 5, 836–843 (2014)CrossRefGoogle Scholar
  7. 7.
    Dharmalingam, M., Amalraj, R.: Supervised Elman neural network architecture for solving double dummy bridge problem in contract bridge. Int. J. Sci. Res. (IJSR) 3(6), 2745–2750 (2014)Google Scholar
  8. 8.
    Francis, H., Truscott, A., Francis, D. (eds.): The Official Encyclopedia of Bridge, 5th edn. American Contract Bridge League Inc., Memphis (1994)Google Scholar
  9. 9.
    Ginsberg, M.L.: http://www.gibware.com
  10. 10.
    Ginsberg, M.L.: Library of double-dummy results. http://www.cirl.uoregon.edu/ginsberg/gibresearch.html
  11. 11.
    Ho, C.Y., Lin, H.T.: Contract bridge bidding by learning. In: AAAI Workshop: Computer Poker and Imperfect Information (2015)Google Scholar
  12. 12.
    Mańdziuk, J., Mossakowski, K.: Example-based estimation of hand’s strength in the game of bridge with or without using explicit human knowledge. In: IEEE Symposium on Computational Intelligence in Data Mining, Honolulu, Hawaii, USA, pp. 413–420 (2007)Google Scholar
  13. 13.
    Mańdziuk, J., Mossakowski, K.: Neural networks compete with expert human players in solving the double dummy bridge problem. In: 2009 IEEE Symposium on Computational Intelligence and Games, pp. 117–124, September 2009Google Scholar
  14. 14.
    Mossakowski, K., Mańdziuk, J.: Artificial neural networks for solving double dummy bridge problems. In: Rutkowski, L., Siekmann, J.H., Tadeusiewicz, R., Zadeh, L.A. (eds.) ICAISC 2004. LNCS (LNAI), vol. 3070, pp. 915–921. Springer, Heidelberg (2004).  https://doi.org/10.1007/978-3-540-24844-6_142CrossRefzbMATHGoogle Scholar
  15. 15.
    Mossakowski, K., Mańdziuk, J.: Neural networks and the estimation of hands’ strength in contract bridge. In: Rutkowski, L., Tadeusiewicz, R., Zadeh, L.A., Żurada, J.M. (eds.) ICAISC 2006. LNCS (LNAI), vol. 4029, pp. 1189–1198. Springer, Heidelberg (2006).  https://doi.org/10.1007/11785231_124CrossRefGoogle Scholar
  16. 16.
    Mossakowski, K., Mańdziuk, J.: Learning without human expertise: a case study of the double dummy bridge problem. IEEE Trans. Neural Netw. 20(2), 278–299 (2009)CrossRefGoogle Scholar
  17. 17.
    Muthusamy, D.: Double dummy bridge problem in contract bridge: an overview. Artif. Intell. Syst. Mach. Learn. 10(1), 1–7 (2018)Google Scholar
  18. 18.
    Ng, A., Ngiam, J., Foo, C.Y., Mai, Y., Suen, C.: UFLDL tutorial. http://ufldl.stanford.edu/wiki/index.php/UFLDL_Tutorial
  19. 19.
    Yegnanarayana, B., Khemani, D., Sarkar, M.: Neural networks for contract bridge bidding. Sadhana 21(3), 395–413 (1996)CrossRefGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  1. 1.Faculty of Mathematics and Information ScienceWarsaw University of TechnologyWarsawPoland

Personalised recommendations