On the Design and Training of Bots to Play Backgammon Variants

Conference paper
Part of the IFIP Advances in Information and Communication Technology book series (IFIPAICT, volume 381)


Recently, a backgammon bot named Palamedes won the first prize in backgammon at the 16th Computer Olympiad. Palamedes is an ongoing work aimed at developing intelligent bots to play a variety of popular backgammon variants. Currently, the Greek variants Portes, Plakoto and Fevga are supported. A different neural network has been designed, trained and evaluated for each one of these variants. This paper presents the details of the architecture and the training procedure for each case. New expert features as inputs to the networks are also introduced, whereas experimental results demonstrate improvement over previous versions of Palamedes.


TD(λNeural Networks Self-Play Backgammon Plakoto Fevga 


  1. 1.
    Andrews, R., Diederich, J., Tickle, A.: Survey and critique of techniques for extractingrules from trained artificial neural networks. Knowledge-Based Systems 8(6), 373–389 (1995)CrossRefGoogle Scholar
  2. 2.
    BackGammon Variants,
  3. 3.
  4. 4.
    Hauk, T., Buro, M., Schaeffer, J.: *-Minimax Performance in Backgammon. In: van den Herik, H.J., Björnsson, Y., Netanyahu, N.S. (eds.) CG 2004. LNCS, vol. 3846, pp. 51–66. Springer, Heidelberg (2006)CrossRefGoogle Scholar
  5. 5.
    Michie, D.: Game-playing and game-learning automata. In: Fox, L. (ed.) Advances in Programming and Non-Numerical Computation, pp. 183–200 (1966)Google Scholar
  6. 6.
  7. 7.
    Papahristou, N., Refanidis, I.: Training Neural Networks to Play Backgammon Variants Using Reinforcement Learning. In: Di Chio, C., Cagnoni, S., Cotta, C., Ebner, M., Ekárt, A., Esparcia-Alcázar, A.I., Merelo, J.J., Neri, F., Preuss, M., Richter, H., Togelius, J., Yannakakis, G.N. (eds.) EvoApplications 2011, Part I. LNCS, vol. 6624, pp. 113–122. Springer, Heidelberg (2011)CrossRefGoogle Scholar
  8. 8.
    Papahristou, N., Refanidis, I.: Improving Temporal Difference Learning Performance in Backgammon Variants. In: van den Herik, H.J., Plaat, A. (eds.) ACG 2011. LNCS, vol. 7168, pp. 134–145. Springer, Heidelberg (2012)CrossRefGoogle Scholar
  9. 9.
    Pubeval source code backgammon benchmark player,
  10. 10.
    Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning 3(1), 9–44 (1988)Google Scholar
  11. 11.
    Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Indroduction. MIT Press (1998)Google Scholar
  12. 12.
    Tesauro, G.: Practical issues in temporal differnce learning. Machine Learning 4, 257–277 (1992)Google Scholar
  13. 13.
    Tesauro, G.: Programming backgammon using self-teching neural nets. Artificial Intelligence 134, 181–199 (2002)zbMATHCrossRefGoogle Scholar
  14. 14.
  15. 15.
    Tesauro, G.: Temporal Difference Learning and TD-Gammon. Communications of the ACM 38(3), 58–68 (1995)CrossRefGoogle Scholar
  16. 16.
    Wiering, M.A.: Self-Play and Using an Expert to Learn to Play Backgammon with Temporal Difference Learning. Journal of Intelligent Learning Systems and Applications 2, 57–68 (2010)CrossRefGoogle Scholar
  17. 17.
    Wilson, D.R., Martinez, T.R.: The general inefficiency of batch training for gradient descent learning. Neural Networks 16(10), 1429–1451 (2003)CrossRefGoogle Scholar

Copyright information

© IFIP International Federation for Information Processing 2012

Authors and Affiliations

  1. 1.Department of Applied InformaticsUniversity of MacedoniaThessalonikiGreece

Personalised recommendations