Abstract
Backgammon is a board game that has been studied considerably by computer scientists. Apart from standard backgammon, several yet unexplored variants of the game exist, which use the same board, number of checkers, and dice but may have different rules for moving the checkers, starting positions and movement direction. This paper studies two popular variants in Greece and neighboring countries, named Fevga and Plakoto. Using reinforcement learning and Neural Network function approximation we train agents that learn a game position evaluation function for these games. We show that the resulting agents significantly outperform the open-source program Tavli3D.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
BackGammon Variants, http://www.bkgm.com/variants
van Eck, N.J., van Wezel, M.: Application of reinforcement learning to the game of Othello. Computers and Operations Research 35(6), 1999–2017 (2008)
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. 35–50. Springer, Heidelberg (2006)
Schaeffer, J., Hlynka, M., Vili, J.: Temporal Difference Learning Applied to a High-Performance Game-Playing Program. In: Proceedings IJCAI, pp. 529–534 (2001)
Sutton, R.S.: Learning to predict by the methods of temporal differences. Machine Learning, 9–44 (1988)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Indroduction. MIT Press, Cambridge (1998)
Szepesvári, C.: Algorithms for Reinforcement Learning (Electronic Draft Version) (June 2010), http://www.sztaki.hu/~szcsaba/papers/RLAlgsInMDPs-lecture.pdf
Tesauro, G.: Practical issues in temporal differnce learning. Machine Learning 4, 257–277 (1992)
Tesauro, G.: Programming backgammon using self-teching neural nets. Artificial Intelligence 134, 181–199 (2002)
Tesauro, G.: Temporal Difference Learning and TD-Gammon. Communications of the ACM 38(3), 58–68 (1995)
Veness, J., Silver, D., Uther, W., Blair, A.: Bootstrapping from Game Tree Search. Advances in Neural Information Processing Systems 22, 1937–1945 (2009)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2011 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Papahristou, N., Refanidis, I. (2011). Training Neural Networks to Play Backgammon Variants Using Reinforcement Learning. In: Di Chio, C., et al. Applications of Evolutionary Computation. EvoApplications 2011. Lecture Notes in Computer Science, vol 6624. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-20525-5_12
Download citation
DOI: https://doi.org/10.1007/978-3-642-20525-5_12
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-20524-8
Online ISBN: 978-3-642-20525-5
eBook Packages: Computer ScienceComputer Science (R0)