Abstract
Computing Nash equilibrium solutions is an important problem in the domain of imperfect information games. Counterfactual Regret Minimization+ (CFR+) can be used to (essentially weakly) solve two-player limit Texas Hold’em, but it cannot be applied to large multi-player games due to the problem of space complexity. In this paper, we use Neural Fictitious Self-Play (NFSP) to calculate approximate Nash equilibrium solutions for imperfect information games with more than two players. Although there are no theoretical guarantees of convergence for NFSP in such games, we empirically demonstrate that NFSP enables us to calculate strategy profiles that are significantly less exploitable than random players in simple poker variants with three or more players.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bowling, M., Burch, N., Johanson, M., Tammelin, O.: Heads-up limit hold’em poker is solved. Science 347(6218), 145–149 (2015)
Brown, G.W.: Iterative solution of games by fictitious play. Activity Anal. Prod. Allocation 13(1), 374–376 (1951)
Heinrich, J., Lanctot, M., Silver, D.: Fictitious self-play in extensive-form games. In: Proceedings of ICML. JMLR Workshop and Conference Proceedings, pp. 805–813 (2015)
Heinrich, J., Silver, D.: Deep reinforcement learning from self-play in imperfect-information games. arXiv:1603.01121 (2016)
Johanson, M., Waugh, K., Bowling, M., Zinkevich, M.: Accelerating best response calculation in large extensive games. In: Proceedings of the 22nd IJCAI, vol. 1, pp. 258–265 (2011)
Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. CoRR (2014)
Kuhn, H.W.: A simplified two-person poker. Contrib. Theory Games 1, 97–103 (1950)
Lanctot, M., Waugh, K., Zinkevich, M., Bowling, M.: Monte Carlo sampling for regret minimization in extensive games. In: Advances in NIPS 22, pp. 1078–1086 (2009)
Leslie, D.S., Collins, E.: Generalised weakened fictitious play. Games Econ. Behav. 56(2), 285–298 (2006)
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A.A., Veness, J., Bellemare, M.G., Graves, A., Riedmiller, M., Fidjeland, A.K., Ostrovski, G., Petersen, S., Beattie, C., Sadik, A., Antonoglou, I., King, H., Kumaran, D., Wierstra, D., Legg, S., Hassabis, D.: Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015)
Risk, N.A., Szafron, D.: Using counterfactual regret minimization to create competitive multiplayer poker agents. In: Proceedings of the 9th AAMAS, vol. 1, pp. 159–166 (2010)
Shamma, J.S., Arslan, G.: Dynamic fictitious play, dynamic gradient play, and distributed convergence to nash equilibria. IEEE Trans. Autom. Control 50(3), 312–327 (2005)
Southey, F., Bowling, M., Larson, B., Piccione, C., Burch, N., Billings, D., Rayner, C.: Bayes’ bluff: opponent modelling in poker. In: Proceedings of the 21st Conference on UAI, UAI 2005, pp. 550–558. AUAI Press, Arlington (2005)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (1998)
Tammelin, O.: Solving large imperfect information games using CFR+. arXiv:1407.5042 (2014)
Vitter, J.S.: Random sampling with a reservoir. ACM Trans. Math. Softw. 11(1), 37–57 (1985)
Watkins, C.J., Dayan, P.: Technical note: Q-learning. Mach. Learn. 8(3), 279–292 (1992)
Zinkevich, M., Johanson, M., Bowling, M., Piccione, C.: Regret minimization in games with incomplete information. In: Advances in NIPS 20, pp. 1729–1736. Curran Associates, Inc. (2008)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Kawamura, K., Mizukami, N., Tsuruoka, Y. (2018). Neural Fictitious Self-Play in Imperfect Information Games with Many Players. In: Cazenave, T., Winands, M., Saffidine, A. (eds) Computer Games. CGW 2017. Communications in Computer and Information Science, vol 818. Springer, Cham. https://doi.org/10.1007/978-3-319-75931-9_5
Download citation
DOI: https://doi.org/10.1007/978-3-319-75931-9_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-75930-2
Online ISBN: 978-3-319-75931-9
eBook Packages: Computer ScienceComputer Science (R0)