Abstract
We prove that if one or more players in a locally finite positional game have winning strategies, then they can find it by themselves, not losing more than a bounded number of plays and not using more than a linear-size memory, independently of the strategies applied by the other players. We design two algorithms for learning how to win. One of them can also be modified to determine a strategy that achieves a draw, provided that no winning strategy exists for the player in question but with properly chosen moves a draw can be ensured from the starting position. If a drawing- or winning strategy exists, then it is learnt after no more than a linear number of plays lost (linear in the number of edges of the game graph).
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Berlekamp ER, Conway JH, Guy RK (1982) Winning ways for mathematical games. Academic Press, New York
Bouton CL (1901–1902) Nim, a game with a complete mathematical theory. Ann Math Princeton 3: 35–39
Ernst A (2005) Gewinnstrategien auf Graphen. Diploma-Thesis Technische Univers ität Ilmenau
Fraenkel AS (2008) Combinatorial games: selected bibliography with a Succinct Gourmet introduction. Electr J Combinat (http://www.combinatorics.org/Surveys/index.html, accessed on June 20th)
Fraenkel AS, Rahat O (2001) Infinite cyclic impartial games. Theor Comp Sci 252: 13–22
Fudenberg D, Tirole J (1991) Game theory. MIT Press, Cambridge
Jacobs K (1983) Einführung in die Kombinatorik. Walter de Gruyter, Berlin
Kummer B (1979) Spiele auf Graphen. Deutscher Verlag der Wissenschaften, Berlin
Michie D (1961) Trial and error. In: Barnett SA, McLaren A (eds) Science Survey, Part 2. Harmondsworth, Penguin, pp 129–145
Michie D (1963) Experiments on the mechanisation of game learning. 1. Characterization of the model and its parameters. Comp J 1: 232–263
Schwalbe U, Walker P (2001) Zermelo and the early history of game theory. Games Econ Behav 34: 123–137
Sutton RS, Barto AG (1998) Reinforcement learning: an introduction. MIT Press, Cambridge
Yang J, Liao S, Pawlak M (2001) On a decomposition method for finding winning strategy in Hex game. In: Sing ALW, Man WH, Wai W (eds) Proceedings ADCOG: internatational conference application and development of computer games. City University of Hong kong, Kowloon, pp 96–111
Zermelo E (1912) Über eine Anwendung der Mengenlehre auf die Theorie des Schachspiels. In: Proceedings of fifth congress of mathematicians (Cambridge 1912). Cambridge University Press, Cambridge, pp 501–504
Author information
Authors and Affiliations
Corresponding author
Additional information
Z. Tuza’s research has been supported in part by the grant OTKA T-049613.
Rights and permissions
About this article
Cite this article
Böhme, T., Göring, F., Tuza, Z. et al. Learning of winning strategies for terminal games with linear-size memory. Int J Game Theory 38, 155–168 (2009). https://doi.org/10.1007/s00182-008-0142-5
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00182-008-0142-5