Abstract
Consider a repeated two-person game. The question is how much smarter should a player be to effectively predict the moves of the other player. The answer depends on the formal definition of effective prediction, the number of actions each player has in the stage game, as well as on the measure of smartness. Effective prediction means that, no matter what the stage-game payoff function, the player can play (with high probability) a best reply in most stages. Neyman and Spencer [4] provide a complete asymptotic solution when smartness is measured by the size of the automata that implement the strategies.
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Ben-Porath, E.: Repeated games with finite automata. Journal of Economic Theory 59, 17–32 (1993)
Neyman, A.: Cooperation, repetition, and automata. In: Hart, S., Mas Colell, A. (eds.) Cooperation: Game-Theoretic Approaches. NATO ASI Series F, vol. 155, pp. 233–255. Springer, Heidelberg (1997)
Neyman, A.: The strategic value of memory (tentative title) (forthcoming, 2006)
Neyman, A., Spencer, J.: The complexity threshold for effective prediction (tentative title) (forthcoming, 2006)
Neyman, A., Okada, D.: Two-person repeated games with finite automata. International Journal of Game Theory 29, 309–325 (2000)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2006 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Neyman, A. (2006). Recent Developments in Learning and Competition with Finite Automata (Extended Abstract). In: Spirakis, P., Mavronicolas, M., Kontogiannis, S. (eds) Internet and Network Economics. WINE 2006. Lecture Notes in Computer Science, vol 4286. Springer, Berlin, Heidelberg. https://doi.org/10.1007/11944874_1
Download citation
DOI: https://doi.org/10.1007/11944874_1
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-68138-0
Online ISBN: 978-3-540-68141-0
eBook Packages: Computer ScienceComputer Science (R0)