Abstract
In every (discrete) period of time a decision maker (for short, an agent) makes a decision and, simultaneously, Nature selects a state of the world. The agent receives a payoff which depends on both his action and the state. Nature’s behavior is ex-ante unknown to the agent, it may be as simple as an i.i.d. environment or as sophisticated as a strategic play of a rational player. The agent’s objective is to select a sequence of decisions which guarantees to him the long-run average payoff as large as the best-reply payoff against Nature’s empirical distribution of play, no matter what Nature does. A behavior rule of the agent which fulfills this objective is called universally consistent1: the rule is “consistent” if it is optimized against the empirical play of Nature; the word “ universally” refers to its applicability to any behavior of Nature.
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
D. Blackwell. An analog of the minmax theorem for vector payoffs. Pacific Journal of Mathematics, 6:1–8, 1956.
N. Cesa-Bianchi and G. Lugosi. Potential-based algorithms in on-line prediction and game theory. Machine Learning, 51:239–261, 2003.
N. Cesa-Bianchi, Y. Freund, D. Helmbold, D. Haussler, R. Shapire, and M. Warmuth. How to use expert advice. Journal of the ACM, 44:427–485, 1997.
Dean Foster and Rakesh Vohra. Regret in the online decision problem. Games and Economic Behavior, 29:7–35, 1999.
Yoav Freund and Robert Schapire. Game theory, on-line prediction and boosting. In Proceedings of the Ninth Annual Conference on Computational Learning Theory, pages 325–332, 1996.
Drew Fudenberg and David Levine. Universal consistency and cautious fictitious play. Journal of Economic Dynamics and Control, 19:1065–1089, 1995.
J Hannan. Approximation to Bayes risk in repeated play. In M. Dresher, A. W. Tucker, and P. Wolfe, editors, Contributions to the Theory of Games, Vol. III, Annals of Mathematics Studies 39, pages 97–139. Princeton University Press, 1957.
Sergiu Hart and Andreu Mas-Colell. A simple adaptive procedure leading to correlated equilibrium. Econometrica, 68:1127–1150, 2000.
Sergiu Hart and Andreu Mas-Colell. A general class of adaptive procedures. Journal of Economic Theory, 98:26–54, 2001.
Ehud Lehrer and Eilon Solan. No regret with bounded computational capacity. The Center for Mathematical Studies in Economics and Management Science, Northwestern University. Discussion Paper 1373, 2003.
N. Littlestone and M. Warmuth. The weighted majority algorithm. Information and Computation, 108:212–261, 1994.
V. Vovk. A game of prediction with expert advice. Journal of Computer and System Sciences, 56:153–173, 1998.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2007 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Zapechelnyuk, A. (2007). Better-Reply Strategies with Bounded Recall. In: Consiglio, A. (eds) Artificial Markets Modeling. Lecture Notes in Economics and Mathematical Systems, vol 599. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-73135-1_19
Download citation
DOI: https://doi.org/10.1007/978-3-540-73135-1_19
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-73134-4
Online ISBN: 978-3-540-73135-1
eBook Packages: Business and EconomicsEconomics and Finance (R0)