Adaptive Game Playing Using Multiplicative Weights

347Citations
Citations of this article
194Readers
Mendeley users who have this article in their library.
Get full text

Abstract

We present a simple algorithm for playing a repeated game. We show that a player using this algorithm suffers average loss that is guaranteed to come close to the minimum loss achievable by any fixed strategy. Our bounds are nonasymptotic and hold for any opponent. The algorithm, which uses the multiplicative-weight methods of Littlestone and Warmuth, is analyzed using the Kullback-Liebler divergence. This analysis yields a new, simple proof of the min-max theorem, as well as a provable method of approximately solving a game. A variant of our game-playing algorithm is proved to be optimal in a very strong sense. Journal of Economic Literature Classification Numbers: C44, C70, D83. © 1999 Academic Press.

Cite

CITATION STYLE

APA

Freund, Y., & Schapire, R. E. (1999). Adaptive Game Playing Using Multiplicative Weights. Games and Economic Behavior, 29(1), 79–103. https://doi.org/10.1006/game.1999.0738

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free