A Simple Adaptive Procedure Leading to Correlated Equilibrium by Sergiu Hart
نویسندگان
چکیده
We propose a new and simple adaptive procedure for playing a game: ‘‘regret-matching.’’ In this procedure, players may depart from their current play with probabilities that are proportional to measures of regret for not having used other strategies in the past. It is shown that our adaptive procedure guarantees that, with probability one, the empirical distributions of play converge to the set of correlated equilibria of the game.
منابع مشابه
A Reinforcement Procedure Leading to Correlated Equilibrium
We consider repeated games where at any period each player knows only his set of actions and the stream of payoffs that he has received in the past. He knows neither his own payoff function, nor the characteristics of the other players (how many there are, their strategies and payoffs). In this context, we present an adaptive procedure for play — called “modified-regret-matching” — which is int...
متن کاملAdaptive Heuristics
We exhibit a large class of simple rules of behavior, which we call adaptive heuristics, and show that they generate rational behavior in the long run. These adaptive heuristics are based on natural regret measures, and may be viewed as a bridge between rational and behavioral viewpoints. Taken together, the results presented here establish a solid connection between the dynamic approach of ada...
متن کاملSimple Adaptive Strategies: From Regret-Matching to Uncoupled Dynamics, Sergiu Hart, Andreu Mas-Colell. World Scientific Publishing Company, Singapore (2013)
The general framework of this volume is that of game theory, with multiple participants (“players”) who interact repeatedly over time. The players may be people, corporations, nations, computers—even genes. See the Handbook of Game Theory (Aumann and Hart 1994, 2002, 2004; Young and Zamir 2012). Many of the standard concepts of game theory are static by their very nature. This is certainly true...
متن کاملA General Class of Adaptive Strategies
We exhibit and characterize an entire class of simple adaptive strategies, in the repeated play of a game, having the Hannan-consistency property: in the long-run, the player is guaranteed an average payoff as large as the best-reply payoff to the empirical distribution of play of the other players; i.e., there is no ``regret.'' Smooth fictitious play (Fudenberg and Levine [1995, J. Econ. Dynam...
متن کاملMarkets, correlation, and regret-matching
Inspired by the existing work on correlated equilibria and regretbased dynamics in games, we carry out a first exploration of the links between the leading equilibrium concept for (exchange) economies, Walrasian equilibrium, and the dynamics, specifically regret-matching dynamics, of trading games that fit the economic structure and have the property that their pure Nash equilibria implement th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2000