This article studies situations in which agents do not initially know the effect of their decisions, but learn from experience the payoffs induced by their choices and their opponents'. We chararacterize equilibrium payoffs in terms of simple strategies in which an exploration phase is followed...

We consider the "and" communication device that receives inputs from two players and outputs the public signal yes if both messages are yes, and outputs no otherwise. We prove that no correlation can securely be implemented using this device, even when infinitely many stages of communication are...

We consider the "and" communication mechanism that inputs messages from two players and outputs the public signal "yes" if both messages are "yes", and outputs "no" otherwise. We prove that no correlation can securely be implemented through finite or infinite repetition of this mechanism.

This paper studies situations in which agents do not initially know the effect of their decisions, but learn from experience the payoffs induced by their choices and their opponent's. We characterize equilibrium paysoffs in termsof simple strategies in which an explanation phase is followed by a...

We consider the “and” communication device that receives inputs from two players and outputs the public signal yes if both messages are yes, and outputs no otherwise. We prove that no correlation can securely be implemented using this device, even when infinitely many stages of communication...

Le maxmin pour une certaine classe de jeux répétés à observation imparfaite est obtenu comme la solution d'un problème d'optimisation défini sur l'ensemble des distributions de probabilités sous contraintes d'entropie. Cette article offre une méthode pour résoudre un tel problème dans...

We characterize the minmax values of a class of repeated games with imperfect monitoring. Our result relies on the optimal trade-off for the team formed by punishing players between optimization of stage-payoffs and generation of signals for future correlation. Amounts of correlation are...

An observer of a process View the MathML source believes the process is governed by Q whereas the true law is P. We bound the expected average distance between P(xt|x1,…,xt−1) and Q(xt|x1,…,xt−1) for t=1,…,n by a function of the relative entropy between the marginals of P and Q on the...