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...

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...

Correlated equilibria and communication equilibria are useful notions to understand the strategic effects of information and communication. Between these two models, a protocol generates information through communication. We define a secure protocol as a protocol from which no individual may...

We study the existence of uniform correlated equilibrium payoffs in stochastic games. The correlation devices that we use are either autonomous (they base their choice of signal on previous signals, but not on previous states or actions) or stationary (their choice is independent of any data and...

We prove the existence of the maxmin of zero-sum recursive games with one sided information.

We prove that, in every stochastic game with finitely many states and actions, there exists at least one state, starting from which an equilibrium payoff exists. This is achieved by proving that there exists a solvable set. This generalizes to an arbitrary number of players a result due to...

Quitting games are n-player sequential games in which, at any stage, each player has the choice between continuing and quitting. The game ends as soon as at least one player chooses to quit; player i then receives a payoff riS, which depends on the set S of players that did choose to quit. If...

We study a class of symmetric strategic experimentation games. Each of two players faces an (exponential) two-armed bandit problem, and must decide when to stop experimenting with the risky arm. The equilibrium amount of experimentation depends on the degree to which experimentation outcomes are...