Learn More
Completely uncoupled dynamic is a repited play of a game, when in every given time the action of every player depends only on his own payo¤s in the past. In this paper we try to formulate the minimal set of necessary conditions that guarantee a convergence to a Nash equilibrium in completely uncoupled model. The main results are: 1. The convergence to a(More)
We study lower bounds on the query complexity of determining correlated equilibrium. In particular, we consider a query model in which an <i>n</i>-player game is specified via a black box that returns players' utilities at pure action profiles. In this model, we establish that in order to compute a correlated equilibrium, any <i>deterministic</i> algorithm(More)
We conjecture that <b>PPAD</b> has a PCP-like complete problem, seeking a near equilibrium in which all but very few players have very little incentive to deviate. We show that, if one assumes that this problem requires exponential time, several open problems in this area are settled. The most important implication, proved via a "birthday repetition"(More)
We study the problem of reaching a pure Nash equilibrium in multi-person games that are repeatedly played, under the assumption of uncoupledness: EVERY player knows only his own payoff function. We consider strategies that can be implemented by finite-state automata, and characterize the minimal number of states needed in order to guarantee that a pure Nash(More)
We show that in an n-player m-action strategic form game, we can obtain an approximate equilibrium by sampling any mixed-action equilibrium a small number of times. We study three notions of equilibrium: Nash, correlated and coarse correlated. For each one of them we obtain upper and lower bounds on the asymptotic (where max(m, n) → ∞) worst-case number of(More)