Calibrated Learning and CorrelatedEquilibriumDean

  title={Calibrated Learning and CorrelatedEquilibriumDean},
  author={P................... and FosterUniversity and Of and PennsylvaniaPhiladelphia and V. S. Rakesh and VohraOhio},
Suppose two players meet each other in a repeated game where: 1. each uses a learning rule with the property that it is a calibrated forecast of the others plays, and 2. each plays a best response to this forecast distribution. Then, the limit point of the sequence of plays are Correlated Equilibria. In fact, for each Correlated equilibrium there is some calibrated learning rule that the players can use which result in their playing this correlated equilibrium in the limit. Thus, the… CONTINUE READING


Publications referenced by this paper.

Similar Papers

Loading similar papers…