A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically …, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any …

A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically …, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any …

version of this idea, called interactive trial and error learning, which has the property that it implements Nash equilibrium …), the method requires no statistical estimation. Unlike a learning procedure proposed by Hart and Mas-Colell (2006), it … requires no knowledge of the other players' actions: learning proceeds purely by responding to one's own payoff history. The …

A learning rule is uncoupled if a player does not condition his strategy on the opponent's payoffs. It is radically …, radically uncoupled learning rules whose period-by-period behavior comes arbitrarily close to Nash equilibrium behavior in any …