Optimal Rates for Feasible Payoff Set Estimation in Games

ArXi:2602.04397v2 Announce Type: replace-cross We study a setting in which two players play a (possibly approximate) Nash equilibrium of a bimatrix game, while a learner observes only their actions and has no knowledge of the equilibrium or the underlying game. A natural question is whether the learner can rationalize the observed behavior by inferring the players' payoff functions.