No-regret Sample-efficient Bayesian Optimization for Finding Nash Equilibria with Unknown Utilities

Sebastian Shenghong Tay, Quoc Phong Nguyen, Chuan Sheng Foo, Bryan Kian Hsiang Low

Abstract: The Nash equilibrium (NE) is a classic solution concept for normal-form games that is stable under potential unilateral deviations by self-interested agents. Bayesian optimization (BO) has been use...