Fast Complete Algorithm for Multiplayer Nash Equilibrium

Sam Ganzfried

Abstract: We describe a new complete algorithm for computing Nash equilibrium in multiplayer general-sum games, based on a quadratically-constrained feasibility program formulation. We demonstrate that the algorithm runs significantly faster than the prior fastest complete algorithm on several game classes previously studied and that its runtimes even outperform the best incomplete algorithms. We expect our algorithm to be applicable to important game models in economics, political science, security, and many other fields.