A gradient-based approach for computing Nash equilibria of large sequential games

We propose a new gradient based scheme to approximate Nash equilibria of large sequential two-player, zero-sum games. The algorithm uses modern smoothing techniques for saddle-point problems tailored specifically for the polytopes used in the Nash equilibrium problem.

Citation

Working Paper, Tepper School of Business, Carnegie Mellon University

Article

Download

View A gradient-based approach for computing Nash equilibria of large sequential games