Computing equilibria by minimizing exploitability with best-response ensembles

In this paper, we study the problem of computing an approximate Nash equilibrium of a continuous game. Such games naturally model many situations involving space, time, money, and other fine-grained resources or quantities. The standard measure of the closeness of a strategy profile to Nash equilibrium is exploitability, which measures how much utility players can gain from changing their strategy unilaterally. We introduce a new equilibrium-finding method that minimizes an approximation of the exploitability. This approximation employs a best-response ensemble for each player that maintains multiple candidate best responses for that player. In each iteration, the best-performing element of each ensemble is used in a gradient-based scheme to update the current strategy profile. The strategy profile and best-response ensembles are simultaneously trained to minimize and maximize the approximate exploitability, respectively. Experiments on a suite of benchmark games show that it outperforms previous methods.