Approximate Nash equilibria in large nonconvex aggregative games.

Summary This paper shows the existence of O(1/n^γ)-Nash equilibria in n-player noncooperative aggregative games where the players' cost functions depend only on their own action and the average of all the players' actions, and is lower semicontinuous in the former while γ-Hölder continuous in the latter. Neither the action sets nor the cost functions need to be convex. For an important class of aggregative games which includes congestion games with γ being 1, a proximal best-reply algorithm is used to construct an O(1/n)-Nash equilibria with at most O(n^3) iterations. These results are applied in a numerical example of demand-side management of the electricity system. The asymptotic performance of the algorithm is illustrated when n tends to infinity.