Stochastic Learning of Strategic Equilibria for Auctions

摘要

This article presents a new application of stochastic adaptive learning algorithms to the computation of strategic equilibria in auctions. The proposed approach addresses the problems of tracking a moving target and balancing exploration (of action space) versus exploitation (of better modeled regions of action space). Neural networks are sued to represent a stochastic decision model for each bidder. Experiments confirm the cor- rectness and usefulness of the approach.