Probabilistic Analysis of Simulation-Based Games

The field of game theory has proved to be of great importance in modeling interactions between self-interested parties in a variety of settings. Traditionally, game-theoretic analysis relied on highly stylized models to provide interesting insights about problems at hand. The shortcoming of such models is that they often do not capture vital detail. On the other hand, many real strategic settings, such as sponsored search auctions and supply-chains, can be modeled in high resolution using simulations. Recently, a number of approaches have been introduced to perform analysis of game-theoretic scenarios via simulation-based models. The first contribution of this work is the asymptotic analysis of Nash equilibria obtained from simulation-based models. The second contribution is to derive expressions for probabilistic bounds on the quality of Nash equilibrium solutions obtained using simulation data. In this vein, we derive very general distribution-free bounds, as well as bounds which rely on the standard normality assumptions, and extend the bounds to infinite games via Lipschitz continuity. Finally, we introduce a new maximum-a-posteriori estimator of Nash equilibria based on game-theoretic simulation data and show that it is consistent and almost surely unique.