Learning and Approximating the Optimal Strategy to Commit To

Computing optimal Stackelberg strategies in general two-player Bayesian games (not to be confused with Stackelberg strategies in routing games) is a topic that has recently been gaining attention, due to their application in various security and law enforcement scenarios. Earlier results consider the computation of optimal Stackelberg strategies, given that all the payoffs and the prior distribution over types are known. We extend these results in two different ways. First, we consider learning optimal Stackelberg strategies. Our results here are mostly positive. Second, we consider computing approximately optimal Stackelberg strategies. Our results here are mostly negative.

• Type: Conference
• Year: 2009
• Where: SAGT
• Authors: Joshua Letchford, Vincent Conitzer, Kamesh Munagala
• Keywords: Game Theory, Law Enforcement Scenarios, Optimal Stackelberg Strategies, SAGT 2009, Two-player Bayesian Games