Learning Optimal Strategies to Commit To

Over the past decades, various theories and algorithms have been developed under the framework of Stackelberg games and part of these innovations have been fielded under the scenarios of national security defenses and wildlife protections. However, one of the remaining difficulties in the literature is that most of theoretical works assume full information of the payoff matrices, while in applications, the leader often has no prior knowledge about the follower’s payoff matrix, but may gain information about the follower’s utility function through repeated interactions. In this paper, we study the problem of learning the optimal leader strategy in Stackelberg (security) games and develop novel algorithms as well as new hardness results.

Authors

• Binghui Peng
• Weiran Shen Gaoling School of Artificial Intelligence, Renmin University of China
• Pingzhong Tang Institute for Interdisciplinary Information Sciences, Tsinghua University
• Song Zuo

Keywords

No keywords are indexed for this paper.