Stochastic incentive design problems entail hierarchical stochastic decision-making between a leader and a single (or multiple) follower(s) with possibly different goals. The leader seeks to induce a desired behavior from one or more followers through a soft policy that penalizes the followers for deviating from her desired responses, but the penalty varies smoothly in said deviations. Such problems arise in different contexts, such as designing tax codes and imposing environmental regulations on corporations. The design of such policies relies on the knowledge of followers’ costs and observations. In the first part of this talk, I will present our recent results on incentive design when such knowledge on costs and observations are relaxed. The key conclusion of this part is that the leader can still roughly induce the desired behavior from the followers under reasonable assumptions. In the second half of the talk, I will discuss the question of incentive design with many followers and its mean-field limits. A perhaps surprising result of this part is that mean-field limits of such Stackelberg games are not well-defined. I will discuss a variant of the original game that admits such limits. I will conclude the talk with ongoing work on learning follower’s costs in repeated incentive design settings.
Subhonmesh Bose is an Associate Professor and Stanley Helm Fellow in the Department of Electrical and Computer Engineering and the Coordinated Science Laboratory at University of Illinois Urbana-Champaign (UIUC). His research lies in the intersection of optimization, control theory, game theory, and machine learning, with applications in power system operations and transportation electrification. Before joining UIUC, he was a postdoctoral fellow at the Atkinson Center for Sustainability at Cornell University. Prior to that, he received his MS and Ph.D. degrees from Caltech in 2012 and 2014, respectively. He received the NSF CAREER Award in 2021. His research projects have been supported by grants from the NSF, PSERC, Siebel Energy Institute, and C3.ai, among others.
