Abstract: Key to autonomous design is the ability to control a system in dynamic non-stationary environments. While off-the-shelf models may not be available for these environments, it is vitally important to build models on the fly in a way where models can be compared, and learned controllers in environments can be repurposed to warm-start reinforcement learning algorithms in similar environments. In this talk, we will present a framework for autonomous design in piecewise-stationary environments, offer simulation results, and identify key theoretical analysis required to study the computational considerations for said design. Specifically, we will present two sets of theoretical results that define key elements of this design. Namely, they are characterization of computational complexity of sparse model learning in reproducing kernel Hilbert spaces and an analysis of change detection in transition kernels of Markov decision processes.
Bio: 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.