Imitation learning, Model Predictive Control, and data-driven learning and control of constrained dynamic systems.

May 10, 2024, ESB 2001

Ali Jadbabaie


Over the past few years, Imitation Learning (IL) has become a topic of intense recent focus in the Reinforcement Learning (RL) literature. In its simplest form, imitation learning is an approach that tries to learn an expert policy by querying samples from an expert (usually a human). Recent work in imitation learning has shown that having an expert controller that is both suitably smooth and stable enables much stronger guarantees on the performance of the approximating learned controller. Constructing such smoothed expert controllers for arbitrary systems remains challenging, especially in the presence of input and state constraints. I will discuss some of our recent results that show how such a smoothed expert can be designed for a general class of systems using a log-barrier-based relaxation of a standard Model Predictive Control (MPC) optimization problem. I will also discuss our new results on providing dimension-less, non-asymptotic statistical complexity results for data-driven identification of modes of a switched linear system, which will enable a non-asymptotic analysis of switching-based supervisory control. Time permitting, I will also discuss some of our recent works on using generative AI techniques such as Denoising Diffusion probabilistic Models (DDPM) for generating trajectories. Joint work with Daniel Pfrommer, Swati Padmanabhan, Haoyuan Sun, Kwangjun Ahn, Zak Mhammedi and others.

Speaker's Bio

Ali Jadbabaie is the JR East Professor and Head of the Department of Civil and Environmental Engineering at Massachusetts Institute of Technology (MIT), where he is also a core faculty in the Institute for Data, Systems, and Society (IDSS) and a Principal Investigator with the Laboratory for Information and Decision Systems. Previously, he served as the Director of the Sociotechnical Systems Research Center and as the Associate Director of IDSS as co-founder of its flagship PhD program in Social and Engineering Systems. He received a B.S. degree with High Honors in electrical engineering with a focus on control systems from the Sharif University of Technology, an M.S. degree in electrical and computer engineering from the University of New Mexico, and a Ph.D. degree in control and dynamical systems from the California Institute of Technology. He was a Postdoctoral Scholar at Yale University before joining the faculty at the University of Pennsylvania, where he was subsequently promoted through the ranks and held the Alfred Fitler Moore Professorship in network science in the Department of Electrical and Systems Engineering. He is a recipient of a National Science Foundation Career Development Award, an US Office of Naval Research Young Investigator Award, the O. Hugo Schuck Best Paper Award from the American Automatic Control Council, and the George S. Axelby Best Paper Award from the IEEE Control Systems Society. He has been a senior author of several student best paper awards, in several conferences including ACC, IEEE CDC and IEEE ICASSP. He is an IEEE fellow, and the recipient of a Vannevar Bush Fellowship from the Office of Secretary of Defense and a member of the Bush Fellows Research Study Group. His research interests are broadly in systems theory, decision theory, optimization and control, in particular optimization for machine learning, network science, and social and economic systems.

Video URL: