In this talk, I discuss recent advances in reinforcement learning for optimal control of dynamical systems with unknown dynamics, focusing on linear-quadratic settings. The emphasis is on fundamental questions of sample complexity, convergence, and stability in model-free policy learning. In particular, I highlight sample-efficient algorithms and approaches that relax traditional stability assumptions.
Bahman Gharesifard is a Professor with the Department of Mathematics and Statistics at Queen's University. He was a Professor with the Electrical and Computer Engineering Department at the University of California, Los Angeles from 2021 to 2024, where he was the Area Director for Signals and Systems 2023-2024. He was an Alexander von Humboldt research fellow with the Institute for Systems Theory and Automatic Control at the University of Stuttgart in 2019-2020. He held postdoctoral positions with the Coordinated Science Laboratory at the University of Illinois at Urbana-Champaign from 2012-2013 and with the Department of Mechanical and Aerospace Engineering at University of California, San Diego 2009-2012.