The explosive growth of machine learning and data-driven methodologies has revolutionized numerous fields. Yet, translating these successes to dynamical physical systems remains a significant challenge, hindered by the complexity, uncertainty, and safety-critical nature of such environments. In this talk, we present a unified framework that bridges this gap by introducing novel generative representations for reinforcement learning and control. On the critic side, we develop a structured representation of system dynamics that focuses on modeling how actions influence future state distributions. This transition-based perspective enables the design of nonlinear stochastic control and reinforcement learning algorithms that are efficient, safe, robust, and scalable, with provable guarantees. On the actor side, we represent stochastic feedback policies using diffusion-based generative models, treating control as a generative process. This approach leads to new methods for policy optimization, while providing a flexible and expressive framework for decision-making in dynamical systems. We further demonstrate how these representations help close the sim-to-real gap, improve data efficiency in imitation learning, and enable scalable computation of localized policies for large-scale nonlinear networked systems, with applications including robotics and energy systems.

Bio

Na Li is a Winokur Family Professor of Electrical Engineering and Applied Mathematics at Harvard University. She received her BS degree in Mathematics from Zhejiang University in 2007 and PhD degree in Control and Dynamical systems from California Institute of Technology in 2013. She was a postdoctoral associate at the Massachusetts Institute of Technology 2013-2014. She has held a variety of short-term visiting appointments including the Simons Institute for the Theory of Computing, MIT, Google Brain, and MERL. Her research lies in the control, learning, and optimization of networked systems, including theory development, algorithm design, and applications to real-world cyber-physical societal systems. She is an IEEE fellow and a senior editor of IEEE Transactions on Control of Network Systems. She was an associate editor for IEEE Transactions on Automatic Control, Systems & Control Letters, IEEE Control Systems Letters and also served on the organizing committee for a few conferences and workshops such as IEEE CDC, AMC E-energy, and NSF workshop on Reinforcement Learning. She received the NSF career award, AFSOR Young Investigator Award, ONR Young Investigator Award, Donald P. Eckman Award, McDonald Mentoring Award, IEEE CSS Distinguished Lecturer, IFAC Distinguished Lecturer, IFAC Manfred Thoma Medal, Ruberti Young Researcher Prize, along with other awards.