Representation-based Learning and Control for Dynamical Systems

The explosive growth of machine learning and data-driven methodologies have revolutionized numerous fields. Yet, their application to real-world dynamical physical systems remains a significant challenge. Closing the loop from data to actions in these systems faces many difficulties, stemming from the need for sample efficiency and computational feasibility, along with many other requirements such as verifiability, robustness, and safety. In this talk, we bridge this gap by introducing innovative representations to develop nonlinear stochastic control and reinforcement learning methods. The key in the representation is to represent the stochastic, nonlinear dynamics linearly onto a nonlinear feature space. We present a comprehensive framework that integrates these components to develop reinforcement learning and control strategies that are not only tailored for the complexities of physical systems but also achieve efficiency, safety, and robustness with provable performance. Lastly, we will use a few examples of real-world applications to briefly discuss how to use domain knowledge and the physical structures of systems to further improve the design of algorithms.