Yang Zheng (UC Sand Diego)

Department Colloquium

Speaker: Yang Zheng (UC Sand Diego)

Title: Extended Convex Lifting for Policy Optimization in Control

Abstract:
Direct policy search has achieved great empirical success in reinforcement learning. Many recent studies have revisited its theoretical foundation for continuous control, which reveals elegant nonconvex geometry in various benchmark problems. In this talk, we introduce an Extended Convex Lifting (ECL) framework, which reveals hidden convexity in classical optimal and robust control problems from a modern optimization perspective. Our ECL offers a bridge between nonconvex policy optimization and convex reformulations. Despite non-convexity and non-smoothness, the existence of an ECL not only reveals that minimizing the original function is equivalent to a convex problem, but also certifies a class of first-order non-degenerate stationary points to be globally optimal. We believe that the ECL framework may be of independent interest for analyzing nonconvex problems beyond control.