Optimization Landscape of Gradient Descent for Discrete-time Static Output Feedback

Jie Li, Jingliang Duan, Shengbo Eben Li, Lin Zhao

Publication date: 27 September 2021

Abstract: In this paper, we analyze the optimization landscape of gradient descent methods for static output feedback (SOF) control of discrete-time linear time-invariant systems with quadratic cost. The SOF setting can be quite common, for example, when there are unmodeled hidden states in the underlying process. We first establish several important properties of the SOF cost function, including coercivity, L-smoothness, and M-Lipschitz continuous Hessian. We then utilize these properties to show that the gradient descent is able to converge to a stationary point at a dimension-free rate. Furthermore, we prove that under some mild conditions, gradient descent converges linearly to a local minimum if the starting point is close to one. These results not only characterize the performance of gradient descent in optimizing the SOF problem, but also shed light on the efficiency of general policy gradient methods in reinforcement learning.

Has companion code repository: https://github.com/soc-ucsd/lqg_gradient

This page was built for publication: Optimization Landscape of Gradient Descent for Discrete-time Static Output Feedback

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6378700)