Globally Convergent Policy Gradient Methods for Linear Quadratic Control of Partially Observed Systems
Year: 2023
Type: article
Abstract: While the optimization landscape of policy gradient methods has been recently investigated for partially observed linear systems in terms of both static output feedback and dynamical controllers, they only provide convergence guarantees to stationary points. In this paper, we propose a new policy parameterization for partially observed linear systems, using a past input-output trajectory of finite length as feedback. We show that the solution set to the parameterized optimization problem is a matrix space, which is invariant to similarity transformation. By proving a gradient dominance property, we show the global convergence of policy gradient methods. Moreover, we observe that the gradient is orthogonal to the solution set, revealing an explicit relation between the resulting solution and the initial policy. Finally, we perform simulations to validate our theoretical results.
Source: IFAC-PapersOnLine
Authors: Feiran Zhao, Xingyun Fu, Keyou You
Institution: Tsinghua University
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: diamond
Award: G1850434087
OpenAlex ID: W4388917690
