Policy Gradient Method for LQG Control via Input-Output-History Representation: Convergence to $O(ε)$-Stationary Points

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Sadamoto, Tomonori, Tanaka, Takashi
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911226083147776
author Sadamoto, Tomonori
Tanaka, Takashi
author_facet Sadamoto, Tomonori
Tanaka, Takashi
contents We study the policy gradient method (PGM) for the linear quadratic Gaussian (LQG) dynamic output-feedback control problem using an input-output-history (IOH) representation of the closed-loop system. First, we show that any dynamic output-feedback controller is equivalent to a static partial-state feedback gain for a new system representation characterized by a finite-length IOH. Leveraging this equivalence, we reformulate the search for an optimal dynamic output feedback controller as an optimization problem over the corresponding partial-state feedback gain. Next, we introduce a relaxed version of the IOH-based LQG problem by incorporating a small process noise with covariance $εI$ into the new system to ensure coerciveness, a key condition for establishing gradient-based convergence guarantees. Consequently, we show that a vanilla PGM for the relaxed problem converges to an $\mathcal{O}(ε)$-stationary point, i.e., $\overline{K}$ satisfying $\|\nabla J(\overline{K})\|_F \leq \mathcal{O}(ε)$, where $J$ denotes the original LQG cost. Numerical experiments empirically indicate convergence to the vicinity of the globally optimal LQG controller.
format Preprint
id arxiv_https___arxiv_org_abs_2510_19141
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Policy Gradient Method for LQG Control via Input-Output-History Representation: Convergence to $O(ε)$-Stationary Points
Sadamoto, Tomonori
Tanaka, Takashi
Optimization and Control
Systems and Control
We study the policy gradient method (PGM) for the linear quadratic Gaussian (LQG) dynamic output-feedback control problem using an input-output-history (IOH) representation of the closed-loop system. First, we show that any dynamic output-feedback controller is equivalent to a static partial-state feedback gain for a new system representation characterized by a finite-length IOH. Leveraging this equivalence, we reformulate the search for an optimal dynamic output feedback controller as an optimization problem over the corresponding partial-state feedback gain. Next, we introduce a relaxed version of the IOH-based LQG problem by incorporating a small process noise with covariance $εI$ into the new system to ensure coerciveness, a key condition for establishing gradient-based convergence guarantees. Consequently, we show that a vanilla PGM for the relaxed problem converges to an $\mathcal{O}(ε)$-stationary point, i.e., $\overline{K}$ satisfying $\|\nabla J(\overline{K})\|_F \leq \mathcal{O}(ε)$, where $J$ denotes the original LQG cost. Numerical experiments empirically indicate convergence to the vicinity of the globally optimal LQG controller.
title Policy Gradient Method for LQG Control via Input-Output-History Representation: Convergence to $O(ε)$-Stationary Points
topic Optimization and Control
Systems and Control
url https://arxiv.org/abs/2510.19141