Sub-optimality of the Separation Principle for Quadratic Control from Bilinear Observations

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Sattar, Yahya, Choi, Sunmook, Jedra, Yassir, Fazel, Maryam, Dean, Sarah
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912663388291072
author Sattar, Yahya
Choi, Sunmook
Jedra, Yassir
Fazel, Maryam
Dean, Sarah
author_facet Sattar, Yahya
Choi, Sunmook
Jedra, Yassir
Fazel, Maryam
Dean, Sarah
contents We consider the problem of controlling a linear dynamical system from bilinear observations with minimal quadratic cost. Despite the similarity of this problem to standard linear quadratic Gaussian (LQG) control, we show that when the observation model is bilinear, neither does the Separation Principle hold, nor is the optimal controller affine in the estimated state. Moreover, the cost-to-go is non-convex in the control input. Hence, finding an analytical expression for the optimal feedback controller is difficult in general. Under certain settings, we show that the standard LQG controller locally maximizes the cost instead of minimizing it. Furthermore, the optimal controllers (derived analytically) are not unique and are nonlinear in the estimated state. We also introduce a notion of input-dependent observability and derive conditions under which the Kalman filter covariance remains bounded. We illustrate our theoretical results through numerical experiments in multiple synthetic settings.
format Preprint
id arxiv_https___arxiv_org_abs_2504_11555
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Sub-optimality of the Separation Principle for Quadratic Control from Bilinear Observations
Sattar, Yahya
Choi, Sunmook
Jedra, Yassir
Fazel, Maryam
Dean, Sarah
Optimization and Control
Machine Learning
Systems and Control
We consider the problem of controlling a linear dynamical system from bilinear observations with minimal quadratic cost. Despite the similarity of this problem to standard linear quadratic Gaussian (LQG) control, we show that when the observation model is bilinear, neither does the Separation Principle hold, nor is the optimal controller affine in the estimated state. Moreover, the cost-to-go is non-convex in the control input. Hence, finding an analytical expression for the optimal feedback controller is difficult in general. Under certain settings, we show that the standard LQG controller locally maximizes the cost instead of minimizing it. Furthermore, the optimal controllers (derived analytically) are not unique and are nonlinear in the estimated state. We also introduce a notion of input-dependent observability and derive conditions under which the Kalman filter covariance remains bounded. We illustrate our theoretical results through numerical experiments in multiple synthetic settings.
title Sub-optimality of the Separation Principle for Quadratic Control from Bilinear Observations
topic Optimization and Control
Machine Learning
Systems and Control
url https://arxiv.org/abs/2504.11555