Quantized Online LQR

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Han, Barron, Kostina, Victoria, Hassibi, Babak
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915935175049216
author Han, Barron
Kostina, Victoria
Hassibi, Babak
author_facet Han, Barron
Kostina, Victoria
Hassibi, Babak
contents We study online linear-quadratic regulation (LQR) with unknown dynamics under communication rate constraints. Classical networked control quantizes the plant state at every time step, requiring $O(T)$ total bits while injecting persistent quantization noise that limits control performance. We consider a setting where the plant observes its state locally and can estimate system dynamics via ordinary least squares, while a remote controller possesses knowledge of the control cost. Rather than quantizing the raw state, the plant transmits learned dynamics estimates over a rate-limited uplink, and the controller returns the optimal control policy so that the plant can compute actions locally using its superior state knowledge. We first prove a fundamental information-theoretic lower bound: any scheme achieving $O(T^α)$ regret for $α\in [1/2,1)$ compared to the optimal infinite horizon LQR controller that knows the true system dynamics must transmit at least $Ω(\log T)$ bits. We then design the \textbf{Quantized Certainty Equivalent (QCE-LQR)} algorithm, which matches this bound. The resulting regret bound contains inflation factors $Q_{\mathrm{slow}}(\varrho)$ and $Q_{\mathrm{fast}}(\varrho)$ that vanish as the codebook resolution increases, smoothly recovering the unquantized baseline regret. Numerical experiments on four benchmark systems -- from a scalar unstable plant to a 24-parameter Boeing 747 lateral model -- confirm that a variant of QCE-LQR achieves regret comparable to an unquantized certainty equivalent controller over a horizon of $T=10{,}000$ steps.
format Preprint
id arxiv_https___arxiv_org_abs_2604_11930
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Quantized Online LQR
Han, Barron
Kostina, Victoria
Hassibi, Babak
Systems and Control
Information Theory
We study online linear-quadratic regulation (LQR) with unknown dynamics under communication rate constraints. Classical networked control quantizes the plant state at every time step, requiring $O(T)$ total bits while injecting persistent quantization noise that limits control performance. We consider a setting where the plant observes its state locally and can estimate system dynamics via ordinary least squares, while a remote controller possesses knowledge of the control cost. Rather than quantizing the raw state, the plant transmits learned dynamics estimates over a rate-limited uplink, and the controller returns the optimal control policy so that the plant can compute actions locally using its superior state knowledge. We first prove a fundamental information-theoretic lower bound: any scheme achieving $O(T^α)$ regret for $α\in [1/2,1)$ compared to the optimal infinite horizon LQR controller that knows the true system dynamics must transmit at least $Ω(\log T)$ bits. We then design the \textbf{Quantized Certainty Equivalent (QCE-LQR)} algorithm, which matches this bound. The resulting regret bound contains inflation factors $Q_{\mathrm{slow}}(\varrho)$ and $Q_{\mathrm{fast}}(\varrho)$ that vanish as the codebook resolution increases, smoothly recovering the unquantized baseline regret. Numerical experiments on four benchmark systems -- from a scalar unstable plant to a 24-parameter Boeing 747 lateral model -- confirm that a variant of QCE-LQR achieves regret comparable to an unquantized certainty equivalent controller over a horizon of $T=10{,}000$ steps.
title Quantized Online LQR
topic Systems and Control
Information Theory
url https://arxiv.org/abs/2604.11930