Input perturbations for adaptive control and learning

DOI10.1016/J.AUTOMATICA.2020.108950MaRDI QIDQ2184498zbMATH OpenOpenAlexFDO

Authors Mohamad Kazem Shirani Faradonbeh, Ambuj Tewari, George Michailidis

Publication date 29 May 2020

Published in Automatica (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1811.04258

zbMATH Keywords

adaptive LQRsdecision-making under uncertaintyexploration-exploitationfinite-time optimalitygreedy policieslinear-quadraticsystem identification

Mathematics Subject Classification ID

Linear systems in control theory (93C05) Multivariable systems, multidimensional control systems (93C35) Adaptive control/observation systems (93C40) Perturbations in control/observation systems (93C73)

Abstract: This paper studies adaptive algorithms for simultaneous regulation (i.e., control) and estimation (i.e., learning) of Multiple Input Multiple Output (MIMO) linear dynamical systems. It proposes practical, easy to implement control policies based on perturbations of input signals. Such policies are shown to achieve a worst-case regret that scales as the square-root of the time horizon, and holds uniformly over time. Further, it discusses specific settings where such greedy policies attain the information theoretic lower bound of logarithmic regret. To establish the results, recent advances on self-normalized martingales together with a novel method of policy decomposition are leveraged.

Recommendations

• On adaptive linear-quadratic regulators
• scientific article; zbMATH DE number 440431
• Adaptive regulator for MIMO Hammerstein and Wiener systems
• Low-complexity learning of linear quadratic regulators from noisy data
• Controlling unknown linear dynamics with bounded multiplicative regret

Cites work

• A note on the structure of two subsets of the parameter space in adaptive control problems
• Adaptive control of linear time invariant systems: the ``Bet on the best principle
• Adaptive Linear Quadratic Gaussian Control: The Cost-Biased Approach Revisited
• Asymptotically efficient adaptive allocation rules
• Control Techniques for Complex Networks
• Finite time identification in unstable linear systems
• Finite-Time Adaptive Stabilization of Linear Systems
• scientific article; zbMATH DE number 3711820 (Why is no real title available?)
• scientific article; zbMATH DE number 1095138 (Why is no real title available?)
• scientific article; zbMATH DE number 796797 (Why is no real title available?)
• scientific article; zbMATH DE number 796853 (Why is no real title available?)
• On adaptive linear-quadratic regulators
• On the necessity of identifying the true parameter in adaptive LQ control
• Online learning in the embedded manifold of low-rank matrices
• Optimal control of LTI systems over unreliable communication links
• Optimality of Fast-Matching Algorithms for Random Networks With Applications to Structural Controllability
• Small sample properties of forecasts from autoregressive models under structural breaks
• Stabilization of discrete-time nonlinear uncertain systems by feedback based on LS algorithm
• The AAstrom-Wittenmark self-tuning regulator revisited and ELS-based adaptive trackers
• User-friendly tail bounds for sums of random matrices

Cited in

(9)

• Remarks on input to state stability of perturbed gradient flows, motivated by model-free feedback control learning
• On adaptive linear-quadratic regulators
• Performance analysis of the compressed distributed least squares algorithm
• Adaptive Optimal Feedback Control with Learned Internal Dynamics Models
• scientific article; zbMATH DE number 778097 (Why is no real title available?)
• scientific article; zbMATH DE number 7626780 (Why is no real title available?)
• Enhanced P-Type Control: Indirect Adaptive Learning From Set-Point Updates
• Joint learning of linear time-invariant dynamical systems
• Finite-time regret minimization for linear quadratic adaptive controllers: an experiment design approach

This page was built for publication: Input perturbations for adaptive control and learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2184498)