Controlling unknown linear dynamics with bounded multiplicative regret

DOI10.4171/RMI/1377MaRDI QIDQ2692507zbMATH OpenFDO

Authors Jacob Carruth, M. F. Eggl, Clarence W. Rowley, Melanie Weber, Charles Fefferman

Publication date 21 March 2023

Published in Revista Matemática Iberoamericana (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/2109.06350

zbMATH Keywords

adaptive controlbounded regretcompetitive ratioLQR control

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Review text

Summary: We consider a simple control problem in which the underlying dynamics depend on a parameter that is unknown and must be learned. We exhibit a control strategy which is optimal to within a multiplicative constant. While most authors find strategies which are successful as the time horizon tends to infinity, our strategy achieves lowest expected cost up to a constant factor for a fixed time horizon.

Recommendations

• Optimal control with learning on the fly: a toy problem
• Optimal Control of an Unknown Linear Process with Learning
• scientific article; zbMATH DE number 17342
• On the sample complexity of the linear quadratic regulator
• Optimal control of unknown discrete-time linear systems with additive noise

Cites work

• Adaptive subgradient methods for online learning and stochastic optimization
• scientific article; zbMATH DE number 3435336 (Why is no real title available?)
• scientific article; zbMATH DE number 3349081 (Why is no real title available?)
• Optimal control with learning on the fly: a toy problem
• Regret analysis of stochastic and nonstochastic multi-armed bandit problems
• Some aspects of the sequential design of experiments

Cited in

(14)

• Input perturbations for adaptive control and learning
• On the sample complexity of the linear quadratic regulator
• Logarithmic regret in online linear quadratic control using Riccati updates
• scientific article; zbMATH DE number 3847250 (Why is no real title available?)
• Optimal Control of an Unknown Linear Process with Learning
• scientific article; zbMATH DE number 17342 (Why is no real title available?)
• On-the-Fly Control of Unknown Nonlinear Systems With Sublinear Regret
• Regret bounds for online-learning-based linear quadratic control under database attacks
• On the relation between dynamic regret and closed-loop stability
• Controlling Unknown Linear Dynamics with Bounded Multiplicative Regret
• Controlling unknown linear dynamics with almost optimal regret
• Optimal agnostic control of unknown linear dynamics in a bounded parameter range
• Optimal control with learning on the fly from finite to infinite-dimensional systems
• Optimal control with learning on the fly: a toy problem

Describes a project that uses

Uses Software

• AdaGrad

This page was built for publication: Controlling unknown linear dynamics with bounded multiplicative regret

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2692507)