Low-complexity learning of linear quadratic regulators from noisy data

DOI10.1016/j.automatica.2021.109548zbMath1461.93485arXiv2005.01082OpenAlexW3137642493MaRDI QIDQ2021294

Claudio De Persis, Pietro Tesi

Publication date: 26 April 2021

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2005.01082

Mathematics Subject Classification ID

Nonlinear systems in control theory (93C10) Linear systems in control theory (93C05) Stochastic systems in control theory (general) (93E03)

Related Items (10)

On data-driven stabilization of systems with nonlinearities satisfying quadratic constraints ⋮ Virtual reference feedback tuning for linear discrete-time systems with robust stability guarantees based on set membership ⋮ Distributed data-driven consensus control of multi-agent systems under switched uncertainties ⋮ Data-driven dynamic relatively optimal control ⋮ Data-driven control of linear systems via quantized feedback ⋮ Data‐driven control for networked systems with multiple packet dropouts ⋮ Trade-offs in learning controllers from noisy data ⋮ Online learning of data-driven controllers for unknown switched linear systems ⋮ Data-driven control via Petersen's lemma ⋮ A convex optimization approach to synthesizing state feedback data-driven controllers for switched linear systems

Uses Software

• CVX

Cites Work

• Unnamed Item
• Unnamed Item
• Data-driven design of two degree-of-freedom nonlinear controllers: the \(\operatorname{D}^2\)-IBC approach
• Optimal sampled-data control systems
• On the sample complexity of the linear quadratic regulator
• From model-based control to data-driven control: survey, classification and perspective
• A note on persistency of excitation
• High-Dimensional Statistics
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness
• Finite sample properties of system identification methods
• On the Theory of the Brownian Motion II
• Data Informativity: A New Perspective on Data-Driven Analysis and Control

This page was built for publication: Low-complexity learning of linear quadratic regulators from noisy data