Trade-offs in learning controllers from noisy data

DOI10.1016/j.sysconle.2021.104985zbMath1478.93705arXiv2103.08629OpenAlexW3139533914MaRDI QIDQ2242918

Claudio De Persis, Andrea Bisoffi, Pietro Tesi

Publication date: 10 November 2021

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2103.08629

zbMATH Keywords

linear matrix inequalitiesrobust controluncertainty reductiondata-driven controlcontroller learningdata affected by disturbance with energy or instantaneous bounds

Mathematics Subject Classification ID

Sensitivity (robustness) (93B35) Perturbations in control/observation systems (93C73) Stochastic stability in control theory (93E15)

Related Items (6)

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 control of linear systems via quantized feedback ⋮ Data-driven design of safe control for polynomial systems ⋮ Online learning of data-driven controllers for unknown switched linear systems ⋮ Data-driven control via Petersen's lemma

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Data-based stabilization of unknown bilinear systems with guaranteed basin of attraction
• Low-complexity learning of linear quadratic regulators from noisy data
• On the sample complexity of the linear quadratic regulator
• A note on persistency of excitation
• Linear Matrix Inequalities in System and Control Theory
• Formulas for Data-Driven Control: Stabilization, Optimality, and Robustness

This page was built for publication: Trade-offs in learning controllers from noisy data