4 papers
Low-complexity Learning of Linear Quadratic Regulators from Noisy Data
Claudio De Persis, Pietro Tesi
This paper considers the Linear Quadratic Regulator problem for linear systems with unknown dynamics, a central problem in data-driven control and reinforcement learning. We propos…
Learning control for polynomial systems using sum of squares relaxations
Meichen Guo, Claudio De Persis, Pietro Tesi
This paper considers the problem of learning control laws for nonlinear polynomial systems directly from the data, which are input-output measurements collected in an experiment ov…
Willems' Fundamental Lemma for State-space Systems and its Extension to Multiple Datasets
Henk J. van Waarde, Claudio De Persis, M. Kanat Camlibel +1
Willems et al.'s fundamental lemma asserts that all trajectories of a linear system can be obtained from a single given one, assuming that a persistency of excitation condition hol…
Data-driven Linear Quadratic Regulation via Semidefinite Programming
Monica Rotulo, Claudio De Persis, Pietro Tesi
This paper studies the finite-horizon linear quadratic regulation problem where the dynamics of the system are assumed to be unknown and the state is accessible. Information on the…