Low-complexity Learning of Linear Quadratic Regulators from Noisy Data
Abstract
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 propose a method that uses data to directly return a controller without estimating a model of the system. Sufficient conditions are given under which this method returns a stabilizing controller with guaranteed relative error when the data used to design the controller are affected by noise. This method has low complexity as it only requires a finite number of samples of the system response to a sufficiently exciting input, and can be efficiently implemented as a semi-definite program. Further, the method does not require assumptions on the noise statistics, and the relative error nicely scales with the noise magnitude.
Cite
@article{arxiv.2005.01082,
title = {Low-complexity Learning of Linear Quadratic Regulators from Noisy Data},
author = {Claudio De Persis and Pietro Tesi},
journal= {arXiv preprint arXiv:2005.01082},
year = {2020}
}