Controlling unknown linear dynamics with bounded multiplicative regret
Jacob Carruth
Princeton University, USAMaximilian F. Eggl
University of Mainz Medical Center, GermanyCharles Fefferman
Princeton University, USAClarence W. Rowley
Princeton University, USAMelanie Weber
University of Oxford, UK
Abstract
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.
Cite this article
Jacob Carruth, Maximilian F. Eggl, Charles Fefferman, Clarence W. Rowley, Melanie Weber, Controlling unknown linear dynamics with bounded multiplicative regret. Rev. Mat. Iberoam. 38 (2022), no. 7, pp. 2185–2216
DOI 10.4171/RMI/1377