Work

Controlling unknown linear dynamics with almost optimal regret

Year: 2024

Type: article

Abstract: Here and in a companion paper, we consider a simple control problem in which the underlying dynamics depend on a parameter a that is unknown and must be learned. In this paper, we assume that a can be any real number and we do not assume that we have a prior belief about a . We seek a control strategy that minimizes a quantity called the regret. Given any \varepsilon>0 , we produce a strategy that minimizes the regret to within a multiplicative factor of (1+\varepsilon) .

Source: Revista Matemática Iberoamericana

DOI: 10.4171/rmi/1511

Authors: Jacob Carruth, Maximilian F. Eggl, Charles Fefferman, Clarence W. Rowley

Institutions: Princeton University, University of Bonn

Language: English

Topic: Advanced Bandit Algorithms Research

Subfield: Management Science and Operations Research

Field: Decision Sciences

Domain: Social Sciences

Open Access status: diamond

Funders: Joachim Herz Stiftung, Air Force Office of Scientific Research

Awards: G1523888516, G6562578720