Skip to main content

Non-Stochastic Control with Bandit Feedback

Author(s): Gradu, Paula; Hallman, John; Hazan, Elad

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1wg37
Abstract: We study the problem of controlling a linear dynamical system with adversarial perturbations where the only feedback available to the controller is the scalar loss, and the loss function itself is unknown. For this problem, with either a known or unknown system, we give an efficient sublinear regret algorithm. The main algorithmic difficulty is the dependence of the loss on past controls. To overcome this issue, we propose an efficient algorithm for the general setting of bandit convex optimization for loss functions with memory, which may be of independent interest.
Publication Date: 2020
Citation: Gradu, Paula, John Hallman, and Elad Hazan. "Non-Stochastic Control with Bandit Feedback." Advances in Neural Information Processing Systems 33 (2020).
ISSN: 1049-5258
Type of Material: Conference Article
Journal/Proceeding Title: Advances in Neural Information Processing Systems
Version: Final published version. Article is made available in OAR by the publisher's permission or policy.



Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.