Lale, Sahin and Azizzadenesheli, Kamyar and Hassibi, Babak and Anandkumar, Anima (2020) Logarithmic Regret Bound in Partially Observable Linear Dynamical Systems. In: Advances in neural information processing systems 33 pre-proceedings (NeurIPS 2020). Neural Information Processing Foundation , La Jolla, CA, pp. 1-13. ISBN 9781713829546. https://resolver.caltech.edu/CaltechAUTHORS:20221222-222544264
Full text is not posted in this repository. Consult Related URLs below.
Use this Persistent URL to link to this item: https://resolver.caltech.edu/CaltechAUTHORS:20221222-222544264
Abstract
We study the problem of adaptive control in partially observable linear dynamical systems. We propose a novel algorithm, adaptive control online learning algorithm (AdaptOn), which efficiently explores the environment, estimates the system dynamics episodically and exploits these estimates to design effective controllers to minimize the cumulative costs. Through interaction with the environment, AdaptOn deploys online convex optimization to optimize the controller while simultaneously learning the system dynamics to improve the accuracy of controller updates. We show that when the cost functions are strongly convex, after T times step of agent-environment interaction, AdaptOn achieves regret upper bound of polylog(T). To the best of our knowledge, AdaptOn is the first algorithm which achieves polylog(T) regret in adaptive control of unknown partially observable linear dynamical systems which includes linear quadratic Gaussian (LQG) control.
Item Type: | Book Section | ||||||||||||||||||||||||||||||||
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
Related URLs: |
| ||||||||||||||||||||||||||||||||
ORCID: |
| ||||||||||||||||||||||||||||||||
Additional Information: | S. Lale is supported in part by DARPA PAI. K. Azizzadenesheli gratefully acknowledge the financial support of Raytheon and Amazon Web Services. B. Hassibi is supported in part by the National Science Foundation under grants CNS-0932428, CCF-1018927, CCF-1423663 and CCF-1409204, by a grant from Qualcomm Inc., by NASA’s Jet Propulsion Laboratory through the President and Director’s Fund, and by King Abdullah University of Science and Technology. A. Anandkumar is supported in part by Bren endowed chair, DARPA PAIHR00111890035 and LwLL grants, Raytheon, Microsoft, Google, and Adobe faculty fellowships. | ||||||||||||||||||||||||||||||||
Funders: |
| ||||||||||||||||||||||||||||||||
Record Number: | CaltechAUTHORS:20221222-222544264 | ||||||||||||||||||||||||||||||||
Persistent URL: | https://resolver.caltech.edu/CaltechAUTHORS:20221222-222544264 | ||||||||||||||||||||||||||||||||
Usage Policy: | No commercial reproduction, distribution, display or performance rights in this work are provided. | ||||||||||||||||||||||||||||||||
ID Code: | 118598 | ||||||||||||||||||||||||||||||||
Collection: | CaltechAUTHORS | ||||||||||||||||||||||||||||||||
Deposited By: | George Porter | ||||||||||||||||||||||||||||||||
Deposited On: | 23 Dec 2022 00:25 | ||||||||||||||||||||||||||||||||
Last Modified: | 23 Dec 2022 00:25 |
Repository Staff Only: item control page