A Caltech Library Service

Expert Selection in High-Dimensional Markov Decision Processes

Rubies-Royo, Vicenç and Mazumdar, Eric and Dong, Roy and Tomlin, Claire and Sastry, S. Shankar (2020) Expert Selection in High-Dimensional Markov Decision Processes. In: 2020 59th IEEE Conference on Decision and Control (CDC). IEEE , Piscataway, NJ, pp. 3604-3610. ISBN 978-1-7281-7447-1.

[img] PDF - Accepted Version
See Usage Policy.


Use this Persistent URL to link to this item:


In this work we present a multi-armed bandit framework for online expert selection in Markov decision processes and demonstrate its use in high-dimensional settings. Our method takes a set of candidate expert policies and switches between them to rapidly identify the best performing expert using a variant of the classical upper confidence bound algorithm, thus ensuring low regret in the overall performance of the system. This is useful in applications where several expert policies may be available, and one needs to be selected at run-time for the underlying environment.

Item Type:Book Section
Related URLs:
URLURL TypeDescription Paper
Mazumdar, Eric0000-0002-1815-269X
Dong, Roy0000-0001-8034-4329
Tomlin, Claire0000-0003-3192-3185
Additional Information:© 2020 IEEE.
Record Number:CaltechAUTHORS:20210903-222215578
Persistent URL:
Official Citation:V. Rubies-Royo, E. Mazumdar, R. Dong, C. Tomlin and S. S. Sastry, "Expert Selection in High-Dimensional Markov Decision Processes," 2020 59th IEEE Conference on Decision and Control (CDC), 2020, pp. 3604-3610, doi: 10.1109/CDC42340.2020.9303788
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:110733
Deposited By: George Porter
Deposited On:07 Sep 2021 15:19
Last Modified:07 Sep 2021 20:05

Repository Staff Only: item control page