@inproceedings{0a5b00d19b9540f5b70cb6a2eaa1b34e,
title = "Expert Selection in High-Dimensional Markov Decision Processes",
abstract = "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.",
author = "Vicenc Rubies-Royo and Eric Mazumdar and Roy Dong and Claire Tomlin and Sastry, {S. Shankar}",
note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 59th IEEE Conference on Decision and Control, CDC 2020 ; Conference date: 14-12-2020 Through 18-12-2020",
year = "2020",
month = dec,
day = "14",
doi = "10.1109/CDC42340.2020.9303788",
language = "English (US)",
series = "Proceedings of the IEEE Conference on Decision and Control",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "3604--3610",
booktitle = "2020 59th IEEE Conference on Decision and Control, CDC 2020",
address = "United States",
}