Expert Selection in High-Dimensional Markov Decision Processes
Machine Learning
2020-10-30 v1 Artificial Intelligence
Systems and Control
Systems and Control
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.
Cite
@article{arxiv.2010.15599,
title = {Expert Selection in High-Dimensional Markov Decision Processes},
author = {Vicenc Rubies-Royo and Eric Mazumdar and Roy Dong and Claire Tomlin and S. Shankar Sastry},
journal= {arXiv preprint arXiv:2010.15599},
year = {2020}
}
Comments
In proceedings of the 59th IEEE Conference on Decision and Control 2020. arXiv admin note: text overlap with arXiv:1707.05714