Boosting for Control of Dynamical Systems
Machine Learning
2020-02-25 v2 Machine Learning
Abstract
We study the question of how to aggregate controllers for dynamical systems in order to improve their performance. To this end, we propose a framework of boosting for online control. Our main result is an efficient boosting algorithm that combines weak controllers into a provably more accurate one. Empirical evaluation on a host of control settings supports our theoretical findings.
Keywords
Cite
@article{arxiv.1906.08720,
title = {Boosting for Control of Dynamical Systems},
author = {Naman Agarwal and Nataly Brukhim and Elad Hazan and Zhou Lu},
journal= {arXiv preprint arXiv:1906.08720},
year = {2020}
}