Boosting for Control of Dynamical Systems

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.

Cite

Text

Agarwal et al. "Boosting for Control of Dynamical Systems." International Conference on Machine Learning, 2020.

Markdown

[Agarwal et al. "Boosting for Control of Dynamical Systems." International Conference on Machine Learning, 2020.](https://mlanthology.org/icml/2020/agarwal2020icml-boosting/)

BibTeX

@inproceedings{agarwal2020icml-boosting,
  title     = {{Boosting for Control of Dynamical Systems}},
  author    = {Agarwal, Naman and Brukhim, Nataly and Hazan, Elad and Lu, Zhou},
  booktitle = {International Conference on Machine Learning},
  year      = {2020},
  pages     = {96-103},
  volume    = {119},
  url       = {https://mlanthology.org/icml/2020/agarwal2020icml-boosting/}
}