Boosting for Control of Dynamical Systems

Agarwal, Naman; Brukhim, Nataly; Hazan, Elad; Lu, Zhou

Boosting for Control of Dynamical Systems

Author(s): Agarwal, Naman; Brukhim, Nataly; Hazan, Elad; Lu, Zhou

Download

To refer to this page use: http://arks.princeton.edu/ark:/88435/pr15s05

Full metadata record

DC Field	Value	Language
dc.contributor.author	Agarwal, Naman	-
dc.contributor.author	Brukhim, Nataly	-
dc.contributor.author	Hazan, Elad	-
dc.contributor.author	Lu, Zhou	-
dc.date.accessioned	2021-10-08T19:51:01Z	-
dc.date.available	2021-10-08T19:51:01Z	-
dc.date.issued	2020	en_US
dc.identifier.citation	Agarwal, Naman, Nataly Brukhim, Elad Hazan, and Zhou Lu. "Boosting for Control of Dynamical Systems." In Proceedings of the 37th International Conference on Machine Learning (2020): pp. 96-103.	en_US
dc.identifier.issn	2640-3498	-
dc.identifier.uri	http://proceedings.mlr.press/v119/agarwal20b/agarwal20b.pdf	-
dc.identifier.uri	http://arks.princeton.edu/ark:/88435/pr15s05	-
dc.description.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.	en_US
dc.format.extent	96 - 103	en_US
dc.language.iso	en_US	en_US
dc.relation.ispartof	Proceedings of the 37th International Conference on Machine Learning	en_US
dc.rights	Final published version. Article is made available in OAR by the publisher's permission or policy.	en_US
dc.title	Boosting for Control of Dynamical Systems	en_US
dc.type	Conference Article	en_US
pu.type.symplectic	http://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceeding	en_US

Files in This Item:

File	Description	Size	Format
BoostingControlDynamicalSystems.pdf		2.73 MB	Adobe PDF	View/Download

Show Simple Item Record