Skip to main content

Online Control with Adversarial Disturbances

Author(s): Agarwal, Naman; Bullins, Brian; Hazan, Elad; Kakade, Sham; Singh, Karan

Download
To refer to this page use: http://arks.princeton.edu/ark:/88435/pr1hz7d
Full metadata record
DC FieldValueLanguage
dc.contributor.authorAgarwal, Naman-
dc.contributor.authorBullins, Brian-
dc.contributor.authorHazan, Elad-
dc.contributor.authorKakade, Sham-
dc.contributor.authorSingh, Karan-
dc.date.accessioned2021-10-08T19:49:35Z-
dc.date.available2021-10-08T19:49:35Z-
dc.date.issued2019en_US
dc.identifier.citationAgarwal, Naman, Brian Bullins, Elad Hazan, Sham Kakade, and Karan Singh. "Online Control with Adversarial Disturbances." In Proceedings of the 36th International Conference on Machine Learning (2019): pp. 111-119.en_US
dc.identifier.issn2640-3498-
dc.identifier.urihttp://proceedings.mlr.press/v97/agarwal19c/agarwal19c.pdf-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/pr1hz7d-
dc.description.abstractWe study the control of linear dynamical systems with adversarial disturbances, as opposed to statistical noise. We present an efficient algorithm that achieves nearly-tight regret bounds in this setting. Our result generalizes upon previous work in two main aspects: the algorithm can accommodate adversarial noise in the dynamics, and can handle general convex costs.en_US
dc.format.extent111 - 119en_US
dc.language.isoen_USen_US
dc.relation.ispartofProceedings of the 36th International Conference on Machine Learningen_US
dc.rightsFinal published version. Article is made available in OAR by the publisher's permission or policy.en_US
dc.titleOnline Control with Adversarial Disturbancesen_US
dc.typeConference Articleen_US
pu.type.symplectichttp://www.symplectic.co.uk/publications/atom-terms/1.0/conference-proceedingen_US

Files in This Item:
File Description SizeFormat 
OnlineControlAdversarialDisturbances.pdf275.69 kBAdobe PDFView/Download


Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.