Online learning with sample path constraints

We study online learning where a decision maker interacts with Nature with the objective of maximizing her long-term average reward subject to some sample path average constraints. We de ne the reward-in-hindsight as the highest reward the decision maker could have achieved, while satisfying the...

Descripció completa

Dades bibliogràfiques
Autors principals: Mannor, Shie, Tsitsiklis, John N., Yu, Jia Yuan
Altres autors: Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Format: Article
Idioma:en_US
Publicat: MIT Press 2010
Accés en línia:http://hdl.handle.net/1721.1/51700
https://orcid.org/0000-0003-2658-8239