Online mirror descent algorithm for controlled homogeneous finite Markov chains with unknown mean losses

Alexander Nazin, Boris Miller

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

1 Citation (Scopus)

Abstract

We consider the adaptative stochastic problem for a system described by a controlled Markov Chain (CMC) with a finite number of states. The novelty of the approach consists in the adaptation technique for optimization of the system with unknown distribution of the cost function.
Original languageEnglish
Title of host publicationProceedings of the 18th IFAC World Congress
EditorsSergio Bittani, Angelo Cedenese, Sandro Zampieri
Place of PublicationUnited Kingdom
PublisherElsevier
Pages12421 - 12426
Number of pages6
Volume18
ISBN (Print)9783902661937
DOIs
Publication statusPublished - 2011
EventInternational Federation of Automatic Control World Congress 2011 - Università Cattolica del Sacro Cuore, Milano, Italy
Duration: 28 Aug 20112 Sep 2011
Conference number: 18th
https://www.ifac2011.org/

Conference

ConferenceInternational Federation of Automatic Control World Congress 2011
Abbreviated titleIFAC 2011
CountryItaly
CityMilano
Period28/08/112/09/11
Internet address

Cite this