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

Alexander Nazin; Boris Miller

doi:10.3182/20110828-6-IT-1002.03450

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

Alexander Nazin, Boris Miller

School of Mathematics

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-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 language	English
Title of host publication	Proceedings of the 18th IFAC World Congress
Editors	Sergio Bittani, Angelo Cedenese, Sandro Zampieri
Place of Publication	United Kingdom
Publisher	Elsevier
Pages	12421 - 12426
Number of pages	6
Volume	18
ISBN (Print)	9783902661937
DOIs	https://doi.org/10.3182/20110828-6-IT-1002.03450
Publication status	Published - 2011
Event	International Federation of Automatic Control World Congress 2011 - Università Cattolica del Sacro Cuore, Milano, Italy Duration: 28 Aug 2011 → 2 Sep 2011 Conference number: 18th https://www.ifac2011.org/

Conference

Conference	International Federation of Automatic Control World Congress 2011
Abbreviated title	IFAC 2011
Country	Italy
City	Milano
Period	28/08/11 → 2/09/11
Internet address	https://www.ifac2011.org/

Access to Document

10.3182/20110828-6-IT-1002.03450

RM sElocation

Cite this

@inproceedings{7e40fada120d4d8781ce1bf40c336f0c,

title = "Online mirror descent algorithm for controlled homogeneous finite Markov chains with unknown mean losses",

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.",

author = "Alexander Nazin and Boris Miller",

year = "2011",

doi = "10.3182/20110828-6-IT-1002.03450",

language = "English",

isbn = "9783902661937",

volume = "18",

pages = "12421 -- 12426",

editor = "Sergio Bittani and Angelo Cedenese and Sandro Zampieri",

booktitle = "Proceedings of the 18th IFAC World Congress",

publisher = "Elsevier",

address = "Netherlands",

note = "International Federation of Automatic Control World Congress 2011, IFAC 2011 ; Conference date: 28-08-2011 Through 02-09-2011",

url = "https://www.ifac2011.org/",

}

Nazin, A & Miller, B 2011, Online mirror descent algorithm for controlled homogeneous finite Markov chains with unknown mean losses. in S Bittani, A Cedenese & S Zampieri (eds), Proceedings of the 18th IFAC World Congress. vol. 18, Elsevier, United Kingdom, pp. 12421 - 12426, International Federation of Automatic Control World Congress 2011, Milano, Italy, 28/08/11. https://doi.org/10.3182/20110828-6-IT-1002.03450

Online mirror descent algorithm for controlled homogeneous finite Markov chains with unknown mean losses. / Nazin, Alexander; Miller, Boris.

Proceedings of the 18th IFAC World Congress. ed. / Sergio Bittani; Angelo Cedenese; Sandro Zampieri. Vol. 18 United Kingdom : Elsevier, 2011. p. 12421 - 12426.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Online mirror descent algorithm for controlled homogeneous finite Markov chains with unknown mean losses

AU - Nazin, Alexander

AU - Miller, Boris

N1 - Conference code: 18th

PY - 2011

Y1 - 2011

N2 - 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.

AB - 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.

UR - http://www.ifac-papersonline.net/Detailed/51551.html

U2 - 10.3182/20110828-6-IT-1002.03450

DO - 10.3182/20110828-6-IT-1002.03450

M3 - Conference Paper

SN - 9783902661937

VL - 18

SP - 12421

EP - 12426

BT - Proceedings of the 18th IFAC World Congress

A2 - Bittani, Sergio

A2 - Cedenese, Angelo

A2 - Zampieri, Sandro

PB - Elsevier

CY - United Kingdom

T2 - International Federation of Automatic Control World Congress 2011

Y2 - 28 August 2011 through 2 September 2011

ER -