Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain

Alexander V Nazin; Boris Miller

doi:10.3182/20130619-3-RU-3018.00149

Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain

Alexander V Nazin, Boris Miller

School of Mathematics

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

Original language	English
Title of host publication	Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control
Editors	Natalia Bakhtadze, Kirill Chernyshov, Alexandre Dolgui, Vladimir Lotosky
Place of Publication	Oxford England
Publisher	Elsevier
Pages	939 - 943
Number of pages	5
Volume	7
DOIs	https://doi.org/10.3182/20130619-3-RU-3018.00149
Publication status	Published - 2013
Event	IFAC Conference on Manufacturing Modelling, Management, and Control 2013 - Saint Petersburg State University, Saint Petersburg, Russian Federation Duration: 19 Jun 2013 → 21 Jun 2013 http://mim2013.org/

Conference

Conference	IFAC Conference on Manufacturing Modelling, Management, and Control 2013
Abbreviated title	IFAC MIM 2013
Country/Territory	Russian Federation
City	Saint Petersburg
Period	19/06/13 → 21/06/13
Other	International Federation of Automatic Control (IFAC)
Internet address	http://mim2013.org/

Access to Document

10.3182/20130619-3-RU-3018.00149

Cite this

Nazin, A. V., & Miller, B. (2013). Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain. In N. Bakhtadze, K. Chernyshov, A. Dolgui, & V. Lotosky (Eds.), Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control (Vol. 7, pp. 939 - 943). Elsevier. https://doi.org/10.3182/20130619-3-RU-3018.00149

Nazin, Alexander V ; Miller, Boris. / Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain. Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control. editor / Natalia Bakhtadze ; Kirill Chernyshov ; Alexandre Dolgui ; Vladimir Lotosky. Vol. 7 Oxford England : Elsevier, 2013. pp. 939 - 943

@inproceedings{a50f57d6e8e54fbe8c5456afcdeb3c45,

title = "Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain",

author = "Nazin, \{Alexander V\} and Boris Miller",

year = "2013",

doi = "10.3182/20130619-3-RU-3018.00149",

language = "English",

volume = "7",

pages = "939 -- 943",

editor = "Natalia Bakhtadze and Kirill Chernyshov and Alexandre Dolgui and Vladimir Lotosky",

booktitle = "Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control",

publisher = "Elsevier",

address = "Netherlands",

note = "IFAC Conference on Manufacturing Modelling, Management, and Control 2013, IFAC MIM 2013 ; Conference date: 19-06-2013 Through 21-06-2013",

url = "http://mim2013.org/",

}

Nazin, AV & Miller, B 2013, Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain. in N Bakhtadze, K Chernyshov, A Dolgui & V Lotosky (eds), Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control. vol. 7, Elsevier, Oxford England, pp. 939 - 943, IFAC Conference on Manufacturing Modelling, Management, and Control 2013, Saint Petersburg, Russian Federation, 19/06/13. https://doi.org/10.3182/20130619-3-RU-3018.00149

Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain. / Nazin, Alexander V; Miller, Boris.
Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control. ed. / Natalia Bakhtadze; Kirill Chernyshov; Alexandre Dolgui; Vladimir Lotosky. Vol. 7 Oxford England: Elsevier, 2013. p. 939 - 943.

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

TY - GEN

T1 - Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain

AU - Nazin, Alexander V

AU - Miller, Boris

PY - 2013

Y1 - 2013

UR - https://www.scopus.com/pages/publications/84884331927

U2 - 10.3182/20130619-3-RU-3018.00149

DO - 10.3182/20130619-3-RU-3018.00149

M3 - Conference Paper

VL - 7

SP - 939

EP - 943

BT - Preprints of the 2013 IFAC Conference on Manufacturing Modelling, Management, and Control

A2 - Bakhtadze, Natalia

A2 - Chernyshov, Kirill

A2 - Dolgui, Alexandre

A2 - Lotosky, Vladimir

PB - Elsevier

CY - Oxford England

T2 - IFAC Conference on Manufacturing Modelling, Management, and Control 2013

Y2 - 19 June 2013 through 21 June 2013

ER -

Robust mirror decent algorithm for a multi-armed bandit governed by a stationary finite Markov chain

Conference

Access to Document

Other files and links

Cite this