On the optimal amount of experimentation in sequential decision problems

Dinah Rosenberg; Eilon Solan; Nicolas Vieille

doi:10.1016/j.spl.2009.11.014

On the optimal amount of experimentation in sequential decision problems

Dinah Rosenberg, Eilon Solan^*, Nicolas Vieille

^*Corresponding author for this work

School of Mathematical Sciences

Research output: Contribution to journal › Article › peer-review

Abstract

We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.

Original language	English
Pages (from-to)	381-385
Number of pages	5
Journal	Statistics and Probability Letters
Volume	80
Issue number	5-6
DOIs	https://doi.org/10.1016/j.spl.2009.11.014
State	Published - 2010

Access to Document

10.1016/j.spl.2009.11.014

Cite this

@article{b08c586f6c604347ac5b35379e564e74,

title = "On the optimal amount of experimentation in sequential decision problems",

abstract = "We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.",

author = "Dinah Rosenberg and Eilon Solan and Nicolas Vieille",

year = "2010",

doi = "10.1016/j.spl.2009.11.014",

language = "אנגלית",

volume = "80",

pages = "381--385",

journal = "Statistics and Probability Letters",

issn = "0167-7152",

publisher = "Elsevier",

number = "5-6",

}

TY - JOUR

T1 - On the optimal amount of experimentation in sequential decision problems

AU - Rosenberg, Dinah

AU - Solan, Eilon

AU - Vieille, Nicolas

PY - 2010

Y1 - 2010

N2 - We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.

AB - We provide a tight bound on the amount of experimentation under the optimal strategy in sequential decision problems. We show the applicability of the result by providing a bound on the cut-off in a one-arm bandit problem.

UR - http://www.scopus.com/inward/record.url?scp=74849137428&partnerID=8YFLogxK

U2 - 10.1016/j.spl.2009.11.014

DO - 10.1016/j.spl.2009.11.014

M3 - ???researchoutput.researchoutputtypes.contributiontojournal.article???

AN - SCOPUS:74849137428

SN - 0167-7152

VL - 80

SP - 381

EP - 385

JO - Statistics and Probability Letters

JF - Statistics and Probability Letters

IS - 5-6

ER -

On the optimal amount of experimentation in sequential decision problems

Abstract

Access to Document

Other files and links

Fingerprint

Cite this