Corrections to â€œSatisficing in Multiarmed Bandit Problemsâ€� [Aug 17 3788-3803]

Paul Reverdy; Vaibhav Srivastava; Naomi Ehrich Leonard

doi:10.1109/TAC.2020.2981433

Corrections to â€œSatisficing in Multiarmed Bandit Problemsâ€� [Aug 17 3788-3803]

Paul Reverdy
, Vaibhav Srivastava
, Naomi Ehrich Leonard

Aerospace and Mechanical Engineering

Research output: Contribution to journal › Comment/debate › peer-review

1 Scopus citations

Abstract

An unfortunate mistake in the proof of Theorem 8 of the above article is corrected. (Table Presented) (Formula Presented) 1The result in [1, Th. 22] is stated for bounded rewards, but it extends immediately to sub-Gaussian rewards by noting that the upper bound on the moment generating function for a bounded random variable obtained using a Hoeffding inequality has the same functional form as the sub-Gaussian random variable.

Original language	English (US)
Article number	9039571
Pages (from-to)	476-478
Number of pages	3
Journal	IEEE Transactions on Automatic Control
Volume	66
Issue number	1
DOIs	https://doi.org/10.1109/TAC.2020.2981433
State	Published - Jan 2021

ASJC Scopus subject areas

Control and Systems Engineering
Computer Science Applications
Electrical and Electronic Engineering

Access to Document

10.1109/TAC.2020.2981433

Cite this

@article{27cda76f1b3343d398287344cb9255e3,

title = "Corrections to {\^a}€{\oe}Satisficing in Multiarmed Bandit Problems{\^a}€� [Aug 17 3788-3803]",

abstract = "An unfortunate mistake in the proof of Theorem 8 of the above article is corrected. (Table Presented) (Formula Presented) 1The result in [1, Th. 22] is stated for bounded rewards, but it extends immediately to sub-Gaussian rewards by noting that the upper bound on the moment generating function for a bounded random variable obtained using a Hoeffding inequality has the same functional form as the sub-Gaussian random variable.",

author = "Paul Reverdy and Vaibhav Srivastava and Leonard, \{Naomi Ehrich\}",

note = "Publisher Copyright: {\textcopyright} 1963-2012 IEEE.",

year = "2021",

month = jan,

doi = "10.1109/TAC.2020.2981433",

language = "English (US)",

volume = "66",

pages = "476--478",

journal = "IEEE Transactions on Automatic Control",

issn = "0018-9286",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "1",

}

TY - JOUR

T1 - Corrections to â€œSatisficing in Multiarmed Bandit Problemsâ€� [Aug 17 3788-3803]

AU - Reverdy, Paul

AU - Srivastava, Vaibhav

AU - Leonard, Naomi Ehrich

PY - 2021/1

Y1 - 2021/1

N2 - An unfortunate mistake in the proof of Theorem 8 of the above article is corrected. (Table Presented) (Formula Presented) 1The result in [1, Th. 22] is stated for bounded rewards, but it extends immediately to sub-Gaussian rewards by noting that the upper bound on the moment generating function for a bounded random variable obtained using a Hoeffding inequality has the same functional form as the sub-Gaussian random variable.

AB - An unfortunate mistake in the proof of Theorem 8 of the above article is corrected. (Table Presented) (Formula Presented) 1The result in [1, Th. 22] is stated for bounded rewards, but it extends immediately to sub-Gaussian rewards by noting that the upper bound on the moment generating function for a bounded random variable obtained using a Hoeffding inequality has the same functional form as the sub-Gaussian random variable.

UR - https://www.scopus.com/pages/publications/85098671432

UR - https://www.scopus.com/pages/publications/85098671432#tab=citedBy

U2 - 10.1109/TAC.2020.2981433

DO - 10.1109/TAC.2020.2981433

M3 - Comment/debate

AN - SCOPUS:85098671432

SN - 0018-9286

VL - 66

SP - 476

EP - 478

JO - IEEE Transactions on Automatic Control

JF - IEEE Transactions on Automatic Control

IS - 1

M1 - 9039571

ER -

Corrections to â€œSatisficing in Multiarmed Bandit Problemsâ€� [Aug 17 3788-3803]

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this