Erratum: Satisficing in Multiarmed Bandit Problems (IEEE Trans. Autom. Control (2017) 62:8 (3788–3803) DOI: 10.1109/TAC.2016.2644380)

Paul Reverdy, Vaibhav Srivastava, Naomi Ehrich Leonard

Research output: Contribution to journalComment/debatepeer-review

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 languageEnglish (US)
Article number9039571
Pages (from-to)476-478
Number of pages3
JournalIEEE Transactions on Automatic Control
Volume66
Issue number1
DOIs
StatePublished - Jan 2021

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'Erratum: Satisficing in Multiarmed Bandit Problems (IEEE Trans. Autom. Control (2017) 62:8 (3788–3803) DOI: 10.1109/TAC.2016.2644380)'. Together they form a unique fingerprint.

Cite this