Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit

DOI10.1007/s42519-022-00280-wOpenAlexW4289341771MaRDI QIDQ2081727

Timothy J. Keaton, Arman Sabbaghi

Publication date: 30 September 2022

Published in: Journal of Statistical Theory and Practice (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s42519-022-00280-w

zbMATH Keywords

Bayesian inferencesequential designbinomial banditnormal banditPoisson bandit

Mathematics Subject Classification ID

Mathematical programming (90Cxx) Mathematical economics (91Bxx) Sequential statistical methods (62Lxx)

Uses Software

• BayesDA

Cites Work

• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Best subset, forward stepwise or Lasso? Analysis and recommendations based on extensive comparisons
• Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
• Hannan Consistency in On-Line Learning in Case of Unbounded Losses Under Partial Monitoring
• Near-Optimal Regret Bounds for Thompson Sampling
• The Nonstochastic Multiarmed Bandit Problem
• Simple Bayesian Algorithms for Best-Arm Identification
• Finite-time analysis of the multiarmed bandit problem
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Dismemberment and design for controlling the replication variance of regret for the multi-armed bandit