Nonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit models

DOI10.1080/07474946.2021.1847965zbMath1464.62360arXiv1905.03495OpenAlexW3138493539MaRDI QIDQ4987192

Emilie Kaufmann, Aurélien Garivier

Publication date: 29 April 2021

Published in: Sequential Analysis (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1905.03495

zbMATH Keywords

generalized likelihood ratio testmulti-armed banditssequential testingbest arm identification

Mathematics Subject Classification ID

Parametric hypothesis testing (62F03) Sequential statistical analysis (62L10)

Related Items (2)

Policy space identification in configurable environments ⋮ Unnamed Item

Cites Work

• Unnamed Item
• Unnamed Item
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Asymptotically efficient adaptive allocation rules
• Boundary crossing problems for sample means
• The expected sample size of some tests of power one
• Sequential Design of Experiments
• A fully sequential procedure for indifference-zone selection in simulation
• Explore First, Exploit Next: The True Shape of Regret in Bandit Problems
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• The Large-Sample Distribution of the Likelihood Ratio for Testing Composite Hypotheses
• Some aspects of the sequential design of experiments
• Sequential Tests of Statistical Hypotheses

This page was built for publication: Nonasymptotic sequential tests for overlapping hypotheses applied to near-optimal arm identification in bandit models