Robust sequential design for piecewise-stationary multi-armed bandit problem in the presence of outliers

DOI10.1080/24754269.2021.1902687OpenAlexW3154350176MaRDI QIDQ5880072

Zhicheng Peng, Qian Xiao, Ri-quan Zhang, Ya Ping Wang

Publication date: 7 March 2023

Published in: Statistical Theory and Related Fields (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/24754269.2021.1902687

zbMATH Keywords

noisy dataonline learningchange-point detectiontruncated loss

Mathematics Subject Classification ID

Statistics (62-XX)

Cites Work

• Unnamed Item
• Asymptotically efficient adaptive allocation rules
• On Upper-Confidence Bound Policies for Switching Bandit Problems
• Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/153244303321897663
• Bandit Algorithms
• Optimal Exploration–Exploitation in a Multi-armed Bandit Problem with Non-stationary Rewards
• Inference about the change-point from cumulative sum tests
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Robust sequential design for piecewise-stationary multi-armed bandit problem in the presence of outliers