Regret bounds for Narendra-Shapiro bandit algorithms

DOI10.1080/17442508.2018.1457675zbMath1498.60303arXiv1502.04874OpenAlexW1693596837MaRDI QIDQ5086451

Sébastien Gadat, Fabien Panloup, Sofiane Saadane

Publication date: 5 July 2022

Published in: Stochastics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1502.04874

zbMATH Keywords

piecewise deterministic Markov processesregretstochastic bandit algorithms

Mathematics Subject Classification ID

Continuous-time Markov processes on general state spaces (60J25) Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Sequential statistical analysis (62L10)

Cites Work

• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Total variation estimates for the TCP process
• A penalized bandit algorithm
• Stochastic approximation methods for constrained and unconstrained systems
• When can the two-armed bandit algorithm be trusted?
• On the linear model with two absorbing barriers
• Long time behavior of Markov processes and beyond
• How Fast Is the Bandit?
• The Nonstochastic Multiarmed Bandit Problem
• 10.1162/153244303321897663
• Use of Stochastic Automata for Parameter Self-Optimization with Multimodal Performance Criteria
• Some aspects of the sequential design of experiments
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: Regret bounds for Narendra-Shapiro bandit algorithms