Approximations of the Restless Bandit Problem

zbMath1490.62038arXiv1702.06972MaRDI QIDQ4633023

Steffen Grünewälder, Azadeh Khaleghi

Publication date: 2 May 2019

Full work available at URL: https://arxiv.org/abs/1702.06972

zbMATH Keywords

approximate solutionsreal-world applicationsonline sampling under dependence

Mathematics Subject Classification ID

Stationary stochastic processes (60G10) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Compound decision problems in statistical decision theory (62C25)

Cites Work

• Unnamed Item
• Regret bounds for restless Markov bandits
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• Basic properties of strong mixing conditions. A survey and some open questions
• Mixing: Properties and examples
• Asymptotic theory of weakly dependent stochastic processes
• The Complexity of Optimal Queuing Network Control
• Approximation algorithms for restless bandit problems
• Mathematical Foundations of Infinite-Dimensional Statistical Models
• Real Analysis and Probability
• Uniform Central Limit Theorems
• Comparison of perturbation bounds for the stationary distribution of a Markov chain
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Approximations of the Restless Bandit Problem