Low-complexity algorithm for restless bandits with imperfect observations

DOI10.1007/S00186-024-00868-XMaRDI QIDQ6629533zbMATH OpenFDO

Authors Keqin Liu, Richard Weber, Chengzhong Zhang

Publication date 30 October 2024

Published in Mathematical Methods of Operations Research (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/S00186-024-00868-X

zbMATH Keywords

continuous state spaceindex policyobservation errorsrestless bandits

Mathematics Subject Classification ID

Stochastic scheduling theory in operations research (90B36) Markov and semi-Markov decision processes (90C40) Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35)

Recommendations

• Indexability and optimal index policies for a class of reinitialising restless bandits
• Approximation algorithms for restless bandit problems
• Conditions for indexability of restless bandits and an algorithm to compute Whittle index
• Optimal policies for observing time series and related restless bandit problems
• Regret Bounds for Restless Markov Bandits

Cites work

• Addendum to ‘On an index policy for restless bandits'
• An asymptotically optimal heuristic for general nonstationary finite-horizon restless multi-armed, multi-action bandits
• Dynamic Multichannel Access With Imperfect Channel State Detection
• scientific article; zbMATH DE number 4087408 (Why is no real title available?)
• scientific article; zbMATH DE number 3638998 (Why is no real title available?)
• scientific article; zbMATH DE number 2219854 (Why is no real title available?)
• Indexability of Restless Bandit Problems and Optimality of Whittle Index for Dynamic Multichannel Access
• Multi-armed bandit allocation indices. With a foreword by Peter Whittle.
• On an index policy for restless bandits
• On the Whittle Index for Restless Multiarmed Hidden Markov Bandits
• Testing indexability and computing Whittle and Gittins index in subcubic time
• The complexity of optimal queuing network control
• The Optimal Control of Partially Observable Markov Processes over the Infinite Horizon: Discounted Costs

This page was built for publication: Low-complexity algorithm for restless bandits with imperfect observations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6629533)