Exponential asymptotic optimality of Whittle index policy

DOI10.1007/S11134-023-09875-XzbMath1517.90155OpenAlexW4377148696MaRDI QIDQ6164144

Nicolas Gast, Bruno Gaujal, Chen Yan

Publication date: 27 July 2023

Published in: Queueing Systems (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1007/s11134-023-09875-x

zbMATH Keywords

asymptotic optimalityWhittle indexmulti-armed bandits

Mathematics Subject Classification ID

Communication networks in operations research (90B18) Linear programming (90C05) Markov and semi-Markov decision processes (90C40) Probabilistic games; gambling (91A60)

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Whittle index approach to size-aware scheduling for time-varying channels with multiple states
• Asymptotically optimal priority policies for indexable and nonindexable restless bandits
• Differential equation approximations for Markov chains
• Strong approximation theorems for density dependent Markov chains
• Whittle's index policy for a multi-class queueing system with convex holding costs
• The Complexity of Optimal Queuing Network Control
• Multi‐Armed Bandit Allocation Indices
• Addendum to ‘On an index policy for restless bandits'
• On the asymptotic optimality of greedy index heuristics for multi-action restless bandits
• On an index policy for restless bandits
• Whittle Index Policy for Crawling Ephemeral Content
• On the Whittle Index for Restless Multiarmed Hidden Markov Bandits
• Bandit Algorithms
• An asymptotically optimal heuristic for general nonstationary finite-horizon restless multi-armed, multi-action bandits
• Indexability of Restless Bandit Problems and Optimality of Whittle Index for Dynamic Multichannel Access
• The stability of saturated linear dynamical systems is undecidable
• Testing indexability and computing Whittle and Gittins index in subcubic time

This page was built for publication: Exponential asymptotic optimality of Whittle index policy