Index-based policies for discounted multi-armed bandits on parallel machines.

DOI10.1214/AOAP/1019487512zbMath1073.90568OpenAlexW2042312241MaRDI QIDQ1872472

Darren J. Wilkinson, Kevin D. Glazebrook

Publication date: 6 May 2003

Published in: The Annals of Applied Probability (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1214/aoap/1019487512

zbMATH Keywords

parallel machinesGittins indexmulti-armed bandit problemAverage-overtaking optimalaverage-reward optimalsuboptimality bound

Mathematics Subject Classification ID

Minimax problems in mathematical programming (90C47) Stochastic scheduling theory in operations research (90B36) Markov and semi-Markov decision processes (90C40)

Related Items (1)

Stochastic scheduling: a short history of index policies and new approaches to index generation for dynamic resource allocation

Cites Work

• Unnamed Item
• Almost optimal policies for stochastic systems which almost satisfy conservation laws
• A Characterization of Waiting Time Performance Realizable by Single-Server Queues
• Multiclass Queueing Systems: Polymatroidal Structure and Optimal Scheduling Control
• Conservation Laws, Extended Polymatroids and Multiarmed Bandit Problems; A Polyhedral Approach to Indexable Systems
• Discrete Dynamic Programming
• On Finding Optimal Policies in Discrete Dynamic Programming with No Discounting
• An Optimality Condition for Discrete Dynamic Programming with no Discounting

This page was built for publication: Index-based policies for discounted multi-armed bandits on parallel machines.