Integrated online learning and adaptive control in queueing systems with uncertain payoffs

DOI10.1287/OPRE.2021.2100zbMATH Open1490.90090OpenAlexW3135074392MaRDI QIDQ5080672FDOQ5080672

Authors: Wei-Kang Hsu, Jiaming Xu, Xiaojun Lin, Mark R. Bell 

Publication date: 31 May 2022

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1287/opre.2021.2100

Recommendations

• Matching while learning
• Learning unknown service rates in queues: a multiarmed bandit approach
• Online resource allocation with personalized learning
• Dynamic admission and service rate control of a queue
• Online self-organizing network control with time averaged weighted throughput objective

zbMATH Keywords

convex optimizationonline learningstochastic modelsdecentralized algorithmsonline service platforms

Mathematics Subject Classification ID

Convex programming (90C25) Queues and service in operations research (90B22)

Cites Work

• Asymptotically efficient adaptive allocation rules
• Multi-armed bandit allocation indices. With a foreword by Peter Whittle.
• Title not available (Why is that?)
• The Nonstochastic Multiarmed Bandit Problem
• Finite-time analysis of the multiarmed bandit problem
• Stability properties of constrained queueing systems and scheduling policies for maximum throughput in multihop radio networks
• Stability of queueing networks and scheduling policies
• On the Connection-Level Stability of Congestion-Controlled Communication Networks
• Online Advertisement, Optimization and Stochastic Networks
• Open bandit processes and optimal scheduling of queueing networks
• Decentralized Learning for Multiplayer Multiarmed Bandits
• Adaptive matching for expert systems with uncertain task types

Cited In (3)

• Online resource allocation with personalized learning
• A distributionally robust chance-constrained kernel-free quadratic surface support vector machine
• Matching while learning

This page was built for publication: Integrated online learning and adaptive control in queueing systems with uncertain payoffs

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5080672)