Applying reinforcement learning to basic routing problem

DOI10.1007/978-3-319-93736-6_18MaRDI QIDQ1673501zbMATH OpenOpenAlexFDO

Authors Sigurur Gauti Samúelsson, Esa Hyytiä

Publication date 12 September 2018

Full work available at URL https://doi.org/10.1007/978-3-319-93736-6_18

zbMATH Keywords

machine learningvalue functionreinforcement learningtask assignmentparallel serversjob dispatching

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Queues and service in operations research (90B22) Queueing theory (aspects of probability theory) (60K25)

Recommendations

• Generalised ‘join the shortest queue’ policies for the dynamic routing of jobs to multi-class queues
• Reinforcement learning for call admission control and routing under quality of Service constraints in multimedia networks
• Open-loop routing of N arrivals to M parallel queues
• Queueing network controls via deep reinforcement learning
• Open-loop routeing to M parallel servers with no buffers

Cited in

(7)

• Queueing network controls via deep reinforcement learning
• scientific article; zbMATH DE number 2043510 (Why is no real title available?)
• Reinforcing reachable routes.
• Reinforcement approach to adaptive package scheduling in routers
• Minimizing mean weighted tardiness in unrelated parallel machine scheduling with reinforcement learning
• Information-directed routing in sensor networks using real-time reinforcement learning
• An SDN routing algorithm based on deep reinforcement learning

This page was built for publication: Applying reinforcement learning to basic routing problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1673501)