Multi-armed bandits with switching penalties

DOI10.1109/9.486316zbMath0847.90137OpenAlexW2168709337MaRDI QIDQ4884105

Manjari Asawa, Demosthenis Teneketzis

Publication date: 8 July 1996

Published in: IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1109/9.486316

zbMATH Keywords

Gittins indexmulti-armed bandit problemoptimal scheduling policiesoptimal allocation policyscheduling of parallel queuesswitching penalties

Mathematics Subject Classification ID

Deterministic scheduling theory in operations research (90B35) Queueing theory (aspects of probability theory) (60K25) Queues and service in operations research (90B22) Optimal stochastic control (93E20) Markov and semi-Markov decision processes (90C40) Applications of queueing theory (congestion, allocation, storage, traffic, etc.) (60K30)

Related Items

A State Dependent Approach to Resource Allocation Strategies ⋮ Multi-armed bandit processes with optimal selection of the operating times ⋮ A perpetual search for talents across overlapping generations: a learning process ⋮ Open Problem—M/G/1 Scheduling with Preemption Delays ⋮ Optimal hysteresis for a class of deterministic deteriorating two-armed bandit problem with switching costs. ⋮ Dynamic priority allocation via restless bandit marginal productivity indices ⋮ Some indexable families of restless bandit problems ⋮ Response adaptive designs that incorporate switching costs and constraints ⋮ Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting

This page was built for publication: Multi-armed bandits with switching penalties