Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost

DOI10.1109/9.7243MaRDI QIDQ3835405zbMATH OpenOpenAlexFDO

Authors Rajeev Agrawal, Manjunath V. Hegde, Demosthenis Teneketzis

Publication date 1988

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

Full work available at URL https://doi.org/10.1109/9.7243

zbMATH Keywords

asymptotic performancemultiarmed bandit problemsresource allocation problemsswitching costs

Mathematics Subject Classification ID

Applications of queueing theory (congestion, allocation, storage, traffic, etc.) (60K30) Stochastic games, stochastic differential games (91A15) Probabilistic games; gambling (91A60) Optimal stochastic control (93E20)

Recommendations

• Multi-armed bandit problems with multiple plays and switching cost
• Multi-armed bandits with switching penalties
• Asymptotically optimal multi-armed bandit policies under a cost constraint
• Adaptive treatment allocation and the multi-armed bandit problem
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards

Cited in

(21)

• Adaptive treatment allocation and the multi-armed bandit problem
• Certainty equivalence control with forcing: Revisited
• Average optimality in a Poissonian bandit with switching arms
• Optimal learning and experimentation in bandit problems.
• Arbitrary side observations in bandit problems
• Multi-armed bandit problems with multiple plays and switching cost
• Online Regret Bounds for Markov Decision Processes with Deterministic Transitions
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part I: I.I.D. rewards
• Asymptotically efficient allocation rules for the multiarmed bandit problem with multiple plays-Part II: Markovian rewards
• scientific article; zbMATH DE number 4064878 (Why is no real title available?)
• Multi-armed bandits with switching penalties
• Sequential resource allocation in a stochastic environment: an overview and numerical experiments
• Gittins Index for Simple Family of Markov Bandit Processes with Switching Cost and No Discounting
• Multi-armed Bandits with Metric Switching Costs
• Asymptotically optimal multi-armed bandit policies under a cost constraint
• Some indexable families of restless bandit problems
• Generalized Bandit Problems
• Simple fixes that accommodate switching costs in multi-armed bandits
• A perpetual search for talents across overlapping generations: a learning process
• Online regret bounds for Markov decision processes with deterministic transitions
• Response adaptive designs that incorporate switching costs and constraints

This page was built for publication: Asymptotically efficient adaptive allocation rules for the multiarmed bandit problem with switching cost

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3835405)