On the improvement of allocation rules for multi-armed bandit problem

DOI10.1080/02331939408843954MaRDI QIDQ4764899zbMATH OpenOpenAlexFDO

Authors S. Pohlenz, Hans-Joachim Girlich

Publication date 20 April 1995

Published in Optimization (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1080/02331939408843954

zbMATH Keywords

Bather's randomized policyBayes analysisbeta-distributed priormulti-armed bandit problems

Mathematics Subject Classification ID

Applications of queueing theory (congestion, allocation, storage, traffic, etc.) (60K30) Markov and semi-Markov decision processes (90C40)

Recommendations

• 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
• scientific article; zbMATH DE number 4064878
• Monotone stopping-allocation problems
• Dynamic allocation policies for the finite horizon one armed bandit problem

Cites work

• Bayesian dynamic programming
• scientific article; zbMATH DE number 3906232 (Why is no real title available?)
• scientific article; zbMATH DE number 3474804 (Why is no real title available?)
• scientific article; zbMATH DE number 194374 (Why is no real title available?)
• On the Allocation of Treatments in Sequential Medical Trials
• On the optimal solution of the one-armed bandit adaptive control problem

Cited in

(9)

• Adaptive treatment allocation and the multi-armed bandit problem
• Multi-armed bandit models for the optimal design of clinical trials: benefits and challenges
• scientific article; zbMATH DE number 4064878 (Why is no real title available?)
• scientific article; zbMATH DE number 4127033 (Why is no real title available?)
• Dynamic allocation policies for the finite horizon one armed bandit problem
• A better resource allocation algorithm with semi-bandit feedback
• scientific article; zbMATH DE number 7596797 (Why is no real title available?)
• Monotone stopping-allocation problems
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem

This page was built for publication: On the improvement of allocation rules for multi-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4764899)