A lemma on the multiarmed bandit problem

DOI10.1109/TAC.1986.1104332MaRDI QIDQ3722290zbMATH OpenOpenAlexWikidataFDO

Authors John N. Tsitsiklis

Publication date 1986

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

Full work available at URL https://doi.org/10.1109/tac.1986.1104332

zbMATH Keywords

classical multiarmed bandit problemgeometric discountingGittins index ruleswrite-off policies

Mathematics Subject Classification ID

Dynamic programming (90C39)

Recommendations

• Multi-armed bandit problem revisited
• scientific article; zbMATH DE number 775000
• On the Gittins index for multiarmed bandits
• Four proofs of Gittins' multiarmed bandit theorem
• A short proof of the Gittins index theorem

Cited in

(5)

• Multi-armed bandit problem revisited
• The archievable region method in the optimal control of queueing systems; formulations, bounds and policies
• Multi-armed bandit processes with optimal selection of the operating times
• A two armed bandit type problem revisited
• Optimal control of single-server queueing networks

This page was built for publication: A lemma on the multiarmed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3722290)