Anytime algorithms for multi-armed bandit problems

DOI10.1145/1109557.1109659zbMath1192.91072OpenAlexW4248403059MaRDI QIDQ3581512

Robert D. Kleinberg

Publication date: 16 August 2010

Published in: Proceedings of the seventeenth annual ACM-SIAM symposium on Discrete algorithm - SODA '06 (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/1109557.1109659

Mathematics Subject Classification ID

Computational aspects related to convexity (52B55) Probabilistic games; gambling (91A60) General topics in the theory of algorithms (68W01)

Related Items (3)

Nonstochastic bandits: Countable decision set, unbounded costs and reactive environments ⋮ Competitive collaborative learning ⋮ Adaptive Incentive-Compatible Sponsored Search Auction

This page was built for publication: Anytime algorithms for multi-armed bandit problems