A learning algorithm for the finite-time two-armed bandit problem

DOI10.1109/TSMC.1984.6313253MaRDI QIDQ3342234zbMATH OpenFDO

Authors Mitsuo Sato, H. Takeda, Kenichi Abe

Publication date 1984

Published in IEEE Transactions on Systems, Man, and Cybernetics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TSMC.1984.6313253

zbMATH Keywords

controlling processestimating processfinite-time two-armed bandit problemlearning algorithm

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Recommendations

• On optimal prior learning time in the two-armed bandit problem
• Finite-time analysis of the multiarmed bandit problem
• When can the two-armed bandit algorithm be trusted?
• The Continuum-Armed Bandit Problem
• Optimal learning and experimentation in bandit problems.

Cited in

(10)

• A penalized bandit algorithm
• When can the two-armed bandit algorithm be trusted?
• On the value of learning for Bernoulli bandits with unknown parameters
• An Efficient Algorithm for Learning with Semi-bandit Feedback
• How Fast Is the Bandit?
• Machine learning and nonparametric bandit theory
• Solving two-armed Bernoulli bandit problems using a Bayesian learning automaton
• scientific article; zbMATH DE number 7380836 (Why is no real title available?)
• Satisficing in Time-Sensitive Bandit Learning
• On optimal prior learning time in the two-armed bandit problem

This page was built for publication: A learning algorithm for the finite-time two-armed bandit problem

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3342234)