Normal bandits of unknown means and variances

MaRDI QIDQ4558474zbMATH OpenFDO

Authors Wesley Cowan, Junya Honda, Michael N. Katehakis

Publication date 22 November 2018

Full work available at URL http://jmlr.csail.mit.edu/papers/v18/15-154.html

zbMATH Keywords

multi-armed banditssequential allocationinflated sample meansUCB policies

Mathematics Subject Classification ID

Central limit and other weak theorems (60F05) Sequential estimation (62L12)

Recommendations

• Optimal adaptive policies for sequential allocation problems
• scientific article; zbMATH DE number 4059270
• Optimal sequential sampling from two populations.
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Adaptive treatment allocation and the multi-armed bandit problem

Cites work

• scientific article; zbMATH DE number 1467230 (Why is no real title available?)
• scientific article; zbMATH DE number 1895496 (Why is no real title available?)
• 10.1162/1532443041827907
• ASYMPTOTIC BAYES ANALYSIS FOR THE FINITE-HORIZON ONE-ARMED-BANDIT PROBLEM
• An asymptotically optimal policy for finite support models in the multiarmed bandit problem
• Asymptotically efficient adaptive allocation rules
• Asymptotically optimal Bayesian sequential change detection and identification rules
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Multi-armed bandit allocation indices. With a foreword by Peter Whittle.
• Multi-armed bandits under general depreciation and commitment
• Non-asymptotic analysis of a new bandit algorithm for semi-bounded rewards
• On large deviations properties of sequential allocation problems
• On the Gittins index for multiarmed bandits
• Online Learning of Rested and Restless Bandits
• Optimal Adaptive Policies for Markov Decision Processes
• Optimal adaptive policies for sequential allocation problems
• Some aspects of the sequential design of experiments
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem

Cited in

(4)

• Adaptive policies for perimeter surveillance problems
• Exploration-exploitation policies with almost sure, arbitrarily slow growing asymptotic regret
• Optimal activation of halting multi‐armed bandit models
• scientific article; zbMATH DE number 6982311 (Why is no real title available?)

This page was built for publication: Normal bandits of unknown means and variances

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4558474)