The multi-armed bandit problem: an efficient nonparametric solution

DOI10.1214/19-AOS1809zbMath1442.62180arXiv1703.08285OpenAlexW3007054292MaRDI QIDQ2176624

Hock Peng Chan

Publication date: 5 May 2020

Published in: The Annals of Statistics (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1703.08285

zbMATH Keywords

efficiencysubsamplingThompson samplingKL-UCBupper confidence bound (UCB)

Mathematics Subject Classification ID

Nonparametric tolerance and confidence regions (62G15) Sequential statistical design (62L05) Optimal stopping in statistics (62L15) Compound decision problems in statistical decision theory (62C25)

Related Items (2)

A non-parametric solution to the multi-armed bandit problem with covariates ⋮ Infinite Arms Bandit: Optimality via Confidence Bounds

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Nonparametric bandit methods
• Asymptotically efficient adaptive allocation rules
• Adaptive treatment allocation and the multi-armed bandit problem
• Optimal learning and experimentation in bandit problems.
• Optimal adaptive policies for sequential allocation problems
• Asymptotically efficient adaptive allocation schemes for controlled Markov chains: finite parameter space
• A new approach to the design of reinforcement schemes for learning automata
• Optimal stopping and dynamic allocation
• Asymptotically Efficient Adaptive Choice of Control Laws inControlled Markov Chains
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Some Remarks on the Two-Armed Bandit
• A Bernoulli Two-armed Bandit
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: The multi-armed bandit problem: an efficient nonparametric solution