Pure exploration in finitely-armed and continuous-armed bandits

DOI10.1016/J.TCS.2010.12.059MaRDI QIDQ2431430zbMATH OpenOpenAlexFDO

Authors Sébastien Bubeck, Rémi Munos, Gilles Stoltz

Publication date 14 April 2011

Published in Theoretical Computer Science (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.tcs.2010.12.059

zbMATH Keywords

continuous-armed banditsefficient explorationmulti-armed banditssimple regret

Mathematics Subject Classification ID

Sequential statistical design (62L05) Inference from stochastic processes and prediction (62M20)

Recommendations

• Pure exploration in multi-armed bandits problems
• X-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• The sample complexity of exploration in the multi-armed bandit problem
• Explore first, exploit next: the true shape of regret in bandit problems

Cites work

• Asymptotically efficient adaptive allocation rules
• Combinatorial methods in density estimation
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Finite-time analysis of the multiarmed bandit problem
• scientific article; zbMATH DE number 2089367 (Why is no real title available?)
• scientific article; zbMATH DE number 4170917 (Why is no real title available?)
• scientific article; zbMATH DE number 3274494 (Why is no real title available?)
• Learning Theory
• Probability Inequalities for Sums of Bounded Random Variables
• Sharp dichotomies for regret minimization in metric spaces
• Some aspects of the sequential design of experiments
• The Nonstochastic Multiarmed Bandit Problem
• The sample complexity of exploration in the multi-armed bandit problem

Cited in

(28)

• Gaussian process bandits with adaptive discretization
• A PAC algorithm in relative precision for bandit problem with costly sampling
• Trading utility and uncertainty: applying the value of information to resolve the exploration-exploitation dilemma in reinforcement learning
• A bad arm existence checking problem: how to utilize asymmetric problem structure?
• Intrinsically motivated model learning for developing curious robots
• On two continuum armed bandit problems in high dimensions
• Bayesian Incentive-Compatible Bandit Exploration
• Pure exploration in multi-armed bandits problems
• Learning the distribution with largest mean: two bandit frameworks
• On multi-armed bandit designs for dose-finding trials
• scientific article; zbMATH DE number 7626761 (Why is no real title available?)
• Bandit Theory: Applications to Learning Healthcare Systems and Clinical Trials
• Robust Learning of Consumer Preferences
• Deep learning for ranking response surfaces with applications to optimal stopping problems
• Explore first, exploit next: the true shape of regret in bandit problems
• Sequential design for ranking response surfaces
• X-armed bandits
• Sharp dichotomies for regret minimization in metric spaces
• On the Worth of Perfect Information in Bandits with Random Discounting
• Information theory for ranking and selection
• Adaptive Algorithm for Multi-Armed Bandit Problem with High-Dimensional Covariates
• Thompson sampling-based recursive block elimination for dynamic assignment under limited budget in pure-exploration
• Optimizing Sharpe ratio: risk-adjusted decision-making in multi-armed bandits
• Optimal -correct best-arm selection for heavy-tailed distributions
• Bayesian optimization by kernel regression and density-based exploration
• Monotone bandits: power of maximum likelihood estimation in online decision-making
• An asymptotically optimal strategy for constrained multi-armed bandit problems
• Simple and cumulative regret for continuous noisy optimization

This page was built for publication: Pure exploration in finitely-armed and continuous-armed bandits

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2431430)