Learning the distribution with largest mean: two bandit frameworks

DOI10.1051/proc/201760114zbMath1426.68237arXiv1702.00001OpenAlexW2584453124MaRDI QIDQ4606431

Emilie Kaufmann, Aurélien Garivier

Publication date: 7 March 2018

Published in: ESAIM: Proceedings and Surveys (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1702.00001

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Optimal stopping in statistics (62L15)

Related Items

Unnamed Item, Response-adaptive randomization in clinical trials: from myths to practical considerations, Learning the distribution with largest mean: two bandit frameworks

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Batched bandit problems
• The multi-armed bandit problem with covariates
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Context tree selection: a unifying view
• Asymptotically efficient adaptive allocation rules
• Landmark learning: An illustration of associative search
• On Bayesian index policies for sequential resource allocation
• Optimal adaptive policies for sequential allocation problems
• Pure exploration in finitely-armed and continuous-armed bandits
• On Upper-Confidence Bound Policies for Switching Bandit Problems
• Thompson Sampling: An Asymptotically Optimal Finite-Time Analysis
• Sequential Design of Experiments
• Asymptotically efficient adaptive allocation schemes for controlled i.i.d. processes: finite parameter space
• Asymptotically Efficient Adaptive Choice of Control Laws inControlled Markov Chains
• Learning the distribution with largest mean: two bandit frameworks
• A minimax and asymptotically optimal algorithm for stochastic bandits
• Sample mean based index policies by O(log n) regret for the multi-armed bandit problem
• Simple Bayesian Algorithms for Best-Arm Identification
• Regret Analysis of Stochastic and Nonstochastic Multi-armed Bandit Problems
• Prediction, Learning, and Games
• Some aspects of the sequential design of experiments
• A Single-Sample Multiple Decision Procedure for Ranking Means of Normal Populations with known Variances
• Finite-time analysis of the multiarmed bandit problem