ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT

DOI10.1017/S026996481600036XzbMath1373.62040arXiv1509.02857OpenAlexW2963946176MaRDI QIDQ5358116

Michael N. Katehakis, Odysseas Kanavetas, Apostolos N. Burnetas

Publication date: 19 September 2017

Published in: Probability in the Engineering and Informational Sciences (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1509.02857

zbMATH Keywords

stochastic modellingapplied probability

Mathematics Subject Classification ID

Decision theory (91B06) Stochastic programming (90C15) Compound decision problems in statistical decision theory (62C25)

Related Items (1)

A General Theory of MultiArmed Bandit Processes with Constrained Arm Switches

Cites Work

• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Asymptotically optimal Bayesian sequential change detection and identification rules
• An asymptotically optimal policy for finite support models in the multiarmed bandit problem
• Applications of mathematics and informatics in military science. Based on a conference, Hellenic Army Academy, Greece, April 2011
• UCB revisited: improved regret bounds for the stochastic multi-armed bandit problem
• Exploration-exploitation tradeoff using variance estimates in multi-armed bandits
• Asymptotically efficient adaptive allocation rules
• Optimal adaptive policies for sequential allocation problems
• Close the Gaps: A Learning-While-Doing Algorithm for Single-Product Revenue Management Problems
• Multi‐Armed Bandit Allocation Indices
• The Multi-Armed Bandit Problem: Decomposition and Computation
• Dynamic allocation policies for the finite horizon one armed bandit problem
• Optimal Adaptive Policies for Markov Decision Processes
• Bandits with Knapsacks
• ASYMPTOTIC BAYES ANALYSIS FOR THE FINITE-HORIZON ONE-ARMED-BANDIT PROBLEM
• 10.1162/1532443041827907
• On large deviations properties of sequential allocation problems
• MULTI-ARMED BANDITS UNDER GENERAL DEPRECIATION AND COMMITMENT
• Finite-time analysis of the multiarmed bandit problem
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item

This page was built for publication: ASYMPTOTICALLY OPTIMAL MULTI-ARMED BANDIT POLICIES UNDER A COST CONSTRAINT