Technical Note—A Note on the Equivalence of Upper Confidence Bounds and Gittins Indices for Patient Agents

DOI10.1287/opre.2020.1987zbMath1482.91072arXiv1904.04732OpenAlexW3115527245MaRDI QIDQ4994155

Daniel J. Russo

Publication date: 17 June 2021

Published in: Operations Research (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/1904.04732

zbMATH Keywords

Gittins indexupper confidence boundmultiarmed bandits

Mathematics Subject Classification ID

Bayesian problems; characterization of Bayes procedures (62C10) Decision theory (91B06)

Related Items (1)

Optimistic Gittins Indices

Cites Work

• Unnamed Item
• Unnamed Item
• Kullback-Leibler upper confidence bounds for optimal sequential allocation
• Asymptotically efficient adaptive allocation rules
• On the Gittins index for multiarmed bandits
• Computing a Classic Index for Finite-Horizon Bandits
• Multi‐Armed Bandit Allocation Indices
• Information Relaxations and Duality in Stochastic Dynamic Programs
• Linearly Parameterized Bandits
• Optimal stopping and dynamic allocation
• ASYMPTOTIC BAYES ANALYSIS FOR THE FINITE-HORIZON ONE-ARMED-BANDIT PROBLEM
• Information-Theoretic Regret Bounds for Gaussian Process Optimization in the Bandit Setting
• Uncertainty, Information, and Sequential Experiments
• Finite-time analysis of the multiarmed bandit problem

This page was built for publication: Technical Note—A Note on the Equivalence of Upper Confidence Bounds and Gittins Indices for Patient Agents