On the Worth of Perfect Information in Bandits with Random Discounting

DOI10.1080/07474940701801952zbMATH Open1256.62045OpenAlexW2010443695MaRDI QIDQ5458027FDOQ5458027

Authors: Reginald Koo, Martin L. Jones 

Publication date: 10 April 2008

Published in: Sequential Analysis (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1080/07474940701801952

Recommendations

• Worth of perfect information in bernoulli bandits
• A Note on Performance Limitations in Bandit Problems With Side Information
• scientific article; zbMATH DE number 3854141
• Two-armed restless bandits with imperfect information: stochastic control and indexability
• Extensions of the multiarmed bandit problem: The discounted case
• scientific article; zbMATH DE number 34427
• On the problem of the two-armed bandit with impulse controls and discounting
• Pure exploration in finitely-armed and continuous-armed bandits
• An information-theoretic analysis of Thompson sampling

zbMATH Keywords

random discountingbandit processessequential allocation of experiments

Mathematics Subject Classification ID

Sequential statistical design (62L05) Statistical decision theory (62C99)

Cites Work

• Title not available (Why is that?)
• Worth of perfect information in bernoulli bandits
• Modifications in the discount sequence for bandit processes

Cited In (4)

• Title not available (Why is that?)
• A Note on Performance Limitations in Bandit Problems With Side Information
• Worth of perfect information in bernoulli bandits
• Modifications in the discount sequence for bandit processes

This page was built for publication: On the Worth of Perfect Information in Bandits with Random Discounting

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5458027)