On Upper-Confidence Bound Policies for Switching Bandit Problems

Aurélien Garivier; Éric Moulines

doi:10.1007/978-3-642-24412-4_16

ScienceGate Book Chapters

BOOK-CHAPTER

On Upper-Confidence Bound Policies for Switching Bandit Problems

Aurélien Garivier Éric Moulines

Year: 2011 Lecture notes in computer science Pages: 174-188 Publisher: Springer Science+Business Media

DOI: 10.1007/978-3-642-24412-4_16

Get Full-Text PDF Get Analytical Report

Keywords:

Regret Upper and lower bounds Bounding overwatch Logarithm Computer science Sliding window protocol Mathematical optimization Algorithm Applied mathematics Mathematics Window (computing) Artificial intelligence Mathematical analysis Machine learning

Metrics

406

Cited By

14.16

FWCI (Field Weighted Citation Impact)

Refs

0.99

Citation Normalized Percentile

Is in top 1%

Is in top 10%

Citation History

Topics

Advanced Bandit Algorithms Research

Social Sciences → Decision Sciences → Management Science and Operations Research

Distributed Sensor Networks and Detection Algorithms

Physical Sciences → Computer Science → Computer Networks and Communications

Age of Information Optimization

Physical Sciences → Computer Science → Computer Networks and Communications

On Upper-Confidence Bound Policies for Switching Bandit Problems

Metrics

Citation History

Topics

Related Documents

Maximal expectation as upper confidence bound for multi-armed bandit problems

Relative Upper Confidence Bound for the K-Armed Dueling Bandit Problem

Pairwise Regression with Upper Confidence Bound for Contextual Bandit with Multiple Actions

Linear Upper Confidence Bound Algorithm for Contextual Bandit Problem with Piled Rewards

Upper Confidence Bound Versus Adaptive Posterior Sampling for Multi-Armed Bandit Game Models