Title
Best-Arm Identification in Correlated Multi-Armed Bandits
Abstract
In this paper we consider the problem of best-arm identification in multi-armed bandits in the fixed confidence setting, where the goal is to identify, with probability $1-\delta $ for some $\delta >0$ , the arm with the highest mean reward in minimum possible samples from the set of arms $\mathcal {K}$ . Most existing best-arm identification algorithms and analyses operate under the assumptio...
Year
DOI
Venue
2021
10.1109/JSAIT.2021.3082028
IEEE Journal on Selected Areas in Information Theory
Keywords
DocType
Volume
Correlation,Upper bound,Complexity theory,Sports,Information theory,Drugs,Context modeling
Journal
2
Issue
ISSN
Citations 
2
IEEE Journal on Selected Areas in Information Theory (Volume: 2, Issue: 2, June 2021)
1
PageRank 
References 
Authors
0.39
0
3
Name
Order
Citations
PageRank
Samarth Gupta1135.60
Gauri Joshi230829.70
Osman Yağan310.39