Asymptotically Efficient Allocation Rules for the Multiarmed Bandit Problem with Multiple Plays Part I: I.I.D. Rewards, Part II: Markovian Rewards
Venkat Anantharam, Pravin Varaiya and Jean Walrand
EECS Department
University of California, Berkeley
Technical Report No. UCB/ERL M86/62
1986
BibTeX citation:
@techreport{Anantharam:M86/62,
Author = {Anantharam, Venkat and Varaiya, Pravin and Walrand, Jean},
Title = {Asymptotically Efficient Allocation Rules for the Multiarmed Bandit Problem with Multiple Plays Part I: I.I.D. Rewards, Part II: Markovian Rewards},
Institution = {EECS Department, University of California, Berkeley},
Year = {1986},
URL = {http://www.eecs.berkeley.edu/Pubs/TechRpts/1986/724.html},
Number = {UCB/ERL M86/62}
}
EndNote citation:
%0 Report %A Anantharam, Venkat %A Varaiya, Pravin %A Walrand, Jean %T Asymptotically Efficient Allocation Rules for the Multiarmed Bandit Problem with Multiple Plays Part I: I.I.D. Rewards, Part II: Markovian Rewards %I EECS Department, University of California, Berkeley %D 1986 %@ UCB/ERL M86/62 %U http://www.eecs.berkeley.edu/Pubs/TechRpts/1986/724.html %F Anantharam:M86/62