Abstract
Two models for the "many-armed bandit" problem with two distributions are considered. Feldman's result is extended to these models.
Citation
Leiba Rodman. "On the Many-armed Bandit Problem." Ann. Probab. 6 (3) 491 - 498, June, 1978. https://doi.org/10.1214/aop/1176995533
Information
Published: June, 1978
First available in Project Euclid: 19 April 2007
zbMATH: 0394.62007
MathSciNet: MR494728
Digital Object Identifier: 10.1214/aop/1176995533
Subjects:
Primary:
60C10
Keywords:
dynamic programming
,
Many-armed bandit problem
,
optimal policy
Rights: Copyright © 1978 Institute of Mathematical Statistics
