Average optimality in a Poissonian bandit with switching arms

A symmetric Poissonian two-armed bandit becomes, in terms of a posteriori probabilities, a piecewise deterministic Markov decision process. For the case of the switching arms, only of one which creates rewards, we solve explicitly the average optimality equation and prove that a myopic policy is average optimal. Copyright Physica-Verlag 1997

MoreLess

Year of publication:	1997
Authors:	Donchev, Doncho ; Yushkevich, Alexander
Published in:	Mathematical Methods of Operations Research. - Springer. - Vol. 45.1997, 2, p. 265-280
Publisher:	Springer
Subject:	Two-armed bandit \| continuous time \| switching arms \| average criterion

More details

Extent:	text/html
Type of publication:	Article
Source:	RePEc - Research Papers in Economics

Persistent link: https://www.econbiz.de/10010950140