<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>17</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Burnetas, AN</style></author><author><style face="normal" font="default" size="100%">Katehakis, M.N.</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Dynamic allocation policies for the finite horizon one armed bandit problem</style></title><secondary-title><style face="normal" font="default" size="100%">Stochastic Analysis and Applications</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">1998</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://www.scopus.com/inward/record.uri?eid=2-s2.0-0032391888&amp;partnerID=40&amp;md5=db1e06b4e6d58bb8b0cabfa37734cb8d</style></url></web-urls></urls><number><style face="normal" font="default" size="100%">5</style></number><volume><style face="normal" font="default" size="100%">16</style></volume><pages><style face="normal" font="default" size="100%">811-824</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">The unknown performance of a new experiment is to be evaluated and compared with that of an existing one over a finite horizon. The explicit structure of an optimal sequential allocation policy is obtained under pertinent reward/loss functions, when the experiments are characterized by random variables with distributions from the one parameter exponential family.</style></abstract><notes><style face="normal" font="default" size="100%">cited By 2</style></notes></record></records></xml>