<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="7.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Burnetas, Apostolos N</style></author><author><style face="normal" font="default" size="100%">Katehakis, Michael N</style></author></authors></contributors><titles><title><style face="normal" font="default" size="100%">Efficient estimation and control for Markov processes</style></title><secondary-title><style face="normal" font="default" size="100%">Proceedings of the IEEE Conference on Decision and Control</style></secondary-title></titles><keywords><keyword><style  face="normal" font="default" size="100%">Adaptive control systems</style></keyword><keyword><style  face="normal" font="default" size="100%">Constraint theory</style></keyword><keyword><style  face="normal" font="default" size="100%">Control theory</style></keyword><keyword><style  face="normal" font="default" size="100%">Convergence of numerical methods</style></keyword><keyword><style  face="normal" font="default" size="100%">Decision theory</style></keyword><keyword><style  face="normal" font="default" size="100%">Index function</style></keyword><keyword><style  face="normal" font="default" size="100%">Markov decision process</style></keyword><keyword><style  face="normal" font="default" size="100%">Markov processes</style></keyword><keyword><style  face="normal" font="default" size="100%">Mathematical models</style></keyword><keyword><style  face="normal" font="default" size="100%">probability</style></keyword><keyword><style  face="normal" font="default" size="100%">Queueing control</style></keyword><keyword><style  face="normal" font="default" size="100%">Queueing theory</style></keyword><keyword><style  face="normal" font="default" size="100%">State estimation</style></keyword><keyword><style  face="normal" font="default" size="100%">Statistical methods</style></keyword><keyword><style  face="normal" font="default" size="100%">Transition probabilities</style></keyword></keywords><dates><year><style  face="normal" font="default" size="100%">1995</style></year></dates><urls><web-urls><url><style face="normal" font="default" size="100%">https://www.scopus.com/inward/record.uri?eid=2-s2.0-0029517410&amp;partnerID=40&amp;md5=690fdefb70e718ba7a488ebe838d6ddf</style></url></web-urls></urls><publisher><style face="normal" font="default" size="100%">IEEE, Piscataway, NJ, United States</style></publisher><pub-location><style face="normal" font="default" size="100%">New Orleans, LA, USA</style></pub-location><volume><style face="normal" font="default" size="100%">2</style></volume><pages><style face="normal" font="default" size="100%">1402-1407</style></pages><language><style face="normal" font="default" size="100%">eng</style></language><abstract><style face="normal" font="default" size="100%">We consider the problem of sequential control for a finite state and action Markovian Decision Process with incomplete information regarding the transition probabilities P ∈ Papprox. Under suitable irreducibility assumptions for Papprox.. We construct adaptive policies that maximize the rate of convergence of realized rewards to that of the optimal (non adaptive) policy under complete information. These adaptive policies are specified via an easily computable index function, of states, controls and statistics, so that one takes a control with the largest index value in the current state in every period.</style></abstract><notes><style face="normal" font="default" size="100%">cited By 2; Conference of Proceedings of the 1995 34th IEEE Conference on Decision and Control. Part 1 (of 4) ; Conference Date: 13 December 1995 Through 15 December 1995; Conference Code:44367</style></notes></record></records></xml>