Policy iteration for continuous-time average reward Markov decision processes in Polish spaces.

Zhu, Quanxin, Yang, Xinsong, and Huang, Chuangxia. "Policy iteration for continuous-time average reward Markov decision processes in Polish spaces.." Abstract and Applied Analysis 2009 (2009): Article ID 103723, 17 p.-Article ID 103723, 17 p.. <http://eudml.org/doc/226313>.

@article{Zhu2009,
author = {Zhu, Quanxin, Yang, Xinsong, Huang, Chuangxia},
journal = {Abstract and Applied Analysis},
keywords = {transition rates; reward rates; average reward optimality equation},
language = {eng},
pages = {Article ID 103723, 17 p.-Article ID 103723, 17 p.},
publisher = {Hindawi Publishing Corporation, New York},
title = {Policy iteration for continuous-time average reward Markov decision processes in Polish spaces.},
url = {http://eudml.org/doc/226313},
volume = {2009},
year = {2009},
}

TY - JOUR
AU - Zhu, Quanxin
AU - Yang, Xinsong
AU - Huang, Chuangxia
TI - Policy iteration for continuous-time average reward Markov decision processes in Polish spaces.
JO - Abstract and Applied Analysis
PY - 2009
PB - Hindawi Publishing Corporation, New York
VL - 2009
SP - Article ID 103723, 17 p.
EP - Article ID 103723, 17 p.
LA - eng
KW - transition rates; reward rates; average reward optimality equation
UR - http://eudml.org/doc/226313
ER -