@inproceedings{3f78aa2dcefa4e929e92948bc24d7e9b,
title = "A unified approach for semi-Markov decision processes with discounted and average reward criteria",
abstract = "On the basis of the sensitivity-based optimization, we develop a unified optimization approach for semi-Markov decision processes (SMDPs) with infinite horizon discounted and average reward criteria. We show that the sensitivity formula under average reward criteria is a limitation case of discounted reward criteria. On the basis of the performance sensitivity formulas, we provide a unified formulation for the policy iteration algorithms of semi-Markov decision processes with discounted and average reward criteria.",
keywords = "Performance difference, Policy iteration, SMDPs",
author = "Yanjie Li and Huijing Wang and Haoyao Chen",
note = "Publisher Copyright: {\textcopyright} 2014 IEEE.; 2014 11th World Congress on Intelligent Control and Automation, WCICA 2014 ; Conference date: 29-06-2014 Through 04-07-2014",
year = "2015",
month = mar,
day = "2",
doi = "10.1109/WCICA.2014.7052983",
language = "英语",
series = "Proceedings of the World Congress on Intelligent Control and Automation (WCICA)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "March",
pages = "1741--1744",
booktitle = "Proceeding of the 11th World Congress on Intelligent Control and Automation, WCICA 2014",
address = "美国",
edition = "March",
}