Sumeetpal S. Singh, Vladislav B. Tadic, Arnaud Doucet. A policy gradient method for semi-Markov decision processes with application to call admission control. European Journal of Operational Research, 178(3):808-818, 2007. [doi]
@article{SinghTD07,
title = {A policy gradient method for semi-Markov decision processes with application to call admission control},
author = {Sumeetpal S. Singh and Vladislav B. Tadic and Arnaud Doucet},
year = {2007},
doi = {10.1016/j.ejor.2006.02.023},
url = {http://dx.doi.org/10.1016/j.ejor.2006.02.023},
tags = {Markov},
researchr = {https://researchr.org/publication/SinghTD07},
cites = {0},
citedby = {0},
journal = {European Journal of Operational Research},
volume = {178},
number = {3},
pages = {808-818},
}