Ioannis Ch. Paschalidis, Keyong Li, Reza Moazzez Estanjini. An actor-critic method using Least Squares Temporal Difference learning. In Proceedings of the 48th IEEE Conference on Decision and Control, CDC 2009, combined withe the 28th Chinese Control Conference, December 16-18, 2009, Shanghai, China. pages 2564-2569, IEEE, 2009. [doi]
@inproceedings{PaschalidisLE09,
title = {An actor-critic method using Least Squares Temporal Difference learning},
author = {Ioannis Ch. Paschalidis and Keyong Li and Reza Moazzez Estanjini},
year = {2009},
doi = {10.1109/CDC.2009.5400592},
url = {http://dx.doi.org/10.1109/CDC.2009.5400592},
researchr = {https://researchr.org/publication/PaschalidisLE09},
cites = {0},
citedby = {0},
pages = {2564-2569},
booktitle = {Proceedings of the 48th IEEE Conference on Decision and Control, CDC 2009, combined withe the 28th Chinese Control Conference, December 16-18, 2009, Shanghai, China},
publisher = {IEEE},
}