Doina Precup, Richard S. Sutton, Sanjoy Dasgupta
Off-Policy Temporal Difference Learning with Function Approximation
ICML, 2001.
@inproceedings{ICML-2001-PrecupSD,
author = "Doina Precup and Richard S. Sutton and Sanjoy Dasgupta",
booktitle = "{Proceedings of the 18th International Conference on Machine Learning}",
isbn = "1-55860-778-1",
pages = "417--424",
publisher = "{Morgan Kaufmann}",
title = "{Off-Policy Temporal Difference Learning with Function Approximation}",
year = 2001,
}











