Policy Gradient Methods for Reinforcement Learning with Function Approximation.
R. Sutton, D. Mcallester, S. Singh, and Y. Mansour. Advances in Neural Information Processing Systems 12, NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999, page 1057--1063. The MIT Press, (1999)
%0 Conference Paper
%1 Sutton:99
%A Sutton, Richard S.
%A Mcallester, David A.
%A Singh, Satinder P.
%A Mansour, Yishay
%B Advances in Neural Information Processing Systems 12, NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999
%D 1999
%E Solla, Sara A.
%E Leen, Todd K.
%E Müller, Klaus R.
%I The MIT Press
%K imported
%P 1057--1063
%T Policy Gradient Methods for Reinforcement Learning with Function Approximation.
@inproceedings{Sutton:99,
added-at = {2008-03-11T14:52:34.000+0100},
author = {Sutton, Richard S. and Mcallester, David A. and Singh, Satinder P. and Mansour, Yishay},
biburl = {https://www.bibsonomy.org/bibtex/2f25c4f6da0380afa371cfa50bc2be5bb/idsia},
booktitle = {Advances in Neural Information Processing Systems 12, [NIPS Conference, Denver, Colorado, USA, November 29 - December 4, 1999]},
citeulike-article-id = {2375000},
editor = {Solla, Sara A. and Leen, Todd K. and M{\"u}ller, Klaus R.},
interhash = {7db746ffbdad9f59d8382c7d5314ec4f},
intrahash = {f25c4f6da0380afa371cfa50bc2be5bb},
keywords = {imported},
pages = {1057--1063},
priority = {2},
publisher = {The MIT Press},
timestamp = {2008-03-11T15:05:43.000+0100},
title = {Policy Gradient Methods for Reinforcement Learning with Function Approximation.},
year = 1999
}