Tetsuro Morimura, Takayuki Osogami, Tomoyuki Shirai. Mixing-Time Regularized Policy Gradient. In Carla E. Brodley, Peter Stone, editors, Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, July 27 -31, 2014, Québec City, Québec, Canada. pages 1997-2003, AAAI Press, 2014. [doi]
@inproceedings{MorimuraOS14,
title = {Mixing-Time Regularized Policy Gradient},
author = {Tetsuro Morimura and Takayuki Osogami and Tomoyuki Shirai},
year = {2014},
url = {http://www.aaai.org/ocs/index.php/AAAI/AAAI14/paper/view/8522},
researchr = {https://researchr.org/publication/MorimuraOS14},
cites = {0},
citedby = {0},
pages = {1997-2003},
booktitle = {Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, July 27 -31, 2014, Québec City, Québec, Canada},
editor = {Carla E. Brodley and Peter Stone},
publisher = {AAAI Press},
isbn = {978-1-57735-661-5},
}