@inproceedings{DBLP:conf/icml/JiangL16,
author = {Nan Jiang and
Lihong Li},
title = {Doubly Robust Off-policy Value Evaluation for Reinforcement Learning},
booktitle = {Proceedings of the 33nd International Conference on Machine Learning,
{ICML} 2016, New York City, NY, USA, June 19-24, 2016},
pages = {652--661},
year = {2016},
crossref = {DBLP:conf/icml/2016},
url = {https://proceedings.mlr.press/v48/jiang16.html},
timestamp = {Wed, 29 May 2019 08:41:46 +0200},
biburl = {https://dblp.org/rec/bib/conf/icml/JiangL16},
bibsource = {dblp computer science bibliography, https://dblp.org}
}
Get .bib