Nan Jiang, Lihong Li 0001
Doubly Robust Off-policy Value Evaluation for Reinforcement Learning
ICML, 2016.
@inproceedings{ICML-2016-JiangL,
author = "Nan Jiang and Lihong Li 0001",
booktitle = "{Proceedings of the 33rd International Conference on Machine Learning}",
ee = "http://proceedings.mlr.press/v48/jiang16.html",
pages = "652--661",
publisher = "{JMLR.org}",
title = "{Doubly Robust Off-policy Value Evaluation for Reinforcement Learning}",
year = 2016,
}