George Tucker, Surya Bhupatiraju, Shixiang Gu, Richard E. Turner, Zoubin Ghahramani, Sergey Levine
The Mirage of Action-Dependent Baselines in Reinforcement Learning
ICML, 2018.
@inproceedings{ICML-2018-TuckerBGTGL,
author = "George Tucker and Surya Bhupatiraju and Shixiang Gu and Richard E. Turner and Zoubin Ghahramani and Sergey Levine",
booktitle = "{Proceedings of the 35th International Conference on Machine Learning}",
ee = "http://proceedings.mlr.press/v80/tucker18a.html",
pages = "5022--5031",
publisher = "{PMLR}",
title = "{The Mirage of Action-Dependent Baselines in Reinforcement Learning}",
year = 2018,
}
Tags: