Ofir Nachum, Mohammad Norouzi 0002, George Tucker, Dale Schuurmans
Smoothed Action Value Functions for Learning Gaussian Policies
ICML, 2018.
@inproceedings{ICML-2018-Nachum0TS,
author = "Ofir Nachum and Mohammad Norouzi 0002 and George Tucker and Dale Schuurmans",
booktitle = "{Proceedings of the 35th International Conference on Machine Learning}",
ee = "http://proceedings.mlr.press/v80/nachum18a.html",
pages = "3689--3697",
publisher = "{PMLR}",
title = "{Smoothed Action Value Functions for Learning Gaussian Policies}",
year = 2018,
}
Tags: