Aviral Kumar, Justin Fu, Matthew Soh, George Tucker, Sergey Levine. Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction. In Hanna M. Wallach, Hugo Larochelle, Alina Beygelzimer, Florence d'Alché-Buc, Edward A. Fox, Roman Garnett, editors, Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada. pages 11761-11771, 2019. [doi]
@inproceedings{KumarFSTL19,
title = {Stabilizing Off-Policy Q-Learning via Bootstrapping Error Reduction},
author = {Aviral Kumar and Justin Fu and Matthew Soh and George Tucker and Sergey Levine},
year = {2019},
url = {http://papers.nips.cc/paper/9349-stabilizing-off-policy-q-learning-via-bootstrapping-error-reduction},
researchr = {https://researchr.org/publication/KumarFSTL19},
cites = {0},
citedby = {0},
pages = {11761-11771},
booktitle = {Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, 8-14 December 2019, Vancouver, BC, Canada},
editor = {Hanna M. Wallach and Hugo Larochelle and Alina Beygelzimer and Florence d'Alché-Buc and Edward A. Fox and Roman Garnett},
}