Aviral Kumar, Aurick Zhou, George Tucker, Sergey Levine. Conservative Q-Learning for Offline Reinforcement Learning. In Hugo Larochelle, Marc'Aurelio Ranzato, Raia Hadsell, Maria-Florina Balcan, Hsuan-Tien Lin, editors, Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual. 2020. [doi]
@inproceedings{KumarZTL20,
title = {Conservative Q-Learning for Offline Reinforcement Learning},
author = {Aviral Kumar and Aurick Zhou and George Tucker and Sergey Levine},
year = {2020},
url = {https://proceedings.neurips.cc/paper/2020/hash/0d2b2061826a5df3221116a5085a6052-Abstract.html},
researchr = {https://researchr.org/publication/KumarZTL20},
cites = {0},
citedby = {0},
booktitle = {Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual},
editor = {Hugo Larochelle and Marc'Aurelio Ranzato and Raia Hadsell and Maria-Florina Balcan and Hsuan-Tien Lin},
}