Jiafei Lyu, Xiaoteng Ma, Xiu Li, Zongqing Lu. Mildly Conservative Q-Learning for Offline Reinforcement Learning. In Sanmi Koyejo, S. Mohamed, A. Agarwal, Danielle Belgrave, K. Cho, A. Oh, editors, Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022. 2022. [doi]
@inproceedings{LyuMLL22, title = {Mildly Conservative Q-Learning for Offline Reinforcement Learning}, author = {Jiafei Lyu and Xiaoteng Ma and Xiu Li and Zongqing Lu}, year = {2022}, url = {http://papers.nips.cc/paper_files/paper/2022/hash/0b5669c3b07bb8429af19a7919376ff5-Abstract-Conference.html}, researchr = {https://researchr.org/publication/LyuMLL22}, cites = {0}, citedby = {0}, booktitle = {Advances in Neural Information Processing Systems 35: Annual Conference on Neural Information Processing Systems 2022, NeurIPS 2022, New Orleans, LA, USA, November 28 - December 9, 2022}, editor = {Sanmi Koyejo and S. Mohamed and A. Agarwal and Danielle Belgrave and K. Cho and A. Oh}, isbn = {9781713871088}, }