Kaiyang Guo, Yunfeng Shao, Yanhui Geng. Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief. 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{GuoSG22,
title = {Model-Based Offline Reinforcement Learning with Pessimism-Modulated Dynamics Belief},
author = {Kaiyang Guo and Yunfeng Shao and Yanhui Geng},
year = {2022},
url = {http://papers.nips.cc/paper_files/paper/2022/hash/03469b1a66e351b18272be23baf3b809-Abstract-Conference.html},
researchr = {https://researchr.org/publication/GuoSG22},
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},
}