Yijun Yang, Jing Jiang 0002, Zhuowei Wang 0003, Qiqi Duan, Yuhui Shi. BiES: Adaptive Policy Optimization for Model-Based Offline Reinforcement Learning. In Guodong Long, Xinghuo Yu 0001, Sen Wang 0001, editors, AI 2021: Advances in Artificial Intelligence - 34th Australasian Joint Conference, AI 2021, Sydney, NSW, Australia, February 2-4, 2022, Proceedings. Volume 13151 of Lecture Notes in Computer Science, pages 570-581, Springer, 2022. [doi]
@inproceedings{YangJWDS22,
title = {BiES: Adaptive Policy Optimization for Model-Based Offline Reinforcement Learning},
author = {Yijun Yang and Jing Jiang 0002 and Zhuowei Wang 0003 and Qiqi Duan and Yuhui Shi},
year = {2022},
doi = {10.1007/978-3-030-97546-3_46},
url = {https://doi.org/10.1007/978-3-030-97546-3_46},
researchr = {https://researchr.org/publication/YangJWDS22},
cites = {0},
citedby = {0},
pages = {570-581},
booktitle = {AI 2021: Advances in Artificial Intelligence - 34th Australasian Joint Conference, AI 2021, Sydney, NSW, Australia, February 2-4, 2022, Proceedings},
editor = {Guodong Long and Xinghuo Yu 0001 and Sen Wang 0001},
volume = {13151},
series = {Lecture Notes in Computer Science},
publisher = {Springer},
isbn = {978-3-030-97546-3},
}