Chenjia Bai, Lingxiao Wang 0003, Jianye Hao, Zhuoran Yang, Bin Zhao 0001, Zhen Wang, Xuelong Li 0001. Pessimistic value iteration for multi-task data sharing in Offline Reinforcement Learning. Artificial Intelligence, 326:104048, January 2024. [doi]
@article{BaiWHYZWL24,
title = {Pessimistic value iteration for multi-task data sharing in Offline Reinforcement Learning},
author = {Chenjia Bai and Lingxiao Wang 0003 and Jianye Hao and Zhuoran Yang and Bin Zhao 0001 and Zhen Wang and Xuelong Li 0001},
year = {2024},
month = {January},
doi = {10.1016/j.artint.2023.104048},
url = {https://doi.org/10.1016/j.artint.2023.104048},
researchr = {https://researchr.org/publication/BaiWHYZWL24},
cites = {0},
citedby = {0},
journal = {Artificial Intelligence},
volume = {326},
pages = {104048},
}