Zobrazeno 1 - 10
of 464
pro vyhledávání: '"Zheng, Xuejing"'
Autor:
Zheng, Xuejing, Yu, Chao
In this paper, we study the cooperative Multi-Agent Reinforcement Learning (MARL) problems using Reward Machines (RMs) to specify the reward functions such that the prior knowledge of high-level events in a task can be leveraged to facilitate the lea
Externí odkaz:
http://arxiv.org/abs/2403.07005
Autor:
Liu, Hui, Zhang, Qian, Zhang, Yafei, Li, Xiumin, Tang, Keyong, Liu, Jie, Zheng, Xuejing, Pei, Ying
Content: Nowadays, tannery pollution is of great concern worldwide. The unhairing and fiber bundle-opening processes contribute the majority of the pollution by the use of sodium sulfide and calcium hydroxide, which were proposed to be replaced by ne
Externí odkaz:
https://slub.qucosa.de/id/qucosa%3A34317
https://slub.qucosa.de/api/qucosa%3A34317/attachment/ATT-0/
https://slub.qucosa.de/api/qucosa%3A34317/attachment/ATT-0/
Reinforcement Learning(RL) has achieved tremendous development in recent years, but still faces significant obstacles in addressing complex real-life problems due to the issues of poor system generalization, low sample efficiency as well as safety an
Externí odkaz:
http://arxiv.org/abs/2304.12090
Publikováno v:
In Chemical Engineering Journal 1 November 2024 499
Publikováno v:
In International Journal of Biological Macromolecules October 2024 277 Part 2
Publikováno v:
In Food Hydrocolloids October 2024 155
Autor:
Zhao, Han, Liu, Zihan, Sang, Yufeng, Chang, Junzhi, Zheng, Xuejing, Jurasz, Jakub, Zheng, Wandong
Publikováno v:
In Energy 1 September 2024 302
Autor:
Zheng, Xuejing1 (AUTHOR), Liu, Xu1 (AUTHOR), Zhang, Xinxin1 (AUTHOR), Zhao, Zhenguo1 (AUTHOR), Wu, Wence2 (AUTHOR), Yu, Shengji1 (AUTHOR) zlyygk@163.com
Publikováno v:
Journal of Hematology & Oncology. 8/20/2024, Vol. 17 Issue 1, p1-5. 5p.
Autor:
Yang, Xueqing, Chen, Yuxi, Zhou, Zhihua, Du, Yahui, Wang, Cheng, Liu, Junwei, Guo, Ziqiang, Yang, Haibin, Yu, Lu, Zhang, Shuqi, Zheng, Xuejing, Yan, Jinyue
Publikováno v:
In Applied Energy 15 December 2024 376 Part A
Continuously learning new tasks using high-level ideas or knowledge is a key capability of humans. In this paper, we propose Lifelong reinforcement learning with Sequential linear temporal logic formulas and Reward Machines (LSRM), which enables an a
Externí odkaz:
http://arxiv.org/abs/2111.09475