Zero-shot policy generation in lifelong reinforcement learning q

doi:10.1016/j.neucom.2021.02.058

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 机器人应用与理论组

	Zero-shot policy generation in lifelong reinforcement learning q
	Qian, Yi-Ming 1,2; Xiong, Fang-Zhou 2,3; Liu, Zhi-Yong 1,2,4
刊名	NEUROCOMPUTING
	2021-07-25
卷号	446 页码:65-73
关键词	Lifelong reinforcement learning Generalization policy Task domain
ISSN号	0925-2312
DOI	10.1016/j.neucom.2021.02.058
通讯作者	Liu, Zhi-Yong(zhiyong.liu@ia.ac.cn)
英文摘要	Lifelong reinforcement learning (LRL) is an important approach to achieve continual lifelong learning of multiple reinforcement learning tasks. The two major methods used in LRL are task decomposition and policy knowledge extraction. Policy knowledge extraction method in LRL can share knowledge for tasks in different task domains and for tasks in the same task domain with different system environmental coefficients. However, the generalization ability of policy knowledge extraction method is limited on learned tasks rather than learned task domains. In this paper, we propose a cross-domain lifelong reinforcement learning algorithm with zero-shot policy generation ability (CDLRL-ZPG) to improve generalization ability of policy knowledge extraction method from learned tasks to learned task domains. In experiments, we evaluated CDLRL-ZPG performance on four task domains. And our results show that the proposed algorithm can directly generate satisfactory results without needing a trial and error learning process to achieve zero-shot learning in general. (c) 2021 Elsevier B.V. All rights reserved.
资助项目	National Key Research and Development Plan of China[2020AAA0108902] ; Strategic Priority Research Program of Chinese Academy of Science[XDB32050100] ; NSFC, China[61627808] ; Dongguan core technology research frontier project[2019622101001]
WOS研究方向	Computer Science
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000660569000006
资助机构	National Key Research and Development Plan of China ; Strategic Priority Research Program of Chinese Academy of Science ; NSFC, China ; Dongguan core technology research frontier project
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/45331]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组
通讯作者	Liu, Zhi-Yong
作者单位	1.Univ Chinese Acad Sci UCAS, Sch Artificial Intelligence, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 3.Meituan, Beijing, Peoples R China 4.Chinese Acad Sci, CAS Ctr Excellence Brain Sci & Intelligence Techn, Shanghai 200031, Peoples R China
推荐引用方式 GB/T 7714	Qian, Yi-Ming,Xiong, Fang-Zhou,Liu, Zhi-Yong. Zero-shot policy generation in lifelong reinforcement learning q[J]. NEUROCOMPUTING,2021,446:65-73.
APA	Qian, Yi-Ming,Xiong, Fang-Zhou,&Liu, Zhi-Yong.(2021).Zero-shot policy generation in lifelong reinforcement learning q.NEUROCOMPUTING,446,65-73.
MLA	Qian, Yi-Ming,et al."Zero-shot policy generation in lifelong reinforcement learning q".NEUROCOMPUTING 446(2021):65-73.