Zero-shot policy generation in lifelong reinforcement learning q

doi:10.1016/j.neucom.2021.02.058

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	Zero-shot policy generation in lifelong reinforcement learning q
	Qian, Yi-Ming 1,2; Xiong, Fang-Zhou2,3 ; Liu, Zhi-Yong1,2,4
发表期刊	NEUROCOMPUTING
ISSN	0925-2312
	2021-07-25
卷号	446 页码:65-73
通讯作者	Liu, Zhi-Yong(zhiyong.liu@ia.ac.cn)
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.
关键词	Lifelong reinforcement learning Generalization policy Task domain
DOI	10.1016/j.neucom.2021.02.058
收录类别	SCI
语种	英语
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]
项目资助者	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
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:000660569000006
出版者	ELSEVIER
七大方向——子方向分类	强化与进化学习
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/45332
专题	多模态人工智能系统全国重点实验室_机器人理论与应用
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
第一作者单位	中国科学院自动化研究所
通讯作者单位	中国科学院自动化研究所
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.