Comprehensive comparison of online ADP algorithms for continuous-time optimal control
Zhu, Yuanheng1,2; Zhao, Dongbin1,2
2018-04-01
发表期刊ARTIFICIAL INTELLIGENCE REVIEW
卷号49期号:4页码:531-547
文章类型Article
摘要Online learning is an important property of adaptive dynamic programming (ADP). Online observations contain plentiful dynamics information, and ADP algorithms can utilize them to learn the optimal control policy. This paper reviews the research of online ADP algorithms for the optimal control of continuous-time systems. With the intensive study, ADP has been developed towards model free and data efficient. After separately introducing the algorithms, we compare their performance on the same problem. This paper is desired to provide a comprehensive understanding of continuous-time online ADP algorithms.
关键词Adaptive Dynamic Programming Policy Iteration Integral Reinforcement Learning Experience Replay Off-policy
WOS标题词Science & Technology ; Technology
DOI10.1007/s10462-017-9548-4
关键词[WOS]NONLINEAR-SYSTEMS ; EXPERIENCE REPLAY
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61533017 ; Early Career Development Award of SKLMCCS ; 61573353 ; 61603382)
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000426912500004
引用统计
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/15287
专题复杂系统管理与控制国家重点实验室_深度强化学习
作者单位1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
2.Univ Chinese Acad Sci, Beijing, Peoples R China
推荐引用方式
GB/T 7714
Zhu, Yuanheng,Zhao, Dongbin. Comprehensive comparison of online ADP algorithms for continuous-time optimal control[J]. ARTIFICIAL INTELLIGENCE REVIEW,2018,49(4):531-547.
APA Zhu, Yuanheng,&Zhao, Dongbin.(2018).Comprehensive comparison of online ADP algorithms for continuous-time optimal control.ARTIFICIAL INTELLIGENCE REVIEW,49(4),531-547.
MLA Zhu, Yuanheng,et al."Comprehensive comparison of online ADP algorithms for continuous-time optimal control".ARTIFICIAL INTELLIGENCE REVIEW 49.4(2018):531-547.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
art%3A10.1007%2Fs104(766KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhu, Yuanheng]的文章
[Zhao, Dongbin]的文章
百度学术
百度学术中相似的文章
[Zhu, Yuanheng]的文章
[Zhao, Dongbin]的文章
必应学术
必应学术中相似的文章
[Zhu, Yuanheng]的文章
[Zhao, Dongbin]的文章
相关权益政策
暂无数据
收藏/分享
文件名: art%3A10.1007%2Fs10462-017-9548-4.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。