Comprehensive comparison of online ADP algorithms for continuous-time optimal control
文献类型：期刊论文
| 作者 | Zhu, Yuanheng1,2 ; Zhao, Dongbin1,2
|
| 刊名 | ARTIFICIAL INTELLIGENCE REVIEW
 |
| 出版日期 | 2018-04-01 |
| 卷号 | 49期号:4页码:531-547 |
| 关键词 | Adaptive Dynamic Programming Policy Iteration Integral Reinforcement Learning Experience Replay Off-policy |
| DOI | 10.1007/s10462-017-9548-4 |
| 文献子类 | Article |
| 英文摘要 | 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. |
| WOS关键词 | NONLINEAR-SYSTEMS ; EXPERIENCE REPLAY |
| WOS研究方向 | Computer Science |
| 语种 | 英语 |
| WOS记录号 | WOS:000426912500004 |
| 资助机构 | National Natural Science Foundation of China(61533017 ; Early Career Development Award of SKLMCCS ; 61573353 ; 61603382) |
| 源URL | [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. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
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。