CASIA OpenIR  > 复杂系统管理与控制国家重点实验室  > 深度强化学习
A data-based online reinforcement learning algorithm satisfying probably approximately correct principle
Zhu, Yuanheng; Zhao, Dongbin
Source PublicationNEURAL COMPUTING & APPLICATIONS
2015-05-01
Volume26Issue:4Pages:775-787
SubtypeArticle
AbstractThis paper proposes a probably approximately correct (PAC) algorithm that directly utilizes online data efficiently to solve the optimal control problem of continuous deterministic systems without system parameters for the first time. The dependence on some specific approximation structures is crucial to limit the wide application of online reinforcement learning (RL) algorithms. We utilize the online data directly with the kd-tree technique to remove this limitation. Moreover, we design the algorithm in the PAC principle. Complete theoretical proofs are presented, and three examples are simulated to verify its good performance. It draws the conclusion that the proposed RL algorithm specifies the maximum running time to reach a near-optimal control policy with only online data.
KeywordReinforcement Learning Probably Approximately Correct Kd-tree
WOS HeadingsScience & Technology ; Technology
WOS KeywordTIME NONLINEAR-SYSTEMS
Indexed BySCI
Language英语
WOS Research AreaComputer Science
WOS SubjectComputer Science, Artificial Intelligence
WOS IDWOS:000353356000003
Citation statistics
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/8114
Collection复杂系统管理与控制国家重点实验室_深度强化学习
AffiliationChinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
Recommended Citation
GB/T 7714
Zhu, Yuanheng,Zhao, Dongbin. A data-based online reinforcement learning algorithm satisfying probably approximately correct principle[J]. NEURAL COMPUTING & APPLICATIONS,2015,26(4):775-787.
APA Zhu, Yuanheng,&Zhao, Dongbin.(2015).A data-based online reinforcement learning algorithm satisfying probably approximately correct principle.NEURAL COMPUTING & APPLICATIONS,26(4),775-787.
MLA Zhu, Yuanheng,et al."A data-based online reinforcement learning algorithm satisfying probably approximately correct principle".NEURAL COMPUTING & APPLICATIONS 26.4(2015):775-787.
Files in This Item: Download All
File Name/Size DocType Version Access License
art%3A10.1007%2Fs005(1331KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Zhu, Yuanheng]'s Articles
[Zhao, Dongbin]'s Articles
Baidu academic
Similar articles in Baidu academic
[Zhu, Yuanheng]'s Articles
[Zhao, Dongbin]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Zhu, Yuanheng]'s Articles
[Zhao, Dongbin]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: art%3A10.1007%2Fs00521-014-1738-2.pdf
Format: Adobe PDF
This file does not support browsing at this time
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.