A data-based online reinforcement learning algorithm satisfying probably approximately correct principle
Zhu, Yuanheng; Zhao, Dongbin
2015-05-01
发表期刊NEURAL COMPUTING & APPLICATIONS
卷号26期号:4页码:775-787
文章类型Article
摘要This 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.
关键词Reinforcement Learning Probably Approximately Correct Kd-tree
WOS标题词Science & Technology ; Technology
关键词[WOS]TIME NONLINEAR-SYSTEMS
收录类别SCI
语种英语
WOS研究方向Computer Science
WOS类目Computer Science, Artificial Intelligence
WOS记录号WOS:000353356000003
引用统计
被引频次:6[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/173211/8114
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Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing, Peoples R China
推荐引用方式
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.
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%2Fs005(1331KB)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%2Fs00521-014-1738-2.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。