Improved value iteration for neural-network-based stochastic optimal control design

doi:10.1016/j.neunet.2020.01.004

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 复杂系统智能机理与平行控制团队

	Improved value iteration for neural-network-based stochastic optimal control design
	Liang, Mingming1 ; Wang, Ding2,3 ; Liu, Derong 4
发表期刊	NEURAL NETWORKS
ISSN	0893-6080
	2020-04-01
卷号	124 页码:280-295
通讯作者	Wang, Ding(dingwang@bjut.edu.cn)
摘要	In this paper, a novel value iteration adaptive dynamic programming (ADP) algorithm is presented, which is called an improved value iteration ADP algorithm, to obtain the optimal policy for discrete stochastic processes. In the improved value iteration ADP algorithm, for the first time we propose a new criteria to verify whether the obtained policy is stable or not for stochastic processes. By analyzing the convergence properties of the proposed algorithm, it is shown that the iterative value functions can converge to the optimum. In addition, our algorithm allows the initial value function to be an arbitrary positive semi-definite function. Finally, two simulation examples are presented to validate the effectiveness of the developed method. (C) 2020 Elsevier Ltd. All rights reserved.
关键词	Adaptive critic designs Adaptive dynamic programming Neural networks Optimal control Stochastic processes Value iteration
DOI	10.1016/j.neunet.2020.01.004
关键词[WOS]	ALGORITHMS
收录类别	SCI
语种	英语
资助项目	Beijing Natural Science Foundation, China[JQ19013] ; National Natural Science Foundation of China[61773373] ; National Natural Science Foundation of China[61533017] ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
项目资助者	Beijing Natural Science Foundation, China ; National Natural Science Foundation of China ; Youth Innovation Promotion Association of the Chinese Academy of Sciences
WOS研究方向	Computer Science ; Neurosciences & Neurology
WOS类目	Computer Science, Artificial Intelligence ; Neurosciences
WOS记录号	WOS:000518860600025
出版者	PERGAMON-ELSEVIER SCIENCE LTD
七大方向——子方向分类	智能控制
引用统计	被引频次：12[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/173211/38631
专题	多模态人工智能系统全国重点实验室_复杂系统智能机理与平行控制团队
通讯作者	Wang, Ding
作者单位	1.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China 2.Beijing Univ Technol, Fac Informat Technol, Beijing 100124, Peoples R China 3.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China 4.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Peoples R China
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Liang, Mingming,Wang, Ding,Liu, Derong. Improved value iteration for neural-network-based stochastic optimal control design[J]. NEURAL NETWORKS,2020,124:280-295.
APA	Liang, Mingming,Wang, Ding,&Liu, Derong.(2020).Improved value iteration for neural-network-based stochastic optimal control design.NEURAL NETWORKS,124,280-295.
MLA	Liang, Mingming,et al."Improved value iteration for neural-network-based stochastic optimal control design".NEURAL NETWORKS 124(2020):280-295.

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
1-s2.0-S089360802030（5875KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载