A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints
文献类型：期刊论文
| 作者 | Wang, Ding1 ; Liu, Derong1,2; Zhao, Dongbin1; Huang, Yuzhu1; Zhang, Dehua1
|
| 刊名 | NEURAL COMPUTING & APPLICATIONS
 |
| 出版日期 | 2013-02-01 |
| 卷号 | 22期号:2页码:219-227 |
| 关键词 | Adaptive critic designs Adaptive dynamic programming Approximate dynamic programming Neural dynamic programming Neural networks Optimal control Reinforcement learning |
| 英文摘要 | In this paper, a novel neural-network-based iterative adaptive dynamic programming (ADP) algorithm is proposed. It aims at solving the optimal control problem of a class of nonlinear discrete-time systems with control constraints. By introducing a generalized nonquadratic functional, the iterative ADP algorithm through globalized dual heuristic programming technique is developed to design optimal controller with convergence analysis. Three neural networks are constructed as parametric structures to facilitate the implementation of the iterative algorithm. They are used for approximating at each iteration the cost function, the optimal control law, and the controlled nonlinear discrete-time system, respectively. A simulation example is also provided to verify the effectiveness of the control scheme in solving the constrained optimal control problem. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | ADAPTIVE CRITIC DESIGNS ; DISCRETE-TIME-SYSTEMS ; FEEDBACK-CONTROL ; REINFORCEMENT ; ADP |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000313657600004 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3518]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 作者单位 | 1.Chinese Acad Sci, Inst Automat, Key Lab Complex Syst & Intelligence Sci, Beijing 100190, Peoples R China 2.Univ Illinois, Dept Elect & Comp Engn, Chicago, IL 60607 USA |
| 推荐引用方式 GB/T 7714 | Wang, Ding,Liu, Derong,Zhao, Dongbin,et al. A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints[J]. NEURAL COMPUTING & APPLICATIONS,2013,22(2):219-227. |
| APA | Wang, Ding,Liu, Derong,Zhao, Dongbin,Huang, Yuzhu,&Zhang, Dehua.(2013).A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints.NEURAL COMPUTING & APPLICATIONS,22(2),219-227. |
| MLA | Wang, Ding,et al."A neural-network-based iterative GDHP approach for solving a class of nonlinear optimal control problems with control constraints".NEURAL COMPUTING & APPLICATIONS 22.2(2013):219-227. |
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。