Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm
文献类型：期刊论文
| 作者 | Liu, Derong; Li, Hongliang; Wang, Ding
|
| 刊名 | NEUROCOMPUTING
 |
| 出版日期 | 2013-06-13 |
| 卷号 | 110页码:92-100 |
| 关键词 | Adaptive dynamic programming Approximate dynamic programming Heuristic dynamic programming Neural networks Zero-sum game H-infinity optimal control |
| 英文摘要 | In this paper, we solve the zero-sum game problems for discrete-time affine nonlinear systems with known dynamics via iterative adaptive dynamic programming algorithm. First, a greedy heuristic dynamic programming iteration algorithm is developed to solve the zero-sum game problems, which can be used to solve the Hamilton-Jacobi-Isaacs equation associated with H-infinity optimal regulation control problems. The convergence analysis in terms of value function and control policy is provided. To facilitate the implementation of the algorithm, three neural networks are used to approximate the control policy, the disturbance policy, and the value function, respectively. Then, we extend the algorithm to R, optimal tracking control problems through system transformation. Finally, two simulation examples are presented to demonstrate the effectiveness of the proposed scheme. (C) 2013 Elsevier B.V. All rights reserved. |
| 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] | H-INFINITY-CONTROL ; OPTIMAL TRACKING CONTROL ; FEEDBACK-CONTROL ; CRITIC DESIGNS ; CONVERGENCE ; EQUATIONS ; PROOF |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000318457700011 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/3871]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_智能化团队 |
| 作者单位 | Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Derong,Li, Hongliang,Wang, Ding. Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm[J]. NEUROCOMPUTING,2013,110:92-100. |
| APA | Liu, Derong,Li, Hongliang,&Wang, Ding.(2013).Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm.NEUROCOMPUTING,110,92-100. |
| MLA | Liu, Derong,et al."Neural-network-based zero-sum game for discrete-time nonlinear systems via iterative adaptive dynamic programming algorithm".NEUROCOMPUTING 110(2013):92-100. |
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。