Adaptive Reinforcement Learning Control Based on Neural Approximation for Nonlinear Discrete-Time Systems With Unknown Nonaffine Dead-Zone Input
文献类型：期刊论文
| 作者 | Liu, Yan-Jun1 ; Li, Shu1; Tong, Shaocheng1; Chen, C. L. Philip2,3,4
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2019 |
| 卷号 | 30期号:1页码:295-305 |
| 关键词 | Discrete-time systems neural networks (NNs) nonlinear systems optimal control reinforcement learning |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2018.2844165 |
| 通讯作者 | Liu, Yan-Jun(liuyanjun@live.com) |
| 英文摘要 | In this paper, an optimal control algorithm is designed for uncertain nonlinear systems in discrete-time, which are in nonaffine form and with unknown dead-zone. The main contributions of this paper are that an optimal control algorithm is for the first time framed in this paper for nonlinear systems with nonaffine dead-zone, and the adaptive parameter law for dead-zone is calculated by using the gradient rules. The mean value theory is employed to deal with the nonaffine dead-zone input and the implicit function theory based on reinforcement learning is appropriately introduced to find an unknown ideal controller which is approximated by using the action network. Other neural networks are taken as the critic networks to approximate the strategic utility functions. Based on the Lyapunov stability analysis theory, we can prove the stability of systems, i.e., the optimal control laws can guarantee that all the signals in the closed-loop system are bounded and the tracking errors are converged to a small compact set. Finally, two simulation examples demonstrate the effectiveness of the design algorithm. |
| WOS关键词 | BARRIER LYAPUNOV FUNCTIONS ; OUTPUT-FEEDBACK CONTROL ; DYNAMIC SURFACE CONTROL ; TRACKING CONTROL ; MULTIAGENT SYSTEMS ; POLICY ITERATION ; NETWORK CONTROL ; DESIGN ; COMPENSATION ; ALGORITHM |
| 资助项目 | National Natural Science Foundation of China[61622303] ; National Natural Science Foundation of China[61603164] ; National Natural Science Foundation of China[61473139] ; National Natural Science Foundation of China[61773188] ; Program for Liaoning Innovative Research Team in University[LT2016006] ; Program for Distinguished Professor of Liaoning Province |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000454329300024 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Program for Liaoning Innovative Research Team in University ; Program for Distinguished Professor of Liaoning Province |
| 源URL | [http://ir.ia.ac.cn/handle/173211/25627]  |
| 专题 | 离退休人员 |
| 通讯作者 | Liu, Yan-Jun |
| 作者单位 | 1.Liaoning Univ Technol, Coll Sci, Jinzhou 121001, Peoples R China 2.Univ Macau, Dept Comp & Informat Sci, Fac Sci & Technol, Macau 99999, Peoples R China 3.Dalian Maritime Univ, Nav Coll, Dalian 116026, Peoples R China 4.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China |
| 推荐引用方式 GB/T 7714 | Liu, Yan-Jun,Li, Shu,Tong, Shaocheng,et al. Adaptive Reinforcement Learning Control Based on Neural Approximation for Nonlinear Discrete-Time Systems With Unknown Nonaffine Dead-Zone Input[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2019,30(1):295-305. |
| APA | Liu, Yan-Jun,Li, Shu,Tong, Shaocheng,&Chen, C. L. Philip.(2019).Adaptive Reinforcement Learning Control Based on Neural Approximation for Nonlinear Discrete-Time Systems With Unknown Nonaffine Dead-Zone Input.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,30(1),295-305. |
| MLA | Liu, Yan-Jun,et al."Adaptive Reinforcement Learning Control Based on Neural Approximation for Nonlinear Discrete-Time Systems With Unknown Nonaffine Dead-Zone Input".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 30.1(2019):295-305. |
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。