Optimized Adaptive Nonlinear Tracking Control Using Actor-Critic Reinforcement Learning Strategy
文献类型：期刊论文
| 作者 | Wen, Guoxing1,2; Chen, C. L. Philip3,4,5; Ge, Shuzhi Sam6,7; Yang, Hongli8; Liu, Xiaoguang9,10 |
| 刊名 | IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
 |
| 出版日期 | 2019-09-01 |
| 卷号 | 15期号:9页码:4969-4977 |
| 关键词 | Lyapunov function neural networks (NNs) nonlinear systems optimized tracking control reinforcement learning (RL) of actor-critic architecture |
| ISSN号 | 1551-3203 |
| DOI | 10.1109/TII.2019.2894282 |
| 通讯作者 | Wen, Guoxing(wengx_sd@hotmail.com) |
| 英文摘要 | This paper proposes an optimized tracking control approach using neural network (NN) based reinforcement learning (RL) for a class of nonlinear dynamic systems, which requires both tracking and optimizing to be performed simultaneously. Generally, for obtaining optimal control solution, Hamilton-Jacobi-Bellman equation is expected to be solvable, but, owing to strong nonlinearity, the equation is solved difficultly or even impossibly by analytical methods. Therefore, adaptive NN approximation based RL is usually considered. In the optimized control design, for driving output state following to the desired trajectory, an error term is split from optimal performance index function, and then both actor and critic NNs are built to perform RL algorithm. Actor NN aims to execute control behaviors, and critic NN aims to appraise control performance and make feedback to actor. The proof of stability concludes that the desired control performances are obtained. A numerical simulation is designed and implemented, and the desired results are shown. |
| WOS关键词 | NEURAL-NETWORKS ; SYSTEMS |
| 资助项目 | Shandong Provincial Natural Science Foundation, China[ZR2018MF015] ; National Natural Science Foundation of China[61751202] ; National Natural Science Foundation of China[61572540] ; Doctoral Scientific Research Staring Fund of Binzhou University[2016Y14] ; mobility program of Shandong University of Science and Technology |
| WOS研究方向 | Automation & Control Systems ; Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000489584600012 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | Shandong Provincial Natural Science Foundation, China ; National Natural Science Foundation of China ; Doctoral Scientific Research Staring Fund of Binzhou University ; mobility program of Shandong University of Science and Technology |
| 源URL | [http://ir.ia.ac.cn/handle/173211/26669]  |
| 专题 | 离退休人员 |
| 通讯作者 | Wen, Guoxing |
| 作者单位 | 1.Binzhou Univ, Coll Sci, Binzhou 256600, Peoples R China 2.Binzhou Univ, IAET, Binzhou 256600, Peoples R China 3.Univ Macau, Dept Comp & Informat Sci, Fac Sci & Technol, Macau 99999, Peoples R China 4.Dalian Maritime Univ, Dalian 116026, Peoples R China 5.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100080, Peoples R China 6.Natl Univ Singapore, Dept Elect & Comp Engn, Singapore 117576, Singapore 7.Qingdao Univ, Inst Future, Qingdao 266071, Shandong, Peoples R China 8.Shandong Univ Sci & Technol, Math & Syst Sci Coll, Qingdao 266590, Shandong, Peoples R China 9.Southwest Minzu Univ, Key Lab Comp Syst, State Ethn Affairs Commiss, Chengdu 610041, Sichuan, Peoples R China 10.Southwest Minzu Univ, Sch Comp Sci & Technol, Chengdu 610041, Sichuan, Peoples R China |
| 推荐引用方式 GB/T 7714 | Wen, Guoxing,Chen, C. L. Philip,Ge, Shuzhi Sam,et al. Optimized Adaptive Nonlinear Tracking Control Using Actor-Critic Reinforcement Learning Strategy[J]. IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,2019,15(9):4969-4977. |
| APA | Wen, Guoxing,Chen, C. L. Philip,Ge, Shuzhi Sam,Yang, Hongli,&Liu, Xiaoguang.(2019).Optimized Adaptive Nonlinear Tracking Control Using Actor-Critic Reinforcement Learning Strategy.IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS,15(9),4969-4977. |
| MLA | Wen, Guoxing,et al."Optimized Adaptive Nonlinear Tracking Control Using Actor-Critic Reinforcement Learning Strategy".IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS 15.9(2019):4969-4977. |
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。