Reinforcement Learning-Based Optimal Stabilization for Unknown Nonlinear Systems Subject to Inputs With Uncertain Constraints
文献类型：期刊论文
| 作者 | Zhao, Bo1,2 ; Liu, Derong4; Luo, Chaomin3
|
| 刊名 | IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
 |
| 出版日期 | 2020-10-01 |
| 卷号 | 31期号:10页码:4330-4340 |
| 关键词 | Nonlinear systems Optimal control Artificial neural networks Actuators Observers Feedforward systems Adaptive dynamic programming (ADP) neural networks (NNs) optimal control reinforcement learning (RL) uncertain input constraints unknown nonlinear systems |
| ISSN号 | 2162-237X |
| DOI | 10.1109/TNNLS.2019.2954983 |
| 通讯作者 | Zhao, Bo(zhaobo@bnu.edu.cn) |
| 英文摘要 | This article presents a novel reinforcement learning strategy that addresses an optimal stabilizing problem for unknown nonlinear systems subject to uncertain input constraints. The control algorithm is composed of two parts, i.e., online learning optimal control for the nominal system and feedforward neural networks (NNs) compensation for handling uncertain input constraints, which are considered as the saturation nonlinearities. Integrating the input-output data and recurrent NN, a Luenberger observer is established to approximate the unknown system dynamics. For nominal systems without input constraints, the online learning optimal control policy is derived by solving Hamilton-Jacobi-Bellman equation via a critic NN alone. By transforming the uncertain input constraints to saturation nonlinearities, the uncertain input constraints can be compensated by employing a feedforward NN compensator. The convergence of the closed-loop system is guaranteed to be uniformly ultimately bounded by using the Lyapunov stability analysis. Finally, the effectiveness of the developed stabilization scheme is illustrated by simulation studies. |
| WOS关键词 | ZERO-SUM GAMES ; DECENTRALIZED TRACKING CONTROL ; ADAPTIVE OPTIMAL-CONTROL ; FAULT-TOLERANT CONTROL ; NEURAL-NETWORK CONTROL ; DISCRETE-TIME-SYSTEMS ; POLICY ITERATION ; ALGORITHMS ; CONTROLLER ; EQUATION |
| 资助项目 | National Natural Science Foundation of China[61973330] ; National Natural Science Foundation of China[61603387] ; National Natural Science Foundation of China[61773075] ; National Natural Science Foundation of China[61533017] ; National Natural Science Foundation of China[U1501251] ; Fundamental Research Funds for the Central Universities[2019NTST25] ; Early Career Development Award of SKLMCCS[20180201] ; State Key Laboratory of Synthetical Automation for Process Industries[2019-KF-23-03] |
| WOS研究方向 | Computer Science ; Engineering |
| 语种 | 英语 |
| WOS记录号 | WOS:000576436600045 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; Fundamental Research Funds for the Central Universities ; Early Career Development Award of SKLMCCS ; State Key Laboratory of Synthetical Automation for Process Industries |
| 源URL | [http://ir.ia.ac.cn/handle/173211/42104]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室 |
| 通讯作者 | Zhao, Bo |
| 作者单位 | 1.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China 2.Beijing Normal Univ, Sch Syst Sci, Beijing 100875, Peoples R China 3.Mississippi State Univ, Dept Elect & Comp Engn, Mississippi State, MS 39762 USA 4.Guangdong Univ Technol, Sch Automat, Guangzhou 510006, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Bo,Liu, Derong,Luo, Chaomin. Reinforcement Learning-Based Optimal Stabilization for Unknown Nonlinear Systems Subject to Inputs With Uncertain Constraints[J]. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,2020,31(10):4330-4340. |
| APA | Zhao, Bo,Liu, Derong,&Luo, Chaomin.(2020).Reinforcement Learning-Based Optimal Stabilization for Unknown Nonlinear Systems Subject to Inputs With Uncertain Constraints.IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS,31(10),4330-4340. |
| MLA | Zhao, Bo,et al."Reinforcement Learning-Based Optimal Stabilization for Unknown Nonlinear Systems Subject to Inputs With Uncertain Constraints".IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS 31.10(2020):4330-4340. |
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。