期刊
IEEE TRANSACTIONS ON CYBERNETICS
卷 50, 期 11, 页码 4573-4584出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TCYB.2020.2963849
关键词
Optimal control; Adaptive systems; Backstepping; Nonlinear systems; Discrete-time systems; Control design; Reinforcement learning; Adaptive control; neural network (NN); nonstrict-feedback systems; optimal controller; reinforcement learning (RL)
类别
资金
- National Natural Science Foundation of China [51939001, 61903092, 61976033, 61903174, 61751202, U1813203]
- Science and Technology Innovation Funds of Dalian [2018J11CY022]
- Natural Science Foundation of Liaoning Province [2019-ZD-0151]
This article investigates an adaptive reinforcement learning (RL) optimal control design problem for a class of nonstrict-feedback discrete-time systems. Based on the neural network (NN) approximating ability and RL control design technique, an adaptive backstepping RL optimal controller and a minimal learning parameter (MLP) adaptive RL optimal controller are developed by establishing a novel strategic utility function and introducing external function terms. It is proved that the proposed adaptive RL optimal controllers can guarantee that all signals in the closed-loop systems are semiglobal uniformly ultimately bounded (SGUUB). The main feature is that the proposed schemes can solve the optimal control problem that the previous literature cannot deal with. Furthermore, the proposed MPL adaptive optimal control scheme can reduce the number of adaptive laws, and thus the computational complexity is decreased. Finally, the simulation results illustrate the validity of the proposed optimal control schemes.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据