Display Settings:

Format

Send to:

Choose Destination
See comment in PubMed Commons below
Neural Netw. 2014 Jul;55:30-41. doi: 10.1016/j.neunet.2014.03.008. Epub 2014 Mar 28.

Discrete-time online learning control for a class of unknown nonaffine nonlinear systems using reinforcement learning.

Author information

  • 1The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. Electronic address: xiong.yang@ia.ac.cn.
  • 2The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. Electronic address: derongliu@gmail.com.
  • 3The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. Electronic address: ding.wang@ia.ac.cn.
  • 4The State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China. Electronic address: qinglai.wei@ia.ac.cn.

Abstract

In this paper, a reinforcement-learning-based direct adaptive control is developed to deliver a desired tracking performance for a class of discrete-time (DT) nonlinear systems with unknown bounded disturbances. We investigate multi-input-multi-output unknown nonaffine nonlinear DT systems and employ two neural networks (NNs). By using Implicit Function Theorem, an action NN is used to generate the control signal and it is also designed to cancel the nonlinearity of unknown DT systems, for purpose of utilizing feedback linearization methods. On the other hand, a critic NN is applied to estimate the cost function, which satisfies the recursive equations derived from heuristic dynamic programming. The weights of both the action NN and the critic NN are directly updated online instead of offline training. By utilizing Lyapunov's direct method, the closed-loop tracking errors and the NN estimated weights are demonstrated to be uniformly ultimately bounded. Two numerical examples are provided to show the effectiveness of the present approach.

Copyright © 2014 Elsevier Ltd. All rights reserved.

KEYWORDS:

Adaptive critic design; Neural network; Nonaffine nonlinear system; Online learning; Reinforcement learning

PMID:
24721223
[PubMed - in process]
PubMed Commons home

PubMed Commons

0 comments
How to join PubMed Commons

    Supplemental Content

    Full text links

    Icon for Elsevier Science
    Loading ...
    Write to the Help Desk