Transactions of the Institute of Systems, Control and Information Engineers
Online ISSN : 2185-811X
Print ISSN : 1342-5668
ISSN-L : 1342-5668
One-shot Input-Output History Feedback Controller Design for Unknown Linear Systems
—Reinforcement Learning Approach
Takumi HiraiTomonori Sadamoto
Author information
JOURNAL FREE ACCESS

2021 Volume 34 Issue 9 Pages 235-242

Details
Abstract

In this paper, we propose a method of designing input-output history feedback controllers for unknown linear discrete-time systems. Many conventional reinforcement-learning based controls such as policy iteration are state-feedback. We extend the policy iteration by incorporating a method to statically estimate state variables from a history of finite-time input-output data. The convergence of the policy to model-based optimal solution has been theoretically guaranteed. Moreover, the proposed method is one-shot learning, i.e., the optimal controller can be obtained by using initial experiment data only. The effectiveness of the proposed method is shown through a numerical simulation through an oscillator network.

Content from these authors
© 2021 The Institute of Systems, Control and Information Engineers
Next article
feedback
Top