Beta
ManageSearchChatDiscover
64788

A MODIFIED REINFORCEMENT LEARNING APPROACH FOR CONTROLLING THE MULTIVARIABLE MEAN ARTERIAL BLOOD PRESSURE

Article

Last updated: 04 Jan 2025

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

The original reinforcement learning scheme comprises two networks, one performs a controller and the other stands for an evaluator. Based on temporal difference predictive techniques, the evaluative network predicts an external reinforcement signal and estimates a more informative internal signal to adapt a set of  parameters of the controller. This paper introduces a modified reinforcement learning scheme to simplify the original  scheme. The mean theme of the proposed scheme is that it replaces the fuzzy neural network (FNN) evaluator by a simple evaluator that depends directly  on the environment of the process be controlled. Based on a performance index, the proposed evaluator outputs a reinforcement signal in the range of [-1,1] using two methods, one is fuzzy and the other is a  discrete uniform  of reinforcement signals. Compared with the original reinforcement scheme, the computational demand of the proposed scheme is relatively insignificant. That is that no parameters/structure learning is needed for the proposed evaluator.  That makes the proposed reinforcement scheme suitable for controlling real time intensive processes. The mean features of the proposed scheme are reflected in our simulation results on controlling the multivariable mean arterial blood pressure.

DOI

10.21608/mjeer.2006.64788

Keywords

Fuzzy Set Theory, Neural Networks, Predictive Control, Reinforcement Learning Schemes

Authors

First Name

Hamdy A.

Last Name

Awad

MiddleName

-

Affiliation

Faculty of Electronic Engineering, Menoufia University, Menoufia, Egypt

Email

-

City

-

Orcid

-

Volume

16

Article Issue

1

Related Issue

9700

Issue Date

2006-01-01

Receive Date

2019-12-11

Publish Date

2006-01-01

Page Start

61

Page End

83

Print ISSN

1687-1189

Online ISSN

2682-3535

Link

https://mjeer.journals.ekb.eg/article_64788.html

Detail API

https://mjeer.journals.ekb.eg/service?article_code=64788

Order

7

Type

Original Article

Type Code

1,088

Publication Type

Journal

Publication Title

Menoufia Journal of Electronic Engineering Research

Publication Link

https://mjeer.journals.ekb.eg/

MainTitle

A MODIFIED REINFORCEMENT LEARNING APPROACH FOR CONTROLLING THE MULTIVARIABLE MEAN ARTERIAL BLOOD PRESSURE

Details

Type

Article

Created At

22 Jan 2023