An adaptive unidirectional linear response fuzzy controller based on reinforcement learning

Zheng Tang; Masakazu Komori; Okihiko Ishizuka; Koichi Tanno

doi:10.1002/ecjc.4430790203

An adaptive unidirectional linear response fuzzy controller based on reinforcement learning

Zheng Tang^*, Masakazu Komori, Okihiko Ishizuka, Koichi Tanno

^*Corresponding author for this work

Intellectual Information Engineering

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

This paper presents an adaptive fuzzy controller using unidirectional linear response (ULR) elements. The basic functions for a fuzzy controller including membership, minimum and defuzzification functions are realized by the ULR elements. Because the ULR element has diode-like characteristics, it can be implemented by a diode-connected mean-opinion score (MOS) transistor in current-mode implementations. The hardware implementation of the fuzzy controller using ULR elements should also be very simple and straightforward. The ULR fuzzy controller is applied to an inverted pendulum problem, and the effectiveness of the proposed ULR controller architecture and its learning capability based on reinforcement learning are demonstrated.

Original language	English
Pages (from-to)	22-30
Number of pages	9
Journal	Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)
Volume	79
Issue number	2
DOIs	https://doi.org/10.1002/ecjc.4430790203
State	Published - 1996/02

Keywords

Adaptive
Fuzzy controller
Reinforcement learning
ULR

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1002/ecjc.4430790203

Cite this

@article{491200344ca7428a95516bb999912087,

title = "An adaptive unidirectional linear response fuzzy controller based on reinforcement learning",

abstract = "This paper presents an adaptive fuzzy controller using unidirectional linear response (ULR) elements. The basic functions for a fuzzy controller including membership, minimum and defuzzification functions are realized by the ULR elements. Because the ULR element has diode-like characteristics, it can be implemented by a diode-connected mean-opinion score (MOS) transistor in current-mode implementations. The hardware implementation of the fuzzy controller using ULR elements should also be very simple and straightforward. The ULR fuzzy controller is applied to an inverted pendulum problem, and the effectiveness of the proposed ULR controller architecture and its learning capability based on reinforcement learning are demonstrated.",

keywords = "Adaptive, Fuzzy controller, Reinforcement learning, ULR",

author = "Zheng Tang and Masakazu Komori and Okihiko Ishizuka and Koichi Tanno",

year = "1996",

month = feb,

doi = "10.1002/ecjc.4430790203",

language = "英語",

volume = "79",

pages = "22--30",

journal = "Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)",

issn = "1042-0967",

publisher = "John Wiley & Sons Inc.",

number = "2",

}

An adaptive unidirectional linear response fuzzy controller based on reinforcement learning. / Tang, Zheng; Komori, Masakazu; Ishizuka, Okihiko et al.
In: Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi), Vol. 79, No. 2, 02.1996, p. 22-30.

Research output: Contribution to journal › Article › peer-review

TY - JOUR

T1 - An adaptive unidirectional linear response fuzzy controller based on reinforcement learning

AU - Tang, Zheng

AU - Komori, Masakazu

AU - Ishizuka, Okihiko

AU - Tanno, Koichi

PY - 1996/2

Y1 - 1996/2

N2 - This paper presents an adaptive fuzzy controller using unidirectional linear response (ULR) elements. The basic functions for a fuzzy controller including membership, minimum and defuzzification functions are realized by the ULR elements. Because the ULR element has diode-like characteristics, it can be implemented by a diode-connected mean-opinion score (MOS) transistor in current-mode implementations. The hardware implementation of the fuzzy controller using ULR elements should also be very simple and straightforward. The ULR fuzzy controller is applied to an inverted pendulum problem, and the effectiveness of the proposed ULR controller architecture and its learning capability based on reinforcement learning are demonstrated.

AB - This paper presents an adaptive fuzzy controller using unidirectional linear response (ULR) elements. The basic functions for a fuzzy controller including membership, minimum and defuzzification functions are realized by the ULR elements. Because the ULR element has diode-like characteristics, it can be implemented by a diode-connected mean-opinion score (MOS) transistor in current-mode implementations. The hardware implementation of the fuzzy controller using ULR elements should also be very simple and straightforward. The ULR fuzzy controller is applied to an inverted pendulum problem, and the effectiveness of the proposed ULR controller architecture and its learning capability based on reinforcement learning are demonstrated.

KW - Adaptive

KW - Fuzzy controller

KW - Reinforcement learning

KW - ULR

UR - http://www.scopus.com/inward/record.url?scp=5244317094&partnerID=8YFLogxK

U2 - 10.1002/ecjc.4430790203

DO - 10.1002/ecjc.4430790203

M3 - 学術論文

AN - SCOPUS:5244317094

SN - 1042-0967

VL - 79

SP - 22

EP - 30

JO - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

JF - Electronics and Communications in Japan, Part III: Fundamental Electronic Science (English translation of Denshi Tsushin Gakkai Ronbunshi)

IS - 2

ER -

An adaptive unidirectional linear response fuzzy controller based on reinforcement learning

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this