Genetic Takagi-Sugeno fuzzy reinforcement learning

被引：5

作者：

Yan, XW ^{[1
]}

Deng, ZD ^{[1
]}

Sun, ZQ ^{[1
]}

机构：

[1] Tsing Hua Univ, State Key Lab Intelligent Technol & Syst, Beijing 100084, Peoples R China

来源：

PROCEEDINGS OF THE 2001 IEEE INTERNATIONAL SYMPOSIUM ON INTELLIGENT CONTROL (ISIC'01) | 2001年

关键词：

reinforcement learning; genetic algorithms; Takagi-Sugeno fuzzy inference systems; neuro-fuzzy control;

D O I：

10.1109/ISIC.2001.971486

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper presents two fuzzy reinforcement learning methods for solving complicated learning tasks of continuous domains. Takagi-Sugeno fuzzy reinforcement learning (TSFRL) is constructed by combining Takagi-Sugeno type fuzzy inference systems with Q-learning. Next, genetic Takagi-Sugeno fuzzy reinforcement learning (GTSFRL) is introduced by embedding TSFRL into genetic algorithms. Both proposed learning algorithms can also be used to design Takagi-Sugeno fuzzy logic controllers. Experiments on the double inverted pendulum system demonstrate the performance and applicability of the proposed schemes. Finally, the conclusion remark is drawn.

引用

页码：67 / 72

页数：6

共 50 条

[31] Genetic learning of fuzzy controllers
Dumitrache, I
Buiu, C
[J]. MATHEMATICS AND COMPUTERS IN SIMULATION, 1999, 49 (1-2) : 13 - 26
[32] NeuroCrossover: An intelligent genetic locus selection scheme for genetic algorithm using reinforcement learning
Liu, Haoqiang
Zong, Zefang
Li, Yong
Jin, Depeng
[J]. APPLIED SOFT COMPUTING, 2023, 146
[33] Neuro-fuzzy gait synthesis with reinforcement learning for a biped walking robot
Zhou C.
[J]. Soft Computing, 2000, 4 (04) : 238 - 250
[34] Combining reinforcement learning and genetic algorithms to learn behaviours in mobile robotics
Iglesias, R.
Rodriguez, M.
Regueiro, C. V.
Correa, J.
Barro, S.
[J]. ICINCO 2006: PROCEEDINGS OF THE THIRD INTERNATIONAL CONFERENCE ON INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS: ROBOTICS AND AUTOMATION, 2006, : 188 - 195
[35] Evolving Heterotic Gauge Backgrounds: Genetic Algorithms versus Reinforcement Learning
Abel, Steven
Constantin, Andrei
Harvey, Thomas R.
Lukas, Andre
[J]. FORTSCHRITTE DER PHYSIK-PROGRESS OF PHYSICS, 2022, 70 (05):
[36] Reinforcement Learning in Continuous Spaces by Using Learning Fuzzy Classifier Systems
Chen, Gang
Douch, Colin
Zhang, Mengjie
Pang, Shaoning
[J]. NEURAL INFORMATION PROCESSING, PT II, 2015, 9490 : 320 - 328
[37] A New Reinforcement Learning Method for Fuzzy Logic Controllers
王直杰
方建安
邵世煌
[J]. Journal of China Textile University(English Edition), 1998, (02) : 42 - 45
[38] Knowledge acquisition for a soccer agent by fuzzy reinforcement learning
Nakashima, T
Udo, M
Ishibuchi, H
[J]. 2003 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN AND CYBERNETICS, VOLS 1-5, CONFERENCE PROCEEDINGS, 2003, : 4256 - 4261
[39] A Fuzzy RANSAC Algorithm Based on Reinforcement Learning Concept
Watanabe, Toshihiko
[J]. 2013 IEEE INTERNATIONAL CONFERENCE ON FUZZY SYSTEMS (FUZZ - IEEE 2013), 2013,
[40] A Reinforcement Learning Adaptive Fuzzy Controller for Differential Games
Sidney N. Givigi
Howard M. Schwartz
Xiaosong Lu
[J]. Journal of Intelligent and Robotic Systems, 2010, 59 : 3 - 30

← 1 2 3 4 5 →