Fuzzy Q-learning in continuous state and action space

被引：4

作者：

Xu M.-L. ^{[1
,2
]}

Xu W.-B. ^{[2
]}

机构：

[1] Department of Electronic Information Engineering, Wuxi City College of Vocational Technology

[2] School of Information Technology, Jiangnan University

来源：

Journal of China Universities of Posts and Telecommunications | 2010年 / 17卷 / 04期

基金：

中国国家自然科学基金;

关键词：

adaptation; continuous; FIS; Q-learning;

D O I：

10.1016/S1005-8885(09)60495-7

中图分类号：

学科分类号：

摘要：

An adaptive fuzzy Q-learning (AFQL) based on fuzzy inference systems (FIS) is proposed. The FIS realized by a normalized radial basis function (NRBF) neural network is used to approach Q-value function, whose input is composed of state and action. The rules of FIS are created incrementally according to the novelty of each element of the pair of state-action. Moreover the premise part and consequent part of the FIS are updated using extended Kalman filter (EKF). The action that impacts on environment is the one with maximum output of FIS in the current state and generated through optimization method. Simulation results in the wall-following task of mobile robots and the inverted pendulum balancing problem demonstrate that the superiority and applicability of the proposed AFQL method. © 2010 The Journal of China Universities of Posts and Telecommunications.

引用

页码：100 / 109

页数：9

共 50 条

[41] Double action Q-learning for obstacle avoidance in a dynamically changing environment [J].

Ngai, DCK ;

Yung, NHC .

2005 IEEE Intelligent Vehicles Symposium Proceedings, 2005, :211-216

[42] EBMICQL: Improving Efficiency of Blockchain Miner Pools via Incremental and Continuous Q-Learning Framework [J].

Mulchandani, Mona ;

Nair, Pramod S. S. .

INTERNATIONAL JOURNAL OF IMAGE AND GRAPHICS, 2024, 24 (03)

[43] Learning to Play Pac-Xon with Q-Learning and Two Double Q-Learning Variants [J].

Schilperoort, Jits ;

Mak, Ivar ;

Drugan, Madalina M. ;

Wiering, Marco A. .

2018 IEEE SYMPOSIUM SERIES ON COMPUTATIONAL INTELLIGENCE (IEEE SSCI), 2018, :1151-1158

[44] Switching reinforcement learning for continuous action space [J].

Nagayoshi, Masato ;

Murao, Hajime ;

Tamaki, Hisashi .

ELECTRONICS AND COMMUNICATIONS IN JAPAN, 2012, 95 (03) :37-44

[45] Fuzzy Q-learning obstacle avoidance algorithm of humanoid robot in unknown environment [J].

Wen, Shuhuan ;

Chen, Jianhua ;

Li, Zhen ;

Rad, Ahmad B. ;

Othman, Kamal Mohammed .

2018 37TH CHINESE CONTROL CONFERENCE (CCC), 2018, :5186-5190

[46] Inverse Q-Learning Optimal Control for Takagi-Sugeno Fuzzy Systems [J].

Song, Wenting ;

Ning, Jun ;

Tong, Shaocheng .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2025, 33 (07) :2308-2320

[47] Fuzzy lattices assisted EJAYA Q-learning for automated pulmonary diseases classification [J].

Kukker, Amit ;

Sharma, Rajneesh ;

Pandey, Gaurav ;

Faseehuddin, Mohammad .

BIOMEDICAL PHYSICS & ENGINEERING EXPRESS, 2024, 10 (06)

[48] Hierarchical fuzzy ART for Q-learning and its application in air combat simulation [J].

Zhou Y. ;

Ma Y. ;

Song X. ;

Gong G. .

International Journal of Modeling, Simulation, and Scientific Computing, 2017, 8 (04)

[49] Underestimation estimators to Q-learning [J].

Abliz, Patigul ;

Ying, Shi .

INFORMATION SCIENCES, 2022, 607 :173-185

[50] Adaptive Optimal Control via Q-Learning for Ito Fuzzy Stochastic Nonlinear Continuous-Time Systems With Stackelberg Game [J].

Ming, Zhongyang ;

Zhang, Huaguang ;

Yan, Ying ;

Yang, Liu .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2024, 32 (04) :2029-2038

← 1 2 3 4 5 →