Q learning based on self-organizing fuzzy radial basis function network

被引:0
|
作者
Wang, Xuesong [1 ]
Cheng, Yuhu [1 ]
Sun, Wei [1 ]
机构
[1] China Univ Min & Technol, Sch Informat & Elect Engn, Jiangsu 221008, Peoples R China
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
A fuzzy Q learning based on a self-organizing fuzzy radial basis function (FRBF) network is proposed to solve the 'Curse of dimensionality' problem caused by state space generalization in the paper. A FRBF network is used to represent continuous action and the corresponding Q value. The interpolation technique is adopted to represent the appropriate utility value for the wining local action of every fuzzy rule. Neurons can be organized by the FRBF network itself. The methods of the structure and parameter learning. based on new adding and merging neurons techniques and a gradient descent algorithm, are simple and effective, with a high accuracy and a compact structure. Simulation results on balancing control of inverted pendulum illustrate the performance and applicability of the proposed fuzz), Q learning scheme to real-world problems with continuous states and continuous actions.
引用
收藏
页码:607 / 615
页数:9
相关论文
共 50 条
  • [1] Research on an online self-organizing radial basis function neural network
    Han, Honggui
    Chen, Qili
    Qiao, Junfei
    [J]. NEURAL COMPUTING & APPLICATIONS, 2010, 19 (05): : 667 - 676
  • [2] Self-organizing radial basis function network modeling for robot manipulator
    Kim, D
    Huh, SH
    Seo, SJ
    Park, GT
    [J]. INNOVATIONS IN APPLIED ARTIFICIAL INTELLIGENCE, 2005, 3533 : 579 - 587
  • [3] Research on an online self-organizing radial basis function neural network
    Honggui Han
    Qili Chen
    Junfei Qiao
    [J]. Neural Computing and Applications, 2010, 19 : 667 - 676
  • [4] Self-organizing design of radial basis function neural network based on neuron characteristics
    基于神经元特性的径向基函数神经网络自组织设计方法
    [J]. Qiao, Jun-Fei (junfeiq@bjut.edu.cn), 1600, South China University of Technology (37): : 2618 - 2626
  • [5] SELF-ORGANIZING FUZZY RADIAL BASIS FUNCTION NEURAL-NETWORK CONTROLLER FOR ROBOTIC MOTION CONTROL
    Lian, Ruey-Jing
    Huang, Chung-Neng
    [J]. INTERNATIONAL JOURNAL OF INNOVATIVE COMPUTING INFORMATION AND CONTROL, 2012, 8 (3A): : 1955 - 1971
  • [6] Self-organizing fuzzy radial basis function neural-network controller for robotic motion control
    Department of Management and Information Technology, Vanung University, No. 1, Wanneng Rd., Jhongli City, Toayuan County 32061, Taiwan
    不详
    [J]. Int. J. Innov. Comput. Inf. Control, 2012, 3 A (1955-1971):
  • [7] Using Self-organizing Incremental Neural Network (SOINN) For Radial Basis Function Networks
    Lu, Jie
    Shen, Furao
    Zhao, Jinxi
    [J]. PROCEEDINGS OF THE 2014 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2014, : 2142 - 2148
  • [8] Self-organizing radial basis function neural network using accelerated second-order learning algorithm
    Han, Hong-Gui
    Ma, Miao-Li
    Yang, Hong-Yan
    Qiao, Jun-Fei
    [J]. NEUROCOMPUTING, 2022, 469 : 1 - 12
  • [9] Probabilistic self-organizing map and radial basis function networks
    Anouar, F
    Badran, F
    Thiria, S
    [J]. NEUROCOMPUTING, 1998, 20 (1-3) : 83 - 96
  • [10] Time series forecasting by combining the radial basis function network and the self-organizing map
    Lin, GF
    Chen, LH
    [J]. HYDROLOGICAL PROCESSES, 2005, 19 (10) : 1925 - 1937