Robot reinforcement learning accuracy-based learning classifier systems with Fuzzy Policy Gradient descent(XCS-FPGRL)

被引：0
|
作者：
Shao, Jie [1 ]
Yu, Jingru [1 ]
机构：
[1] Zhengzhou Chenggong Univ Finance & Econ, Dept Informat Engn, Zhengzhou 451200, Peoples R China
来源：
PROCEEDINGS OF THE INTERNATIONAL CONFERENCE ON ADVANCES IN MECHANICAL ENGINEERING AND INDUSTRIAL INFORMATICS | 2015年 / 15卷
关键词：
Convergence; Rrobot; Reinforcement learning; Accuracy-based learning classifier system with Gradient descent (XCS-FPGRL); XCS (Accuracy-based learning classifier system);
D O I：
暂无
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper presented a novel approach XCS-FPGRL to research on robot reinforcement learning. XCS-FPGRL combines covering operator and genetic algorithm. The systems is responsible for adjusting precision and reducing search space according to some reward obtained from the environment, acts as an innovation discovery component which is responsible for discovering new better reinforcement learning rules. The experiment and simulation showed that robot reinforcement learning can achieved convergence very quickly.
引用
收藏
页码：1013 / 1018
页数：6
相关论文
共 50 条
  • [31] Using policy gradient reinforcement learning on autonomous robot controllers
    Grudic, GZ
    Kumar, V
    Ungar, L
    IROS 2003: PROCEEDINGS OF THE 2003 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, 2003, : 406 - 411
  • [32] Robot behavior adaptation for human-robot interaction based on policy gradient reinforcement learning
    Mitsunaga, N
    Smith, C
    Kanda, T
    Ishiguro, H
    Hagita, N
    2005 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS, VOLS 1-4, 2005, : 1594 - 1601
  • [33] An iterative gradient descent-based reinforcement learning policy for active control of structural vibrations
    Panda, Jagajyoti
    Chopra, Mudit
    Matsagar, Vasant
    Chakraborty, Souvik
    COMPUTERS & STRUCTURES, 2024, 290
  • [34] A policy gradient reinforcement learning algorithm with fuzzy function approximation
    Gu, DB
    Yang, EF
    IEEE ROBIO 2004: Proceedings of the IEEE International Conference on Robotics and Biomimetics, 2004, : 936 - 940
  • [35] Direct gradient-based reinforcement learning for robot behavior learning
    El-Fakdi, Andres
    Carreras, Marc
    Ridao, Pere
    INFORMATICS IN CONTROL, AUTOMATION AND ROBOTICS II, 2007, : 175 - +
  • [36] XCS-based reinforcement learning algorithm for motion planning of a spherical mobile robot
    Roozegar, M.
    Mahjoob, M. J.
    Esfandyari, M. J.
    Panahi, M. Shariat
    APPLIED INTELLIGENCE, 2016, 45 (03) : 736 - 746
  • [37] Robot learning with GA-based fuzzy reinforcement learning agents
    Zhou, CJ
    INFORMATION SCIENCES, 2002, 145 (1-2) : 45 - 68
  • [38] Building anticipations in an accuracy-based learning classifier system by use of an artificial neural network
    O'Hara, T
    Bull, L
    2005 IEEE CONGRESS ON EVOLUTIONARY COMPUTATION, VOLS 1-3, PROCEEDINGS, 2005, : 2046 - 2052
  • [39] XCS-based reinforcement learning algorithm for motion planning of a spherical mobile robot
    M. Roozegar
    M. J. Mahjoob
    M. J. Esfandyari
    M. Shariat Panahi
    Applied Intelligence, 2016, 45 : 736 - 746
  • [40] Natural policy gradient reinforcement learning for a CPG control of a biped robot
    Nakamura, Y
    Mori, T
    Ishii, S
    PARALLEL PROBLEM SOLVING FROM NATURE - PPSN VIII, 2004, 3242 : 972 - 981
12345