Journal of University of Chinese Academy of Sciences >
Reinforcement-Learning-Based On-Line Neural-Fuzzy Control System
Received date: 2004-10-20
Revised date: 2004-11-22
Online published: 2005-09-15
To solve non-training data based on-line learning for neural-fuzzy controller, this paper proposes a reinforcement learning-based neural-fuzzy control system and the corresponding learning algorithm. This control system consists of a neural-fuzzy predictor and a neural-fuzzy controller. Based on fuzzy if then rules with certainty grades,the extended neural-fuzzy network proposed is used as the structure of the neural-fuzzy controller. In learning process of the control system, by using reinforcement signal to estimate the desired output of an input state, reinforcement learning is treated and solved according to training data-based learning algorithm. Computer simulations illustrate the rationality and applicability of the proposed control system and the learning algorithm.
LI Jia-Ning , YI Jian-Qiang , ZHAO Dong-Bin , XI Guang-Cheng . Reinforcement-Learning-Based On-Line Neural-Fuzzy Control System[J]. Journal of University of Chinese Academy of Sciences, 2005 , 22(5) : 631 -638 . DOI: 10.7523/j.issn.2095-6134.2005.5.013
[1] Yan PF.Reinforcement learning —theory,algorithms and applications in intelligent control.Information and Control,1996,25 (1) :28～34 (inChinese with English abstract)
[2] Lin CT,Lee CSG.Reinforcement structurePparameter learning for neural2network2based fuzzy logic control systems.IEEE Transaction on Fuzzy Systems,1994,2 (1) : 46～63
[3] Lin CT,Kan MC.Adaptive fuzzy command acquisition with reinforcement learning.IEEE Transaction on Fuzzy Systems,1998,6 (1) : 102～121
[4] Ye C,Yung NHC,Wang DW.A fuzzy controller with supervised learning assisted reinforcement learning algorithm for obstacle avoidance.IEEETransaction on Systems,Man and Cybernetics2Part B,2003,33 (1) : 17～27
[5] Barto AG,Sutton RS,Anderson CW.Neuronlike adaptive elements that can solve difficult learning control problems.IEEE Transaction on Systems, Man and Cybernetics,1983,13 (5) : 834～846
[6] Ishibuchi H,Nozaki K,Tanaka H.Distributed representation of fuzzy rules and its applications to pattern classification.Fuzzy Sets and Systems,1992,52 (1) : 21～32
[7] Li JN,Yi JQ,Zhao DB.On2line rule generation for robotic behavior controller based on a neural2fuzzy inference network.IEEE InternationalConference on Machine Learning and Cybernetics,2004 : 558～563
[8] Lin CJ,Lin CT.Reinforcement learning for an ART2based fuzzy adaptive learning control network.IEEE Transaction on Neural Network,1996,7(3) : 709～731
[9] Brooks R.A robust layered control systems for a mobile robot.IEEE Transactions on Robotics and Automation,1986,2 (1) : 14～23
[1] 阎平凡.再励学习———原理、算法及其在智能控制中的应用.信息与控制,1996,25 (1) : 28～34
/
| 〈 |
|
〉 |