Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지

Automatic Fuzzy Rule Generation Using Neural Networks Based Reinforcement Larning

신경망의 보상학습기능을 이용한 퍼지규칙의 자동생성기법

  • Published : 1998.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

본 논문에서는 보상 신호를 이용하는 근사 추론에 기반한 개선된 퍼지 논리 제어기를 제안한다. 제안된 방법은 근사 추론을 위한 인위적인 퍼지 규칙의 생성이나 소속함수의 정의 없이 자동적으로 퍼지 논리 제어기를 구성할 수 있다. 제안된 퍼지 논리 제어기를 cart-pole 제어에 적용하여 기존의 방법들과의 비교를 통해 제시한 방법의 유용성을 검증한다.

Keywords

References

  1. IEEE Control Systems Acquiring robot skills via reinforcement learning V.Gullapalli;J.A.Franklin;H.Benbrahim
  2. IEEE Trans.on Computers v.40 no.12 Neural-network-based fuzzy logic control and decision system C.T.Lin;C.S.George Lee
  3. IEEE Trans.Syst.Man,Cynern. v.SMC-13 no.5 Neuronlike adaptive elements that can solve difficult learning control problems A.G.Barto;R.S.Sutton;C.W.Anderson
  4. Int.J.Intelligent System v.5 no.3 A Selt-learning rule-based controller employing approximate reasoning and neural net concepts C.C.Lee
  5. Beyond regression:New tools for prediction and analysis in the behavior science P.Werbos
  6. IEEE Trans.on Neural Networks v.3 no.5 Self-learning fuzzy controllers based on temporal back propagation J.R.Jang
  7. An Introduction to Fuzzy Logic Applications in Intelligent Systems Fuzzy Logic controllers H.R.Berenji;R.R.Yager(ed.);L.A.Zadeh(ed.)
  8. IEEE Control Syst.Mag v.8 no.5 Use of rule-based system for process control J.A.Bernard
  9. Proc.Int.Congress Transportation Electronics Electronically controlled continuously variable transmission Y.Kasai;Y.Morimoto
  10. Automatica v.15 no.1 A linguistic self organizing process controller T.J.Procyk;E.H.Mamdani
  11. Proc.IEEE.Int.Symp.Intelligent Control An intelligent controller based on approximate reasoning and reinforcement learning C.C.Lee;H.R.Berenji
  12. Machine Learning v.3 Learning to predict by the methods of temporal differences R.S.Sutton
  13. Neural Computation v.1 Fast learning in neural networks of locally-tuned processing units J.Moody;C.J.Darken
  14. Temporal credit assignment in reinforcement learning R.S.Sutton
  15. IEEE Trans.on Neural Networks v.3 no.5 Learning and tuning fuzzy logic controllers through reinforcements H.R.Beremji
  16. IEEE Trans.Syst.Man,Cybern. v.SMC-13 Neuronlike adaptive elements that can solve difficult learning control problems A.G.Barto;R.S.Sutton;C.W.Anderson