GENETIC REINFORCEMENT LEARNING OF FUZZY INFERENCE SYSTEM APPLICATION TO MOBILE ROBOTIC

Abdelkrim Nemra, Hacene Rezine, Abdelkrim Souici

2007

Abstract

An efficient genetic reinforcement learning algorithm for designing Fuzzy Inference System (FIS) with out any priory knowledge is proposed in this paper. Reinforcement learning using Fuzzy Q-Learning (FQL) is applied to select the consequent action values of a fuzzy inference system, in this method, the consequent value is selected from a predefined value set which is kept unchanged during learning and if the optimal solution is not present in the randomly generated set, then the performance may be poor. Also genetic algorithms (Genetic Algorithm) are performed to on line search for better consequent and premises parameters based on the learned Q-values as adaptation function. In Fuzzy-Q-Learning Genetic Algorithm (FQLGA), memberships (premises) parameters are distributed equidistant and the consequent parts of fuzzy rules are randomly generated. The algorithm is validated in simulation and experimentation on mobile robot reactive navigation behaviors.

References

  1. L. Jouffe, “Actor-Critic Learning Based on Fuzzy Inference System”, Proc of the IEEE International Conference on Systems, Man and Cybernetics. Beijing, China, pp.339-344, 1996.
  2. C.Watkins, P. Dayan: “Q-Learning Machine Learning”, pp.279-292, 1992.
  3. P. Y. Glorennec and L. Jouffe, “Fuzzy Q-learning,” Proc. Of IEEE Int. Con On Fuzzy Systems, pp. 659-662, 1997
  4. Dongbing Gu, Huosheng Hu, Libor Spacek “ Learning Fuzzy Logic Controller for Reactive Robot Behaviours” Proc. of IEEE/ASME International Conference on Advanced Japan, pp.20-24 July, 2003.
  5. A. Souici : “Apprentissage par Renforcement des Systèmes d'inférence Floue par des Méthodes par renforcement application à la navigation réactive d'un robot mobile”, Thèse de Magistère, Ecole Militaire Polytechnique, Janvier 2005.
  6. Chia-Feng Juang “ Combination of online Clustering and Q-Value Based GA for Reinforcement Fuzzy System Design” IEEE Transactions On Systems, Man, And Cybernetics Vol. 13, N°. 3, pp.289-302, June 2005
  7. Min-Soeng Kim and Kim and Ju-Jang Lee. “Constructing a Fuzzy Logic ControllerUsing Evolutionary QLearning” IEEE. pp.1785-1790, 2000
  8. Chia-Feng Juang and Chun-Feng Lu. Combination of Online Clustering and Q-value Based Genetic Reinforcement Learning For Fuzzy Network Design 0- 7803-7898-9/03/$17.00 0 2003 IEEE.
  9. David Goldberg “Algorithme génétique Exploration, optimisation et apprentissage automatique”» Edition Addison-Wesley, France 1994.
Download


Paper Citation


in Harvard Style

Nemra A., Rezine H. and Souici A. (2007). GENETIC REINFORCEMENT LEARNING OF FUZZY INFERENCE SYSTEM APPLICATION TO MOBILE ROBOTIC . In Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO, ISBN 978-972-8865-82-5, pages 206-213. DOI: 10.5220/0001645902060213


in Bibtex Style

@conference{icinco07,
author={Abdelkrim Nemra and Hacene Rezine and Abdelkrim Souici},
title={GENETIC REINFORCEMENT LEARNING OF FUZZY INFERENCE SYSTEM APPLICATION TO MOBILE ROBOTIC},
booktitle={Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,},
year={2007},
pages={206-213},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0001645902060213},
isbn={978-972-8865-82-5},
}


in EndNote Style

TY - CONF
JO - Proceedings of the Fourth International Conference on Informatics in Control, Automation and Robotics - Volume 1: ICINCO,
TI - GENETIC REINFORCEMENT LEARNING OF FUZZY INFERENCE SYSTEM APPLICATION TO MOBILE ROBOTIC
SN - 978-972-8865-82-5
AU - Nemra A.
AU - Rezine H.
AU - Souici A.
PY - 2007
SP - 206
EP - 213
DO - 10.5220/0001645902060213