Browse > Article
http://dx.doi.org/10.5391/JKIIS.2003.13.6.635

Function Approximation for accelerating learning speed in Reinforcement Learning  

Lee, Young-Ah (경희대학교 컴퓨터공학과)
Chung, Tae-Choong (경희대학교 컴퓨터공학과)
Publication Information
Journal of the Korean Institute of Intelligent Systems / v.13, no.6, 2003 , pp. 635-642 More about this Journal
Abstract
Reinforcement learning got successful results in a lot of applications such as control and scheduling. Various function approximation methods have been studied in order to improve the learning speed and to solve the shortage of storage in the standard reinforcement learning algorithm of Q-Learning. Most function approximation methods remove some special quality of reinforcement learning and need prior knowledge and preprocessing. Fuzzy Q-Learning needs preprocessing to define fuzzy variables and Local Weighted Regression uses training examples. In this paper, we propose a function approximation method, Fuzzy Q-Map that is based on on-line fuzzy clustering. Fuzzy Q-Map classifies a query state and predicts a suitable action according to the membership degree. We applied the Fuzzy Q-Map, CMAC and LWR to the mountain car problem. Fuzzy Q-Map reached the optimal prediction rate faster than CMAC and the lower prediction rate was seen than LWR that uses training example.
Keywords
Q-learning; CMAC; LWR;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Juan Carlos Santamaria, Richard S. Sutton, Ashwin Ram, "Experiments with Reinforcement Learning in Problems with Continuous State and Action Spaces", COINS Technical Report 96-88, December 1996.
2 William D. Smart, Leslie Pack Kaelbling, "Reinforcement Learning for Robot Control", In "Mobile Robots XVI", 2001.
3 Chris Gaskett, David Wettergreen, and Alexander Zelinsky, "Q learning in continuous state and action spaces", Australian Joint Conference on Artificial Intelligence 1999.
4 Andrea Bonarini, "Delayed Reinforcement, Fuzzy Q-Iearning and Fuzzy Logic Controllers", In Herrera, F., Verdegay, J. L. (Eds.) Genetic Algorithms and Soft Computing, (Studies in Fuzziness, 8), Physica-Verlag, Berlin, D, 447-466.
5 Lionel Jouffe, "Fuzzy Inference System Learning by Reinforcement Methods", Ieee Transactions on System, Man and Cybernetics, vol.98, no 3, August,1998.
6 William D. Smart, Leslie Pack Kaelbling, "Practical Reinforcement Learning in Continuous Spaces", Proceedings of the sixteenth International Conference on Machine Learning, 2000.
7 Stephan ten Hagen and Ben Krose, "Q learning for System with continuous state and action spaces", BENELEARN 2000, 10th Belgian-Dutch conference on Machine Learning.
8 정석일, 이연정, "분포 기여도를 이용한 퍼지 Q-learning", 퍼지 및 지능시스템학회 논문지 2001, Vol. 11, No.5 pp.388-394.   과학기술학회마을
9 Richard S. Sutton, Andrew G. Barto "Reinforcement Learning: An Introduction". The MIT Press, Cambridge, MA., 1998.
10 Pierre Yves Glorennec, Lionel Jouffe, "Fuzzy Q-Iearning", Proceedings of Fuzz-Ieee'97, Sixth International Conference on Fuzzy Systems, P719-724, Barcelona, july,1997.
11 Jan Jantzen, "Neurofuzzy Modelling", Technical Report, Technical University of Denmark 1998.
12 전효병,이동욱,김대준,심귀보, "퍼지추론에 의한 리커런트 뉴럴 네트워크 강화학습", 한국퍼지 및 지능 시스템 학회 '97년도 춘계학술대회 논문집.
13 Artistidis Likas, "A Reinforcement Learning: Approach to On-Line Clustering", Neural Computation, vol. 11, no. 8, pp. 1915-1932, 1999.   DOI   ScienceOn
14 William Donald Smart, "Making Reinforcement Learning Work on Real Robots", Ph D Thesis, Department of Computer Science, Brown University, 2002.