Embedding fuzzy mechanisms and knowledge in box-type reinforcement learning controllers

IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics

Volumn 32, Issue 5, 2002, Pages 645-653

  Su, Shun Feng ^a,b   Hsieh, Sheng Hsiung ^b  

^a IEEE   (Taiwan)

^b NATIONAL TAIWAN UNIVERSITY OF SCIENCE AND TECHNOLOGY   (Taiwan)

Author keywords

Fuzzy; Knowledge embedding; Makarovic's rules; Reinforcement learning

Indexed keywords

FUZZY MECHANISMS; KNOWLEDGE EMBEDDING; MAKAROVIC RULE; NONFUZZY LEARNING CONTROL; REINFORCEMENT LEARNING CONTROLLERS;

COMPUTER SIMULATION; EMBEDDED SYSTEMS; FUZZY CONTROL; FUZZY SETS; KNOWLEDGE BASED SYSTEMS; LEARNING ALGORITHMS; VARIATIONAL TECHNIQUES;

LEARNING SYSTEMS;

EID: 0036791564     PISSN: 10834419     EISSN: None     Source Type: Journal    
DOI: 10.1109/TSMCB.2002.1033183     Document Type: Article

References (25)

1. M. M. Kokar, "Learning control methods, needs, and architectures," in An Introduction to Intelligent and Autonomous Control. Boston, MA: Kluwer, 1992.
2. C. T. Lin and C. S. G. Lee, Neural Fuzzy System: A Neuro-Fuzzy Synergism to Intelligent Systems. Englewood Cliffs, NJ: Prentice-Hall, 1996.
3. M. L. Minsky, "Steps toward artificial intelligence," Proc. IRE, vol. 49, pp. 8-30, 1961.
4. M. D. Waltz and K. S. Fu, "A heuristic approach to reinforcement learning control systems," IEEE Trans. Automat. Contr., vol. AC-10, pp. 390-398, Mar. 1965.
5. A. L. Samuel, "Some studies in machine learning using the game of checkers," IBM J. Res. Develop., vol. 3, pp. 210-229, 1959.
6. A. G. Barto, R. S. Sutton, and C. W. Anderson, "Neuronlike adaptive elements that can solve difficult learning control problems," IEEE Trans. Syst., Man, Cybern., vol. SMC-13, pp. 834-846, Sept./Oct. 1983.
7. C. W. Anderson, "Learning to control an inverted pendulum using neural network," IEEE Control Syst. Mag., pp. 31-36, Apr. 1989.
8. C. C. Lee, "Self-learning rule-based controller employing approximate reasoning and neural-net concepts," Int. J. Intell. Syst., vol. 6, pp. 71-93, 1991.
9. S.-F. Su, S.-H. Hsieh, and C.-C. Chuang, "On the study of embedding fuzzy concept in reinforcement learning," J. Chin. Inst. Eng., vol. 24, no. 3, pp. 357-368, 2001.
10. C. T. Lin and C. S. G. Lee, "Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems," IEEE Trans. Fuzzy Syst., vol. 2, pp. 46-63, Feb. 1994.
11. H. R. Berenji and P. Khedkar, "Learning and tuning fuzzy logic controllers through reinforcements," IEEE Trans. Neural Networks, vol. 3, pp. 724-740, Sept. 1992.
12. Y. Takahashi and M. Asada, "Behavior acquisition by multilayered reinforcement learning," in Proc. IEEE SMC Conf., vol. 6, 1999, pp. 716-721.
13. R. Schoknecht and M. Riedmiller, "Using reinforcement learning for engine control," in Proc. ICANN, vol. 1, 1999, pp. 329-334.
14. R. Sun and T. Peterson, "Partitioning in reinforcement learning," in Proc. IJCNN, vol. 4, 1999, pp. 2259-2264.
15. O. Grigore, "Reinforcement learning neural network used in control of nonlinear systems," in Proc. IEEE ICIT, vol. 1, 2000, pp. 662-665.
16. C.-T. Lin and C.-P. Jou, "GA-based fuzzy reinforcement learning for control of a magnetic bearing system," IEEE Trans. Syst., Man, Cybern. B., vol. 30, no. 2, pp. 276-289, 2000.
17. R. S. Sutton, "Learning to predict by the methods of temporal differences," Mach. Learn., vol. 3, pp. 9-44, 1988.
18. S.-H. Hsieh, "On the study of embedding fuzzy concept and prior knowledge in reinforcement learning," M.S. thesis, Dept. Elect. Eng., National Taiwan University of Science and Technology, Taiwan, R.O.C., 1997.
19. P. L. Kim, "Analysis and study of neural-networks-based reinforcement learning," M.S. thesis, Dept. Elect. Eng., Nat. Taiwan Univ. Sci. Technol., Taipei, Taiwan, R.O.C., 1995.
20. T. Takagi and M. Sugeno, "Fuzzy identification of system and its applications to modeling and control," IEEE Trans. Syst., Man, Cybern., vol. SMC-15, no. 1, pp. 116-132, 1985.
21. M. Mizumoto, "Realization of PID controls by fuzzy control methods," in Proc. 1st IEEE CFS, San Diego, CA, 1992, pp. 709-715.
22. R. R. Yager and D. P. Filev, Essentials of Fuzzy Modeling and Control. New York: Wiley, 1994.
23. J. S. R. Jang, C.-T. Sun, and E. Mizutani, Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Intelligence, ser. NJ. Englewood Cliffs: Prentice-Hall, 1997.
24. C. C. Lee, "Modeling behavioral substates of associative learning and memory: Adaptive neural models," IEEE Trans. Syst., Man, Cybern., vol. 21, no. 3, pp. 510-520, 1991.
25. A. Makarovic, "A qualitative way of solving the pole balancing problem," Univ. Twente, Twente, The Netherlands, Memo. Inf-88-44, 1988.