A Learning Algorithm for the Control of Continuous Action Set-Point Regulator Systems

Journal of Computational Analysis and Applications

Volumn 1, Issue 2, 1999, Pages 121-145

  Esogbue, Augustine O ^a   Hearnes II, Warren E ^a  

^a Georgia Institute of Technology   (United States)

Author keywords

Approximate dynamic programming; Computational complexity; Continuous Action Space algorithm; Nonlinear optimization; Reinforcement learning; Set point regulator problem

Indexed keywords

EID: 0347625319     PISSN: 15211398     EISSN: None     Source Type: Journal    
DOI: 10.1023/A:1022685208277     Document Type: Article

References (21)

1. A. G. Barto, S. J. Bradtke, and S. P. Singh, Learning to act using real-time dynamic programming, Artificial Intelligence 72(1-2), 81-138 (1995).
2. A. G. Barto, R. S. Sutton, and C. W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems, IEEE Trans. Systems, Man, Cybernetics 13, 834-846 (1983).
3. H. R. Berenji and P. Khedkar. Learning and tuning fuzzy logic controllers through reinforcements, IEEE Trans. Neural Networks 3, 724-740 (1992).
4. D. P. Bertsekas and J. N. Tsitsiklis, Neuro-Dynamic Programming, Athena Scientific, Belmont, MA, 1996.
5. S.-J. Cheng, Y. S. Chow, O. P. Malik, and G. S. Hope, An adaptive synchronous machine stabilizer, IEEE Trans. Power Systems 1, 101-107 (1986).
6. S.-J. Cheng, O. P. Malik, and G. S. Hope, Self-tuning stabilizer for a multimachine power system, IEEE Proc. 133-C, 176-185 (1986).
7. S. E. Dreyfus and A. M. Law, The Art and Theory of Dynamic Programming, Academic Press, New York, 1977.
8. A. O. Esogbue and W. E. Hearnes, Approximate policy improvement for continuous action set-point regulation problems. Proc. 1998 World Congr. Computational Intelligence, pp. 1692-1697, Anchorage, AK, May 4-9, 1998.
9. A. O. Esogbue and J. A. Murrell, A fuzzy adaptive controller using reinforcement learning neural networks, Proc. 2nd IEEE Intern. Conf. Fuzzy Systems, pp. 178-183, March 28-April 1, 1993.
10. A. O. Esogbue, Q. Song, and W. E. Hearnes, Application of a self-learning fuzzy-neuro controller to the power system stabilization problem, Proc. 1995 World Congr. Neural Networks, Vol. II, pp. 699-702, Washington, DC, July 17-21, 1995.
11. A. O. Esogbue, Q. Song and W. E. Hearnes, Defuzzification filters and applications to power stabilization problems, Proc. 1996 IEEE Intern. Conf. Systems, Man, Cybernetics Inform. Intelligence Systems, Beijing, China, October 14-17, 1996.
12. Y.-Y. Hsu and C.-Y. Hsu, Design of a proportional-integral power system stabilizer, IEEE Trans. Power Systems 1, 46-53 (1986).
13. F. Kirchner, Q-learning of complex behaviors on a six-legged walking machine, Proc. 2nd EUROMICRO Workshop Adv. Mobile Robots, Brescia, Italy, October 22-24, 1997.
14. T. Miller, III, R. S. Sutton, and P. J. Werbos, eds., Neural Networks for Control, MIT Press, Cambridge, MA, 1990.
15. J. A. Murrell, A Statistical Fuzzy Associative Learning Approach to Intelligent Control. PhD thesis, School of Industrial and Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 1993.
16. D. L. Pepyne, Application of Q-learning to elevator dispatching. Proc. 13th World Congr. Vol. J: Identification II, Discrete Event Systems, pp. 317-322, San Francisco, CA, June 30-July 5, 1996.
17. S. Ross, Introduction to Stochastic Dynamic Programming, Academic Press, San Diego, CA, 1983.
18. J. Shi, L. H. Herron, and A. Kalam, A fuzzy logic controller applied to power system stabilizer for a synchronous machine power system, Proc. IEEE Region 10 Conf. Tencon 92, Melbourne, Australia, November 11-13, 1992.
19. R. S. Sutton, Learning to predict by the method of temporal differences. Machine Learning 3, 9-44 (1988).
20. C. J. C. H. Watkins, Learning from Delayed Rewards, PhD thesis, Cambridge University, England, 1989.
21. C. J. C. H. Watkins and P. Dayan, Q-learning, Machine Learning 8, 279-292 (1992).