Using fuzzy logic for performance evaluation in Reinforcement Learning

International Journal of Approximate Reasoning

Volumn 18, Issue 1-2, 1998, Pages 131-144

  Berenji, Hamid R ^a   Khedkar, Pratap S ^b  

^a NASA AMES RESEARCH CENTER   (United States)

^b GE GLOBAL RESEARCH   (United States)

Author keywords

Action evaluation; Adaptive critic; Fuzzy control; Intelligent control; Neural networks; Reinforcement learning

Indexed keywords

EID: 0012643156     PISSN: 0888613X     EISSN: None     Source Type: Journal    
DOI: 10.1016/S0888-613X(97)10007-X     Document Type: Article

References (16)

1. R.S. Sutton, A.G. Barto, Introduction to Reinforcement Learning, MIT Press/Bradford Books, Cambridge, MA, 1998.
2. H.R. Berenji, P. Khedkar, Learning and tuning fuzzy logic controllers through reinforcements, IEEE Transactions on Neural Networks 3 (5) (1992) 724-740.
3. H.R. Berenji, Fuzzy logic controllers, in: R.R. Yager, L.A. Zadeh (Eds.), An Introduction of Fuzzy Logic Applications in Intelligent Systems, Kluwer Academic Publishers. Hingham, MA, 1991, pp. 69-96.
4. C.W. Anderson, Learning to control an inverted pendulum using neural networks, IEEE Control Systems Magazine 9 (3) (1989) 31-37.
5. H.R. Berenji, Neuro-fuzzy systems, in: W. Pedrycz, E. Ruspini, P. Bonissone (Eds.), Handbook of Fuzzy Computation, Oxford University Press, Oxford, 1997.
6. J.S. Jang, Adaptive Neural Network-based Fuzzy Inference Systems, IEEE Transactions on Systems, Man, and Cybernetics 23 (3) (1993) 665-685.
7. J.-S.R. Jang, C.-T. Sun, E. Mizutani, Neuro-Fuzzy and Soft Computing, Prentice-Hall, Englewood Cliffs, NJ, 1997.
8. T. Takagi, M. Sugeno, Derivation of fuzzy control rules from human operator's control actions, in: IFAC Symposium on Fuzzy Information, Knowledge Representation and Decision Analysis, Marseille, France, 1983, pp. 55-60.
9. H.R. Berenji, P.S. Khedkar, A. Malkani, Refining linear fuzzy rules by reinforcement learning, Fifth IEEE International conference on Fuzzy Systems, New Orleans, Louisiana, September 1996.
10. H.R. Berenji, P. Khedkar, Clustering in product space for fuzzy inference. Second International conference on Fuzzy Systems, San Francisco, CA, March 1993.
11. C.T. Lin, C.S.G. Lee, Reinforcement structure/parameter learning for neural-network-based fuzzy logic control systems, IEEE Transactions on Fuzzy Systems 2 (1) (1994) 46-63.
12. C.T. Lin, C.S.G Lee, Real-time Supervised structure/parameter learning for fuzzy neural network, IEEE International conference on Fuzzy Systems, San Diego, CA, March 1992, pp. 1283-1290.
13. M. Mohammadi, C. Lucas, Extending neuro-fuzzy reinforcement learning for inverted pendulum, Technical report, University of Tehran, Electrical Engineering Department, Master of Science Thesis, 1994.
14. H.R. Berenji, Y.Y. Chen, C.C. Lee, S. Murugesan, J.S. Jang, An experiment-based comparative study of fuzzy logic control, American Control Conference, Pittsburgh, 1989.
15. H.R. Berenji, Y.Y. Chen, C.C. Lee, J.S. Jang, S. Murugesan, A hierarchical approach to designing approximate reasoning-based controllers for dynamic physical systems, in: P.P. Bonissone, M. Henrion, L.N. Kanal, J. Lemmer (Eds.), Uncertainty in Artificial Intelligence, vol. VI, Series Machine Intelligence and Pattern Recognition, Elsevier, Amsterdam, 1991. pp. 331-343.
16. B. Kosko, Neural Networks and Fuzzy Systems, Prentice-Hall, Englewood Cliffs, NJ, 1992.