摘要: This paper proposes an adaptation of Watkins' Q-learning (1989, 1992) for fuzzy inference systems where both the actions and Q-functions are inferred from rules. approach is compared with genetic algorithm on cart-centering problem, showing its effectiveness.
sci-hub.se 参考文章(17)
Christopher J. C. H. Watkins, Peter Dayan, Technical Note : \cal Q -Learning Machine Learning. ,vol. 8, pp. 279- 292 ,(1992) , 10.1007/BF00992698
Steven D. Whitehead, A complexity analysis of cooperative mechanisms in reinforcement learning national conference on artificial intelligence. pp. 607- 613 ,(1991)
R. Andrew McCallum, Using Transitional Proximity for Faster Reinforcement Learning international conference on machine learning. pp. 316- 321 ,(1992) , 10.1016/B978-1-55860-247-2.50045-0
Jeffery A. Clouse, Paul E. Utgoff, A Teaching Method for Reinforcement Learning international conference on machine learning. pp. 92- 101 ,(1992) , 10.1016/B978-1-55860-247-2.50017-6
Long-Ji Lin, Self-improvement Based On Reinforcement Learning, Planning and Teaching Machine Learning Proceedings 1991. pp. 323- 327 ,(1991) , 10.1016/B978-1-55860-200-7.50067-2
Christopher J.C.H. Watkins, Peter Dayan, Technical Note Q-Learning Machine Learning. ,vol. 8, pp. 279- 292 ,(1992) , 10.1023/A:1022676722315
H.R. Berenji, Fuzzy Q-learning for generalization of reinforcement learning Proceedings of IEEE 5th International Fuzzy Systems. ,vol. 3, pp. 2208- 2214 ,(1996) , 10.1109/FUZZY.1996.553542
Claude F. Touzet, Neural reinforcement learning for behaviour synthesis Robotics and Autonomous Systems. ,vol. 22, pp. 251- 281 ,(1997) , 10.1016/S0921-8890(97)00042-0
Andrew G. Barto, Richard S. Sutton, Charles W. Anderson, Neuronlike adaptive elements that can solve difficult learning control problems systems man and cybernetics. ,vol. 13, pp. 834- 846 ,(1983) , 10.1109/TSMC.1983.6313077
Richard S. Sutton, Learning to Predict by the Methods of Temporal Differences Machine Learning. ,vol. 3, pp. 9- 44 ,(1988) , 10.1023/A:1022633531479