Adaptive critic control and functional link neural networks
作者： C. Cox , R. Saeks
DOI: 10.1109/ICSMC.1998.728126
关键词:
摘要: An adaptive critic neural control algorithm, employing an analytic relationship between the optimal cost function and law is defined. This approach reduces complexity of by replacing iteration on with solution a nonlinear equation, while simultaneously facilitating development stability robustness criteria. The resultant algorithm can be implemented without priori knowledge plant dynamics, yielding which does not require explicit system identification process. Finally, specialized to linear case where it realized three coupled functional link networks.
sci-hub.se 参考文章(6)
P.E. An, S. Aslam-Mir, M. Brown, C.J. Harris, A reinforcement learning approach to on-line optimal control world congress on computational intelligence. ,vol. 4, pp. 2465- 2471 ,(1994) , 10.1109/ICNN.1994.374607
C. Cox, S. Stepniewski, C. Jorgensen, R. Saeks, C. Lewis, On the design of a neural network autolander International Journal of Robust and Nonlinear Control. ,vol. 9, pp. 1071- 1096 ,(1999) , 10.1002/(SICI)1099-1239(19991215)9:14<1071::AID-RNC453>3.0.CO;2-W
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
R. Zaman, D. Prokhorov, D.C. Wunsch, Adaptive critic design in learning to play game of Go Proceedings of International Conference on Neural Networks (ICNN'97). ,vol. 1, pp. 1- 4 ,(1997) , 10.1109/ICNN.1997.611623
D.V. Prokhorov, L.A. Feldkamp, Primitive adaptive critics Proceedings of International Conference on Neural Networks (ICNN'97). ,vol. 4, pp. 2263- 2267 ,(1997) , 10.1109/ICNN.1997.614396
P.J. Werbos, Backpropagation through time: what it does and how to do it Proceedings of the IEEE. ,vol. 78, pp. 1550- 1560 ,(1990) , 10.1109/5.58337