This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Hierarchical Discretized Pursuit Nonlinear Learning Automata with Rapid Convergence and High Accuracy
August 1994 (vol. 6 no. 4)
pp. 654-659

A new absorbing multiaction learning automaton that is epsilon-optimal is introduced. It is a hierarchical discretized pursuit nonlinear learning automaton that uses a new algorithm for positioning the actions on the leaves of the hierarchical tree. The proposed automaton achieves the highest performance (speed of convergence, central processing unit (CPU) time, and accuracy) among all the absorbing learning automata reported in the literature up to now. Extensive simulation results indicate the superiority of the proposed scheme. Furthermore, it is proved that the proposed automaton is epsilon-optimal in every stationary stochastic environment.

[1] M. A. L. Thathachar and B. J. Oommen, "Discretized reward inaction learning automata,"J. Cybernetics Inform. Sci., pp. 24-29, Spring 1979.
[2] B. J. Oommen, "Absorbing and ergodic discretized two action learning automata,"IEEE Trans. Syst., Man, Cybern., pp. 282-293, 1986.
[3] B. J. Oommen and J. P. R. Christensen, "Epsilon-optimal discretized linear reward-penalty learning automata,"IEEE Trans. Syst., Man, Cybernetics, vol. SMC-18, no. 3, pp. 451-458, May/June 1988.
[4] M. A. L. Thathachar and K. R. Ramakrishnan, "A hierarchical system of learning automata,"IEEE Trans. Syst., Man, Cybernetics, vol. SMC-11, no. 3, pp. 236-241, Mar. 1981.
[5] M. A. L. Thathachar and P. S. Sastry, "A hierarchical system of learning automata that can learn the globally optimal path,"Inform. Sci., vol. 42, pp. 143-166, July 1987.
[6] K. S. Narendra,Learning Automata: An Introduction. Englewood Cliffs, NJ: Prentice-Hall, 1989.
[7] B. J. Oommen and J. K. Lanctot, "Discretized pursuit learning automata,"IEEE Trans. Syst., Man, Cybernetics, vol. SMC-20, no. 4, pp. 931-938, July/Aug. 1990.
[8] M. A. L. Thathachar and P. S. Sastry, "A new approach to the design of reinforcement schemes for learning automata,"IEEE Trans. Syst., Man, Cybernetics, vol. SMC-15, no. 1, pp. 168-175, Jan./Feb. 1985.
[9] H. G. Tucker,A Graduate Course in Probability. New York: Academic Press, 1967.

Index Terms:
finite automata; unsupervised learning; nonlinear systems; convergence; hierarchical systems; rapid convergence; absorbing multiaction learning automaton; discretized pursuit nonlinear learning automata; hierarchical tree; stationary stochastic environment; pursuit learning; nonlinear output function; epsilon-optimal learning; positioning algorithm
Citation:
G.I. Papadimitriou, "Hierarchical Discretized Pursuit Nonlinear Learning Automata with Rapid Convergence and High Accuracy," IEEE Transactions on Knowledge and Data Engineering, vol. 6, no. 4, pp. 654-659, Aug. 1994, doi:10.1109/69.298184
Usage of this product signifies your acceptance of the Terms of Use.