Vv. Phansalkar et Mal. Thathachar, LEARNING AUTOMATA IN FEEDFORWARD CONNECTIONIST SYSTEMS, International Journal of Systems Science, 27(2), 1996, pp. 145-150
Citations number
11
Categorie Soggetti
System Science","Computer Science Theory & Methods","Operatione Research & Management Science
This paper analyses the behaviour of a general class of learning autom
ata algorithms for feedforward connectionist systems in an associative
reinforcement learning environment. The type of connectionist system
considered is also fairly general. The associative reinforcement learn
ing task is first posed as a constrained maximization problem. The alg
orithm is approximated hy an ordinary differential equation using weak
convergence techniques. The equilibrium points of the ordinary differ
ential equation are then compared with the solutions to the constraine
d maximization problem to show that the algorithm does behave as desir
ed.