Phansalkar, VV and Thathachar, MAL (1992) Global Convergence of FeedForward Networks of Learning Automata. In: International Joint Conference on Neural Networks, 1992. IJCNN, 7-11 June, Baltimore,MD, Vol.3, 875 -880.
A feedforward network composed of units of teams of parametrised learning autmata is considered as a mode2 of a reinforcement learning system. The parameters of each learning automaton are updated using an algorithm consisting of a gradient following term and a random perturbation term. The algorithm is approximated by the Ldngevin equation and it is shown that it converges to the global pnaximum. The algorithm is decentralised and the units do not have any information exchange during updating . Simulation results on a pattern recognation problem show that reasonable rates of convergence can be obtained.
|Item Type:||Conference Paper|
|Additional Information:||Copyright 1992 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE|
|Department/Centre:||Division of Electrical Sciences > Electrical Engineering|
|Date Deposited:||30 May 2006|
|Last Modified:||19 Sep 2010 04:27|
Actions (login required)