A strategy for controlling nonlinear systems using a learning automaton

This paper presents an application of learning automaton (LA) for nonlinear system control. The proposed control strategy utilizes a learning automato n in which the reinforcement scheme is based on the Pursuit Algorithm inter acting with a nonstationary environment. Modulated by an adaptive mechanism , the LA selects, at each control period, a local optimal action, which ser ves as input to the controlled system. During the control procedure, the sy stem output value takes into account the changes occurring inside the syste m and provides reward/penalty responses to the learning automaton. (C) 2000 Elsevier Science Ltd. All rights reserved.