Reinforcement learning neural network used in a tracking system controller

A category of methods used in managing the problems that appears in systems control is inspired from intelligent computation area [4] [6]. In this paper is presented a method of designing a controller for nonlinear systems based on a recurrent neural network which is training in real time using a reinforcement learning (RL) procedure [1]. The advantage of this method is over-passing of the difficulties implied by the direct solving of the differential models, which are necessary in a classical approach. Moreover this new technique using a real-time training is better then the MLP network controller [2] [5] and also then the RBF network implementation [3] which need both of them a preliminary training process, based on a set of input-output data that has to be a priory experimentally determinate.