THE FUNCTIONAL-LINK NET AND LEARNING OPTIMAL-CONTROL

We present a strategy for learning optimal control. The approach uses functional-link neural network implementations which have several beneficial properties giving advantages over the more common generalized delta rule implementations. The learning task is decomposed into three parts: identification and monitoring, one-step-ahead control generation, and control path optimization. Each of these parts is accomplished with its own functional-link net and these are coordinated to provide the real-time learning of the optimal control path.