A conceptual framework consisting of sensor-motor, internal representation, and evaluation function spaces for construction of autonomous systems

We present a new framework for constructing autonomous systems, such as agent systems and address an input variable selection for cart pole control utilizing the new framework. Definitions of three spaces (sensor-motor space, internal representation space, and evaluation function space) and discussions on the features of this framework are given in this paper. Based on the framework, we construct an input variable selection mechanism for neural network (NN) learning by using evolutionary programming (EP) for the cart pole control. The specifications of the NN controller are determined by using genetic algorithm (GA). In the internal representation space, a decision tree is constructed by ID3, which is used for the input variable selection. These three search algorithms are streamlined in the framework for easy tuning by the designer. Simulations are done to demonstrate an effective learning system with the input selection mechanism based on the framework.