Genetic-algorithms-based parameter and rule learning for fuzzy logic control systems

Recently, genetic algorithms have been applied to the problem of automatic rule selection and parameter learning for fuzzy logic based control systems. But the question of formulating an effective cost function necessary for guiding the genetic search process, without external supervision or any training data, still presents many difficulties. This research paper presents a framework within which genetic algorithms can be complemented by ideas established in neural network-based reinforcement learning and classifier systems, for automatic rule generation and parameter learning for fuzzy logic based control systems. Initial results obtained from simulation studies on the control of a nonlinear and inherently unstable dynamic system, are encouraging.