Learning Control Systems: Review and Outlook

摘要

The basic concept of learning control is introduced, and the following five learning schemes are briefly reviewed: (1) trainable controllers using pattern classifiers, (2) reinforcement learning control systems, (3) Bayesian estimation, (4) stochastic approximation, and (5) stochastic automata models. Potential applications and problems for further research in learning control are outlined. Theoretically, the algorithms have similar learning properties but, from an engineering viewpoint, the a priori information required and the computation involved are different for the different techniques. (Author)