Concepts and Facilities of a Neural Reinforcement Learning Control Architecture for Technical Process Control

Abstract

The paper presents the concepts of a neural control architecture that is able to learn high quality control behaviour in technical process control from scratch. As the input to the learning system, only the control target must be specified. In the first part of the article, the underlying theoretical principles of dynamic programming methods are explained, and their adaptation to the context of technical process control is described. The second part discusses the basic capabilities of the learning system on a typical benchmark problem, where a special focus lies on the quality of the acquired control law. The application to a highly nonlinear chemical reactor and to an instable multi-output system shows the ability of the proposed neural control architecture to learn even difficult control strategies from scratch.