New approach to real-time adaptive learning control of neural networks based on an evolutionary algorithm. I

This paper discusses the composition of the theory of reinforcement learning, which is applied in real-time learning, and evolutionary strategy, which proves its superiority in the finding of the optimal solution in the off-line learning method. The individuals are reduced in order to learn the evolutionary strategy in real-time, and a new method that guarantees the convergence of evolutionary mutations is proposed. It is possible to control the control object varied as time changes. As the state value of the control object is generated, evolutionary strategy is applied to each sampling time because the learning process of an estimation, selection, mutation is in real-time. These algorithms can be applied by people who do not have knowledge about the technical tuning of dynamic systems to design the controller or problems in which the characteristics of the system dynamics are slightly varied as time changes. In the future, studies are needed on the proof of the theory through experiments and the characteristic considerations of the robustness against outside disturbances.