Dynamical control by recurrent neural networks through genetic algorithms
Toru Kumagai, Mitsuo Wada, Ryoichi Hashimoto, Akio Utsugi · International Journal of Adaptive Control and Signal Processing · 1999
In this study we composed a recurrent neural network learning controller and applied it to the swinging up and stabilization problem of the inverted pendulum. A recurrent neural network was trained by a genetic algorithm which had an internal copy operator or inter-individual copy operator. An appropriate controller was acquired in a recurrent neural network by training with a simple evaluation function. The recurrent neural network acquired two completely different rules for swinging up and stabilization of a pendulum. It outputted these two rules continuously so that swinging up and stabilization of a pendulum was realized. Internal copy and inter-individual copy accelerated learning effectively by copying a part of a chromosome. Copyright © 1999 John Wiley & Sons, Ltd.