Dynamical control by recurrent neural networks through genetic algorithms

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.

[1]  Mitsuo Kawato,et al.  Neural network control for a closed-loop System using Feedback-error-learning , 1993, Neural Networks.

[2]  Toru Kumagai,et al.  On the Dynamics and Applications of a Discrete Time Binary Neural Network with Time Delay , 1994, J. Intell. Fuzzy Syst..

[3]  A. Papaikonomou,et al.  A genetic algorithm for training recurrent neural networks , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[4]  R. E. Eckmiller,et al.  To swing up an inverted Pendulum using stochastic real-valued Reinforcement Learning , 1994 .

[5]  Toru Kumagai,et al.  Learning of limit cycles in discrete-time neural network , 1996, Neurocomputing.

[6]  Idan Segev,et al.  Methods in Neuronal Modeling , 1988 .

[7]  Jeffrey L. Elman,et al.  Finding Structure in Time , 1990, Cogn. Sci..

[8]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[9]  Peter J. Angeline,et al.  An evolutionary algorithm that constructs recurrent neural networks , 1994, IEEE Trans. Neural Networks.

[10]  J J Hopfield,et al.  Neural networks and physical systems with emergent collective computational abilities. , 1982, Proceedings of the National Academy of Sciences of the United States of America.

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[12]  Yinghua Lin,et al.  Building a Fuzzy System from Input-Output Data , 1994, J. Intell. Fuzzy Syst..

[13]  Kenji Doya,et al.  Adaptive neural oscillator using continuous-time back-propagation learning , 1989, Neural Networks.

[14]  Andrew G. Barto,et al.  Learning to Act Using Real-Time Dynamic Programming , 1995, Artif. Intell..