Balancing rotators with evolved neurocontrollers
Frank Pasemann and Ulf Dieckmann
Contact the author: Please use for correspondence this email.
Submission date: 01. Dec. 1997
published in: Biological and artificial computation : from neuroscience to technology ; International Work-Conference on Artificial and Natural Neural Networks, IWANN'97 Lanzarote, Canary Islands, Spain, June 4-6, 1997 proceedings / J. Mira (ed.)
Berlin : Springer, 1997. - P. 1279 - 1287
(Lecture notes in computer science ; 1240)
DOI number (of the published article): 10.1007/BFb0032588
with the following different title: Evolved neurocontrollers for pole-balancing
Download full preprint: PDF (261 kB), PS ziped (128 kB)
The presented evolutionary algorithm is especially designed to generate recurrent neural networks with non-trivial internal dynamics. It is not based on genetic algorithms, and sets no constraints on the number of neurons and the architecture of a network. Network topology and parameters like synaptic weights and bias terms are developed simultaneously. It is well suited for generating neuromodules acting in sensorimotor loops, and therefore it can be used for evolution of neurocontrollers solving also nonlinear control problems. We demonstrate this capability by applying the algorithm successfully to the following task: Stabilize a rotating pendulum - that is mounted on a cart - in an upright position.