We have decided to discontinue the publication of preprints on our preprint server as of 1 March 2024. The publication culture within mathematics has changed so much due to the rise of repositories such as ArXiV (www.arxiv.org) that we are encouraging all institute members to make their preprints available there. An institute's repository in its previous form is, therefore, unnecessary. The preprints published to date will remain available here, but we will not add any new preprints here.
MiS Preprint
35/1997
Evolving neurocontrollers for balancing an inverted pendulum
Frank Pasemann
Abstract
The paper introduces an evolutionary algorithm, that is tailored to generate neural networks functioning as nonlinear controllers. Network size and architecture as well as network parameters like weights and bias terms are developed simultaneously. There is no quantization of inputs, outputs or internal parameters. Different kinds of evolved networks are presented that solve the pole-balancing problem, i.e. balancing an inverted pendulum, with good benchmark performance. Controllers solving the problem for reduced phase space information (only two inputs) use a recurrent connectivity structure and are very small in size. The typical behavior of controllers is characterized by the first return map of their control signals.
