Delve into the future of research at MiS with our preprint repository. Our scientists are making groundbreaking discoveries and sharing their latest findings before they are published. Explore repository to stay up-to-date on the newest developments and breakthroughs.
Evolving neurocontrollers for balancing an inverted pendulum
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.