A recently developed radii-based evolutionary algorithm designed to solve multimodal optimization problems is
presented. The approach can be placed within the genetic chromodynamics framework. The basic motivation for
modifying the original algorithm was to preserve its ability to search for many optima in parallel while
increasing convergence speed, especially for more complex problems, by adopting generational selection and
different replacement schemes.
Presented algorithm is applied to function optimization and used as an engine for a learning classifier system; the
latter is applied for two classification problems. Obtained experimental results encourage further investigation.