Parameter tunning for PBIL algorithm in geometric constraint solving systems

Abstract

In previous works we have shown that applying genetic algorithms to solve the Root Identification Problem is feasible and effective. The behavior of evolutive algorithms is characterized by a set of parameters that have an effect on the algorithms’ performance. In this paper we report on an empirical statistical study conducted to establish the influence of the driving parameters in the Population Based Incremental Learning (PBIL) algorithm when applied to solve the Root Identification Problem. We also identify ranges for the parameters values that optimize the algorithm performance.