Substitution of the Fittest: A Novel Approach for Mitigating Disengagement in Coevolutionary Genetic Algorithms

TL;DR

This paper introduces a new domain-independent technique called substitution of the fittest (SF) to prevent disengagement in coevolutionary genetic algorithms, maintaining engagement and discovering solutions effectively.

Contribution

The paper presents SF, a novel, calibration-free method that improves engagement in coevolutionary algorithms without sacrificing solution quality.

Findings

SF maintains engagement better than existing methods

SF's solution discovery performance is comparable to other techniques

SF offers a simpler mechanism for engagement management

Abstract

We propose substitution of the fittest (SF), a novel technique designed to counteract the problem of disengagement in two-population competitive coevolutionary genetic algorithms. The approach presented is domain-independent and requires no calibration. In a minimal domain, we perform a controlled evaluation of the ability to maintain engagement and the capacity to discover optimal solutions. Results demonstrate that the solution discovery performance of SF is comparable with other techniques in the literature, while SF also offers benefits including a greater ability to maintain engagement and a much simpler mechanism.