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

@inproceedings{AlcarazHerrera2021SubstitutionOT,
  title={Substitution of the Fittest: A Novel Approach for Mitigating Disengagement in Coevolutionary Genetic Algorithms},
  author={Hugo Alcaraz-Herrera and J. Cartlidge},
  booktitle={International Joint Conference on Computational Intelligence},
  year={2021}
}
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 domainindependent 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… 
[PDF] Semantic Reader
1 Citations
Background Citations
1
Methods Citations
1

Figures from this paper

One Citation

Using coevolution and substitution of the fittest for health and well-being recommender systems

. This research explores substitution of the fittest (SF), a technique designed to counteract the problem of disengagement in two-population competitive coevolutionary genetic algorithms. SF is…

References

SHOWING 1-10 OF 23 REFERENCES

Combating Coevolutionary Disengagement by Reducing Parasite Virulence

Inspired by studies of natural host-parasite systems, it is shown that disengagement can be avoided by selecting for individuals that exhibit reduced levels of virulence, rather than maximum ability to defeat coevolutionary adversaries.

A Comparison of Evolutionary and Coevolutionary Search

It is shown that the increased efficacy in the coevolutionary model results from the direct exploitation of low quality strategies by the population of training cases, and there is evidence that the generality of the high-quality strategies can suffer as a result of this same exploitation.

New Methods for Competitive Coevolution

This work uses the games of Nim and 3-D Tic-Tac-Toe as test problems to explore three new techniques in competitive coevolution, which changes the way fitness is measured, shared sampling provides a method for selecting a strong, diverse set of parasites and the hall of fame encourages arms races by saving good individuals from prior generations.

Autonomous Virulence Adaptation Improves Coevolutionary Optimization

A novel approach for the autonomous virulence adaptation (AVA) of competing populations in a coevolutionary optimization framework is presented, which uses a machine learning approach to continuously tune v as system engagement varies.

Coevolutionary search among adversaries

New methods are described that overcome these Aaws and make coevolution more efficient, able to solve several game learning test problems that cannot be efficiently solved without them.

Coevolutionary dynamics in a minimal substrate

Three simple 'number games' are defined that illustrate intransitive superiority and resultant oscillatory dynamics, as well as some other relevant concepts that include the distinction between a player's perceived performance and performance with respect to an external metric, and the significance of strategies with a multidimensional nature.

Coevolutionary Principles

This chapter outlines the ends and means of coevolutionary algorithms: what they are meant to find, and how they should find it.

Selection Methods to Relax Strict Acceptance Condition in Test-Based Coevolution

This work proposes new selection conditions that include both Pareto dominated and Pare to non-dominated solutions, as well as other factors to help provide distinctions for selection, and defines some new performance metrics that allow one to compare the various selection methods in terms of ideal evaluation of coevolution.

Caring versus Sharing: How to Maintain Engagement and Diversity in Coevolving Populations

It is demonstrated that moderating parasite virulence differs significantly from resource sharing, and that its tendency to prevent disengagement can also reduce the likelihood of coevolutionary optimisation halting at mediocre stable states.

Spatial Embedding and Loss of Gradient in Cooperative Coevolutionary Algorithms

A tunably asymmetric function optimization problem domain is constructed and it is found that spatial restrictions for collaboration and selection can help keep population changes balanced when presented with severe asymmetries in the problem.