Improving NeuroEvolution Efficiency by Surrogate Model-based Optimization with Phenotypic Distance Kernels

TL;DR

This paper enhances neuroevolution by integrating surrogate model-based optimization with phenotypic distance kernels, significantly reducing the number of evaluations needed for neural network topology optimization.

Contribution

It introduces phenotypic distance measures into surrogate models for neuroevolution, improving evaluation efficiency on benchmark tasks.

Findings

Phenotypic distance kernels outperform other measures.

Evaluation efficiency is significantly increased.

The approach is validated on a replicable benchmark.

Abstract

In NeuroEvolution, the topologies of artificial neural networks are optimized with evolutionary algorithms to solve tasks in data regression, data classification, or reinforcement learning. One downside of NeuroEvolution is the large amount of necessary fitness evaluations, which might render it inefficient for tasks with expensive evaluations, such as real-time learning. For these expensive optimization tasks, surrogate model-based optimization is frequently applied as it features a good evaluation efficiency. While a combination of both procedures appears as a valuable solution, the definition of adequate distance measures for the surrogate modeling process is difficult. In this study, we will extend cartesian genetic programming of artificial neural networks by the use of surrogate model-based optimization. We propose different distance measures and test our algorithm on a replicable benchmark task. The results indicate that we can significantly increase the evaluation efficiency and that a phenotypic distance, which is based on the behavior of the associated neural networks, is most promising.