An exploration of asocial and social learning in the evolution of variable-length structures

TL;DR

This paper investigates how asocial and social learning mechanisms influence the evolution of variable-length structures, demonstrating that combined social and asocial learning significantly outperforms evolution alone in complex search landscapes.

Contribution

It introduces and analyzes the effectiveness of combined social and asocial learning mechanisms in evolving variable-length structures within a challenging problem landscape.

Findings

Social learning combined with evolution outperforms pure evolutionary approaches.

Pure evolution struggles to find solutions in the complex landscape.

Learning mechanisms improve the efficiency of self-adaptation in evolutionary algorithms.

Abstract

We wish to explore the contribution that asocial and social learning might play as a mechanism for self-adaptation in the search for variable-length structures by an evolutionary algorithm. An extremely challenging, yet simple to understand problem landscape is adopted where the probability of randomly finding a solution is approximately one in a trillion. A number of learning mechanisms operating on variable-length structures are implemented and their performance analysed. The social learning setup, which combines forms of both social and asocial learning in combination with evolution is found to be most performant, while the setups exclusively adopting evolution are incapable of finding solutions.