An exploration of asocial and social learning in the evolution of variable-length structures
This addresses the problem of improving evolutionary algorithms for complex search tasks, but it appears incremental as it builds on existing learning mechanisms.
The study tackled the challenge of evolving variable-length structures in an extremely difficult problem landscape, finding that a social learning setup combining social and asocial learning with evolution was most performant, while setups using only evolution failed to find solutions.
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.