Diversity maintenance techniques in evolutionary computation are designed to mitigate the
problem of deceptive local optima by encouraging exploration. However, as problems …

A challenge for current evolutionary algorithms is to yield highly evolvable representations
like those in nature. Such evolvability in natural evolution is encouraged through selection …

I present a new approach to evolutionary search called novelty search, wherein only
behavioral novelty is rewarded, thereby abstracting evolution as a search for novel forms …

Novelty search is a recently proposed method for evolutionary computation designed to
avoid the problem of deception, in which the fitness function guides the search process …

In evolutionary computation, the fitness function normally measures progress toward an
objective in the search space, effectively acting as an objective function. Through deception …

A large body of research has investigated the advantages of combining phenotype
adaptation and genotype adaptation. The hybridization of genetic search and local search …

Novelty Search, a new type of Evolutionary Algorithm, has shown much promise in the last
few years. Instead of selecting for phenotypes that are closer to an objective, Novelty Search …

When evolving genotypes, ie structures, with an evolutionary algorithm (EA), eg genetic
programming (GP), genetic diversity, ie structural diversity, of each generation is a …

Though based on abstractions of nature, current evolutionary algorithms and artificial life
models lack the drive to complexity characteristic of natural evolution. Thus this paper …

A major goal for researchers in neuroevolution is to evolve artificial neural networks (ANNs)
that can learn during their lifetime. Such networks can adapt to changes in their environment …