Quality-Diversity Meta-Evolution: customising behaviour spaces to a meta-objective

by   David M. Bossens, et al.

Quality-Diversity (QD) algorithms evolve behaviourally diverse and high-performing solutions. To illuminate the elite solutions for a space of behaviours, QD algorithms require the definition of a suitable behaviour space. If the behaviour space is high-dimensional, a suitable dimensionality reduction technique is required to maintain a limited number of behavioural niches. While current methodologies for automated behaviour spaces focus on changing the geometry or on unsupervised learning, there remains a need for customising behavioural diversity to a particular meta-objective specified by the end-user. In the newly emerging framework of QD Meta-Evolution, or QD-Meta for short, one evolves a population of QD algorithms, each with different algorithmic and representational characteristics, to optimise the algorithms and their resulting archives to a user-defined meta-objective. Despite promising results compared to traditional QD algorithms, QD-Meta has yet to be compared to state-of-the-art behaviour space automation methods such as Centroidal Voronoi Tessellations Multi-dimensional Archive of Phenotypic Elites Algorithm (CVT-MAP-Elites) and Autonomous Robots Realising their Abilities (AURORA). This paper performs an empirical study of QD-Meta on function optimisation and multilegged robot locomotion benchmarks. Results demonstrate that QD-Meta archives provide improved average performance and faster adaptation to a priori unknown changes to the environment when compared to CVT-MAP-Elites and AURORA. A qualitative analysis shows how the resulting archives are tailored to the meta-objectives provided by the end-user.


page 9

page 19

page 20


On the use of feature-maps and parameter control for improved quality-diversity meta-evolution

In Quality-Diversity (QD) algorithms, which evolve a behaviourally diver...

Unsupervised Behaviour Discovery with Quality-Diversity Optimisation

Quality-Diversity algorithms refer to a class of evolutionary algorithms...

Multi-Emitter MAP-Elites: Improving quality, diversity and convergence speed with heterogeneous sets of emitters

Quality-Diversity (QD) optimisation is a new family of learning algorith...

Comparing reliability of grid-based Quality-Diversity algorithms using artificial landscapes

Quality-Diversity (QD) algorithms are a recent type of optimisation meth...

Learning to Walk Autonomously via Reset-Free Quality-Diversity

Quality-Diversity (QD) algorithms can discover large and complex behavio...

Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm

The recently introduced Multi-dimensional Archive of Phenotypic Elites (...

Double arcsine transform not appropriate for meta-analysis

The variance-stabilizing Freeman-Tukey double arcsine transform was orig...

Please sign up or login with your details

Forgot password? Click here to reset