Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization

TL;DR

This paper introduces a meta-learning approach to automatically discover new Quality-Diversity algorithms, outperforming traditional heuristics and generalizing well across various domains and dimensions.

Contribution

It proposes using attention-based neural architectures to parameterize and evolve novel Quality-Diversity algorithms, moving beyond heuristic-based methods.

Findings

Discovered algorithms outperform traditional baselines.

Algorithms generalize to higher dimensions and new domains.

Meta-learning naturally maintains diversity even when optimized for fitness.

Abstract

Quality-Diversity has emerged as a powerful family of evolutionary algorithms that generate diverse populations of high-performing solutions by implementing local competition principles inspired by biological evolution. While these algorithms successfully foster diversity and innovation, their specific mechanisms rely on heuristics, such as grid-based competition in MAP-Elites or nearest-neighbor competition in unstructured archives. In this work, we propose a fundamentally different approach: using meta-learning to automatically discover novel Quality-Diversity algorithms. By parameterizing the competition rules using attention-based neural architectures, we evolve new algorithms that capture complex relationships between individuals in the descriptor space. Our discovered algorithms demonstrate competitive or superior performance compared to established Quality-Diversity baselines while exhibiting strong generalization to higher dimensions, larger populations, and out-of-distribution domains like robot control. Notably, even when optimized solely for fitness, these algorithms naturally maintain diverse populations, suggesting meta-learning rediscovers that diversity is fundamental to effective optimization.