Discovering Quality-Diversity Algorithms via Meta-Black-Box Optimization
This work addresses the need for more effective and generalizable Quality-Diversity algorithms in evolutionary computation, though it is incremental as it builds on existing meta-learning and attention-based methods.
The authors tackled the problem of designing Quality-Diversity algorithms by using meta-learning to automatically discover novel algorithms, resulting in discovered algorithms that show competitive or superior performance to established baselines and generalize well to higher dimensions and out-of-distribution domains like robot control.
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.