Representations for black-box optimisation methods (such as evolutionary algorithms) are traditionally constructed using a delicate manual process. This is in contrast to the representation that maps DNAs to phenotypes in biological organisms, which is at the hear of biological complexity and evolvability. Additionally, the core of this process is fundamentally the same across nearly all forms of life, reflecting their shared evolutionary origin. Generative models have shown promise in being learnable representations for black-box optimisation but they are not per se designed to be easily searchable. Here we present a system that can meta-learn such representation by directly optimising for a representation's ability to generate quality-diversity. In more detail, we show our meta-learning approach can find one Neural Cellular Automata, in which cells can attend to different parts of a "DNA" string genome during development, enabling it to grow different solvable 2D maze structures. We show that the evolved genotype-to-phenotype mappings become more and more evolvable, not only resulting in a faster search but also increasing the quality and diversity of grown artefacts.

翻译：黑盒优化方法（如进化算法）的表征传统上通过精细的手动过程构建。这与生物有机体中DNA映射到表型的表征形成对比，后者是生物复杂性和可进化性的核心。此外，该过程的核心在几乎所有生命形式中基本一致，反映了它们共同的进化起源。生成模型已显示出作为黑盒优化可学习表征的潜力，但其本身并非为易于搜索而设计。本文提出一种系统，能够通过直接优化表征生成质量-多样性的能力来元学习此类表征。具体而言，我们展示了元学习方法可找到一种神经细胞自动机，其中细胞在发育过程中能关注"DNA"字符串基因组的不同部分，从而生长出不同的可解二维迷宫结构。实验表明，进化后的基因型-表型映射会变得越来越可进化，不仅加速了搜索过程，还提升了生成产物的质量与多样性。