arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2406.09020cs.NE
收藏

元学习一种可进化的发育编码

Meta-Learning an Evolvable Developmental Encoding

Milton L. Montero, Erwan Plantec, Eleni Nisioti, Joachim W. Pedersen, Sebastian Risi

AI总结:

本文提出通过直接优化质量-多样性生成能力来元学习发育编码,并以神经细胞自动机生成可解二维迷宫,证明所得基因型-表型映射可提升可进化性、搜索效率及产物质量与多样性。

摘要:

黑盒优化方法(例如进化算法)的表示传统上是通过精细的人工过程构建的。这与生物有机体中将 DNA 映射到表型的表示形成对比,后者处于生物复杂性和可进化性的核心。此外,这一过程的核心在几乎所有生命形式中基本相同,反映了它们共同的进化起源。生成式模型已展现出作为黑盒优化可学习表示的前景,但其本身并非为易于搜索而设计。本文提出一个能够元学习此类表示的系统,方法是直接优化表示生成质量-多样性的能力。更具体地,作者表明其元学习方法能够找到一种神经细胞自动机,其中细胞在发育过程中可以关注“DNA”字符串基因组的不同部分,从而使其能够生长出不同的可解二维迷宫结构。研究表明,进化得到的基因型到表型映射会变得越来越具有可进化性,不仅带来更快的搜索,还提高了所生成人工产物的质量和多样性。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑