arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2307.09320cs.AIcs.LGcs.NE
收藏

Biomaker CA:一个采用元胞自动机的生物群系构建项目

Biomaker CA: a Biome Maker project using Cellular Automata

Google Research(谷歌研究院)

Ettore Randazzo, Alexander Mordvintsev

AI总结:

本研究提出基于元胞自动机的Biomaker CA生物群系模拟项目,支持多环境、多模型架构与进化策略,可实现元进化与交互式进化,并已开源。

摘要:

我们介绍Biomaker CA:一个采用元胞自动机(Cellular Automata, CA)的生物群系构建项目。在Biomaker CA中,形态发生是核心特性,小型种子需要生长为类植物有机体,才能在营养匮乏的环境中存活,并最终通过变异繁殖,使生物群系能够长期存续。我们通过二维网格中的元胞自动机规则模拟复杂生物群系,并借助Python的JAX框架在GPU上并行化所有计算。我们展示了该项目如何支持多种不同类型的环境与“物理”法则,以及不同的模型架构和变异策略。我们进一步分析了部分配置,以展示植物智能体如何生长、存活、繁殖和进化,形成稳定与不稳定的生物群系。随后我们演示了如何通过端到端元进化,或是一种被称为培养皿元进化的更精准、高效的方法,对模型进行元进化以使其在恶劣环境中存活。最后,我们展示了如何开展交互式进化:由用户交互式决定植物模型的进化方式,再将其部署到更大的环境中。我们已将Biomaker CA开源,地址为:https://tinyurl.com/2x8yu34s。

英文摘要:

We introduce Biomaker CA: a Biome Maker project using Cellular Automata (CA). In Biomaker CA, morphogenesis is a first class citizen and small seeds need to grow into plant-like organisms to survive in a nutrient starved environment and eventually reproduce with variation so that a biome survives for long timelines. We simulate complex biomes by means of CA rules in 2D grids and parallelize all of its computation on GPUs through the Python JAX framework. We show how this project allows for several different kinds of environments and laws of 'physics', alongside different model architectures and mutation strategies. We further analyze some configurations to show how plant agents can grow, survive, reproduce, and evolve, forming stable and unstable biomes. We then demonstrate how one can meta-evolve models to survive in a harsh environment either through end-to-end meta-evolution or by a more surgical and efficient approach, called Petri dish meta-evolution. Finally, we show how to perform interactive evolution, where the user decides how to evolve a plant model interactively and then deploys it in a larger environment. We open source Biomaker CA at: https://tinyurl.com/2x8yu34s .

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。

↑