arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2205.06771cs.NEcs.AI
收藏

赋能神经细胞自动机

Empowered Neural Cellular Automata

University of Vermont(佛蒙特大学)

Caitlin Grasso, Josh Bongard

AI总结:

本文将赋能适应度函数扩展至神经细胞自动机(NCA),发现将其作为形态发生任务的次要进化目标能提升适应度,揭示两者协同关系,为发育生物学细胞间通信提供潜在机制。

摘要:

信息论适应度函数正变得越来越流行,用于产生普遍有用、与任务无关的行为。其中一个通用函数被称为赋能(empowerment),它衡量智能体通过其感觉运动系统对环境施加的控制量。具体而言,赋能试图最大化智能体的动作与其在稍后时间点接收到的感觉状态之间的互信息。传统上,赋能已被应用于传统的感觉运动装置,例如机器人。在这里,我们将该方法扩展到由神经细胞自动机(NCA)体现的分布式多智能体感觉运动系统。我们表明,在进化NCA以执行形态发生任务(即生长并维持预定形状)的过程中,将赋能作为次要目标加入,与仅针对形态发生进行进化相比,能产生更高的适应度。结果表明,形态发生与赋能之间可能存在协同关系。也就是说,在发育持续时间内间接选择相邻细胞间的协调,对发育过程本身是有益的。这一发现可能通过提供在从单细胞生长到多细胞目标形态过程中细胞间通信的潜在机制,而在发育生物学中具有应用。本文的实验源代码可在以下网址找到:\url{https://github.com/caitlingrasso/empowered-nca}。

英文摘要:

Information-theoretic fitness functions are becoming increasingly popular to produce generally useful, task-independent behaviors. One such universal function, dubbed empowerment, measures the amount of control an agent exerts on its environment via its sensorimotor system. Specifically, empowerment attempts to maximize the mutual information between an agent's actions and its received sensor states at a later point in time. Traditionally, empowerment has been applied to a conventional sensorimotor apparatus, such as a robot. Here, we expand the approach to a distributed, multi-agent sensorimotor system embodied by a neural cellular automaton (NCA). We show that the addition of empowerment as a secondary objective in the evolution of NCA to perform the task of morphogenesis, growing and maintaining a pre-specified shape, results in higher fitness compared to evolving for morphogenesis alone. Results suggest there may be a synergistic relationship between morphogenesis and empowerment. That is, indirectly selecting for coordination between neighboring cells over the duration of development is beneficial to the developmental process itself. Such a finding may have applications in developmental biology by providing potential mechanisms of communication between cells during growth from a single cell to a multicellular, target morphology. Source code for the experiments in this paper can be found at: \url{https://github.com/caitlingrasso/empowered-nca}.

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。

↑