Empowered Neural Cellular Automata

TL;DR

This paper explores how incorporating empowerment, an information-theoretic measure of control, into the evolution of neural cellular automata enhances morphogenesis, leading to more coordinated and effective development of target shapes.

Contribution

It introduces the use of empowerment as a secondary objective in evolving neural cellular automata for morphogenesis, demonstrating improved performance and potential biological insights.

Findings

Empowerment improves morphogenesis fitness in NCA.

Synergistic relationship between empowerment and development.

Potential implications for developmental biology mechanisms.

Abstract

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}.