HyperNCA: Growing Developmental Networks with Neural Cellular Automata

TL;DR

This paper introduces HyperNCA, a novel method that uses neural cellular automata to grow neural networks in a self-organized manner, enabling adaptive solutions for reinforcement learning tasks and their variations.

Contribution

The paper presents a new hypernetwork approach based on neural cellular automata for growing neural networks inspired by biological development processes.

Findings

HyperNCA can grow neural networks that solve reinforcement learning tasks.

The method enables networks to transform and adapt to task variations.

Self-organized growth leads to flexible and efficient network development.

Abstract

In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process. Here we propose a new hypernetwork approach to grow artificial neural networks based on neural cellular automata (NCA). Inspired by self-organising systems and information-theoretic approaches to developmental biology, we show that our HyperNCA method can grow neural networks capable of solving common reinforcement learning tasks. Finally, we explore how the same approach can be used to build developmental metamorphosis networks capable of transforming their weights to solve variations of the initial RL task.