HyperNCA: Growing Developmental Networks with Neural Cellular Automata

Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi

Keywords: developmental networks, hypernetworks, neural cellular automata, self-organization

TL;DR: A new developmental encoding to growing developmental policy networks for RL using neural cellular automata

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.