HyperNCA: Growing Developmental Networks with Neural Cellular Automata

Elias Najarro, Shyam Sudhakaran, Claire Glanois, Sebastian Risi

Research output: Journal Article or Conference Article in JournalConference articleResearchpeer-review


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.
Original languageEnglish
Publication statusPublished - 2022


Dive into the research topics of 'HyperNCA: Growing Developmental Networks with Neural Cellular Automata'. Together they form a unique fingerprint.

Cite this