HyperNCA: Growing Developmental Networks with Neural Cellular Automata

• Main Authors: Najarro, Elias, Sudhakaran, Shyam, Glanois, Claire, Risi, Sebastian
• Format: Journal Article
• Language: English
• Published: 25-04-2022
• Subjects: Computer Science - Artificial Intelligence; Computer Science - Learning; Computer Science - Neural and Evolutionary Computing
• DOI: 10.48550/arxiv.2204.11674

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.