HyperNCA: Growing Developmental Networks with 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.

arXiv commentPaper accepted as a conference paper at ICLR 'From Cells to Societies' workshop 2022

References in corpus (11)

• Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
• A Brief Survey of Deep Reinforcement Learning
• Evolution Strategies as a Scalable Alternative to Reinforcement Learning
• Benchmarking Deep Reinforcement Learning for Continuous Control
• OpenAI Gym
• Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternative for Training Deep Neural Networks for Reinforcement Learning
• Active Learning of Inverse Models with Intrinsically Motivated Goal Exploration in Robots
• Neural GPUs Learn Algorithms
• HyperNetworks
• Cellular automata as convolutional neural networks
• HyperTransformer: Model Generation for Supervised and Semi-Supervised Few-Shot Learning