Inspired by cellular growth and self-organization, Neural Cellular Automata (NCAs) have been capable of "growing" artificial cells into images, 3D structures, and even functional machines.
In contrast to deep reinforcement learning agents, biological neural networks are grown through a self-organized developmental process.
The genome of such a multicellular organism guides the development of its body from a single cell, including its control system.
Neural Cellular Automata (NCAs) have been proven effective in simulating morphogenetic processes, the continuous construction of complex structures from very few starting cells.
In contrast to previous work in Minecraft that focused on learning to play the game, the grand challenge we pose here is to automatically search for increasingly complex artifacts in an open-ended fashion.
We test this hypothesis by decoupling the number of Hebbian learning rules from the number of synapses and systematically varying the number of Hebbian learning rules.
We find that starting from completely random weights, the discovered Hebbian rules enable an agent to navigate a dynamical 2D-pixel environment; likewise they allow a simulated 3D quadrupedal robot to learn how to walk while adapting to morphological damage not seen during training and in the absence of any explicit reward or error signal in less than 100 timesteps.