Towards self-organized control: Using neural cellular automata to robustly control a cart-pole agent

Neural cellular automata are a recent model used to model biological phenomena emerging from multicellular organisms. In these models, artificial neural networks are used as update rules for cellular automata. They are end-to-end differentiable systems where the parameters of the neural network can be optimized to achieve a particular task. In this work, we used them to control a cart-pole agent. The observations of the environment are transmitted in inputs cells, while the values of output cells are used as readout of the system. We trained the model using deep-Q learning, where the states of the output cells were used as the q-value estimates to be optimized. We found that the computing abilities of the cellular automata were maintained over several hundreds of thousands of iterations, producing an emergent stable behavior in the environment it controls for thousands of steps. Moreover, the system demonstrated life-like phenomena such as a developmental phase, regeneration after damage, stability despite a noisy environment, and robustness to unseen disruption such as input deletion.