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

06/29/2021
by   Alexandre Variengien, et al.
24

Neural cellular automata (Neural CA) are a recent framework used to model biological phenomena emerging from multicellular organisms. In these systems, artificial neural networks are used as update rules for cellular automata. Neural CA are end-to-end differentiable systems where the parameters of the neural network can be learned to achieve a particular task. In this work, we used neural CA to control a cart-pole agent. The observations of the environment are transmitted in input cells, while the values of output cells are used as a 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.

READ FULL TEXT

page 4

page 6

page 7

page 8

page 9

page 10

research
04/25/2022

Goal-Guided Neural Cellular Automata: Learning to Control Self-Organising Systems

Inspired by cellular growth and self-organization, Neural Cellular Autom...
research
08/31/2017

Differentiable cellular automata

We describe a class of cellular automata (CAs) that are end-to-end diffe...
research
07/19/2021

Generative Adversarial Neural Cellular Automata

Motivated by the interaction between cells, the recently introduced conc...
research
06/14/2022

Severe Damage Recovery in Evolving Soft Robots through Differentiable Programming

Biological systems are very robust to morphological damage, but artifici...
research
07/13/2021

Carle's Game: An Open-Ended Challenge in Exploratory Machine Creativity

This paper is both an introduction and an invitation. It is an introduct...
research
12/03/2020

Reconstructing cellular automata rules from observations at nonconsecutive times

Recent experiments by Springer and Kenyon have shown that a deep neural ...
research
11/24/2019

Cybernetical Concepts for Cellular Automaton and Artificial Neural Network Modelling and Implementation

As a discipline cybernetics has a long and rich history. In its first ge...

Please sign up or login with your details

Forgot password? Click here to reset