In this exploratory paper we introduce the problem of cognitive agents that learn how to modify their environment according to local sensing to reach a global goal. We concentrate on discrete dynamics (cellular automata) on a two-dimensional system. We show that agents may learn how to approximate their goal when the environment is passive, while this task becomes impossible if the environment follows an active dynamics.
@article{arxiv.2604.10066,
title = {Control of Cellular Automata by Moving Agents with Reinforcement Learning},
author = {Franco Bagnoli and Bassem Sellami and Amira Mouakher and Samira El Yacoubi},
journal= {arXiv preprint arXiv:2604.10066},
year = {2026}
}