本文是一篇探索性研究，提出了认知智能体如何通过局部感知学习修改环境以达成全局目标的问题。我们聚焦于二维系统中的离散动力学（即元胞自动机）。结果表明：当环境为被动动力学时，智能体可学习逼近其目标；而当环境遵循主动动力学时，该任务则无法实现。

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.