Solving the Rubik's Cube with Supervised Learning — Clearly and Thoroughly Explained | by Daniel Warfield | January, 2025
A popular toy in a brave new world
In this article we will create an AI model that can solve a Rubik's Cube. We'll describe our dataset, create a transformer-style model that can learn based on that dataset, and use that model to solve new and randomly shuffled Rubik's Cubes.
In addressing this problem we will discuss practical problems that arise regularly in data science, and the techniques data scientists use to solve those problems.
Who is this useful for? Anyone interested in achieving the breakthroughs of modern AI.
How advanced is this post? This post covers advanced modeling techniques accurately, and is suitable for students of all levels.
Prerequisites: There are no prerequisites for this topic, although an understanding of transformer-style models may be helpful in some of the heavier sections of the code.
References: A link to the code and supporting resources can be found in the reference section at the end of this article.
As you may know, Rubik's Cube is a geometric game consisting of a 3x3x3 cube with a different cube…
