Self-Supervision is All You Need for Solving Rubik's Cube

TL;DR

This paper presents a simple deep learning approach that uses self-supervision to efficiently solve combinatorial puzzles like Rubik's Cube, outperforming previous methods with less data and training.

Contribution

It introduces a self-supervised deep learning method that achieves near-optimal solutions for combinatorial puzzles, reducing complexity and training requirements.

Findings

Outperforms DeepCubeA in solution quality and efficiency

Requires less training data for comparable results

Scales effectively with model size and data volume

Abstract

Existing combinatorial search methods are often complex and require some level of expertise. This work introduces a simple and efficient deep learning method for solving combinatorial problems with a predefined goal, represented by Rubik's Cube. We demonstrate that, for such problems, training a deep neural network on random scrambles branching from the goal state is sufficient to achieve near-optimal solutions. When tested on Rubik's Cube, 15 Puzzle, and 7$\times$7 Lights Out, our method outperformed the previous state-of-the-art method DeepCubeA, improving the trade-off between solution optimality and computational cost, despite significantly less training data. Furthermore, we investigate the scaling law of our Rubik's Cube solver with respect to model size and training data volume.