A Machine Learning Approach That Beats Large Rubik's Cubes

TL;DR

This paper introduces a machine learning-based method that significantly improves Rubik's cube solving, achieving shorter solutions, higher optimality, and faster performance than existing solvers, including for larger cubes beyond 3x3x3.

Contribution

It presents the first machine learning solver capable of efficiently solving large Rubik's cubes like 4x4x4 and 5x5x5, surpassing all previous methods in solution quality and speed.

Findings

Achieves over 98% optimality on 3x3x3 cubes.

Outperforms all existing solvers on larger cubes.

Solves 3x3x3 cubes 26 times faster than previous methods.

Abstract

The paper proposes a novel machine learning-based approach to the pathfinding problem on extremely large graphs. This method leverages diffusion distance estimation via a neural network and uses beam search for pathfinding. We demonstrate its efficiency by finding solutions for 4x4x4 and 5x5x5 Rubik's cubes with unprecedentedly short solution lengths, outperforming all available solvers and introducing the first machine learning solver beyond the 3x3x3 case. In particular, it surpasses every single case of the combined best results in the Kaggle Santa 2023 challenge, which involved over 1,000 teams. For the 3x3x3 Rubik's cube, our approach achieves an optimality rate exceeding 98%, matching the performance of task-specific solvers and significantly outperforming prior solutions such as DeepCubeA (60.3%) and EfficientCube (69.6%). Additionally, our solution is more than 26 times faster in solving 3x3x3 Rubik's cubes while requiring up to 18.5 times less model training time than the most efficient state-of-the-art competitor.