English

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

Machine Learning 2023-05-24 v5

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×\times7 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.

Keywords

Cite

@article{arxiv.2106.03157,
  title  = {Self-Supervision is All You Need for Solving Rubik's Cube},
  author = {Kyo Takano},
  journal= {arXiv preprint arXiv:2106.03157},
  year   = {2023}
}

Comments

Our code is available at https://github.com/kyo-takano/efficientcube

R2 v1 2026-06-24T02:53:04.858Z