0

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

A deep learning method for solving combinatorial problems like Rubik's Cube outperforms existing approaches with less training data and better resource efficiency.

Year
2021
Venue
self-supervision-is-all-you-need-for-solving
Authors
1
Hosting
Abstract onlyARXIV-DEFAULT

Cite

Notes

Only stored in your browser.

Attribution

Abstract & full text
arxiv.org/abs/2106.03157v5ARXIV-DEFAULT
TL;DR
Semantic Scholar
Attribution policy →

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.

Authors

1