Self-Supervision is All You Need for Solving Rubik's Cube
Published in
(2021)External Links:
TL
TL;DR
This work introduces a simple and efficient deep learning method for solving combinatorial problems with a predefined goal, represented by Rubik's Cube, and demonstrates that, for such problems, training a deep neural network on random scrambles branching from the goal state is sufficient to achieve near-optimal solutions.
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.
References41 items
1
Training Compute-Optimal Large Language Models
2
Solving Rubik’s cube via quantum mechanics and deep reinforcement learning
3
Scaling Vision Transformers
4
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
5