Solving the Rubik's Cube Without Human Knowledge
Published in
arXiv.org(2018)External Links:
TL
TL;DR
This work introduces Autodidactic Iteration: a novel reinforcement learning algorithm that is able to teach itself how to solve the Rubik's Cube with no human assistance.
Abstract
A generally intelligent agent must be able to teach itself how to solve problems in complex domains with minimal human supervision. Recently, deep reinforcement learning algorithms combined with self-play have achieved superhuman proficiency in Go, Chess, and Shogi without human data or domain knowledge. In these environments, a reward is always received at the end of the game, however, for many combinatorial optimization environments, rewards are sparse and episodes are not guaranteed to terminate. We introduce Autodidactic Iteration: a novel reinforcement learning algorithm that is able to teach itself how to solve the Rubik's Cube with no human assistance. Our algorithm is able to solve 100% of randomly scrambled cubes while achieving a median solve length of 30 moves -- less than or equal to solvers that employ human domain knowledge.
References36 items
1
Mastering Chess and Shogi by Self-Play with a General Reinforcement Learning Algorithm
2
Mastering the game of Go without human knowledge
3
Thinking Fast and Slow with Deep Learning and Tree Search
4
Neural Combinatorial Optimization with Reinforcement Learning
5