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.
@article{arxiv.1805.07470,
title = {Solving the Rubik's Cube Without Human Knowledge},
author = {Stephen McAleer and Forest Agostinelli and Alexander Shmakov and Pierre Baldi},
journal= {arXiv preprint arXiv:1805.07470},
year = {2018}
}
Comments
First three authors contributed equally. Submitted to NIPS 2018