pith. machine review for the scientific record. sign in

arxiv: 1805.07470 · v1 · pith:XOSOEONSnew · submitted 2018-05-18 · 💻 cs.AI

Solving the Rubik's Cube Without Human Knowledge

classification 💻 cs.AI
keywords humansolveableknowledgealgorithmcubedomainenvironments
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.