%0 Generic %1 mcaleer2018solving %A McAleer, Stephen %A Agostinelli, Forest %A Shmakov, Alexander %A Baldi, Pierre %D 2018 %K 2018 arxiv games paper reinforcement-learning %T Solving the Rubik's Cube Without Human Knowledge %U http://arxiv.org/abs/1805.07470 %X 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.

@misc{mcaleer2018solving, 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.}, added-at = {2018-06-17T20:23:21.000+0200}, author = {McAleer, Stephen and Agostinelli, Forest and Shmakov, Alexander and Baldi, Pierre}, biburl = {https://www.bibsonomy.org/bibtex/246608c1bc89217deb14c3340ce0447bf/achakraborty}, description = {[1805.07470] Solving the Rubik's Cube Without Human Knowledge}, interhash = {965666151bbd287f4d059b3127ece38a}, intrahash = {46608c1bc89217deb14c3340ce0447bf}, keywords = {2018 arxiv games paper reinforcement-learning}, note = {cite arxiv:1805.07470Comment: First three authors contributed equally. Submitted to NIPS 2018}, timestamp = {2018-06-17T20:23:21.000+0200}, title = {Solving the Rubik's Cube Without Human Knowledge}, url = {http://arxiv.org/abs/1805.07470}, year = 2018 }