Skip to main content

Distinguished Professor of Computer Science Pierre Baldi recently published a new paper, “Solving the Rubik’s cube with deep reinforcement learning and search,” in the journal Nature Machine Learning. Co-authors of the paper include Forest Agostinelli, a UCI Ph.D. candidate in computer science; Stephen McAleer, a Ph.D. student in computer science; and Alexander Shmakov, a senior in mathematics. In the paper, the researchers demonstrated that DeepCubeA solved 100 percent of all test configurations, finding the shortest path to the goal state about 60 percent of the time. The algorithm also works on other combinatorial games such as the sliding tile puzzle, Lights Out and Sokoban.

Read more about the research in UCI News, “UCI researchers’ deep learning algorithm solves Rubik’s Cube faster than any human.”