AI solves Rubik's Cube in a fraction of a second

LOS ANGELRS: Scientists have developed a new AI-based algorithm that can solve the Rubik’s Cube in a fraction of a second, without any specific domain knowledge or ingame coaching from humans.

It was invented by a Hungarian architect in 1974.

DeepCubeA, a deep reinforcement learning algorithm programmed by researchers at the University of California , Irvine (UCI) in the US can find the solution in a fraction of a second.

This is no simple task considering that the cube has completion paths numbering in the billions but only one goal state — each of six sides displaying a solid colour — which apparently can’t be found through random moves, researchers said.

The study, published in the journal ‘Nature Machine Intelligence’, demonstrated that DeepCubeA solved 100% of all test configurations, finding the shortest path to the goal state about 60% of the time.