A deep reinforcement learning algorithm programmed by University of California computer scientists and mathematicians -- can solve the Rubik’s Cube in a fraction of a second ...

A deep reinforcement learning algorithm can solve the Rubik's Cube puzzle in a fraction of a second. The work is a step toward making AI systems that can think, reason, plan and make decisions.

For the first time, a deep-learning algorithm has taught itself an efficient way to solve a Rubik’s cube. A Rubik’s cube has over 43 quintillion possible combinations — but only 1 solution ...

AI algorithm, named DeepCubeA, has solved a Rubik's Cube in a fraction of a second without having any specific knowledge of the domain or in-game coaching from humans.

The fastest people need about 50 moves to solve a Rubik’s Cube. “Our AI takes about 20 moves, most of the time solving it in the minimum number of steps,” says the study’s senior author, Pierre Baldi, ...

Researchers at the University of California believe they've created an algorithm that can solve the Rubik's Cube on its own. It depends on "autodidactic iteration" which is a "novel reinforcement ...

Want to solve a Rubik’s Cube? Then you have to know the numbers. Here’s the amazing math behind the legendary toy, and how to use it to solve the puzzle.

Earlier this year, while putting together a video about the world’s fastest solvers of the Rubik’s Cube, I decided to devote some time to learning to solve the classic puzzle myself. Tyson Mao ...

To solve the Rubik's cube, all you need is a slightly expensive connected cube, and time to kill.