Researchers in the University of California have developed an artificial intelligence (AI) algorithm which can solve a Rubik’s cube in a fraction of a second. The AI algorithm which is called DeepCubeA can complete the 3D puzzle within a second, faster than most humans. The algorithm is a step towards making AI systems which can reason, strategise and decide.
According to a study, published in the journal Nature Machine Intelligence, the AI algorithm was provided with 10 billion combinations of the Rubik’s cube along with a target of decoding them in 30 moves. It was then tested on 1,000 cubes, all of which could be solved by the AI. The algorithm found the shortest path to the goal 60.3 per cent of the time.
Solving the Rubik’s cube often takes a lot of steps, and is not something that is easily achievable. “The solution to the Rubik’s Cube involves more symbolic, mathematical and abstract thinking, so a deep learning machine that can crack such a puzzle is getting closer to becoming a system that can think, reason, plan and make decisions,” Pierre Baldi, UCI Distinguished Professor of computer science said in a report.
The algorithm also works on other combinatorial games such as the sliding tile puzzle, Lights Out and Sokoban.
“Artificial intelligence can defeat the world’s best human chess and Go players, but some of the more difficult puzzles, such as the Rubik’s Cube, had not been solved by computers, so we thought they were open for AI approaches,” Baldi said.
“Our AI takes about 20 moves, most of the time solving it in the minimum number of steps,” he said adding that “Right there, you can see the strategy is different, so my best guess is that the AI’s form of reasoning is completely different from a human’s,”.
The ultimate goal of projects such as this one is to build the next generation of AI systems, the report said.