The AI algorithm capable of solving the Rubik’s cube

The AI algorithm capable of solving the Rubik’s cube

Artificial Intelligence continues to take steps in its objective of replicating and overcoming human abilities. His last big challenge has been the resolution of Rubik’s cube.

Rubik’s cube is a game with billions of possible paths to reach a single end. The great difficulty that this poses for machine learning is that the puzzle cannot be solved by random movement sequences.

To meet this challenge, a team of scientists and mathematicians from the University of California has developed a deep learning algorithm with the ability to solve the problem of multiple combinations. The results of his work were published in the journal Nature Machine Intelligence.

In 60% of the tests he found the fastest solution

DeepCubeA has solved 100% of the tests to which it has been subjected, and even managed to find the fastest way to solve the puzzles 60% of the time. The resolving capacity of the new algorithm is not limited to Rubik’s cube, but it has been successful in solving other classic electronic puzzles such as Lights Out or Sobokan by the fastest way.

DeepCubeA has found the best way to solve the Rubik’s cube in just a fraction of a second and without the need for specific knowledge or prior training by humans. This means that the algorithm has learned to solve the puzzle on its own and faster than any human being.

Faster than anyone

The algorithm developed by American scientists has completed Rubik’s cube in an average of 20 movements compared to the 50 required by anyone. “Our Artificial Intelligence finds the solution most of the time in the minimum number of steps. We see that each strategy is different, and from this we have deduced that the method of reasoning of AI is completely different from that of humans, ”according to Pierre Baldi, lead author of the study.

This project represents a new step in the ambitious goal of building the new generation of AI that will mark the future. At present, these systems continue to show weaknesses in the face of creativity and the capacity for human improvisation.

The arrival of new machine learning algorithms will make a difference if you can advance in the field of intelligence, robustness, reasoning and comprehension skills.

Spread the love

Leave a Reply