Posted on 07/25/2019 9:15:39 PM PDT by aimhigh
Since its invention by a Hungarian architect in 1974, the Rubik’s Cube has furrowed the brows of many who have tried to solve it.
DeepCubeA, a deep reinforcement learning algorithm, can find the solution in a fraction of a second, without any specific domain knowledge or in-game coaching from humans.
This is no simple task considering the cube has completion paths numbering in the billions but only one goal state—each of six sides displaying a solid color—which apparently can’t be found through random moves.
For the new study, researchers demonstrated that DeepCubeA solved 100 percent of all test configurations, finding the shortest path to the goal state about 60% of the time. 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,” says senior author Pierre Baldi, professor of computer science at the University of California, Irvine.
(Excerpt) Read more at futurity.org ...
This is analogous to the genises of life. The combination of chemical complexes and DNA could not have happened by accident. Intelligent design. God.
DeepCubeA.
Brilliant. Only in America. Wow.
That’s no big deal. It’s like figuring out how to put the lid on a tea pot. The pathways are pretty obvious. Find something where the pathway is obvious.
I never broke a minute. I think my best time was 1:06.
My best was 15 seconds. All molded plastic faces. A drop of mineral oil inside for speed. Fastest I’ve seen on Youtube by a human was 10.24 seconds.
Incredible performance.
I can't juggle either.
Sorry no. AI is programmed with a great deal of effort to do simple very SPECIFIC things. Once programmed it CAN do things fast.
BUT
try giving this program another type of puzzle without any further specialized programming for it and it will sit there in confusion til the end of time.
Sorry that’s not ‘intelligence’
AI is just another buzzword used to separate RUBES from their money
The cube and juggling are beyond my capabilities.
I subscribe to the Kobayashi Maru solution. Show me a computer with the creativity and dexterity to “solve” a Rubik’s Cube by removing and rearranging all the stickers off the faces, and then I’ll believe AI has equaled human intelligence and innovation.
Me neither...it takes a while to pull the stickers off and put them back all color coordinated like!
The Rubiks Cube isn’t particularly difficult to solve. There are several algorithmic solutions to the different states. It’s pretty simple to use these to solve for the corners, then solve 2 sides, then the middles. It would be more interesting if the program (it’s not really “AI”), were able to determine those algorithmic paths for itself, when starting from scratch, but even that can be nothing more than trial and error.
I take it that you can’t solve several Rubik’s cube while juggling them, either.
That approach becomes a lot easier if you are profoundly color blind.
My grade-school son got so good with the Rubik’s cube
he could do it blind-folded. Well, almost.
*** “My best was 15 seconds. All molded plastic faces. A drop of mineral oil inside for speed. Fastest I’ve seen on Youtube by a human was 10.24 seconds” ***
Never timed myself because I didn’t know what was Fair
With a Can of Spray Paint, do you have to wait till the paint is dry?
That's extremely impressive. It requires very efficient move sequences and very quick hands. I figured out one set of moves that would solve all the cube configurations, then declared victory.
How were you at Rubik's Revenge?
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.