Tag Archives: deep mind

Computer Program Teaches Itself to Solve Rubik’s Cubes!

Posted on by
Reply

I tried to warn you, fellow puzzlers.

I wrote posts about computer programs that play chess, Scrabble, Go, Atari games, and Jeopardy! I wrote posts about programs that solve crosswords. I even wrote posts about robots that solve Rubik’s Cubes in a fraction of a second.

And they’re getting smarter.

Say hello to DeepCube, an AI program that is now the equal of any master Rubik’s Cube solver in the world at solving 3x3x3 cubes.

And unlike other AI programs that have learned to play games like chess and Go through reinforcement learning — determining if particular moves are bad or good — DeepCube taught itself to play by analyzing each move, comparing it to a completed cube, and reverse-engineering how to get to that move.

It’s labor-intensive, yes, but it also requires no human intervention and no previous information. Chess-playing programs like Deep Blue work by analyzing thousands of previously played games. But DeepCube had no previous history to build on.

It started from scratch. By itself.

And became a Rubik’s Cube master.

In only 44 hours.

Compare that to the 10,000 hours it supposedly takes for a human to become an expert in anything, and that’s a mind-blowing accomplishment.

[Image courtesy of YouTube.]

From the Gizmodo article on DeepCube:

The system discovered “a notable amount of Rubik’s Cube knowledge during its training process,” write the researchers, including a strategy used by advanced speedcubers, namely a technique in which the corner and edge cubelets are matched together before they’re placed into their correct location.

Yes, the program even independently recreated techniques designed by human speed-solvers to crack the cubes faster.

The next goal for the DeepCube program is to pit it against 4x4x4 cubes, which are obviously more complex. But supposedly, deposing human puzzle solvers as the top dogs on the planet isn’t the finish line.

No, this sort of three-dimensional puzzle-solving is only an intermediate goal, with the ultimate endgame of predicting protein shapes, analyzing DNA, building better robots, and other advanced projects.

But first, they’re coming for our puzzles.

Thanks for visiting PuzzleNation Blog today! Be sure to sign up for our newsletter to stay up-to-date on everything PuzzleNation!

You can also share your pictures with us on Instagram, friend us on Facebook, check us out on Twitter, Pinterest, and Tumblr, and explore the always-expanding library of PuzzleNation apps and games on our website!

The Robots Are Here and They Can Spell

Posted on by
3

[Image courtesy of World of Weird Things.]

I warned you, fellow puzzlers. You can’t say I didn’t warn you.

The robots are coming, and they want our puzzles and games.

Let’s look at the hit list:

  • Deep Blue defeated Russian chess grandmaster Garry Kasparov under standard chess tournament time constraints
  • IBM’s supercomputer Watson bested previous Jeopardy! champions Brad Rutter and Ken Jennings to nab a million-dollar prize
  • An AI program called DeepMind taught itself to play several Atari games with superhuman proficiency
  • There are several robots constructed out of LEGOs that solve Rubik’s Cubes in seconds flat
  • Dr. Fill, the crossword-solving computer program, competes at the American Crossword Puzzle Tournament, and in a matter of five years, it has jumped from 141st place in the 2012 tournament to 11th place in the 2017 tournament
  • Just last year, an AI developed by Google, AlphaGo (a product of DeepMind), twice defeated Ke Jie, the 19-year-old Go tournament champion ranked number one in the world

And Scrabble fans, you’re the next ones in the crosshairs of the machines.

During last week’s Consumer Electronics Show (CES), the Industrial Technology Research Institute out of Taiwan debuted the IVS Robot — aka The Intelligent Vision System for Companion Robots — a machine capable of defeating human competitors at Scrabble.

[Image courtesy of ABC News.]

Instead of tiles and a standard Scrabble board, the IVS reads letter cubes (similar to a child’s alphabet blocks) played on a slightly larger gameboard. But time limits for play and standard rules still apply.

From an article on Engadget:

It’s hard not to be impressed by all the moving parts here. For one, the robot has to learn and understand the rules of the game and the best strategies for winning. It also needs to be able to see and recognize the game pieces and the spots on the board. That means it can read the letters on the cubes and identify the double-letter and triple-word score spots.

And, last but not least, it needs the dexterity to place the pieces on the board and not disturb the existing letters — which is especially difficult when you’re laying down two words next to each other to rack up those two-letter combos.

A quick Google search confirms that the robot bested practically every reporter, tech-savvy or otherwise, that crossed its path.

In the video below, North American Scrabble champion Will Anderson teams up with reporter Lexy Savvides to battle the robot, but a technical error prevents the game from getting very far:

Still, you can see the potential here. I’m sure it won’t be long before the IVS Robot is making appearances at Scrabble tournaments, attempting to establish machine dominance over another puzzly activity.

Stay strong, fellow puzzlers.

Thanks for visiting PuzzleNation Blog today! Be sure to sign up for our newsletter to stay up-to-date on everything PuzzleNation!

You can also share your pictures with us on Instagram, friend us on Facebook, check us out on Twitter, Pinterest, and Tumblr, and explore the always-expanding library of PuzzleNation apps and games on our website!