Slashdot Mirror

← Back to Stories (view on slashdot.org)

Artificial General Intelligence That Plays Video Games: How Did DeepMind Do It?

Posted by timothy on from the they-can't-let-you-do-that-dave dept.

First time accepted submitter Hallie Siegel writes Last December, an article named 'Playing Atari with Deep Reinforcement Learning' was uploaded to arXiv by employees of a small AI company called DeepMind. Two months later Google bought DeepMind for 500 million euros, and this article is almost the only thing we know about the company. A research team from the Computational Neuroscience Group at University of Tartu's Institute of Computer Science is trying to replicate DeepMind's work and describe its inner workings.

3 of 93 comments (clear)

  1. DeepMind? by ArcadeMan · · Score: 4, Funny

    I've seen the next-generation after DeepMind, and it requires seven and a half million years of calculation to play a video game.

    --
    Get free satoshi (Bitcoin) and Dogecoins
  2. How to do it. by Animats · · Score: 4, Interesting

    That's neat. The demo takes in the video from a video game of the Pong/Donkey Kong era, can operate the controls, and in addition has the score info. It then learns to play the game. How to do that?

    It's been done before, but not this generally. "Pengi", circa 1990, played Pengo using only visual input from the screen. It had hand-written heuristics, but only needed vision input from the game. So we have a starting point.

    The first problem is feature extraction from vision. What do you want to take from the image of the game that you can feed into an optimizer? Motion and change, mostly. Something like an MPEG encoder, which breaks an image into moving blocks and tracks their motion, would be needed. I doubt they're doing that with a neural net.

    Now you have a large number of time-varying scalar values, which is what's needed to feed a neural net. The first thing to learn is how the controls affect the state of the game. Then, how the state of the game affects the score.

    I wonder how fast this thing learns, and how many tries it needs.

  3. How to do it. by Jmstuckman · · Score: 4, Informative

    Advances in Deep Learning have made it far easier to extract features from vision -- in fact, feeding pixels straight to the neural net is pretty close to being all you need to do.

    Take a look at these slides and read about convolutional neural networks: http://www.slideshare.net/0xda...