News for hackers. Stuff that matters.
Re:Barack Obama on A.I., Autonomous Cars, and the Future of ... by Animats on Thursday October 13, 2016 @03:13AM (#12699051)
The systems which learn video games work only for games where the state of the game is entirely visible, and the desired player action can be decided based only on the current state. PacMan, yes. Doom, not that way.
Re:Barack Obama on A.I., Autonomous Cars, and the Future of ... by Houshalter on Thursday October 13, 2016 @03:29AM (#12699102)
That's only because they didn't use recurrent neural networks which save information over time. RNNs make it possible to play games with hidden state. Deepmind is currently working on that with starcraft, which is vastly more complicated than pacman. They also have some work on 3d games like doom.

A few weeks ago there was a paper posted on "Synthetic Gradients" which should make it much more practical to train RNNs for games. Before it required saving every single computation the computer makes to memory, which uses a huge amount of memory and computation. Using synthetic gradients they need only store a few steps in the past. And it can learn online.

Re:Barack Obama on A.I., Autonomous Cars, and the Future of ... by tim333 on Thursday October 13, 2016 @06:09PM (#12704497)
They kind of work with Doom: https://www.youtube.com/watch?v=OHNXdGqxyQA

And have some problems with PacMan as the system can't plan: https://www.technologyreview.com/s/535446/googles-ai-masters...

Maybe those should be the other way around?