They took the same reinforcement learning techniques from the Atria 2600 AI and applied them to Doom. It worked. Next they plan to do it on Quake. Let me give you a hint for the future: It'll work.
It is still noteworthy, since the Atari visual frames are built up from sprites of limited size that are very convenient for a convolutional model: once it has learned to detect the sprites, it has an accurate representation of the location of the relevant objects in the scene. In doom, since it is a 3D scene, there is no such one-to-one correspondence between object identities and visual appearance. The fact that the method still works is not at all trivial.
Yes, you are reading that correctly. The board itself, which starts at $117, will not operate on its own. To make it a full-fledged usable device for projects and other uses, you must add the SolidPC Q4 single-board 'carrier' computer which is $40. In other words, you are looking at a minimum of $157
env.exec("bla bla bla blaa ");
why do you think you need scripts anyways?
So what language is "bla bla bla blaa " then? You're basically telling us that you write your bash scripts without proper syntax highlighting
Org mode is insanely powerful
I just looked at the feature list. Impressive indeed! It's a like having emacs within emacs: a very nice operating system, but
same number of shader units
good news for those looking for deep learning on the road
This is robust at least against the demo attacks given in the article.
As in certain cults it is possible to kill a process if you know its true name. -- Ken Thompson and Dennis M. Ritchie