You can teach a computer to play games, but better that it teach itself(economist.com)
economist.com
You can teach a computer to play games, but better that it teach itself
http://www.economist.com/news/science-and-technology/21645108-you-can-teach-computer-play-games-better-it-teach-itself-computers?fsrc=scn%2Ffb%2Fte%2Fpe%2Fed%2Fcomputersgaming
6 comments
I didn't get much from the linked blurb, but the title made me think: if you sample training data exhaustively and then run a learning process, could you then take the training data maximizing algorithm performance to then better train humans at the same task?
Check out this recent discussion on machine teaching: https://news.ycombinator.com/item?id=9114053
Just realized that feeding video from 2600 games into an AI is a form of cheat. All sprites are going to be fed perfectly into the AI as compared to using a video camera looking at at TV where pixels will not be perfect. Still a nice achievement, but one very complex aspect of "learn by watching" has been eliminated.
Normaizing video into a logical grid is a very simple preliminary task in machine vision. It's not a challenge for state of the art systems.