Re:Yann LeCun's comment on AlphaGo and true AI
by fallingfrog on Monday March 14, 2016 @01:11PM
(#11283982)
I think that's what the AlphaGo team did - they trained their agent against itself, and it learned new moves not explicitly programmed in! With an evaluation function just saying ahead / not ahead.
So if you are able to code an AI so that it can run experiments over itself and gradually build this "learning instruction manual" eventually it will become able to do things you never though of in the first place.