OpenAI
Posted: Sat Dec 12, 2015 7:55 am
Two deep-learning networks were used in AlphaGo: one network learned to predict the next move, and the other learned to predict the outcome from different arrangements on the board. The two networks were combined using a more conventional AI algorithm to look ahead in the game for possible moves. A scientific paper written by researchers from Google that describes the work appears in the journal Nature today.