“So this is the architecture. And we're going to basically…” — Dwarkesh Podcast at 39:04
“So this is the architecture. And we're going to basically train this to predict the outcomes of games given the board state. And we're also going to train this to predict what are good moves. So the OG AlphaGo paper or call AlphaGo lead, initialize this network with a supervised learning data set”
0:00
2:37:29