Story: Reinforcement Learning At Facebook with Jason Gauci
CoRecursive: Coding Stories
00:00
Alphago Can Play Against Itself
Alphago is constantly trying to make the best, what it thinks is the best move. The more confident you want to be that a model isn't worse, the less it's able to change from whatever's out there right now. "We have models that we launched a year ago that are still getting better," he says.
Transcript
Play full episode
