Machine Learning - A Cooperative Game?

Tony jabara is the vice president of machine learning engineering at spartify. He wants to move beyond base line machine learning to a method called reinforcement learning. In games like go chess and starcraft, we're just getting the highest possible score in the moment. Its often not the best long term strategy to actually win the game. Tony lays it out as a kind of three dimensional landscape with longitude, latitude and altitude. If your state is near a valley, if we do some things that are not so good, you may end up getting pushed and nudged by all our surfaces into this valley where you're no longer happy. And then you councel your member an ideally,