And MuZero, which beats AlphaZero and which does not use symbolic search over a simulator of board states but internal search over hidden state and value estimates?
Neural networks, on the other hand, are famously bad at symbolic reasoning tasks, which may ultimately have some basis in the fact that probability does not extend logic.
Considering all the progress on graph and relational networks and inference and theorem-proving and whatnot, this statement is giving a lot of hostages to fortune.
And MuZero, which beats AlphaZero and which does not use symbolic search over a simulator of board states but internal search over hidden state and value estimates?
Considering all the progress on graph and relational networks and inference and theorem-proving and whatnot, this statement is giving a lot of hostages to fortune.