News for hackers. Stuff that matters.
Re:MuZero: Mastering Go, chess, shogi and Atari without rules by thomasahle on Wednesday December 23, 2020 @03:40PM (#25521948)
>> "[It] can start from nothing, and just through trial and error both discover the rules of the world

Unless they've changed a lot of things since the original paper, this is a bit exaggerated.

MuZero learns what moves are allowed in a given position/situation, but it still needs to know a finite overall set of possible actions.

E.g. for chess, it isn't told which fourty moves a available at each point in its search tree, but it still knows to only consider 64x64 discrete options.

Re:MuZero: Mastering Go, chess, shogi and Atari without rules by tromp on Wednesday December 23, 2020 @04:01PM (#25522187)
> only consider 64x64 discrete options

It wouldn't know that moving its King from e1 to g1 must be accompanied by moving its rook from h1 to f1.

Or that moving a white pawn from e5 to d6 must in some cases be accompanied by removing the black pawn on e6.

I guess the environment does these in response. That doesn't suffice for

moving its pawn from b7 to b8 must be accompanied by replacing said pawn by some other piece.