Re:MuZero: Mastering Go, chess, shogi and Atari without rules
by thomasahle on Thursday December 24, 2020 @03:02AM
(#25525827)
I suppose you are right. But MuZero won't be able to do this, since it's training forces it to consider legal moves in its planning.
Re:MuZero: Mastering Go, chess, shogi and Atari without rules
by nightcracker on Thursday December 24, 2020 @09:19AM
(#25527636)
No it doesn't. MuZero does its planning entirely in its own latent space (it may not even actually think of the game in terms of 'moves' but in whatever steps it considers relevant instead), only the output is filtered for legal moves.
It's no different than a monkey operating a chess computer that makes sure the monkey only performs legal moves. Your suggestion would be akin to suggesting that the chess computer would be affecting the monkey's mind so that it can only think in terms of legal chess moves.
This isn't just weak players. E.g. strong chess players often consider moves as if blocking pawns weren't there. They might consider a bishop to be on a strong diagonal despite there being a blocking pawn because they can imagine moves that would happen if that pawn would disappear.