Joe Joyce wrote on Mon, Dec 11, 2017 04:19 AM UTC:
AlphaZero is a neural net which learns by playing against itself, starting with random moves and working up to a rating of over 3300, iirc. It runs on some very fancy hardware, so its learning time is misleading. It played millions of games against itself to learn Go. I'm curious about just what it learns when it's teaching itself a game. How dependent is it on the exact board geometry and each player moving only one (or a few) pieces per turn? If the game is a very large (~1000 - 10,000 squares or more) massively multi-move abstract strategy war game with a board that can change between games, does that sort of thing make any significant difference, or merely add some time to the AI learning process?
AlphaZero is a neural net which learns by playing against itself, starting with random moves and working up to a rating of over 3300, iirc. It runs on some very fancy hardware, so its learning time is misleading. It played millions of games against itself to learn Go. I'm curious about just what it learns when it's teaching itself a game. How dependent is it on the exact board geometry and each player moving only one (or a few) pieces per turn? If the game is a very large (~1000 - 10,000 squares or more) massively multi-move abstract strategy war game with a board that can change between games, does that sort of thing make any significant difference, or merely add some time to the AI learning process?