Skip to main content

New answers tagged

1 vote

Could AlphaZero be trained to prefer "beautiful" games?

Could a model be trained in the same way as AlphaZero, but with an additional component that measures the beauty/interestingness of its play Yes, as long as I can give you a game and you return me a ...
Alberto's user avatar
  • 1,938

Top 50 recent answers are included