>>214の
4. モンテカルロ法(Rollout)は使っていない。
はこれが基だろう
AlphaGo Zero does not use “rollouts” - fast, random games used by other Go programs
to predict which player will win from the current board position.
Instead, it relies on its high quality neural networks to evaluate positions.
https://deepmind.com/blog/alphago-zero-learning-scratch/
