But it does use MCTS in training. You might say that it uses MCTS to generate a better player to learn from.
Sure. But the final player does not use MCTS, and it’s interesting that it’s not necessary then. (It’s even more interesting that the way they discovered they didn’t need MCTS is by hyperparameter optimization, but that’s a different discussion.)
But it does use MCTS in training. You might say that it uses MCTS to generate a better player to learn from.
Sure. But the final player does not use MCTS, and it’s interesting that it’s not necessary then. (It’s even more interesting that the way they discovered they didn’t need MCTS is by hyperparameter optimization, but that’s a different discussion.)