Monte Carlo Tree Search (MCTS) in AlphaGo Zero

In a Go game, AlphaGo Zero uses MC Tree Search to build a local policy to sample the next move. MCTS searches for possible moves and records the results in a search tree. As more searches are performed, the tree grows larger as well as its information. To make a move in Alpha-Go Zero, 1,600 searches will be computed. Then a local policy is constructed.