-
AIs Have Mastered Chess. Will Go Be Next? - IEEE Spectrum
- An MCTS-based program needs some intelligent way to select which branches of the game tree to grow. Good policies for doing that strike a balance between exploration (branching off nodes with few simulations and therefore high uncertainty about their prospects for leading to a win) and exploitation (pursuing moves that branch off the most promising nodes).
- The RAVE component tells the program to collect another set of statistics during each simulation. If the random sequence of moves results in a win, every grid point where the program placed one of its stones (thus roughly half the locations on the board) is given a numerical bonus.
-
Choose the move with the largest number of wins. And this is indeed the standard approach.
-