mcts1.py 文件源码

def _evaluate_rollout(self, state, limit):
        # _, player, legal_moves = Game.possible_moves(state)
        winner = 0

#         old_board = Board()
#         old_board.stones = state
        player = None
        for i in range(limit):
            legal_states, p, legal_moves = Game.possible_moves(state)
            if player is None:
                player = p
            if len(legal_states) == 0:
                break

            probs = self._rollout(state, legal_moves)
            mask = np.full_like(probs, -0.01)
            mask[:, legal_moves] = probs[:, legal_moves]
            probs = mask

            best_move = np.argmax(probs, 1)[0]

            idx = np.where(legal_moves == best_move)[0]
#             if idx.size == 0:
#                 print(i, idx)
#                 print(best_move)
#                 print(probs.shape)
#                 print(legal_moves)
#                 print(probs)
            assert idx.size == 1
            idx = idx[0]
            st1 = legal_states[idx]

            over, winner, last_loc = st1.is_over(state)
            if over:
                break

            state = st1
        else:
            # If no break from the loop, issue a warning.
            print("WARNING: rollout reached move limit")

        if winner == 0:
            return 0
        else:
            return 1 if winner == player else -1