diff --git a/AlphaGo/game.py b/AlphaGo/game.py
index 2a60a06..919a5d5 100644
--- a/AlphaGo/game.py
+++ b/AlphaGo/game.py
@@ -202,6 +202,24 @@ class Executor:
             elif color_estimate < 0:
                 return utils.WHITE
 
+    def _add_nearby_stones(self, neighbor_vertex_set, start_vertex_x, start_vertex_y, x_diff, y_diff, num_step):
+        '''
+        add the nearby stones around the input vertex
+        :param neighbor_vertex_set: input list
+        :param start_vertex_x: x axis of the input vertex
+        :param start_vertex_y: y axis of the input vertex
+        :param x_diff: add x axis
+        :param y_diff: add y axis
+        :param num_step: number of steps to be added
+        :return:
+        '''
+        for step in xrange(num_step):
+            new_neighbor_vertex = (start_vertex_x, start_vertex_y)
+            if self._in_board(new_neighbor_vertex):
+                neighbor_vertex_set.append((start_vertex_x, start_vertex_y))
+            start_vertex_x += x_diff
+            start_vertex_y += y_diff
+
 
 
 
diff --git a/AlphaGo/strategy.py b/AlphaGo/strategy.py
index ff5d79f..327111d 100644
--- a/AlphaGo/strategy.py
+++ b/AlphaGo/strategy.py
@@ -246,7 +246,7 @@ class strategy(object):
         self.simulator.history = copy.copy(history)
         self.simulator.board = copy.copy(history[-1])
         state = self.data_process(self.simulator.history, color)
-        mcts = MCTS(self.simulator, self.evaluator, state, self.simulator.size ** 2 + 1, inverse=True, max_step=100)
+        mcts = MCTS(self.simulator, self.evaluator, state, self.simulator.size ** 2 + 1, inverse=True, max_step=10)
         temp = 1
         prob = mcts.root.N ** temp / np.sum(mcts.root.N ** temp)
         choice = np.random.choice(self.simulator.size ** 2 + 1, 1, p=prob).tolist()[0]