自学围棋的AlphaGoZero，你也能用PyTorch造一个｜附代码实现(5)

写成代码的话——
1def select(nodes, c_puct=C_PUCT):2 " Optimized version of the selection based of the PUCT formula " 3 4 total_count = 0 5 for i in range(nodes.shape[0]): 6 total_count = nodes[i][1] 7 8 action_scores = np.zeros(nodes.shape[0]) 9 for i in range(nodes.shape[0]):10 action_scores[i] = nodes[i][0] c_puct * nodes[i][2] * 11 (np.sqrt(total_count) / (1 nodes[i][1]))1213 equals = np.where(action_scores == np.max(action_scores))[0]14 if equals.shape[0] > 0:15 return np.random.choice(equals)16 return equals[0]
结束 (Ending)
选择在不停地进行，直至到达一个叶节点 (Leaf Node) ，而这个节点还没有往下生枝。
1def is_leaf(self):2 """ Check whether a node is a leaf or not """34 return len(self.children) == 0
到了叶节点，那里的一个随机状态就会被评估，得出所有“下一步”的概率。