使用 alphabeta TicTacToe 找到最佳着法

Question

试图找到最佳着法和分数。我已经让我的程序正确 return 游戏得分，但我希望它也能 return 移动。我如何更改我的代码以使其执行此操作？ 类似于this and this. See my failed code here，如果游戏结束，None returned应该是移动。

def alphabeta(game_state, alpha, beta, our_turn=True):
    if game_state.is_gameover():
         return game_state.score()
    if our_turn:
        score = -9999
        for move in game_state.get_possible_moves():
            child = game_state.get_next_state(move, True)
            temp_max = alphabeta(child, alpha, beta, False) 
            if temp_max > score:
                score = temp_max
            alpha = max(alpha, score)
            if beta <= alpha:
                break
        return score
    else:
        score = 9999
        for move in game_state.get_possible_moves():
            child = game_state.get_next_state(move, False)
            temp_min = alphabeta(child, alpha, beta, True)
            if temp_min < score:
                score = temp_min
            beta = min(beta, score)
            if beta <= alpha:
                break
        return score

Answer 1

您可以跟踪到目前为止的最佳着法，例如：

    if game_state.is_gameover():
         return game_state.score(), None
    if our_turn:
        score = -9999
        for move in game_state.get_possible_moves():
            child = game_state.get_next_state(move, True)
            temp_max, _ = alphabeta(child, alpha, beta, False) # _ to disregard the returned move
            if temp_max > score:
                score = temp_max
                best_move = move
            alpha = max(alpha, score)
            if beta <= alpha:
                break
        return score, best_move

其他情况类似