c# - 连接四(Unity3D 和 C#)的 Minimax : Problems

Question

我正在使用 Unity3D (C#) 中的 AI 开发四连胜游戏。为此，我根据此(德语)Pseudocode 使用 MiniMax 算法.

AI 的表现仍然很糟糕。它试图连续获得 4 个，尽管只有三个空闲字段。 AI 总是遍历行并仅在需要时才阻止。不幸的是，它并不总是会阻塞。

哪里隐藏问题？我忘记了什么？

当下一步没有人赢或输时，我如何整合 AI 的随机 Action 。

这是我的源代码:

最小最大深度 = 4

函数调用:Max(minimaxDepth, fieldCopy);

int Max (int depth, int[,] fieldCopy)
{
    int maxValue = -9999;
    int moveValue;
    bool winAI = false;
    bool winHuman = false;
    bool isStoneBelow = false;

    for (int y = 0; y < 6; y++) {
        for (int x = 0; x < 7; x++) {
            if (y > 0) {
                //is a stone under it?
                if (fieldCopy [x, y - 1] == 1 || fieldCopy [x, y - 1] == 2) {
                    isStoneBelow = true;
                } else {
                    isStoneBelow = false;
                }
            } else {
                isStoneBelow = true;
            }

            // possible move?
            if (fieldCopy [x, y] != 1 && fieldCopy [x, y] != 2 && isStoneBelow == true) {   
                isStoneBelow = false;
                fieldCopy [x, y] = 2; //simulate move
                winAI = false;
                winHuman = false;

                //Is there a winner?
                if (CheckWin (x, y, 2, fieldCopy)) {
                    winAI = true;
                    winHuman = false;
                }

                //No more moves possible?
                if (depth <= 1 || winAI == true) { 
                    moveValue = evaluationFunction (winAI, winHuman);       //evaluate the move
                } else {
                    moveValue = Min (depth - 1, fieldCopy);
                }

                fieldCopy [x, y] = 0; //Reset simulated move

                if (moveValue > maxValue) {
                    maxValue = moveValue;
                    if (depth == minimaxDepth) {
                        aiMoveX = x; // next move
                    }
                }
            }
        }
    }
    return maxValue;
}

int Min (int depth, int[,] fieldCopy)
{
    int minValue = 9999;
    int moveValue;
    bool winAI = false;
    bool winHuman = false;
    bool isStoneBelow = false;
    bool loopBreak = false;

    for (int y = 0; y < 6; y++) {
        for (int x = 0; x < 7; x++) {
            if (y > 0) {
                //is a stone under it?
                if (fieldCopy [x, y - 1] == 1 || fieldCopy [x, y - 1] == 2) {
                    isStoneBelow = true;
                } else {
                    isStoneBelow = false;
                }
            } else {
                isStoneBelow = true;
            }

            // possible move?
            if (fieldCopy [x, y] != 1 && fieldCopy [x, y] != 2 && isStoneBelow == true) {   
                isStoneBelow = false;
                fieldCopy [x, y] = 1; //simulate move
                winHuman = false;
                winAI = false;

                //Is there a winner?    
                if (CheckWin (x, y, 1, fieldCopy)) {
                    winHuman = true;
                    winAI = false;
                }

                //No more moves possible?
                if (depth <= 1 || winHuman == true) {  
                    moveValue = evaluationFunction (winAI, winHuman);       //evaluate the move
                } else {
                    moveValue = Max (depth - 1, fieldCopy);
                }

                fieldCopy [x, y] = 0; //Reset simulated move

                if (moveValue < minValue) {
                    minValue = moveValue;
                }
            }
        }
    }
    return minValue;
}


int evaluationFunction (bool winAI, bool winHuman)
{
    if (winAI) { 
        return 1;
    } else if (winHuman) {
        return -1;
    } else {
        return 0;
    }
}

感谢您的帮助!

Answer 1

我认为问题在于您的评估功能。您不应评估其中一名玩家是否获胜，而应评估他们在游戏中的状态。一个可能的考虑因素是该玩家棋子的最长连续链的长度。这准确地显示了每个玩家距离获胜还有多远，而不是在玩家即将获胜但尚未获胜时返回相同的值。

为清楚起见，这里是伪代码:

int evaluationFunction (int depth)
{
    // max_ai_chain and max_human_chain are global variables that 
    // should be updated at each piece placement

    if (depth % 2 == 0) // assuming AI gets calculated on even depth (you mentioned your depth is 4)
    { 
        return max_ai_chain;
    } else {
        return max_human_chain;
    }
}