LeetCode 464. Can I Win--动态规划

题目链接

464. Can I Win

In the "100 game," two players take turns adding, to a running total, any integer from 1..10. The player who first causes the running total to reach or exceed 100 wins. 

What if we change the game so that players cannot re-use integers? 

For example, two players might take turns drawing from a common pool of numbers of 1..15 without replacement until they reach a total >= 100.

Given an integer maxChoosableInteger and another integer desiredTotal, determine if the first player to move can force a win, assuming both players play optimally. 

You can always assume that maxChoosableInteger will not be larger than 20 and desiredTotal will not be larger than 300.

Example

Input:
maxChoosableInteger = 10
desiredTotal = 11

Output:
false

Explanation:
No matter which integer the first player choose, the first player will lose.
The first player can choose an integer from 1 up to 10.
If the first player choose 1, the second player can only choose integers from 2 up to 10.
The second player will win by choosing 10 and get a total = 11, which is >= desiredTotal.
Same with other integers chosen by the first player, the second player will always win.

解:

如果数字可以重复,那么用动态规划开一个dp数组应该就可以解决了,但是现在数字不能重复,那么在每一次决策时,都要考虑当前哪些数可以选择,所以需要记录这个状态,最大值是20,用一个长度是21的string来记录这个状态就可以了,其中字符'0'代表不可用,'1'代表可用,用STL库的map<string,bool>存储状态string对应的是否能赢,每次得到一个状态的结果就将他放入map,每次用到一个状态是先去map中匹配,能匹配到可以直接返回布尔值,匹配不到,判断后将结果放入map。

能赢的情况:1.当前最大可选的数大于当前的desiredTotal   2.选了其中一个数之后,对方赢不了

代码:

class Solution {
public:
    bool dp(int desiredTotal, string status, map<string,bool>* container, int size) {
        if (container->find(status) != container->end())  return container->at(status);
        for (int i = size; i >= 1; i--) {
            if (status[i] == '1') {
                string a = status;
                a[i] = '0';
                if (i >= desiredTotal || dp(desiredTotal-i, a, container, size) == false) {
                    container->insert(std::pair<string, bool>(status, true));
                    return true;
                }
            }
        }
        container->insert(std::pair<string, bool>(status, false));
        return false;
    }
    bool canIWin(int maxChoosableInteger, int desiredTotal) {
        if (desiredTotal <= maxChoosableInteger)  return true;
        if (desiredTotal > maxChoosableInteger*(maxChoosableInteger+1)/2) return false;
        string status;
        for (int i = 0; i < 21; i++) status += '1';
        map<string, bool>* temp = new map<string, bool>;
        return dp(desiredTotal, status, temp, maxChoosableInteger);
    }
};



六、状压DP的优化技巧 6.1 预处理合法状态 很多问题中,大部分状态是不合法的,可以预先筛选: cpp vector valid_states; for (int state = 0; state < (1 << n); ++state) { if (check(state)) { // 检查state是否合法 valid_states.push_back(state); } } 6.2 滚动数组优化 当状态只依赖前一个阶段时,可以节省空间: cpp vector<vector> dp(2, vector(size)); // 只保留当前和上一个状态 int now = 0, prev = 1; for (int i = 1; i <= n; ++i) { swap(now, prev); for (auto& state : valid_states) { dp[now][state] = 0; // 清空当前状态 // 状态转移… } } 6.3 记忆化搜索实现 有时递归形式更直观: cpp int memo[1<<20][20]; // 记忆化数组 int dfs(int state, int u) { if (memo[state][u] != -1) return memo[state][u]; // 递归处理… return memo[state][u] = res; } 七、常见问题与调试技巧 7.1 常见错误 位运算优先级:总是加括号,如(state & (1 << i)) 数组越界:状态数是2ⁿ,不是n 初始状态设置错误:比如TSP中dp[1][0] = 0 边界条件处理不当:如全选状态是(1<<n)-1,不是1<<n 7.2 调试建议 打印中间状态:将二进制状态转换为可视化的形式 cpp void printState(int state, int n) { for (int i = n-1; i >= 0; --i) cout << ((state >> i) & 1); cout << endl; } 从小规模测试用例开始(如n=3,4) 使用assert检查关键假设 八、学习路线建议 初级阶段: 练习基本位操作 解决简单状压问题(如LeetCode 464、526题) 中级阶段: 掌握经典模型(TSP、棋盘覆盖) 学习优化技巧(预处理、滚动数组) 高级阶段: 处理高维状压(如需要同时压缩多个状态) 结合其他算法(如BFS、双指针) 九、实战练习题目推荐 入门题: LeetCode 78. Subsets(理解状态表示) LeetCode 464. Can I Win(简单状压DP) 中等题: LeetCode 526. Beautiful Arrangement LeetCode 691. Stickers to Spell Word 经典题: POJ 2411. Mondriaan’s Dream(棋盘覆盖) HDU 3001. Travelling(三进制状压) 挑战题: Codeforces 8C. Looking for Order Topcoder SRM 556 Div1 1000. LeftRightDigitsGame2 记住,掌握状压DP的关键在于: 彻底理解二进制状态表示 熟练运用位运算 通过大量练习培养直觉 希望这份超详细的教程能帮助你彻底掌握状压DP!如果还有任何不明白的地方,可以针对具体问题继续深入探讨。 请帮我转成markdown语法输出,谢谢
最新发布
08-13
<think>好的,我现在需要帮用户解决一个Node.js中的TypeError问题,错误信息是“TypeError: cb is nota function”。用户提供的错误堆栈显示这个问题发生在parseCookie函数中,具体是在调用cb的时候。首先,我得分析可能的原因。 首先,错误信息指出cb不是一个函数。这通常意味着在调用某个函数时,传入的回调参数不是函数类型。可能的情况包括: 1. **回调未正确传递**:可能在调用parseCookie时,没有正确传递回调函数,或者传递了错误的参数类型。 2.**函数定义参数不匹配**:parseCookie函数可能期望一个回调函数作为参数,但在调用时可能没有传入或者传入了其他类型的值。 3. **异步处理问题**:可能使用了错误的回调方式,比如应该使用函数的地方用了Promise或其他异步处理方式。 4. **第三方库版本问题**:可能使用的库版本过旧或存在bug,导致回调参数处理异常。 接下来,我需要根据用户提供的堆栈信息来定位具体的位置。错误发生在leetcode.js的parseCookie函数第542行,调用cb的地方。这可能是一个插件或模块中的函数,用户可能在使用VSCode的LeetCode插件时遇到了问题,尤其是在处理cookie登录时。 考虑到用户提到的环境是Node.js v22.17.0,可能存在兼容性问题。某些旧版本的库可能不兼容较新的Node.js版本,导致回调参数未被正确处理。 用户可能需要检查以下几点: -检查parseCookie函数的定义,确认其参数是否正确要求一个回调函数。 -查看调用parseCookie的地方是否正确传递了回调函数。 -确认第三方库(如vsc-leetcode-cli)是否支持当前Node.js版本,可能需要升级或降级版本。- 查看是否有相关的Issue或更新日志,可能其他用户也遇到了类似的问题。 可能的解决方案包括:1. 更新LeetCode插件到最新版本,修复可能存在的bug。2. 降级Node.js版本到更稳定的版本,比如LTS版本,以确保兼容性。 3. 如果问题由特定代码引起,检查代码中回调函数的使用是否正确。 4.清除缓存或重新安装插件,解决可能的配置错误。 此外,用户可能需要提供更多的上下文信息,比如他们正在执行的操作,或者相关的代码片段,以便更准确地定位问题。例如,是否在自定义代码中调用了parseCookie函数,或者这完全是由插件内部触发的错误。 总结来说,用户需要检查回调函数的传递和定义,确认第三方库的兼容性,并考虑环境配置是否合适。如果问题持续存在,建议查看插件的官方文档或提交Issue寻求帮助。</think>`TypeError: cb is not a function` 表示在调用 `parseCookie` 函数时,传递的 `cb` 参数 **不是函数类型**。以下是关键分析及解决方案: --- ### ❌ 错误原因 1. **回调参数类型错误** `parseCookie` 函数内部尝试调用 `cb(...)`,但传入的 `cb` 可能是 `null`、`undefined` 或其他非函数类型(如字符串、数字)。 2. **函数定义与调用不匹配** - 函数定义时要求传入回调函数: ```javascript function parseCookie(cookieStr, cb) { ... } ``` - 调用时却未传递有效回调: ```javascript parseCookie("key=value", "错误参数"); // 第二个参数不是函数 ``` 3. **第三方库兼容性问题** 根据路径 `vsc-leetcode-cli` 和 Node.js v22.17.0,可能是 **LeetCode 插件与最新 Node.js 版本不兼容**,导致内部回调参数传递异常。 --- ### ✅ 解决方案 1. **检查调用方代码** 定位 `parseCookie` 的调用位置(如 `leetcode.js` 第 565 行),确保传递正确的回调函数: ```javascript parseCookie("key=value", (err, result) => { if (err) throw err; console.log(result); }); ``` 2. **更新插件版本** `vsc-leetcode-cli` 可能存在旧版 bug,尝试更新插件: ```bash npm install -g vsc-leetcode-cli@latest ``` 或重新安装 VSCode LeetCode 插件。 3. **降级 Node.js 版本** Node.js v22.x 是较新版本,可能存在兼容性问题。建议切换到 **LTS 版本(如 v18.x 或 v20.x)**: - 使用 [nvm](https://github.com/nvm-sh/nvm) 管理多版本 Node.js。 4. **临时修复(绕过错误)** 在调用 `parseCookie` 前增加类型检查: ```javascript if (typeof cb === 'function') { cb(null, parsedCookie); } else { console.error("回调参数必须为函数"); } ``` --- ### 🧪 验证步骤 1. 确认 Node.js 版本: ```bash node -v # 推荐使用 v18.x 或 v20.x ``` 2. 检查插件依赖: 进入插件目录并更新依赖: ```bash cd ~/.vscode-huawei/extensions/leetcode.vscode-leetcode-0.18.1 npm install ``` --- ### ❓ 常见相关问题
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值