ZOJ 3329 概率dp

#include <cstdio>
#include <cstring>
const int maxn = 5E2 + 10;
int n, T, K1, K2, K3, a, b, c;
double p[maxn], A[maxn], B[maxn];
int main(int argc, char const *argv[])
{
	scanf("%d", &T);
	while (T--)
	{
		scanf("%d%d%d%d%d%d%d", &n, &K1, &K2, &K3, &a, &b, &c);
		double p0 = 1.0 / K1 / K2 / K3;
		memset(p, 0, sizeof(p));
		memset(A, 0, sizeof(A));
		memset(B, 0, sizeof(B));
		for (int i = 1; i <= K1; i++)
			for (int j = 1; j <= K2; j++)
				for (int k = 1; k <= K3; k++)
					if (i != a || j != b || k != c) p[i + j + k] += p0;
		for (int i = n; i >= 0; i--)
		{
			A[i] = p0, B[i] = 1;
			for (int j = 1; j <= K1 + K2 + K3; j++)
				A[i] += A[i + j] * p[j], B[i] += B[i + j] * p[j];
		}
		printf("%.16lf\n", B[0] / (1 - A[0]));
	}
	return 0;
}

设dp[i]表示达到i分时到达目标状态的期望，pk为投掷k分的概率，p0为回到0的概率
则dp[i]=∑(pk*dp[i+k])+dp[0]*p0+1;
都和dp[0]有关系，而且dp[0]就是我们所求，为常数
设dp[i]=A[i]*dp[0]+B[i];
代入上述方程右边得到：
dp[i]=∑(pk*A[i+k]*dp[0]+pk*B[i+k])+dp[0]*p0+1
     =(∑(pk*A[i+k])+p0)dp[0]+∑(pk*B[i+k])+1;

回推A[0]，B[0]，dp[0]=B[0]/(1-A[0])；