求解简单随机对策的递归算法
A Recursive Algorithm for Solving Simple Stochastic Games
摘要:
我们提出了两个递归策略改进算法解决简单的随机对策。首先,我们提出了一个算法,解决SSG度$d$,使用最多$O\left(\left\lfloor(d+1)^2/2\right\rfloor^{n/2}\right)$迭代,与$n$的MAX顶点的数量。然后,我们专注于二进制SSG,并提出了一个算法,具有复杂性$O\left(φ^nPoly(N)\right)$,其中$φ= (1 + \sqrt{5})/2$是黄金比例。据我们所知,这是第一个使用$c < 1$访问$2^{cn}$策略的确定性策略改进算法。
英文摘要:
We present two recursive strategy improvement algorithms for solving simple stochastic games. First we present an algorithm for solving SSGs of degree $d$ that uses at most $O\left(\left\lfloor(d+1)^2/2\right\rfloor^{n/2}\right)$ iterations, with $n$ the number of MAX vertices. Then, we focus on binary SSG and propose an algorithm that has complexity $O\left(φ^nPoly(N)\right)$ where $φ= (1 + \sqrt{5})/2$ is the golden ratio. To the best of our knowledge, this is the first deterministic strategy improvement algorithm that visits $2^{cn}$ strategies with $c < 1$.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。