arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1202.4175cs.LO
收藏

Büchi目标马氏决策过程经典算法的平均情况分析

Average Case Analysis of the Classical Algorithm for Markov Decision Processes with Büchi Objectives

Krishnendu Chatterjee, Manas Joglekar, Nisarg Shah

摘要:

我们认为马尔可夫决策过程(MDP)与$ω$ -定期规格作为奇偶校验的目标。我们考虑的问题,计算的一组几乎肯定获胜的顶点,从那里可以确保目标的概率为1。用于计算奇偶目标的几乎确定获胜集的算法迭代地使用Büchi目标(奇偶目标的特殊情况)的几乎确定获胜集的解。我们首次研究了经典算法的平均情况下的复杂性计算几乎肯定获胜的顶点MDP Büchi目标。我们的贡献如下:首先,我们表明,对于恒定的出度的MDP的预期迭代次数是最多对数和平均情况下的运行时间是线性的(相比最坏情况下的线性迭代次数和二次时间复杂度)。其次,我们表明,一般MDPs的预期迭代次数是恒定的,平均情况下的运行时间是线性的(再次相比,最坏情况下的线性迭代次数和二次时间复杂度)。最后,我们还表明,给定所有的图是同样可能的,经典算法需要超过常数的迭代次数的概率是指数小。

英文摘要:

We consider Markov decision processes (MDPs) with $ω$-regular specifications given as parity objectives. We consider the problem of computing the set of almost-sure winning vertices from where the objective can be ensured with probability 1. The algorithms for the computation of the almost-sure winning set for parity objectives iteratively use the solutions for the almost-sure winning set for Büchi objectives (a special case of parity objectives). We study for the first time the average case complexity of the classical algorithm for computing almost-sure winning vertices for MDPs with Büchi objectives. Our contributions are as follows: First, we show that for MDPs with constant out-degree the expected number of iterations is at most logarithmic and the average case running time is linear (as compared to the worst case linear number of iterations and quadratic time complexity). Second, we show that for general MDPs the expected number of iterations is constant and the average case running time is linear (again as compared to the worst case linear number of iterations and quadratic time complexity). Finally we also show that given all graphs are equally likely, the probability that the classical algorithm requires more than constant number of iterations is exponentially small.

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。

↑