arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2204.12280math.OCcs.LO
收藏

方差惩罚的随机最短路问题

The variance-penalized stochastic shortest path problem

Jakob Piribauer, Ocan Sankur, Christel Baier

摘要:

随机最短路问题(SSPP)要求求解马尔可夫决策过程(MDP)中的非确定性选择,使得在到达目标状态之前的期望累积权重最大化。本文讨论了方差惩罚期望(VPE)的累积权重,这是一个变量的SSPP中,累积权重的方差的倍数作为惩罚。它表明,最佳的VPE在MDP与非负权重,以及最佳的确定性有限内存调度器可以计算在指数空间。最大VPE是否超过一个给定的理性的阈值问题被证明是EXPTIME困难的,并躺在NEXPTIME。此外,在其本身的权利上获得的方式是,方差最小调度所有的期望最优的调度器可以在多项式时间内计算的结果感兴趣。

英文摘要:

The stochastic shortest path problem (SSPP) asks to resolve the non-deterministic choices in a Markov decision process (MDP) such that the expected accumulated weight before reaching a target state is maximized. This paper addresses the optimization of the variance-penalized expectation (VPE) of the accumulated weight, which is a variant of the SSPP in which a multiple of the variance of accumulated weights is incurred as a penalty. It is shown that the optimal VPE in MDPs with non-negative weights as well as an optimal deterministic finite-memory scheduler can be computed in exponential space. The threshold problem whether the maximal VPE exceeds a given rational is shown to be EXPTIME-hard and to lie in NEXPTIME. Furthermore, a result of interest in its own right obtained on the way is that a variance-minimal scheduler among all expectation-optimal schedulers can be computed in polynomial time.

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。

↑