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 2204.04780cs.AI
收藏

局部转移下约束MDP与随机最短路径的完全多项式时间近似方案

A Fully Polynomial Time Approximation Scheme for Constrained MDPs and Stochastic Shortest Path under Local Transitions

Khalifa University(哈利法大学)

Majid Khonji

AI总结:

针对局部转移下即使视界为2仍NP难的约束MDP及CC-MDP/SSP变体,提出可计算近优确定性策略的完全多项式时间近似方案。

摘要:

固定视界约束马尔可夫决策过程(C-MDP)是在运行约束下于随机环境中进行规划的著名模型。机会约束MDP(CC-MDP)是一种变体,它允许约束约束违反概率,这在许多安全关键应用中是理想的。CC-MDP还可以对一类在死端条件下称为随机最短路径(SSP)的MDP进行建模,其中到达目标的概率与到达目标的成本之间存在权衡。本工作研究(C)C-MDP的结构,特别是涉及局部转移的一个重要变体。在该变体中,状态可达性表现出一定程度的局部性,并独立于其余状态。更准确地说,在给定时间,共享某些可达未来状态的状态数量始终是常数。即使规划视界为2,局部转移下的(C)C-MDP也是NP难的。在本工作中,我们为(C)C-MDP提出了一种完全多项式时间近似方案,用于计算(近)最优确定性策略。该算法属于理论上可获得的最佳近似算法之一,并为约束MDP及其变体的可近似性提供了见解。

英文摘要:

The fixed-horizon constrained Markov Decision Process (C-MDP) is a well-known model for planning in stochastic environments under operating constraints. Chance-Constrained MDP (CC-MDP) is a variant that allows bounding the probability of constraint violation, which is desired in many safety-critical applications. CC-MDP can also model a class of MDPs, called Stochastic Shortest Path (SSP), under dead-ends, where there is a trade-off between the probability-to-goal and cost-to-goal. This work studies the structure of (C)C-MDP, particularly an important variant that involves local transition. In this variant, the state reachability exhibits a certain degree of locality and independence from the remaining states. More precisely, the number of states, at a given time, that share some reachable future states is always constant. (C)C-MDP under local transition is NP-Hard even for a planning horizon of two. In this work, we propose a fully polynomial-time approximation scheme for (C)C-MDP that computes (near) optimal deterministic policies. Such an algorithm is among the best approximation algorithm attainable in theory and gives insights into the approximability of constrained MDP and its variants.

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。

↑