arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2601.06976math.OC
收藏

基于信念状态的 restless bandit 治疗依从性模型:通过部分守恒定律的 Whittle 可指标化

A belief-state restless bandit model for treatment adherence: Whittle indexability via partial conservation laws

Universidad Carlos III de Madrid(马德里卡洛斯三世大学)

José Niño-Mora, Ángel Pellitero García

AI总结:

针对容量受限的治疗依从性外展问题,提出基于信念状态的 restless multi-armed bandit 模型,利用部分守恒定律证明单患者阈值策略最优性和可指标化,推导闭式 Whittle 指标,并在多患者场景中实现高效拉格朗日松弛策略。

摘要:

我们通过一个基于信念状态的 restless multi-armed bandit 模型研究临床动机下的容量受限治疗依从性外展问题,其中每个患者是一个部分观测的两状态马尔可夫决策过程,干预会引发重置型信念动态。对于折扣准则,利用基于部分守恒定律(PCL)的条件建立单患者阈值策略最优性和可指标性(阈值可指标性),并得到闭式 Whittle 指标、阈值性能指标和显式最优阈值映射。我们还证明了在不变信念核心上的单患者长期平均准则类似结果,并得到显式平均准则 Whittle 指标。对于多患者模型,PCL 推导的公式给出了解析拉格朗日松弛、高效对偶界和可计算的拉格朗日指标基准策略,包括一种强制容量变体。我们分析了 Whittle 指标如何依赖于 lapse 和自发恢复概率。在具有两种类型、三种类型和抖动有限混合人群的大规模实验中,Whittle 和强制容量拉格朗日指标策略表现最强,而在容量紧张时,短视优先排序可能显著更差。

英文摘要:

We study clinically motivated capacity-constrained treatment-adherence outreach through a belief-state restless multi-armed bandit model, in which each patient is a partially observed two-state Markov decision process and interventions induce reset-type belief dynamics. For the discounted criterion, partial conservation law (PCL)-based conditions are used to establish single-patient threshold-policy optimality and indexability (threshold-indexability) and yield a closed-form Whittle index, threshold performance metrics, and an explicit optimal threshold map. We also prove a single-patient long-run average analogue on the invariant belief core and obtain an explicit average-criterion Whittle index. For the multi-patient model, the PCL-derived formulas give an analytic Lagrangian relaxation, efficient dual bounds, and computable Lagrangian index benchmark policies, including a forced-capacity variant. We analyze how the Whittle index depends on lapse and spontaneous-recovery probabilities. In large-scale experiments with two-type, three-type, and jittered finite-mixture populations, the Whittle and forced-capacity Lagrangian index policies are the strongest performers, while myopic prioritization can be substantially worse under tight capacity.

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。

↑