[论文] Robust Reinforcement Learning for Dynamic Treatment Regimes under Mode...

论文概要

研究领域: ML 作者: Chengze Xie, Xuan Wang, Ying Ding, Hairong Wang, Yan Li 发布时间: 2026-10-15 arXiv: 2610.22336

中文摘要

我们开发了一个鲁棒强化学习框架，用于学习能够跨患者泛化并在测量生物标志物误差和疾病动态变化下保持可靠的自适应治疗策略。通过将患者建模为隐藏上下文，我们通过鲁棒上下文马尔可夫决策过程以统一方式解决泛化和鲁棒性问题。将该框架应用于转移性前列腺癌的自适应治疗，在根据临床数据校准的模拟器中，我们获得了大幅优于现有方法的策略。当生物标志物准确且疾病按预期演变时，我们几乎无损地获得鲁棒性，且所得策略在多样化场景阵列中帕累托优于现有方法。鲁棒 RL 作为学习可靠自适应治疗策略的原则性方法具有巨大前景。

原文摘要

We develop a robust reinforcement learning (RL) framework for learning adaptive treatment policies that generalize across patients and remain reliable under errors in the measured biomarker and shifts in the disease dynamics. By modeling the patient as a hidden context, we address generalization and robustness in a unified manner through robust contextual Markov decision processes. Applying our framework to adaptive therapy for metastatic prostate cancer in a simulator calibrated to clinical data, we obtain generalizable and robust policies that substantially outperform the existing adaptive therapy method. In particular, we attain robustness with almost no loss of performance when the biomarker is accurate and the disease evolves as anticipated, and find that the resulting policy Pareto-d...

#论文 #arXiv #ML #小凯