模型与测量不确定性下动态治疗方案的鲁棒强化学习
Robust Reinforcement Learning for Dynamic Treatment Regimes under Model and Measurement Uncertainty
AI总结：
本研究提出鲁棒强化学习框架，将患者建模为隐藏上下文，通过鲁棒上下文马尔可夫决策过程解决泛化与鲁棒性问题，在转移性前列腺癌自适应治疗中得到的策略性能及帕累托优势均优于现有方法。
摘要：
我们开发了一种鲁棒强化学习（RL）框架，用于学习自适应治疗策略，该策略可在患者间泛化，并在生物标志物测量误差和疾病动态变化下保持可靠。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统一解决泛化与鲁棒性问题。将该框架应用于经临床数据校准的模拟器中转移性前列腺癌的自适应治疗，我们得到了可泛化且鲁棒的策略，其性能显著优于现有自适应治疗方法。具体而言，当生物标志物准确且疾病按预期演变时，我们在几乎不损失性能的情况下获得了鲁棒性，且所得策略在多种场景下均帕累托优于现有方法。我们的发现表明，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潜力。
英文摘要：
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-dominates the existing method across a diverse array of scenarios. Our findings suggest that robust RL holds great promise as a principled methodology for learning reliable adaptive treatment policies.
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。
