用协变量平衡检测隐含混淆，评估医疗强化学习的可靠性
Evaluating covariate balance for long time horizon Markov decision processes
- 引入协变量平衡诊断法识别治疗推荐中的隐藏混淆
- 现有方法难以充分评估离线强化学习研究的稳健性
- 适合关注医疗RL方法论严谨性的研究人员
本文探讨了协变量平衡诊断在离线强化学习（offline RL）研究中的应用，旨在检测治疗推荐任务中潜在的隐藏混淆或模型误设问题。结果表明，现有离线RL研究存在较高的偏倚风险，且当前的协变量平衡度量不足以充分评估这些研究。无论何种情况，现有研究均无法被认定为统计上稳健。论文提出未来研究方向，以推动离线RL在治疗推荐问题上的方法学更趋严谨。
原文摘要 · Abstract (English)
This article explores the application of covariate balance diagnostics for detecting the presence of hidden confounding/model miss-specification in studies applying offline reinforcement learning (RL) to deriving optimal treatment recommendations. The results demonstrate that, either there is a high risk of bias within existing offline RL studies for treatment recommendations or, existing covariate balance metrics are not sufficient to assess such studies. Regardless, existing offline RL studies cannot be concluded as being statistically robust. The conclusions propose future research directions for obtaining more methodologically robust applications of offline RL to treatment recommendation problems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。