让决策模型在不确定时选择放弃，更安全可靠。
Policy Learning with Abstention
- 先找近优策略集，再基于分歧构建拒决规则
- 已知倾向性时达O(1/n)快速收敛，未知时用双重稳健优化
- 适合高风险场景，如医疗、广告个性化推荐
策略学习算法广泛应用于个性化医疗和广告等领域，以制定个体化干预方案。然而，大多数方法在预测不确定时仍强制决策，这在高风险场景中存在风险。本文研究带拒决的策略学习：当策略拒绝决策时，可选择安全默认或专家介入，并获得额外小奖励。我们提出两阶段学习器：首先识别一组近最优策略，再根据其分歧构造拒决规则。当倾向性已知时，建立O(1/n)型的快速后悔上界；通过双重稳健目标，将该上界扩展至倾向性未知情形。进一步表明，拒决是一种通用工具，可在无实现性假设下于边际条件下提升性能，通过防范微小数据偏移连接分布鲁棒策略学习，并支持安全策略改进，确保对基线策略的高概率提升。
原文摘要 · Abstract (English)
Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in high-stakes settings. We study policy learning with abstention, where a policy may defer to a safe default or an expert. When a policy abstains, it receives a small additive reward on top of the value of a random guess. We propose a two-stage learner that first identifies a set of near-optimal policies and then constructs an abstention rule from their disagreements. We establish fast O(1/n)-type regret guarantees when propensities are known, and extend these guarantees to the unknown-propensity case via a doubly robust (DR) objective. We further show that abstention is a versatile tool with direct applications to other core problems in policy learning: it yields improved guarantees under margin conditions without the common realizability assumption, connects to distributionally robust policy learning by hedging against small data shifts, and supports safe policy improvement by ensuring improvement over a baseline policy with high probability.
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。