arXiv cs.CY· Jianhan Zhang, Jitao Wang, John D. Piette, Donglin Zeng, Chengchun Shi, Zhenke Wu·· 10 小时前AI 评分29
用分布映射实现反事实公平的强化学习
A Distribution Mapping Approach to Counterfactually Fair Reinforcement Learning
AI 导读
一篇被 NeurIPS 2026 接收的论文提出数据预处理算法，与策略学习配合可在强化学习中实现反事实公平。该算法采用新的分位数分布映射方法逐步估计反事实状态与奖励，将常见的可加性假设作为特例纳入。作者从理论上证明了每步反事实不公平程度与无限时域次优差距可在温和正则条件下被界定，并在数值实验和真实介入式数字健康数据集上进行了验证。
正文 · 原文
Abstract:Reinforcement learning (RL) seeks to optimize sequential decisions to maximize population-level benefits over time. However, when deployed in high-stakes settings such as healthcare, RL decisions might systematically restrict some subpopulation's access to valuable services in a manner contrary to the values and goals of stakeholders. Counterfactual fairness (CF) offers a promising framework to address this problem based on causal reasoning. This paper develops a data preprocessing algorithm that, when used in tandem with policy learning, enables CF in RL. Our algorithm relies on a novel quantile distribution mapping method for sequentially estimating the counterfactual states and rewards in the data preprocessing step, subsuming common additivity assumptions used for counterfactual prediction as a special case. We theoretically prove that the per-step level of counterfactual unfairness and infinite-horizon suboptimality gap can be bounded under mild regularity conditions. We also empirically test our algorithm in numerical experiments as well as in application to a real-world interventional digital health dataset.
| Comments: | Accepted at NeurIPS 2026 |
| Subjects: | Machine Learning (stat.ML); Computers and Society (cs.CY); Machine Learning (cs.LG); Methodology (stat.ME) |
| Cite as: | arXiv:2608.08743 [stat.ML] |
| (or arXiv:2608.08743v2 [stat.ML] for this version) | |
| https://doi.org/10.48550/arXiv.2608.08743 arXiv-issued DOI via DataCite |
Submission history
From: Jianhan Zhang [view email]
[v1]
Sun, 9 Aug 2026 14:42:47 UTC (2,474 KB)
[v2]
Tue, 10 Nov 2026 07:16:42 UTC (8,056 KB)
来源：arXiv cs.CY · arxiv.org