# Fair Off-Policy Learning from Observational Data

arXiv: https://arxiv.org/abs/2303.08516 · HTML: https://mlsanity.com/paper/2303.08516/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 36 of its 72 references that are in the map.
- First posted on arXiv 15 Mar 2023.

## Builds on (most cited first, 30 of 36)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Learning Adversarially Fair and Transferable Representations](https://mlsanity.com/paper/1802.06309/) (2018)
- [Flexibly Fair Representation Learning by Disentanglement](https://mlsanity.com/paper/1906.02589/) (2019)
- [Avoiding Discrimination through Causal Reasoning](https://mlsanity.com/paper/1706.02744/) (2017)
- [Fair Inference On Outcomes](https://mlsanity.com/paper/1705.10378/) (2017)
- [On the Fairness of Disentangled Representations](https://mlsanity.com/paper/1905.13662/) (2019)
- [Nonparametric Estimation of Heterogeneous Treatment Effects: From Theory to Learning Algorithms](https://mlsanity.com/paper/2101.10943/) (2021)
- [Semiparametric doubly robust targeted double machine learning: a review](https://mlsanity.com/paper/2203.06469/) (2022)
- [Causal Transformer for Estimating Counterfactual Outcomes](https://mlsanity.com/paper/2204.07258/) (2022)
- [Fairness in Reinforcement Learning](https://mlsanity.com/paper/1611.03071/) (2016)
- [Assessing Algorithmic Fairness with Unobserved Protected Class Using Data Combination](https://mlsanity.com/paper/1906.00285/) (2019)
- [Confounding-Robust Policy Improvement](https://mlsanity.com/paper/1805.08593/) (2018)
- [Policy Learning for Fairness in Ranking](https://mlsanity.com/paper/1902.04056/) (2019)
- [Fairness in Credit Scoring: Assessment, Implementation and Profit Implications](https://mlsanity.com/paper/2103.01907/) (2021)
- [Learning Fair Policies in Multiobjective (Deep) Reinforcement Learning with Average and Discounted Rewards](https://mlsanity.com/paper/2008.07773/) (2020)
- [Policy Evaluation and Optimization with Continuous Treatments](https://mlsanity.com/paper/1802.06037/) (2018)
- [Balanced Policy Evaluation and Learning](https://mlsanity.com/paper/1705.07384/) (2017)
- [Discrimination in the Age of Algorithms](https://mlsanity.com/paper/1902.03731/) (2019)
- [Residual Unfairness in Fair Machine Learning from Prejudiced Data](https://mlsanity.com/paper/1806.02887/) (2018)
- [Learning Optimal Fair Policies](https://mlsanity.com/paper/1809.02244/) (2018)
- [Learning Fairness in Multi-Agent Systems](https://mlsanity.com/paper/1910.14472/) (2019)
- [Learning Fair Policies in Decentralized Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2012.09421/) (2020)
- [Causal Conceptions of Fairness and their Consequences](https://mlsanity.com/paper/2207.05302/) (2022)
- [Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning](https://mlsanity.com/paper/2202.09667/) (2022)
- [Deep learning in business analytics and operations research: Models, applications and managerial implications](https://mlsanity.com/paper/1806.10897/) (2018)
- [More Efficient Policy Learning via Optimal Retargeting](https://mlsanity.com/paper/1906.08611/) (2019)
- [Targeting for long-term outcomes](https://mlsanity.com/paper/2010.15835/) (2020)
- [Algorithmic Fairness in Business Analytics: Directions for Research and Practice](https://mlsanity.com/paper/2207.10991/) (2022)

## Built on by (most cited first, 11 of 11)

- [Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework](https://mlsanity.com/paper/2311.18460/) (2023)
- [Treatment Effect Estimation for Optimal Decision-Making](https://mlsanity.com/paper/2505.13092/) (2025)
- [Efficient and Sharp Off-Policy Learning under Unobserved Confounding](https://mlsanity.com/paper/2502.13022/) (2025)
- [Orthogonal Representation Learning for Estimating Causal Quantities](https://mlsanity.com/paper/2502.04274/) (2025)
- [Differentially Private Learners for Heterogeneous Treatment Effects](https://mlsanity.com/paper/2503.03486/) (2025)
- [Towards Regulatory-Confirmed Adaptive Clinical Trials: Machine Learning Opportunities and Solutions](https://mlsanity.com/paper/2503.09226/) (2025)
- [Rank-Learner: Orthogonal Ranking of Treatment Effects](https://mlsanity.com/paper/2602.03517/) (2026)
- [Fairness in Reinforcement Learning with Bisimulation Metrics](https://mlsanity.com/paper/2412.17123/) (2024)
- [Bridging the gap: Towards an Expanded Toolkit for AI-driven Decision-Making in the Public Sector](https://mlsanity.com/paper/2310.19091/) (2023)
- [Learning Optimal Individualized Decision Rules with Conditional Demographic Parity](https://mlsanity.com/paper/2603.05226/) (2026)
- [Long-term Fairness with Selective Labels](https://mlsanity.com/paper/2605.22291/) (2026)

## Abstract (arXiv)

Algorithmic decision-making in practice must be fair for legal, ethical, and societal reasons. To achieve this, prior research has contributed various approaches that ensure fairness in machine learning predictions, while comparatively little effort has focused on fairness in decision-making, specifically off-policy learning. In this paper, we propose a novel framework for fair off-policy learning: we learn decision rules from observational data under different notions of fairness, where we explicitly assume that observational data were collected under a different potentially discriminatory behavioral policy. For this, we first formalize different fairness notions for off-policy learning. We then propose a neural network-based framework to learn optimal policies under different fairness notions. We further provide theoretical guarantees in the form of generalization bounds for the finite-sample version of our framework. We demonstrate the effectiveness of our framework through extensive numerical experiments using both simulated and real-world data. Altogether, our work enables algorithmic decision-making in a wide array of practical applications where fairness must be ensured.