# Policy Learning with Asymmetric Counterfactual Utilities

arXiv: https://arxiv.org/abs/2206.10479 · HTML: https://mlsanity.com/paper/2206.10479/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 52 references that are in the map.
- First posted on arXiv 21 Jun 2022.

## Builds on (most cited first, 10 of 10)

- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Balanced Policy Evaluation and Learning](https://mlsanity.com/paper/1705.07384/) (2017)
- [A semiparametric instrumental variable approach to optimal treatment regimes under endogeneity](https://mlsanity.com/paper/1911.09260/) (2019)
- [Principal Fairness for Human and Algorithmic Decision-Making](https://mlsanity.com/paper/2005.10400/) (2020)
- [Estimating Optimal Treatment Rules with an Instrumental Variable: A Partial Identification Learning Approach](https://mlsanity.com/paper/2002.02579/) (2020)
- [Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment](https://mlsanity.com/paper/2109.11679/) (2021)
- [Multiply robust estimation of causal effects under principal ignorability](https://mlsanity.com/paper/2012.01615/) (2020)
- [Individualized Decision-Making Under Partial Identification: Three Perspectives, Two Optimality Results, and One Paradox](https://mlsanity.com/paper/2110.10961/) (2021)
- [Principal stratification analysis using principal scores](https://mlsanity.com/paper/1602.01196/) (2016)
- [Binary Choice under Asymmetric Loss in a Data-Rich Environment: Theory and an Application to Algorithmic Fairness](https://mlsanity.com/paper/2010.08463/) (2020)

## Built on by (most cited first, 9 of 9)

- [Does AI help humans make better decisions? A statistical evaluation framework for experimental and observational studies](https://mlsanity.com/paper/2403.12108/) (2024)
- [Bayesian Safe Policy Learning with Chance Constrained Optimization: Application to Military Security Assessment during the Vietnam War](https://mlsanity.com/paper/2307.08840/) (2023)
- [Towards Representation Learning for Weighting Problems in Design-Based Causal Inference](https://mlsanity.com/paper/2409.16407/) (2024)
- [Statistical Decision Theory with Counterfactual Loss](https://mlsanity.com/paper/2505.08908/) (2025)
- [Statistical Performance Guarantee for Subgroup Identification with Generic Machine Learning](https://mlsanity.com/paper/2310.07973/) (2023)
- [Statistical Inference of Optimal Allocations I: Regularities and their Implications](https://mlsanity.com/paper/2403.18248/) (2024)
- [Beyond Flatland: A Geometric Take on Matching Methods for Treatment Effect Estimation](https://mlsanity.com/paper/2409.05459/) (2024)
- [Path-specific harm decomposition: A partial identification framework](https://mlsanity.com/paper/2609.29938/) (2026)
- [SAGE: A Statistical Acceptance Gate for Self-Evolving Agents](https://mlsanity.com/paper/2609.36043/) (2026)

## Abstract (arXiv)

Data-driven decision making plays an important role even in high stakes settings like medicine and public policy. Learning optimal policies from observed data requires a careful formulation of the utility function whose expected value is maximized across a population. Although researchers typically use utilities that depend on observed outcomes alone, in many settings the decision maker's utility function is more properly characterized by the joint set of potential outcomes under all actions. For example, the Hippocratic principle to "do no harm" implies that the cost of causing death to a patient who would otherwise survive without treatment is greater than the cost of forgoing life-saving treatment. We consider optimal policy learning with asymmetric counterfactual utility functions of this form that consider the joint set of potential outcomes. We show that asymmetric counterfactual utilities lead to an unidentifiable expected utility function, and so we first partially identify it. Drawing on statistical decision theory, we then derive minimax decision rules by minimizing the maximum expected utility loss relative to different alternative policies. We show that one can learn minimax loss decision rules from observed data by solving intermediate classification problems, and establish that the finite sample excess expected utility loss of this procedure is bounded by the regret of these intermediate classifiers. We apply this conceptual framework and methodology to the decision about whether or not to use right heart catheterization for patients with possible pulmonary hypertension.