# Policy Learning with Observational Data

arXiv: https://arxiv.org/abs/1702.02896 · HTML: https://mlsanity.com/paper/1702.02896/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2017.

## Built on by (most cited first, 19 of 19)

- [A Review of Off-Policy Evaluation in Reinforcement Learning](https://mlsanity.com/paper/2212.06355/) (2022)
- [Control Variates for Slate Off-Policy Evaluation](https://mlsanity.com/paper/2106.07914/) (2021)
- [Treatment Effect Risk: Bounds and Inference](https://mlsanity.com/paper/2201.05893/) (2022)
- [A Survey of Deep Causal Models and Their Industrial Applications](https://mlsanity.com/paper/2209.08860/) (2022)
- [Learning Complementary Policies for Human-AI Teams](https://mlsanity.com/paper/2302.02944/) (2023)
- [Stateful Offline Contextual Policy Evaluation and Learning](https://mlsanity.com/paper/2110.10081/) (2021)
- [Online learning in bandits with predicted context](https://mlsanity.com/paper/2307.13916/) (2023)
- [Confounding-Robust Policy Improvement with Human-AI Teams](https://mlsanity.com/paper/2310.08824/) (2023)
- [Off-Policy Evaluation with Policy-Dependent Optimization Response](https://mlsanity.com/paper/2202.12958/) (2022)
- [Interpretable Off-Policy Learning via Hyperbox Search](https://mlsanity.com/paper/2203.02473/) (2022)
- [Best Arm Identification with Contextual Information under a Small Gap](https://mlsanity.com/paper/2209.07330/) (2022)
- [Beyond traditional assumptions in fair machine learning](https://mlsanity.com/paper/2101.12476/) (2021)
- [Applications of Machine Learning in Document Digitisation](https://mlsanity.com/paper/2102.03239/) (2021)
- [Agnostic learning with unknown utilities](https://mlsanity.com/paper/2104.08482/) (2021)
- [Calibrated Optimal Decision Making with Multiple Data Sources and Limited Outcome](https://mlsanity.com/paper/2104.10554/) (2021)
- [GEAR: On Optimal Decision Making with Auxiliary Data](https://mlsanity.com/paper/2104.10573/) (2021)
- [Towards Robust Off-policy Learning for Runtime Uncertainty](https://mlsanity.com/paper/2202.13337/) (2022)
- [Statistical Consequences of Dueling Bandits](https://mlsanity.com/paper/2111.00870/) (2021)
- [Statistical Learning for Individualized Asset Allocation](https://mlsanity.com/paper/2201.07998/) (2022)

## Abstract (arXiv)

In many areas, practitioners seek to use observational data to learn a treatment assignment policy that satisfies application-specific constraints, such as budget, fairness, simplicity, or other functional form constraints. For example, policies may be restricted to take the form of decision trees based on a limited set of easily observable individual characteristics. We propose a new approach to this problem motivated by the theory of semiparametrically efficient estimation. Our method can be used to optimize either binary treatments or infinitesimal nudges to continuous treatments, and can leverage observational data where causal effects are identified using a variety of strategies, including selection on observables and instrumental variables. Given a doubly robust estimator of the causal effect of assigning everyone to treatment, we develop an algorithm for choosing whom to treat, and establish strong guarantees for the asymptotic utilitarian regret of the resulting policy.