# Contextualized Policy Recovery: Modeling and Interpreting Medical Decisions with Adaptive Imitation Learning

arXiv: https://arxiv.org/abs/2310.07918 · HTML: https://mlsanity.com/paper/2310.07918/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Safe offline RL, one of 13 directions in Offline RL and imitation learning from data.
- Builds on 11 of its 49 references that are in the map.
- First posted on arXiv 11 Oct 2023.

## Placed in

- Offline RL and imitation learning from data / [Safe offline RL](https://mlsanity.com/offlinerl/safe-offline-rl/)

## Builds on (most cited first, 11 of 11)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1606.03476/) (2016)
- [Distilling a Neural Network Into a Soft Decision Tree](https://mlsanity.com/paper/1711.09784/) (2017)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [Imitation Learning via Off-Policy Distribution Matching](https://mlsanity.com/paper/1912.05032/) (2019)
- [Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction](https://mlsanity.com/paper/1703.01030/) (2017)
- [Contextual Explanation Networks](https://mlsanity.com/paper/1705.10301/) (2017)
- [What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes](https://mlsanity.com/paper/2011.05064/) (2020)
- [POETREE: Interpretable Policy Learning with Adaptive Decision Trees](https://mlsanity.com/paper/2203.08057/) (2022)

## Built on by (most cited first, 4 of 4)

- [Retrieval-Augmented Interpretable Learning: Towards Task-Specific Zero-Shot Models in Healthcare](https://mlsanity.com/paper/2607.17508/) (2026)
- [Patient-Specific Models of Treatment Effects Explain Heterogeneity in Tuberculosis](https://mlsanity.com/paper/2411.10645/) (2024)
- [How Should We Represent History in Interpretable Models of Clinical Policies?](https://mlsanity.com/paper/2412.07895/) (2024)
- [Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning](https://mlsanity.com/paper/2505.02228/) (2025)

## Abstract (arXiv)

Interpretable policy learning seeks to estimate intelligible decision policies from observed actions; however, existing models force a tradeoff between accuracy and interpretability, limiting data-driven interpretations of human decision-making processes. Fundamentally, existing approaches are burdened by this tradeoff because they represent the underlying decision process as a universal policy, when in fact human decisions are dynamic and can change drastically under different contexts. Thus, we develop Contextualized Policy Recovery (CPR), which re-frames the problem of modeling complex decision processes as a multi-task learning problem, where each context poses a unique task and complex decision policies can be constructed piece-wise from many simple context-specific policies. CPR models each context-specific policy as a linear map, and generates new policy models textiton-demand as contexts are updated with new observations. We provide two flavors of the CPR framework: one focusing on exact local interpretability, and one retaining full global interpretability. We assess CPR through studies on simulated and real data, achieving state-of-the-art performance on predicting antibiotic prescription in intensive care units (+22% AUROC vs. previous SOTA) and predicting MRI prescription for Alzheimer's patients (+7.7% AUROC vs. previous SOTA). With this improvement, CPR closes the accuracy gap between interpretable and black-box methods, allowing high-resolution exploration and analysis of context-specific decision models.