# Counterfactually Guided Off-policy Transfer in Clinical Settings

arXiv: https://arxiv.org/abs/2006.11654 · HTML: https://mlsanity.com/paper/2006.11654/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Jun 2020.

## Built on by (most cited first, 14 of 14)

- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [MoCoDA: Model-based Counterfactual Data Augmentation](https://mlsanity.com/paper/2210.11287/) (2022)
- [Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes](https://mlsanity.com/paper/2110.15332/) (2021)
- [Fine-Grained Causal Dynamics Learning with Quantization for Improving Robustness in Reinforcement Learning](https://mlsanity.com/paper/2406.03234/) (2024)
- [Training a Resilient Q-Network against Observational Interference](https://mlsanity.com/paper/2102.09677/) (2021)
- [Offline Imitation Learning with Variational Counterfactual Reasoning](https://mlsanity.com/paper/2310.04706/) (2023)
- [Counterfactual Influence in Markov Decision Processes](https://mlsanity.com/paper/2402.08514/) (2024)
- [Learning Under Adversarial and Interventional Shifts](https://mlsanity.com/paper/2103.15933/) (2021)
- [Robust Counterfactual Inference in Markov Decision Processes](https://mlsanity.com/paper/2502.13731/) (2025)
- [Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer](https://mlsanity.com/paper/2505.09114/) (2025)
- [Towards Robust Off-Policy Evaluation via Human Inputs](https://mlsanity.com/paper/2209.08682/) (2022)
- [Inference and Denoise: Causal Inference-based Neural Speech Enhancement](https://mlsanity.com/paper/2211.01189/) (2022)
- [Robust Counterfactual Policy Optimisation via Nondeterministic Causal Models](https://mlsanity.com/paper/2608.02893/) (2026)
- [Robust Counterfactuals for Markov Decision Processes under Statistical and Causal Uncertainties](https://mlsanity.com/paper/2610.20210/) (2026)

## Abstract (arXiv)

Domain shift, encountered when using a trained model for a new patient population, creates significant challenges for sequential decision making in healthcare since the target domain may be both data-scarce and confounded. In this paper, we propose a method for off-policy transfer by modeling the underlying generative process with a causal mechanism. We use informative priors from the source domain to augment counterfactual trajectories in the target in a principled manner. We demonstrate how this addresses data-scarcity in the presence of unobserved confounding. The causal parametrization of our sampling procedure guarantees that counterfactual quantities can be estimated from scarce observational target data, maintaining intuitive stability properties. Policy learning in the target domain is further regularized via the source policy through KL-divergence. Through evaluation on a simulated sepsis treatment task, our counterfactual policy transfer procedure significantly improves the performance of a learned treatment policy when assumptions of "no-unobserved confounding" are relaxed.