# Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding

arXiv: https://arxiv.org/abs/2003.05623 · HTML: https://mlsanity.com/paper/2003.05623/

## Key facts

- Cited by 61 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Mar 2020.

## Built on by (most cited first, 30 of 61)

- [A Review of Off-Policy Evaluation in Reinforcement Learning](https://mlsanity.com/paper/2212.06355/) (2022)
- [A Survey on Causal Reinforcement Learning](https://mlsanity.com/paper/2302.05209/) (2023)
- [Universal Off-Policy Evaluation](https://mlsanity.com/paper/2104.12820/) (2021)
- [Proximal Reinforcement Learning: Efficient Off-Policy Evaluation in Partially Observed Markov Decision Processes](https://mlsanity.com/paper/2110.15332/) (2021)
- [A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes](https://mlsanity.com/paper/2111.06784/) (2021)
- [Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning](https://mlsanity.com/paper/2102.09907/) (2021)
- [Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process](https://mlsanity.com/paper/2202.10589/) (2022)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [Future-Dependent Value-Based Off-Policy Evaluation in POMDPs](https://mlsanity.com/paper/2207.13081/) (2022)
- [An Instrumental Variable Approach to Confounded Off-Policy Evaluation](https://mlsanity.com/paper/2212.14468/) (2022)
- [Off-Policy Evaluation for Episodic Partially Observable Markov Decision Processes under Non-Parametric Models](https://mlsanity.com/paper/2209.10064/) (2022)
- [Causal Multi-Agent Reinforcement Learning: Review and Open Problems](https://mlsanity.com/paper/2111.06721/) (2021)
- [On Covariate Shift of Latent Confounders in Imitation and Reinforcement Learning](https://mlsanity.com/paper/2110.06539/) (2021)
- [Off-Policy Evaluation for Large Action Spaces via Policy Convolution](https://mlsanity.com/paper/2310.15433/) (2023)
- [Robust Fitted-Q-Evaluation and Iteration under Sequentially Exogenous Unobserved Confounders](https://mlsanity.com/paper/2302.00662/) (2023)
- [Finding Counterfactually Optimal Action Sequences in Continuous State Spaces](https://mlsanity.com/paper/2306.03929/) (2023)
- [Model-Free and Model-Based Policy Evaluation when Causality is Uncertain](https://mlsanity.com/paper/2204.00956/) (2022)
- [Offline Policy Evaluation and Optimization under Confounding](https://mlsanity.com/paper/2211.16583/) (2022)
- [Safe Policy Improvement for POMDPs via Finite-State Controllers](https://mlsanity.com/paper/2301.04939/) (2023)
- [Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions](https://mlsanity.com/paper/2306.14351/) (2023)
- [On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation](https://mlsanity.com/paper/2402.14703/) (2024)
- [Strategic Decision-Making in the Presence of Information Asymmetry: Provably Efficient RL with Algorithmic Instruments](https://mlsanity.com/paper/2208.11040/) (2022)
- [Statistical Tractability of Off-policy Evaluation of History-dependent Policies in POMDPs](https://mlsanity.com/paper/2503.01134/) (2025)
- [Causal Markov Decision Processes: Learning Good Interventions Efficiently](https://mlsanity.com/paper/2102.07663/) (2021)
- [Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding](https://mlsanity.com/paper/2306.01157/) (2023)
- [Confounding Robust Deep Reinforcement Learning: A Causal Approach](https://mlsanity.com/paper/2510.21110/) (2025)
- [Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach](https://mlsanity.com/paper/2112.04571/) (2021)
- [Off-Policy Evaluation for Human Feedback](https://mlsanity.com/paper/2310.07123/) (2023)
- [RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation](https://mlsanity.com/paper/2406.01389/) (2024)
- [Efficient and Sharp Off-Policy Learning under Unobserved Confounding](https://mlsanity.com/paper/2502.13022/) (2025)

## Abstract (arXiv)

When observed decisions depend only on observed features, off-policy policy evaluation (OPE) methods for sequential decision making problems can estimate the performance of evaluation policies before deploying them. This assumption is frequently violated due to unobserved confounders, unrecorded variables that impact both the decisions and their outcomes. We assess robustness of OPE methods under unobserved confounding by developing worst-case bounds on the performance of an evaluation policy. When unobserved confounders can affect every decision in an episode, we demonstrate that even small amounts of per-decision confounding can heavily bias OPE methods. Fortunately, in a number of important settings found in healthcare, policy-making, operations, and technology, unobserved confounders may primarily affect only one of the many decisions made. Under this less pessimistic model of one-decision confounding, we propose an efficient loss-minimization-based procedure for computing worst-case bounds, and prove its statistical consistency. On two simulated healthcare examples---management of sepsis patients and developmental interventions for autistic children---where this is a reasonable model of confounding, we demonstrate that our method invalidates non-robust results and provides meaningful certificates of robustness, allowing reliable selection of policies even under unobserved confounding.