Off-Policy Evaluation

Ask about this topic

Overview

Off-policy evaluation (OPE) estimates how a new decision policy would perform using data collected by a different policy, avoiding costly or risky deployment trials. Common approaches reweight logged actions with importance sampling, combine weights with reward models in doubly robust estimators, fit value functions with fitted Q-evaluation, or learn dynamics and occupancy ratios; bootstrap and conformal methods help quantify uncertainty. Applications span contextual bandits and sequential decision processes, including recommendation, healthcare, robotics, and language-model agents, with benchmarks testing policy shift, sparse support, and missing outcomes. Estimates can become biased or unstable when target actions or histories are poorly represented, so overlap diagnostics, sensitivity checks, and calibrated uncertainty matter alongside point estimates.

Latest papers

CardsList

74 papers17 papers in the last four weeks, up 113% on the four weeks before. 0.1% of all new papers.

May 7, 2026

Q-MMR: Off-Policy Evaluation via Recursive Reweighting and Moment Matching

We present a novel theoretical framework, Q-MMR, for off-policy evaluation in finite-horizon MDPs. Q-MMR learns a set of scalar weights, one for each data point, such that the reweighted rewards approximate the expected return under the target policy. The weights are learned inductively in a top-down manner via a moment matching objective against a value-function discriminator class. Notably, and perhaps surprisingly, a data-dependent finite-sample guarantee for general function approximation can be established under only the realizability of QπQ^π, with a dimension-free bound -- that is, the error does not depend on the statistical complexity of the function class. We also establish connections to several existing methods, such as importance sampling and linear FQE. Further theoretical analyses shed new light on the nature of coverage, a concept of fundamental importance to offline RL.

Xiang Li, Nan Jiang

Nanjing University · UIUC

Off-Policy EvaluationValue Function EstimationDistribution MatchingOffline RL
AskPDF
May 7, 2026

SOPE: Stabilizing Off-Policy Evaluation for Online RL with Prior Data

Incorporating prior data into online reinforcement learning accelerates training but typically forces a difficult trade-off between high computational costs and long, multi-stage training pipelines. While fixed-length stabilization phases are significantly more computationally efficient than static update schedules, they require task-dependent manual tuning, risking either the waste of prior knowledge or severe overfitting. To address this, we propose SOPE, an algorithm that uses an actor-aligned Off-Policy Policy Evaluation (OPE) signal as an automated early-stopping mechanism to dynamically control the length of offline training phases. By evaluating the critic on a held-out validation split under the current policy's action distribution, SOPE halts gradient updates exactly when out-of-distribution benefits saturate, eliminating the need for manual schedule tuning. Evaluated on 25 continuous control tasks from the Minari benchmark suite, SOPE improves baseline performance by up to 45.6% while reducing the required TFLOPs by up to 22x, thus balancing the tradeoff between sample and computational efficiency. These findings demonstrate that adaptive, evaluation-driven update schedules are more effective than relying on static, exhaustive update schedules.

Carlo Romeo, Girolamo Macaluso, Alessandro Sestini +1

1Media Integration and Communication Center – University of Florence · 2SEED – Electronic Arts

Off-Policy EvaluationOffline-To-Online RL
AskPDF
May 2, 2026

The Partial Testimony of Logs: Evaluation of Language Model Generation under Confounded Model Choice

Offline evaluation of language models from usage logs is biased when model choice is confounded: the same user-side factors that influence which model is used can also influence how its output is judged, so raw comparisons of logged scores mix self-selected populations rather than estimating a common quantity of interest. A small randomized experiment can break this bias by overriding model choice, but in practice such experiments are scarce and costly. We study a three-source design that combines a large confounded observational log (OBS) for scale, a small randomized experiment (EXP) for unconfounded scoring, and an offline simulator (SIM) that replays candidate models on cached contexts. Our main result is an identification theorem showing that the randomized experiment and the simulator are together enough to recover causal model values; the observational log enters only afterward, to reduce estimation error rather than to make the causal comparison valid. Six estimator families are evaluated in a controlled semi-synthetic validation and in two real-task cached benchmarks for summarization and coding. No family dominates every regime; relative performance depends on the amount of unbiased EXP supervision and on how closely the target reward aligns with OBS-derived structure.

Jikai Jin, Vasilis Syrgkanis

LLM EvaluationOff-Policy EvaluationLanguage Model Generation Evaluation
AskPDF
Apr 25, 2026

Robustness of Refugee-Matching Gains to Off-Policy Evaluation Choices

Previous research has investigated the potential of refugee matching for boosting refugee outcomes, first considered by Bansak et al. (2018). This paper demonstrates the stability of counterfactual impact evaluation results in the context of refugee matching in the United States using a range of off-policy evaluation methods. In order to estimate counterfactual impact and test the robustness of our results, we employ several evaluation methods, including inverse probability weighting (IPW) and multiple variants of augmented inverse probability weighting (AIPW). We also consider various modifications, including alternative modeling architectures and different assignment procedures. The impact estimates remain consistent in magnitude in all scenarios as well as statistically significant in most cases. Furthermore, the estimates are also consistent with the results originally presented in Bansak et al. (2018).

Kirk Bansak, Elisabeth Paulson, Dominik Rothenhäusler +3

Immigration Policy Lab, Stanford University · Department of Political Science, University of California, Berkeley · Technology and Operations Management Unit, Harvard Business School +3

Counterfactual EvaluationCausal Effect EstimationOff-Policy Evaluation
AskPDF
Apr 24, 2026

CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems

Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data support used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly supported generator-item pairs. We propose CASP (Coupled Action-Set Pessimism), a support-aware offline selector for finite libraries of two-stage recommender policies. CASP combines doubly robust value estimation with a support-burden penalty. We show that stagewise rules that ignore downstream continuation value can be arbitrarily suboptimal, and we derive population, finite-class, and reconstructed-propensity guarantees for conservative selection. In simulations and a reconstructed MovieLens 1M application, CASP selects lower-burden policies when estimated value and support credibility are in tension.

Nilson Chapagain

Texas A&M University College Station, TX, USA

Off-Policy EvaluationRecommender SystemsDoubly Robust Estimation
AskPDF
Apr 20, 2026

Distributional Off-Policy Evaluation with Deep Quantile Process Regression

This paper investigates the off-policy evaluation (OPE) problem from a distributional perspective. Rather than focusing solely on the expectation of the total return, as in most existing OPE methods, we aim to estimate the entire return distribution. To this end, we introduce a quantile-based approach for OPE using deep quantile process regression, presenting a novel algorithm called Deep Quantile Process regression-based Off-Policy Evaluation (DQPOPE). We provide new theoretical insights into the deep quantile process regression technique, extending existing approaches that estimate discrete quantiles to estimate a continuous quantile function. A key contribution of our work is the rigorous sample complexity analysis for distributional OPE with deep neural networks, bridging theoretical analysis with practical algorithmic implementations. We show that DQPOPE achieves statistical advantages by estimating the full return distribution using the same sample size required to estimate a single policy value using conventional methods. Empirical studies further show that DQPOPE provides significantly more precise and robust policy value estimates than standard methods, thereby enhancing the practical applicability and effectiveness of distributional reinforcement learning approaches.

Qi Kuang, Chao Wang, Yuling Jiao +1

School of Statistics and Data Science, and Philosophy and Social Sciences Laboratory of Data Science in Finance and Economics at the Ministry of Education,2026 Jiangxi University of Finance and Economics · School of Statistics and Data Science, Shanghai University of Finance and EconomicsApr · School of Artificial Intelligence, and Hubei Key Laboratory of Computational Science, 24 Wuhan University

Distributional RLQuantile RegressionOff-Policy EvaluationSample Complexity
AskPDF
Mar 24, 2026

Off-Policy Evaluation and Learning for Survival Outcomes under Censoring

Optimizing survival outcomes, such as patient survival or customer retention, is a critical objective in data-driven decision-making. Off-Policy Evaluation~(OPE) provides a powerful framework for assessing such decision-making policies using logged data alone, without the need for costly or risky online experiments in high-stakes applications. However, typical estimators are not designed to handle right-censored survival outcomes, as they ignore unobserved survival times beyond the censoring time, leading to systematic underestimation of the true policy performance. To address this issue, we propose a novel framework for OPE and Off-Policy Learning~(OPL) tailored for survival outcomes under censoring. Specifically, we introduce IPCW-IPS and IPCW-DR, which employ the Inverse Probability of Censoring Weighting technique to explicitly deal with censoring bias. We theoretically establish that our estimators are unbiased and that IPCW-DR achieves double robustness, ensuring consistency if either the propensity score or the outcome model is correct. Furthermore, we extend this framework to constrained OPL to optimize policy value under budget constraints. We demonstrate the effectiveness of our proposed methods through simulation studies and illustrate their practical impacts using public real-world data for both evaluation and learning tasks.

Kohsuke Kubota, Mitsuhiro Takahashi, Yuta Saito

NTT DOCOMO, INC. · Hanjuku-kaso, Co, Ltd.

Off-Policy EvaluationOff-Policy RLSurvival AnalysisDoubly Robust Estimation
AskPDF
Mar 23, 2026

Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies

Off-Policy Evaluation (OPE) is an important practical problem in algorithmic ranking systems, where the goal is to estimate the expected performance of a new ranking policy using only offline logged data collected under a different, logging policy. Existing estimators, such as the ranking-wise and position-wise inverse propensity score (IPS) estimators, require the data collection policy to be sufficiently stochastic and suffer from severe bias when the logging policy is fully deterministic. In this paper, we propose novel estimators, Click-based Inverse Propensity Score (CIPS), exploiting the intrinsic stochasticity of user click behavior to address this challenge. Unlike existing methods that rely on the stochasticity of the logging policy, our approach uses click probability as a new form of importance weighting, enabling low-bias OPE even under deterministic logging policies where existing methods incur substantial bias. We provide theoretical analyses of the bias and variance properties of the proposed estimators and show, through synthetic and real-world experiments, that our estimators achieve significantly lower bias compared to strong baselines, for a range of experimental settings with completely deterministic logging policies.

Koichi Tanaka, Kazuki Kawamura, Takanori Muroi +6

Keio University · Sony Group Corporation · Yale University +1

Off-Policy EvaluationInverse Probability Weighting
AskPDF
Mar 10, 2026

From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation

We study off-policy evaluation in the setting of contextual bandits, where we aim to evaluate a new policy using historical data that consists of contexts, actions and received rewards. This historical data typically does not faithfully represent action distribution of the new policy accurately. A common approach, inverse probability weighting (IPW), adjusts for these discrepancies in action distributions. However, this method often suffers from high variance due to the probability being in the denominator. The doubly robust (DR) estimator reduces variance through modeling reward but does not directly address variance from IPW. In this work, we address the limitation of IPW by proposing a Nonparametric Weighting (NW) approach that constructs weights using a nonparametric model. Our NW approach achieves low bias like IPW but typically exhibits significantly lower variance. To further reduce variance, we incorporate reward predictions -- similar to the DR technique -- resulting in the Model-assisted Nonparametric Weighting (MNW) approach. The MNW approach yields accurate value estimates by explicitly modeling and mitigating bias from reward modeling, without aiming to guarantee the standard doubly robust property. Extensive empirical comparisons show that our approaches consistently outperform existing techniques, achieving lower variance in value estimation while maintaining low bias.

Rong J. B. Zhu

Institute of Science and Technology for Brain-inspired Intelligence, Fudan University

Off-Policy EvaluationInverse Probability WeightingImportance WeightingContextual BanditsDoubly Robust Estimation
AskPDF
Mar 9, 2026

Unifying On- and Off-Policy Variance Reduction Methods

Continuous and efficient experimentation is key to the practical success of user-facing applications on the web, both through online A/B-tests and off-policy evaluation. Despite their shared objective -- estimating the incremental value of a treatment -- these domains often operate in isolation, utilising distinct terminologies and statistical toolkits. This paper bridges that divide by establishing a formal equivalence between their canonical variance reduction methods. We prove that the standard online Difference-in-Means estimator is mathematically identical to an off-policy Inverse Propensity Scoring estimator equipped with an optimal (variance-minimising) additive control variate. Extending this unification, we demonstrate that widespread regression adjustment methods (such as CUPED, CUPAC, and ML-RATE) are structurally equivalent to Doubly Robust estimation. This unified view extends our understanding of commonly used approaches, and can guide practitioners and researchers working on either class of problems.

Olivier Jeunen

aampe Antwerp, Belgium

Causal Effect EstimationA/b TestingVariance ReductionOff-Policy EvaluationDoubly Robust Estimation
AskPDF
Mar 3, 2026

A Covering Framework for Offline POMDPs Learning using Belief Space Metric

In off policy evaluation (OPE) for partially observable Markov decision processes (POMDPs), an agent must infer hidden states from past observations, which exacerbates both the curse of horizon and the curse of memory in existing OPE methods. This paper introduces a novel covering analysis framework that exploits the intrinsic metric structure of the belief space (distributions over latent states) to relax traditional coverage assumptions. By assuming value relevant functions are Lipschitz continuous in the belief space, we derive error bounds that mitigate exponential blow ups in horizon and memory length. Our unified analysis technique applies to a broad class of OPE algorithms, yielding concrete error bounds and coverage requirements expressed in terms of belief space metrics rather than raw history coverage. We illustrate the improved sample efficiency of this framework via case studies: the double sampling Bellman error minimization algorithm, and the memory based future dependent value functions (FDVF). In both cases, our coverage definition based on the belief space metric yields tighter bounds.

Youheng Zhu, Yiping Lu

Northwestern University

Off-Policy EvaluationOffline RLPartially Observable Markov Decision ProcessesSample-Efficient RL
AskPDF
Feb 16, 2026

Additive Control Variates Dominate Self-Normalisation in Off-Policy Evaluation

Off-policy evaluation (OPE) is essential for assessing ranking and recommendation systems without costly online interventions. Self-Normalised Inverse Propensity Scoring (SNIPS) is a standard tool for variance reduction in OPE, leveraging a multiplicative control variate. Recent advances in off-policy learning suggest that additive control variates (baseline corrections) may offer superior performance, yet theoretical guarantees for evaluation are lacking. This paper provides a definitive answer: we prove that β⋆β^\star-IPS, an estimator with an optimal additive baseline, asymptotically dominates SNIPS in Mean Squared Error. By analytically decomposing the variance gap, we show that SNIPS is asymptotically equivalent to using a specific -- but generally sub-optimal -- additive baseline. Our results theoretically justify shifting from self-normalisation to optimal baseline corrections for both ranking and recommendation.

Olivier Jeunen, Shashank Gupta

aampe Antwerp, Belgium · Microsoft AI Bangalore, India

Off-Policy EvaluationVariance ReductionImportance Sampling
AskPDF
Dec 29, 2025

Fitted Q-Evaluation without Bellman Completeness via Occupancy Weighting

Fitted QQ-evaluation (FQE) is a standard regression-based method for off-policy evaluation, but under distribution shift, value-function realizability alone does not ensure convergence, and existing analyses often require Bellman completeness. We trace this instability to a geometric mismatch: standard FQE projects Bellman targets in the norm induced by the offline distribution, which need not preserve Bellman contraction. We therefore study occupancy-weighted FQE, which changes only the regression weights. Weighting by a target-policy discounted occupancy ratio aligns the projection norm with the target-policy dynamics and restores contraction of the population projected Bellman operator. We derive finite-sample guarantees with estimated occupancy ratios and function-class misspecification, separating finite-iteration, statistical, approximation, and ratio-estimation errors. Exact occupancy weighting removes the need for Bellman completeness; with estimated weights, approximate completeness and value-function realizability reduce sensitivity to ratio-estimation error, with exact realizability yielding higher-order dependence. Combining occupancy-weighted FQE with fitted occupancy-ratio evaluation gives an end-to-end guarantee governed by the complexities and direct approximation errors of the value-function and occupancy-ratio classes. Under coverage, joint realizability of these two classes suffices for consistent estimation without Bellman or critic-side completeness. Controlled experiments illustrate the projection-norm mechanism and the finite-sample tradeoff between contraction and coverage.

Lars van der Laan, Nathan Kallus

Department of Statistics, University of Washington · Netflix · Cornell University

Off-Policy EvaluationValue Function Estimation
AskPDF
Jul 26, 2025

PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data

Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown that leveraging auxiliary datasets, such as those synthesized by generative models, can improve the accuracy of OPE methods. Unfortunately, such auxiliary datasets may also be biased, and existing methods for using data augmentation within OPE lack principled uncertainty quantification. In high stakes domains like healthcare, reliable uncertainty estimates are important for ensuring safe and informed deployment of RL policies. In this work, we propose two methods to construct valid confidence intervals for OPE with data augmentation. The first provides a confidence interval over Vπ(s)V^π(s), the policy value conditioned on an initial state ss. To do so we introduce a new conformal prediction method suitable for Markov Decision Processes (MDPs) with continuous state spaces, extending prior work to higher-dimensional settings. Second, we consider the more common task of estimating the average policy performance over all initial states, VπV^π; we introduce a method that draws on ideas from doubly robust estimation and prediction powered inference. Across simulators spanning inventory management, robotics, healthcare, and a real healthcare dataset from MIMIC-IV, we find that our methods can effectively leverage auxiliary data and consistently produce confidence intervals that cover the ground truth policy values, unlike previously proposed methods. Our work enables a future in which OPE can provide rigorous uncertainty estimates for high-stakes domains.

Aishwarya Mandyam, Jason Meng, Ge Gao +4

Stanford University · Gladstone Institutes · Stanford University[cs.LG]

Off-Policy EvaluationHealthcareConformal Prediction
AskPDF