{"total":91,"rows":[{"id":"2212.06355","title":"A Review of Off-Policy Evaluation in Reinforcement Learning","created":"2022-12-13","cited_by_count":95,"area":null},{"id":"2103.16596","title":"Benchmarks for Deep Off-Policy Evaluation","created":"2021-03-30","cited_by_count":89,"area":null},{"id":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"area":null},{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"area":null},{"id":"2106.02029","title":"Off-Policy Evaluation via Adaptive Weighting with Data from Contextual Bandits","created":"2021-06-03","cited_by_count":40,"area":null},{"id":"2305.08062","title":"Off-Policy Evaluation for Large Action Spaces via Conjunct Effect Modeling","created":"2023-05-14","cited_by_count":34,"area":null},{"id":"2106.00418","title":"Post-Contextual-Bandit Inference","created":"2021-06-01","cited_by_count":32,"area":null},{"id":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2104.08977","title":"Off-Policy Risk Assessment in Contextual Bandits","created":"2021-04-18","cited_by_count":29,"area":null},{"id":"2101.08490","title":"Estimating Average Treatment Effects via Orthogonal Regularization","created":"2021-01-21","cited_by_count":25,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2211.01939","title":"Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation","created":"2022-11-03","cited_by_count":25,"area":null},{"id":"2110.12343","title":"Off-Policy Evaluation in Partially Observed Markov Decision Processes under Sequential Ignorability","created":"2021-10-24","cited_by_count":24,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"area":null},{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"area":null},{"id":"2106.06854","title":"A Deep Reinforcement Learning Approach to Marginalized Importance Sampling with the Successor Representation","created":"2021-06-12","cited_by_count":19,"area":null},{"id":"2108.04812","title":"Continual Learning for Grounded Instruction Generation by Observing Human Following Behavior","created":"2021-08-10","cited_by_count":19,"area":null},{"id":"2402.02171","title":"Off-Policy Evaluation of Slate Bandit Policies via Optimizing Abstraction","created":"2024-02-03","cited_by_count":17,"area":null},{"id":"2306.15098","title":"Off-Policy Evaluation of Ranking Policies under Diverse User Behavior","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2102.09540","title":"Off-policy Confidence Sequences","created":"2021-02-18","cited_by_count":15,"area":null},{"id":"2202.13234","title":"Safe Exploration for Efficient Policy Evaluation and Comparison","created":"2022-02-26","cited_by_count":15,"area":null},{"id":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2310.15433","title":"Off-Policy Evaluation for Large Action Spaces via Policy Convolution","created":"2023-10-24","cited_by_count":14,"area":null},{"id":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2205.15436","title":"Uncertainty Quantification for Fairness in Two-Stage Recommender Systems","created":"2022-05-30","cited_by_count":10,"area":null},{"id":"2209.13075","title":"Off-policy estimation of linear functionals: Non-asymptotic theory for semi-parametric efficiency","created":"2022-09-26","cited_by_count":10,"area":null},{"id":"2309.08748","title":"Wasserstein Distributionally Robust Policy Evaluation and Learning for Contextual Bandits","created":"2023-09-15","cited_by_count":10,"area":null},{"id":"2101.07781","title":"Minimax Off-Policy Evaluation for Multi-Armed Bandits","created":"2021-01-19","cited_by_count":9,"area":null},{"id":"2211.14297","title":"Doubly robust nearest neighbors in factor models","created":"2022-11-25","cited_by_count":9,"area":null},{"id":"2312.01457","title":"Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits","created":"2023-12-03","cited_by_count":9,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2107.11533","title":"Combining Online Learning and Offline Learning for Contextual Bandits with Deficient Support","created":"2021-07-24","cited_by_count":7,"area":null},{"id":"2209.10444","title":"Off-Policy Risk Assessment in Markov Decision Processes","created":"2022-09-21","cited_by_count":7,"area":null},{"id":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2301.06240","title":"Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency","created":"2023-01-16","cited_by_count":6,"area":null},{"id":"2311.02467","title":"Individualized Policy Evaluation and Learning under Clustered Network Interference","created":"2023-11-04","cited_by_count":6,"area":null},{"id":"2402.15739","title":"Low-Rank Bandits via Tight Two-to-Infinity Singular Subspace Recovery","created":"2024-02-24","cited_by_count":6,"area":null},{"id":"2302.12736","title":"Balanced Off-Policy Evaluation for Personalized Pricing","created":"2023-02-24","cited_by_count":5,"area":null},{"id":"2402.14664","title":"Bayesian Off-Policy Evaluation and Learning for Large Action Spaces","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2404.15084","title":"Hyperparameter Optimization Can Even be Harmful in Off-Policy Learning and How to Deal with It","created":"2024-04-23","cited_by_count":5,"area":null},{"id":"2110.15501","title":"Doubly Robust Interval Estimation for Optimal Policy Evaluation in Online Learning","created":"2021-10-29","cited_by_count":4,"area":null},{"id":"2111.04835","title":"Safe Data Collection for Offline and Online Policy Learning","created":"2021-11-08","cited_by_count":4,"area":null},{"id":"2302.02570","title":"Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2401.11353","title":"Distributionally Robust Policy Evaluation under General Covariate Shift in Contextual Bandits","created":"2024-01-21","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2106.03934","title":"Offline Policy Comparison under Limited Historical Agent-Environment Interactions","created":"2021-06-07","cited_by_count":3,"area":null},{"id":"2301.12357","title":"SPEED: Experimental Design for Policy Evaluation in Linear Heteroscedastic Bandits","created":"2023-01-29","cited_by_count":3,"area":null},{"id":"2403.00886","title":"Evaluating and Correcting Performative Effects of Decision Support Systems via Causal Domain Shift","created":"2024-03-01","cited_by_count":3,"area":null},{"id":"2405.15332","title":"Cross-Validated Off-Policy Evaluation","created":"2024-05-24","cited_by_count":3,"area":null},{"id":"2405.17708","title":"OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators","created":"2024-05-27","cited_by_count":3,"area":null},{"id":"2406.02165","title":"SaVeR: Optimal Data Collection Strategy for Safe Policy Evaluation in Tabular MDP","created":"2024-06-04","cited_by_count":3,"area":null},{"id":"2411.12786","title":"Off-policy estimation with adaptively collected data: the power of online learning","created":"2024-11-19","cited_by_count":3,"area":null},{"id":"2204.10936","title":"Counterfactual Learning To Rank for Utility-Maximizing Query Autocompletion","created":"2022-04-22","cited_by_count":2,"area":null},{"id":"2210.13625","title":"Deploying a Steered Query Optimizer in Production at Microsoft","created":"2022-10-24","cited_by_count":2,"area":null},{"id":"2308.14165","title":"Distributional Off-Policy Evaluation for Slate Recommendations","created":"2023-08-27","cited_by_count":2,"area":null},{"id":"2309.01120","title":"Double Clipping: Less-Biased Variance Reduction in Off-Policy Evaluation","created":"2023-09-03","cited_by_count":2,"area":null},{"id":"2406.18022","title":"Automated Off-Policy Estimator Selection via Supervised Learning","created":"2024-06-26","cited_by_count":2,"area":null},{"id":"2408.12004","title":"CSPI-MT: Calibrated Safe Policy Improvement with Multiple Testing for Threshold Policies","created":"2024-08-21","cited_by_count":2,"area":null},{"id":"2502.04673","title":"Optimistic Algorithms for Adaptive Estimation of the Average Treatment Effect","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2605.12840","title":"Decision Support for Marketplace Policies under Incomplete Evidence: From Replay to Launch Readiness","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2107.03015","title":"Evaluating the progress of Deep Reinforcement Learning in the real world: aligning domain-agnostic and domain-specific research","created":"2021-07-07","cited_by_count":1,"area":null},{"id":"2109.03747","title":"Conservative Policy Construction Using Variational Autoencoders for Logged Data with Missing Values","created":"2021-09-08","cited_by_count":1,"area":null},{"id":"2308.03443","title":"Doubly Robust Estimator for Off-Policy Evaluation with Large Action Spaces","created":"2023-08-07","cited_by_count":1,"area":null},{"id":"2504.17277","title":"ExOSITO: Explainable Off-Policy Learning with Side Information for Intensive Care Unit Blood Test Orders","created":"2025-04-24","cited_by_count":1,"area":null},{"id":"2603.05919","title":"Design Experiments to Compare Multi-armed Bandit Algorithms","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2606.17515","title":"Anytime-valid Optimal Policy Identification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2102.08975","title":"Adaptive Doubly Robust Estimator from Non-stationary Logging Policy under a Convergence of Average Probability","created":"2021-02-17","cited_by_count":0,"area":null},{"id":"2112.09865","title":"Off-Policy Evaluation Using Information Borrowing and Context-Based Switching","created":"2021-12-18","cited_by_count":0,"area":null},{"id":"2209.07749","title":"Sales Channel Optimization via Simulations Based on Observational Data with Delayed Rewards: A Case Study at LinkedIn","created":"2022-09-16","cited_by_count":0,"area":null},{"id":"2211.01518","title":"Bayesian Counterfactual Mean Embeddings and Off-Policy Evaluation","created":"2022-11-02","cited_by_count":0,"area":null},{"id":"2404.01830","title":"Doubly-Robust Off-Policy Evaluation with Estimated Logging Policy","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2409.15143","title":"Designing an Interpretable Interface for Contextual Bandits","created":"2024-09-23","cited_by_count":0,"area":null},{"id":"2503.02735","title":"Clustered KL-barycenter design for policy evaluation","created":"2025-03-04","cited_by_count":0,"area":null},{"id":"2505.00961","title":"DOLCE: Decomposing Off-Policy Evaluation/Learning into Lagged and Current Effects","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2509.00648","title":"Context-Action Embedding Learning for Off-Policy Evaluation in Contextual Bandits","created":"2025-08-31","cited_by_count":0,"area":null},{"id":"2510.15483","title":"Fast Best-in-Class Regret for Contextual Bandits","created":"2025-10-17","cited_by_count":0,"area":null},{"id":"2603.09436","title":"From Weighting to Modeling: A Nonparametric Estimator for Off-Policy Evaluation","created":"2026-03-10","cited_by_count":0,"area":null},{"id":"2603.22900","title":"Off-Policy Evaluation and Learning for Survival Outcomes under Censoring","created":"2026-03-24","cited_by_count":0,"area":null},{"id":"2604.23022","title":"CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems","created":"2026-04-24","cited_by_count":0,"area":null},{"id":"2605.18509","title":"Offline Contextual Bandits in the Presence of New Actions","created":"2026-05-18","cited_by_count":0,"area":null},{"id":"2606.00913","title":"Bandit Simulation for Average Reward Inference","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2607.22012","title":"Cross-Domain Off-Policy Evaluation and Learning for Contextual Bandits","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.12489","title":"When Can You Trust Offline Evaluation of Equal-Cost Top-k Allocation? A Controlled, Reproducible Benchmark and Practitioner's Guide","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.29600","title":"Adaptive Doubly Robust Off-Policy Evaluation for Ranking Policies under Diverse User Behavior","created":"2026-08-30","cited_by_count":0,"area":null},{"id":"2609.30273","title":"Offline Policy Evaluation as a decision support tool for designing Adaptive Experiments","created":"2026-08-10","cited_by_count":0,"area":null},{"id":"2609.30811","title":"Counterfactual Online Conformal Prediction Under Adaptive Logging","created":"2026-09-25","cited_by_count":0,"area":null}],"next_cursor":null}