{"total":87,"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":"2202.06317","title":"Off-Policy Evaluation for Large Action Spaces via Embeddings","created":"2022-02-13","cited_by_count":54,"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":"2108.13703","title":"Evaluating the Robustness of Off-Policy Evaluation","created":"2021-08-31","cited_by_count":32,"area":null},{"id":"2202.05436","title":"Minimax Regret Optimization for Robust Machine Learning under Distribution Shift","created":"2022-02-11","cited_by_count":31,"area":null},{"id":"2202.01562","title":"Doubly Robust Off-Policy Evaluation for Ranking Policies under the Cascade Behavior Model","created":"2022-02-03","cited_by_count":30,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2003.03924","title":"Q* Approximation Schemes for Batch Reinforcement Learning: A Theoretical Comparison","created":"2020-03-09","cited_by_count":22,"area":"offlinerl"},{"id":"2105.02344","title":"Policy Learning with Adaptively Collected Data","created":"2021-05-05","cited_by_count":21,"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":"2411.09891","title":"Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation","created":"2024-11-15","cited_by_count":17,"area":"offlinerl"},{"id":"2109.08331","title":"Accelerating Offline Reinforcement Learning Application in Real-Time Bidding and Recommendation: Potential Use of Simulation","created":"2021-09-17","cited_by_count":16,"area":"offlinerl"},{"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":"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":"2306.07923","title":"Oracle-Efficient Pessimism: Offline Policy Optimization in Contextual Bandits","created":"2023-06-13","cited_by_count":15,"area":"offlinerl"},{"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":"2307.15053","title":"On (Normalised) Discounted Cumulative Gain as an Off-Policy Evaluation Metric for Top-$n$ Recommendation","created":"2023-07-27","cited_by_count":13,"area":null},{"id":"2402.06151","title":"POTEC: Off-Policy Learning for Large Action Spaces via Two-Stage Policy Decomposition","created":"2024-02-09","cited_by_count":13,"area":"deeprl"},{"id":"2405.05736","title":"Optimal Baseline Corrections for Off-Policy Contextual Bandits","created":"2024-05-09","cited_by_count":13,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2506.01183","title":"Doubly Robust Alignment for Large Language Models","created":"2025-06-01","cited_by_count":12,"area":"alignment"},{"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":"2405.10024","title":"$\\Delta\\text{-}{\\rm OPE}$: Off-Policy Estimation with Pairs of Policies","created":"2024-05-16","cited_by_count":9,"area":null},{"id":"2408.11202","title":"Effective Off-Policy Evaluation and Learning in Contextual Combinatorial Bandits","created":"2024-08-20","cited_by_count":8,"area":null},{"id":"2110.12946","title":"Optimal Model Averaging: Towards Personalized Collaborative Learning","created":"2021-10-25","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":"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":"2208.05327","title":"Fast Offline Policy Optimization for Large Scale Recommendation","created":"2022-08-08","cited_by_count":4,"area":"offlinerl"},{"id":"2311.14110","title":"When is Off-Policy Evaluation (Reward Modeling) Useful in Contextual Bandits? A Data-Centric Perspective","created":"2023-11-23","cited_by_count":4,"area":"alignment"},{"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":"2109.06310","title":"State Relevance for Off-Policy Evaluation","created":"2021-09-13","cited_by_count":3,"area":null},{"id":"2212.01925","title":"Counterfactual Learning with General Data-generating Policies","created":"2022-12-04","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":"2303.06389","title":"Uncertainty-Aware Instance Reweighting for Off-Policy Learning","created":"2023-03-11","cited_by_count":3,"area":null},{"id":"2303.16998","title":"Does Sparsity Help in Learning Misspecified Linear Bandits?","created":"2023-03-29","cited_by_count":3,"area":null},{"id":"2404.17398","title":"Online Policy Learning and Inference by Matrix Completion","created":"2024-04-26","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":"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":"2406.03434","title":"Unified PAC-Bayesian Study of Pessimism for Offline Policy Learning with Regularized Importance Sampling","created":"2024-06-05","cited_by_count":3,"area":"offlinerl"},{"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":"2508.00751","title":"Harnessing the Power of Interleaving and Counterfactual Evaluation for Airbnb Search Ranking","created":"2025-08-01","cited_by_count":3,"area":null},{"id":"2101.02553","title":"Off-Policy Evaluation of Slate Policies under Bayes Risk","created":"2021-01-05","cited_by_count":2,"area":null},{"id":"2209.07074","title":"On the Reuse Bias in Off-Policy Reinforcement Learning","created":"2022-09-15","cited_by_count":2,"area":null},{"id":"2209.07148","title":"Semi-supervised Batch Learning From Logged Data","created":"2022-09-15","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":"2502.21304","title":"Clustering Context in Off-Policy Evaluation","created":"2025-02-28","cited_by_count":2,"area":null},{"id":"2506.10677","title":"Exploiting Similarities in A/B Testing with Off-Policy Estimation","created":"2025-06-12","cited_by_count":2,"area":null},{"id":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","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":"2302.11725","title":"Asymptotically Unbiased Off-Policy Policy Evaluation when Reusing Old Data in Nonstationary Environments","created":"2023-02-23","cited_by_count":1,"area":null},{"id":"2506.14439","title":"A General Framework for Off-Policy Learning with Partially-Observed Reward","created":"2025-06-17","cited_by_count":1,"area":null},{"id":"2509.03456","title":"Off-Policy Learning in Large Action Spaces: Optimization Matters More Than Estimation","created":"2025-09-03","cited_by_count":1,"area":null},{"id":"2509.10520","title":"Offline Contextual Bandit with Counterfactual Sample Identification","created":"2025-09-03","cited_by_count":1,"area":"alignment"},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"area":null},{"id":"2603.21485","title":"Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2606.03878","title":"Privacy-Robust Incrementality Measurement for Advertising Systems under Signal Loss","created":"2026-06-02","cited_by_count":1,"area":null},{"id":"2607.01958","title":"A More Accurate Algorithm Comparison through A/B Testing using Offline Evaluation Methods","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2110.09864","title":"Learning Pareto-Efficient Decisions with Confidence","created":"2021-10-19","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":"2206.03851","title":"Reconsidering Learning Objectives in Unbiased Recommendation with Unobserved Confounders","created":"2022-06-07","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":"2504.08773","title":"Counterfactual Inference under Thompson Sampling","created":"2025-04-03","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":"2506.00446","title":"Off-Policy Evaluation of Ranking Policies via Embedding-Space User Behavior Modeling","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2506.10664","title":"Sequential Off-Policy Learning with Logarithmic Smoothing","created":"2025-06-12","cited_by_count":0,"area":null},{"id":"2508.07914","title":"Meta Off-Policy Estimation","created":"2025-08-11","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":"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":"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":"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":"2608.12831","title":"Fast A/B/n Testing: Exact Multi-Policy Comparison via Tree-Coupled Feedback Sharing","created":"2026-08-13","cited_by_count":0,"area":"agents"},{"id":"2608.24858","title":"Bellman Calibration for Marginalized Importance Weighting in Offline Reinforcement Learning","created":"2026-08-25","cited_by_count":0,"area":"offlinerl"},{"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":"2609.39026","title":"Search Shapes Conclusions: Auditing Evidence Selection Bias in Deep Research Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}