{"total":103,"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":"2105.04646","title":"Deeply-Debiased Off-Policy Interval Estimation","created":"2021-05-10","cited_by_count":36,"area":null},{"id":"2106.11960","title":"Variance-Aware Off-Policy Evaluation with Linear Function Approximation","created":"2021-06-22","cited_by_count":34,"area":null},{"id":"2202.09667","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","created":"2022-02-19","cited_by_count":34,"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":"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":"2105.13623","title":"Enhanced Doubly Robust Learning for Debiasing Post-click Conversion Rate Estimation","created":"2021-05-28","cited_by_count":28,"area":null},{"id":"2105.03863","title":"Towards Theoretical Understandings of Robust Markov Decision Processes: Sample Complexity and Asymptotics","created":"2021-05-09","cited_by_count":27,"area":null},{"id":"2106.10251","title":"Active Offline Policy Selection","created":"2021-06-18","cited_by_count":26,"area":null},{"id":"2206.04405","title":"Conformal Off-Policy Prediction in Contextual Bandits","created":"2022-06-09","cited_by_count":25,"area":null},{"id":"2105.10148","title":"On Instrumental Variable Regression for Deep Offline Policy Evaluation","created":"2021-05-21","cited_by_count":22,"area":null},{"id":"2207.13081","title":"Future-Dependent Value-Based Off-Policy Evaluation in POMDPs","created":"2022-07-26","cited_by_count":21,"area":null},{"id":"2212.02779","title":"PrefRec: Recommender Systems with Human Preferences for Reinforcing Long-term User Engagement","created":"2022-12-06","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":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","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":"2211.05311","title":"When is Realizability Sufficient for Off-Policy Reinforcement Learning?","created":"2022-11-10","cited_by_count":17,"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":"2405.14335","title":"Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning","created":"2024-05-23","cited_by_count":16,"area":null},{"id":"2111.14552","title":"Robust On-Policy Sampling for Data-Efficient Policy Evaluation in Reinforcement Learning","created":"2021-11-29","cited_by_count":15,"area":null},{"id":"2303.01049","title":"Model-based Constrained MDP for Budget Allocation in Sequential Incentive Marketing","created":"2023-03-02","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":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"area":null},{"id":"2301.13734","title":"Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design","created":"2023-01-31","cited_by_count":14,"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":"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":"2106.01723","title":"Risk Minimization from Adaptively Collected Data: Guarantees for Supervised and Policy Learning","created":"2021-06-03","cited_by_count":10,"area":null},{"id":"2206.02620","title":"ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor","created":"2022-06-01","cited_by_count":10,"area":null},{"id":"2402.14703","title":"On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation","created":"2024-02-22","cited_by_count":10,"area":null},{"id":"2404.04399","title":"Longitudinal Targeted Minimum Loss-based Estimation with Temporal-Difference Heterogeneous Transformer","created":"2024-04-05","cited_by_count":10,"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":"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":"2103.05612","title":"Challenges for Reinforcement Learning in Healthcare","created":"2021-03-09","cited_by_count":7,"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":"2305.03954","title":"Learning Action Embeddings for Off-Policy Evaluation","created":"2023-05-06","cited_by_count":7,"area":null},{"id":"2310.17146","title":"Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation","created":"2023-10-26","cited_by_count":7,"area":null},{"id":"2202.01721","title":"Variance-Optimal Augmentation Logging for Counterfactual Evaluation in Contextual Bandits","created":"2022-02-03","cited_by_count":6,"area":null},{"id":"2210.13373","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","created":"2022-10-24","cited_by_count":6,"area":null},{"id":"2301.12056","title":"Variational Latent Branching Model for Off-Policy Evaluation","created":"2023-01-28","cited_by_count":6,"area":null},{"id":"2406.00317","title":"Combining Experimental and Historical Data for Policy Evaluation","created":"2024-06-01","cited_by_count":6,"area":null},{"id":"2212.03932","title":"Low Variance Off-policy Evaluation with State-based Importance Sampling","created":"2022-12-07","cited_by_count":5,"area":null},{"id":"2302.09212","title":"HOPE: Human-Centric Off-Policy Evaluation for E-Learning and Healthcare","created":"2023-02-18","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":"2306.15625","title":"Value-aware Importance Weighting for Off-policy Reinforcement Learning","created":"2023-06-27","cited_by_count":4,"area":null},{"id":"2310.18409","title":"State-Action Similarity-Based Representations for Off-Policy Evaluation","created":"2023-10-27","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":"2406.19531","title":"Off-policy Evaluation with Deeply-abstracted States","created":"2024-06-27","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":"2107.01360","title":"Supervised Off-Policy Ranking","created":"2021-07-03","cited_by_count":3,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"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":"2307.07014","title":"Leveraging Factored Action Spaces for Off-Policy Evaluation","created":"2023-07-13","cited_by_count":3,"area":null},{"id":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","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":"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":"2412.08052","title":"CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation","created":"2024-12-11","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":"2105.13420","title":"Model Selection for Production System via Automated Online Experiments","created":"2021-05-27","cited_by_count":2,"area":null},{"id":"2112.11532","title":"Off Environment Evaluation Using Convex Risk Minimization","created":"2021-12-21","cited_by_count":2,"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":"2301.13348","title":"A Reinforcement Learning Framework for Dynamic Mediation Analysis","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2404.00195","title":"Multiple-policy Evaluation via Density Estimation","created":"2024-03-29","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":"2507.13608","title":"Off-Policy Evaluation and Learning for Matching Markets","created":"2025-07-18","cited_by_count":2,"area":null},{"id":"2109.06625","title":"Towards optimized actions in critical situations of soccer games with deep reinforcement learning","created":"2021-09-14","cited_by_count":1,"area":null},{"id":"2202.13337","title":"Towards Robust Off-policy Learning for Runtime Uncertainty","created":"2022-02-27","cited_by_count":1,"area":null},{"id":"2211.11119","title":"Counterfactual Learning with Multioutput Deep Kernels","created":"2022-11-20","cited_by_count":1,"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":"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":"2407.11039","title":"Balancing Immediate Revenue and Future Off-Policy Evaluation in Coupon Allocation","created":"2024-07-06","cited_by_count":1,"area":null},{"id":"2411.19395","title":"Concept-driven Off Policy Evaluation","created":"2024-11-28","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":"2603.05919","title":"Design Experiments to Compare Multi-armed Bandit Algorithms","created":"2026-03-06","cited_by_count":1,"area":null},{"id":"2603.08370","title":"Unifying On- and Off-Policy Variance Reduction Methods","created":"2026-03-09","cited_by_count":1,"area":null},{"id":"2603.18702","title":"Off-Policy Learning with Limited Supply","created":"2026-03-19","cited_by_count":1,"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":"2312.15458","title":"Conservative Exploration for Policy Optimization via Off-Policy Policy Evaluation","created":"2023-12-24","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":"2502.01672","title":"Doubly Robust Monte Carlo Tree Search","created":"2025-02-01","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":"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":"2509.26429","title":"An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes","created":"2025-09-30","cited_by_count":0,"area":null},{"id":"2510.07635","title":"Safely Exploring Novel Actions in Recommender Systems via Deployment-Efficient Policy Learning","created":"2025-10-09","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":"2604.18972","title":"Beyond Bellman: High-Order Generator Regression for Continuous-Time Policy Evaluation","created":"2026-04-21","cited_by_count":0,"area":null},{"id":"2605.14284","title":"Smooth Multi-Policy Causal Effect Estimation in Longitudinal Settings","created":"2026-05-14","cited_by_count":0,"area":null}],"next_cursor":"100"}