{"total":31,"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":"2104.12820","title":"Universal Off-Policy Evaluation","created":"2021-04-26","cited_by_count":43,"area":null},{"id":"2111.06784","title":"A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes","created":"2021-11-12","cited_by_count":36,"area":null},{"id":"2212.09900","title":"Policy learning \"without\" overlap: Pessimism and generalized empirical Bernstein's inequality","created":"2022-12-19","cited_by_count":32,"area":null},{"id":"2108.03706","title":"Online Bootstrap Inference For Policy Evaluation in Reinforcement Learning","created":"2021-08-08","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":"2211.13904","title":"Policy-Adaptive Estimator Selection for Off-Policy Evaluation","created":"2022-11-25","cited_by_count":24,"area":null},{"id":"2210.13132","title":"PAC-Bayesian Offline Contextual Bandits With Guarantees","created":"2022-10-24","cited_by_count":20,"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":"2305.15877","title":"Exponential Smoothing for Off-Policy Learning","created":"2023-05-25","cited_by_count":15,"area":null},{"id":"2207.06364","title":"BR-SNIS: Bias Reduced Self-Normalized Importance Sampling","created":"2022-07-13","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":"2405.21043","title":"Target Networks and Over-parameterization Stabilize Off-policy Bootstrapping with Function Approximation","created":"2024-05-31","cited_by_count":10,"area":null},{"id":"2101.09847","title":"High-Confidence Off-Policy (or Counterfactual) Variance Estimation","created":"2021-01-25","cited_by_count":8,"area":null},{"id":"2211.16110","title":"PAC-Bayes Bounds for Bandit Problems: A Survey and Experimental Comparison","created":"2022-11-29","cited_by_count":7,"area":null},{"id":"2304.02574","title":"Conformal Off-Policy Evaluation in Markov Decision Processes","created":"2023-04-05","cited_by_count":6,"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":"2505.20130","title":"Balancing Interference and Correlation in Spatial Experimental Designs: A Causal Graph Cut Approach","created":"2025-05-26","cited_by_count":5,"area":null},{"id":"2502.10826","title":"Improved Offline Contextual Bandits with Second-Order Bounds: Betting and Freezing","created":"2025-02-15","cited_by_count":4,"area":null},{"id":"2212.01925","title":"Counterfactual Learning with General Data-generating Policies","created":"2022-12-04","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":"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":"2404.00848","title":"Predictive Performance Comparison of Decision Policies Under Confounding","created":"2024-04-01","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":"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":"2606.17515","title":"Anytime-valid Optimal Policy Identification","created":"2026-06-16","cited_by_count":1,"area":null},{"id":"2205.10739","title":"Offline Policy Comparison with Confidence: Benchmarks and Baselines","created":"2022-05-22","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":"2607.15067","title":"Kernel weighted importance sampling for off-policy evaluation in contextual bandits","created":"2026-07-16","cited_by_count":0,"area":null}],"next_cursor":null}