{"total":65,"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":"2202.10589","title":"Off-Policy Confidence Interval Estimation with Confounded Markov Decision Process","created":"2022-02-22","cited_by_count":31,"area":null},{"id":"2112.14582","title":"A Statistical Analysis of Polyak-Ruppert Averaged Q-learning","created":"2021-12-29","cited_by_count":29,"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":"2110.10719","title":"Estimating Optimal Infinite Horizon Dynamic Treatment Regimes via pT-Learning","created":"2021-10-20","cited_by_count":26,"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":"2603.01162","title":"Demystifying Group Relative Policy Optimization: Its Policy Gradient is a U-Statistic","created":"2026-03-01","cited_by_count":21,"area":"lr"},{"id":"2212.14468","title":"An Instrumental Variable Approach to Confounded Off-Policy Evaluation","created":"2022-12-29","cited_by_count":20,"area":null},{"id":"2109.04640","title":"Projected State-action Balancing Weights for Offline Reinforcement Learning","created":"2021-09-10","cited_by_count":16,"area":"offlinerl"},{"id":"2206.06711","title":"Conformal Off-policy Prediction","created":"2022-06-14","cited_by_count":14,"area":null},{"id":"2206.05581","title":"Federated Offline Reinforcement Learning","created":"2022-06-11","cited_by_count":13,"area":"offlinerl"},{"id":"2210.11846","title":"Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities","created":"2022-10-21","cited_by_count":13,"area":null},{"id":"2203.01707","title":"Testing Stationarity and Change Point Detection in Reinforcement Learning","created":"2022-03-03","cited_by_count":12,"area":"offlinerl"},{"id":"2202.13163","title":"Statistically Efficient Advantage Learning for Offline Reinforcement Learning in Infinite Horizons","created":"2022-02-26","cited_by_count":10,"area":"offlinerl"},{"id":"2006.03886","title":"Efficient Evaluation of Natural Stochastic Policies in Offline Reinforcement Learning","created":"2020-06-06","cited_by_count":8,"area":"offlinerl"},{"id":"2202.10887","title":"Policy Evaluation for Temporal and/or Spatial Dependent Experiments","created":"2022-02-22","cited_by_count":8,"area":null},{"id":"2202.00088","title":"Reinforcement Learning with Heterogeneous Data: Estimation and Inference","created":"2022-01-31","cited_by_count":7,"area":null},{"id":"2301.02220","title":"Value Enhancement of Reinforcement Learning via Efficient and Robust Trust Region Optimization","created":"2023-01-05","cited_by_count":7,"area":null},{"id":"2301.08940","title":"Quasi-optimal Reinforcement Learning with Continuous Actions","created":"2023-01-21","cited_by_count":7,"area":null},{"id":"2303.14281","title":"Sequential Knockoffs for Variable Selection in Reinforcement Learning","created":"2023-03-24","cited_by_count":7,"area":null},{"id":"2306.08719","title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","created":"2023-06-14","cited_by_count":7,"area":null},{"id":"2310.18715","title":"Robust Offline Reinforcement learning with Heavy-Tailed Rewards","created":"2023-10-28","cited_by_count":7,"area":"offlinerl"},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2309.13278","title":"Distributional Shift-Aware Off-Policy Interval Estimation: A Unified Error Quantification Framework","created":"2023-09-23","cited_by_count":6,"area":null},{"id":"2403.17285","title":"Unraveling the Interplay between Carryover Effects and Reward Autocorrelations in Switchback Experiments","created":"2024-03-26","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":"2212.14466","title":"Quantile Off-Policy Evaluation via Deep Conditional Generative Learning","created":"2022-12-29","cited_by_count":5,"area":null},{"id":"2302.00141","title":"Revisiting Bellman Errors for Offline Model Selection","created":"2023-01-31","cited_by_count":5,"area":"offlinerl"},{"id":"2310.06268","title":"Bi-Level Offline Policy Optimization with Limited Exploration","created":"2023-10-10","cited_by_count":5,"area":"offlinerl"},{"id":"2405.18556","title":"Reinforcement Learning in Dynamic Treatment Regimes Needs Critical Reexamination","created":"2024-05-28","cited_by_count":5,"area":"offlinerl"},{"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":"2102.00102","title":"Adaptive Sequential Design for a Single Time-Series","created":"2021-01-29","cited_by_count":4,"area":null},{"id":"2202.10574","title":"A Multi-Agent Reinforcement Learning Framework for Off-Policy Evaluation in Two-sided Markets","created":"2022-02-21","cited_by_count":4,"area":null},{"id":"2204.07124","title":"Learning Optimal Dynamic Treatment Regimes Using Causal Tree Methods in Medicine","created":"2022-04-14","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":"2505.09496","title":"Reinforcement Learning for Individual Optimal Policy from Heterogeneous Data","created":"2025-05-14","cited_by_count":4,"area":"offlinerl"},{"id":"2108.04087","title":"Reinforcement Learning for Intelligent Healthcare Systems: A Comprehensive Survey","created":"2021-08-05","cited_by_count":3,"area":null},{"id":"2202.04709","title":"Transfer Q-learning","created":"2022-02-09","cited_by_count":3,"area":"offlinerl"},{"id":"2211.03983","title":"Doubly Inhomogeneous Reinforcement Learning","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2407.00364","title":"Medical Knowledge Integration into Reinforcement Learning Algorithms for Dynamic Treatment Regimes","created":"2024-06-29","cited_by_count":3,"area":"deeprl"},{"id":"2505.00304","title":"Reinforcement Learning with Continuous Actions Under Unmeasured Confounding","created":"2025-05-01","cited_by_count":3,"area":null},{"id":"2201.06229","title":"Targeted Optimal Treatment Regime Learning Using Summary Statistics","created":"2022-01-17","cited_by_count":2,"area":null},{"id":"2211.16566","title":"Relative Sparsity for Medical Decision Problems","created":"2022-11-29","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":"2407.17910","title":"Causal Deepsets for Off-policy Evaluation under Spatial or Spatio-temporal Interferences","created":"2024-07-25","cited_by_count":2,"area":null},{"id":"2502.16195","title":"Statistical Inference in Reinforcement Learning: A Selective Survey","created":"2025-02-22","cited_by_count":2,"area":"deeprl"},{"id":"2507.06961","title":"Off-Policy Evaluation Under Nonignorable Missing Data","created":"2025-07-09","cited_by_count":2,"area":null},{"id":"2507.18118","title":"A Two-armed Bandit Framework for A/B Testing","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2206.05860","title":"IGN : Implicit Generative Networks","created":"2022-06-13","cited_by_count":1,"area":null},{"id":"2309.16188","title":"Stackelberg Batch Policy Learning","created":"2023-09-28","cited_by_count":1,"area":"offlinerl"},{"id":"2408.09155","title":"Learning Robust Treatment Rules for Censored Data","created":"2024-08-17","cited_by_count":1,"area":null},{"id":"2201.07998","title":"Statistical Learning for Individualized Asset Allocation","created":"2022-01-20","cited_by_count":0,"area":null},{"id":"2301.00927","title":"Deep Spectral Q-learning with Application to Mobile Health","created":"2023-01-03","cited_by_count":0,"area":null},{"id":"2301.12553","title":"Asymptotic Inference for Multi-Stage Stationary Treatment Policy with Variable Selection","created":"2023-01-29","cited_by_count":0,"area":null},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2310.14976","title":"Reinforcement learning in large, structured action spaces: A simulation study of decision support for spinal cord injury rehabilitation","created":"2023-10-23","cited_by_count":0,"area":null},{"id":"2311.18725","title":"AI in Pharma for Personalized Sequential Decision-Making: Methods, Applications and Opportunities","created":"2023-11-30","cited_by_count":0,"area":null},{"id":"2407.16062","title":"Artificial Intelligence-based Decision Support Systems for Precision and Digital Health","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2506.23040","title":"Treatment, evidence, imitation, and chat","created":"2025-06-29","cited_by_count":0,"area":null},{"id":"2510.03912","title":"Generalized Fitted Q-Iteration with Clustered Data","created":"2025-10-04","cited_by_count":0,"area":"deeprl"},{"id":"2605.25114","title":"Counterfactually Safe Reinforcement Learning","created":"2026-05-24","cited_by_count":0,"area":"deeprl"},{"id":"2606.04562","title":"Neetyabhas: A Framework for Uncertainty-Aware Public Policy Optimization in Rational Agent-Based Models","created":"2026-06-03","cited_by_count":0,"area":null},{"id":"2608.23480","title":"Primal--Dual Alternating Neural Learning for Timely Classification with Performance Guarantees","created":"2026-08-24","cited_by_count":0,"area":null},{"id":"2609.20389","title":"Model-based Bootstrap for Offline Policy Evaluation in Tabular Reinforcement Learning","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}