{"total":24,"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":"2202.09667","title":"Doubly Robust Distributionally Robust Off-Policy Evaluation and Learning","created":"2022-02-19","cited_by_count":34,"area":null},{"id":"2112.01387","title":"Generalizing Off-Policy Learning under Sample Selection Bias","created":"2021-12-02","cited_by_count":16,"area":null},{"id":"2109.11679","title":"Safe Policy Learning through Extrapolation: Application to Pre-trial Risk Assessment","created":"2021-09-22","cited_by_count":10,"area":null},{"id":"2103.01802","title":"Median Optimal Treatment Regimes","created":"2021-03-02","cited_by_count":7,"area":null},{"id":"2405.01709","title":"Minimax Regret Learning for Data with Heterogeneous Subgroups","created":"2024-05-02","cited_by_count":7,"area":null},{"id":"2301.05491","title":"Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2412.11136","title":"Minimax Regret Estimation for Generalizing Heterogeneous Treatment Effects with Multisite Data","created":"2024-12-15","cited_by_count":5,"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":"2407.03557","title":"Decision-Focused Evaluation of Worst-Case Distribution Shift","created":"2024-07-04","cited_by_count":4,"area":null},{"id":"2103.15933","title":"Learning Under Adversarial and Interventional Shifts","created":"2021-03-29","cited_by_count":3,"area":null},{"id":"2105.00581","title":"Robust Sample Weighting to Facilitate Individualized Treatment Rule Learning for a Target Population","created":"2021-05-03","cited_by_count":3,"area":null},{"id":"2412.01344","title":"Practical Performative Policy Learning with Strategic Agents","created":"2024-12-02","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":"2310.19300","title":"Stage-Aware Learning for Dynamic Treatments","created":"2023-10-30","cited_by_count":2,"area":null},{"id":"2505.08092","title":"Doubly Robust Fusion of Many Treatments for Policy Learning","created":"2025-05-12","cited_by_count":2,"area":null},{"id":"2104.10554","title":"Calibrated Optimal Decision Making with Multiple Data Sources and Limited Outcome","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2506.01348","title":"Distributionally Robust Learning in Survival Analysis","created":"2025-06-02","cited_by_count":1,"area":null},{"id":"2605.08506","title":"Learning Polyhedral Conformal Sets for Robust Optimization","created":"2026-05-08","cited_by_count":1,"area":null},{"id":"2110.08936","title":"Rejoinder: Learning Optimal Distributionally Robust Individualized Treatment Rules","created":"2021-10-17","cited_by_count":0,"area":null},{"id":"2209.08682","title":"Towards Robust Off-Policy Evaluation via Human Inputs","created":"2022-09-18","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":"2603.05568","title":"Learning Optimal Distributionally Robust Individualized Treatment Rules Integrating Multi-Source Data","created":"2026-03-05","cited_by_count":0,"area":null},{"id":"2606.19117","title":"Wasserstein Policy Learning for Distributional Outcomes","created":"2026-06-17","cited_by_count":0,"area":null}],"next_cursor":null}