{"total":15,"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":"2104.07822","title":"Estimating and Improving Dynamic Treatment Regimes With a Time-Varying Instrumental Variable","created":"2021-04-15","cited_by_count":13,"area":null},{"id":"2112.04571","title":"Ambiguous Dynamic Treatment Regimes: A Reinforcement Learning Approach","created":"2021-12-08","cited_by_count":6,"area":null},{"id":"2111.13415","title":"ESCADA: Efficient Safety and Context Aware Dose Allocation for Precision Medicine","created":"2021-11-26","cited_by_count":5,"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":"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":"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":"2106.12886","title":"Constrained Classification and Policy Learning","created":"2021-06-24","cited_by_count":3,"area":null},{"id":"2203.02473","title":"Interpretable Off-Policy Learning via Hyperbox Search","created":"2022-03-04","cited_by_count":3,"area":null},{"id":"2104.10573","title":"GEAR: On Optimal Decision Making with Auxiliary Data","created":"2021-04-21","cited_by_count":1,"area":null},{"id":"2310.15333","title":"Safe and Interpretable Estimation of Optimal Treatment Regimes","created":"2023-10-23","cited_by_count":1,"area":null},{"id":"2106.05031","title":"Estimation of Optimal Dynamic Treatment Assignment Rules under Policy Constraints","created":"2021-06-09","cited_by_count":0,"area":null},{"id":"2107.07875","title":"A Penalized Shared-parameter Algorithm for Estimating Optimal Dynamic Treatment Regimens","created":"2021-07-13","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}],"next_cursor":null}