{"total":19,"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":"2106.07914","title":"Control Variates for Slate Off-Policy Evaluation","created":"2021-06-15","cited_by_count":13,"area":null},{"id":"2201.05893","title":"Treatment Effect Risk: Bounds and Inference","created":"2022-01-15","cited_by_count":12,"area":null},{"id":"2209.08860","title":"A Survey of Deep Causal Models and Their Industrial Applications","created":"2022-09-19","cited_by_count":10,"area":null},{"id":"2302.02944","title":"Learning Complementary Policies for Human-AI Teams","created":"2023-02-06","cited_by_count":7,"area":null},{"id":"2110.10081","title":"Stateful Offline Contextual Policy Evaluation and Learning","created":"2021-10-19","cited_by_count":6,"area":null},{"id":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2310.08824","title":"Confounding-Robust Policy Improvement with Human-AI Teams","created":"2023-10-13","cited_by_count":4,"area":null},{"id":"2202.12958","title":"Off-Policy Evaluation with Policy-Dependent Optimization Response","created":"2022-02-25","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":"2209.07330","title":"Best Arm Identification with Contextual Information under a Small Gap","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2101.12476","title":"Beyond traditional assumptions in fair machine learning","created":"2021-01-29","cited_by_count":2,"area":null},{"id":"2102.03239","title":"Applications of Machine Learning in Document Digitisation","created":"2021-02-05","cited_by_count":2,"area":null},{"id":"2104.08482","title":"Agnostic learning with unknown utilities","created":"2021-04-17","cited_by_count":1,"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":"2104.10573","title":"GEAR: On Optimal Decision Making with Auxiliary Data","created":"2021-04-21","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":"2111.00870","title":"Statistical Consequences of Dueling Bandits","created":"2021-10-16","cited_by_count":0,"area":null},{"id":"2201.07998","title":"Statistical Learning for Individualized Asset Allocation","created":"2022-01-20","cited_by_count":0,"area":null}],"next_cursor":null}