{"total":21,"rows":[{"id":"2202.07234","title":"Long-term Causal Inference Under Persistent Confounding via Data Combination","created":"2022-02-15","cited_by_count":27,"area":null},{"id":"2104.04103","title":"Causal Decision Making and Causal Effect Estimation Are Not the Same... and Why It Matters","created":"2021-04-08","cited_by_count":25,"area":null},{"id":"2203.01303","title":"An Analysis of Ensemble Sampling","created":"2022-03-02","cited_by_count":24,"area":null},{"id":"2209.06203","title":"Normalizing Flows for Interventional Density Estimation","created":"2022-09-13","cited_by_count":21,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2303.08516","title":"Fair Off-Policy Learning from Observational Data","created":"2023-03-15","cited_by_count":11,"area":null},{"id":"2404.15691","title":"Long-term Off-Policy Evaluation and Learning","created":"2024-04-24","cited_by_count":9,"area":null},{"id":"2302.03561","title":"Optimizing Audio Recommendations for the Long-Term: A Reinforcement Learning Perspective","created":"2023-02-07","cited_by_count":8,"area":null},{"id":"2310.08672","title":"Machine Learning Who to Nudge: Causal vs Predictive Targeting in a Field Experiment on Student Financial Aid Renewal","created":"2023-10-12","cited_by_count":8,"area":null},{"id":"2211.12004","title":"Contextual Bandits in a Survey Experiment on Charitable Giving: Within-Experiment Outcomes versus Policy Learning","created":"2022-11-22","cited_by_count":7,"area":null},{"id":"2311.08376","title":"Ensemble sampling for linear bandits: small ensembles suffice","created":"2023-11-14","cited_by_count":7,"area":null},{"id":"2405.03329","title":"Policy Learning for Balancing Short-Term and Long-Term Rewards","created":"2024-05-06","cited_by_count":7,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2306.02948","title":"Learning under random distributional shifts","created":"2023-06-05","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":"2206.12532","title":"Causal Ordering Without Effect Estimation: A Framework for Using Proxies in Treatment Prioritization","created":"2022-06-25","cited_by_count":1,"area":null},{"id":"2311.14698","title":"Business Policy Experiments using Fractional Factorial Designs: Consumer Retention on DoorDash","created":"2023-11-10","cited_by_count":0,"area":null},{"id":"2403.02624","title":"Pareto-Optimal Estimation and Policy Learning on Short-term and Long-term Treatment Effects","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2504.19527","title":"Identification and Estimation of Long-Term Treatment Effects with Monotone Missing","created":"2025-04-28","cited_by_count":0,"area":null},{"id":"2604.00915","title":"Orthogonal Learner for Estimating Heterogeneous Long-Term Treatment Effects","created":"2026-04-01","cited_by_count":0,"area":null},{"id":"2607.29421","title":"Longitudinal Adaptive Experimental Design for Learning Multiple Target Estimands with Semiparametric Efficient Inference","created":"2026-07-31","cited_by_count":0,"area":null}],"next_cursor":null}