{"total":28,"rows":[{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"area":null},{"id":"2206.03944","title":"Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-implementation Guidelines","created":"2022-06-08","cited_by_count":22,"area":null},{"id":"2208.07406","title":"Reward Design For An Online Reinforcement Learning Algorithm Supporting Oral Self-Care","created":"2022-08-15","cited_by_count":18,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2412.03727","title":"Online Experimental Design With Estimation-Regret Trade-off Under Network Interference","created":"2024-12-04","cited_by_count":9,"area":null},{"id":"2111.00137","title":"Efficient Inference Without Trading-off Regret in Bandits: An Allocation Probability Test for Thompson Sampling","created":"2021-10-30","cited_by_count":7,"area":null},{"id":"2307.02108","title":"Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization","created":"2023-07-05","cited_by_count":7,"area":null},{"id":"2103.12198","title":"Challenges in Statistical Analysis of Data Collected by a Bandit Algorithm: An Empirical Exploration in Applications to Adaptively Randomized Experiments","created":"2021-03-22","cited_by_count":6,"area":null},{"id":"2310.18326","title":"Using Adaptive Bandit Experiments to Increase and Investigate Engagement in Mental Health","created":"2023-10-13","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":"2412.08052","title":"CANDOR: Counterfactual ANnotated DOubly Robust Off-Policy Evaluation","created":"2024-12-11","cited_by_count":3,"area":null},{"id":"2311.14359","title":"Thompson sampling for zero-inflated count outcomes with an application to the Drink Less mobile health study","created":"2023-11-24","cited_by_count":2,"area":null},{"id":"2408.07647","title":"Adaptive Behavioral AI: Reinforcement Learning to Enhance Pharmacy Services","created":"2024-08-14","cited_by_count":2,"area":null},{"id":"2408.12778","title":"Data-Centric Approach to Constrained Machine Learning: A Case Study on Conway's Game of Life","created":"2024-08-23","cited_by_count":2,"area":null},{"id":"2112.08507","title":"Algorithms for Adaptive Experiments that Trade-off Statistical Analysis with Reward: Combining Uniform Random Assignment and Reward Maximization","created":"2021-12-15","cited_by_count":1,"area":null},{"id":"2208.11747","title":"Entropy Regularization for Population Estimation","created":"2022-08-24","cited_by_count":1,"area":null},{"id":"2401.08224","title":"Privacy Preserving Adaptive Experiment Design","created":"2024-01-16","cited_by_count":1,"area":null},{"id":"2409.10526","title":"Effective Monitoring of Online Decision-Making Algorithms in Digital Intervention Implementation","created":"2024-08-30","cited_by_count":1,"area":null},{"id":"2409.16098","title":"The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems","created":"2024-09-24","cited_by_count":1,"area":null},{"id":"2511.02944","title":"Power Constrained Nonstationary Bandits with Habituation and Recovery Dynamics","created":"2025-11-04","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":"2303.02075","title":"Adaptive Interventions for Global Health: A Case Study of Malaria","created":"2023-03-03","cited_by_count":0,"area":null},{"id":"2311.09483","title":"Adaptive Interventions with User-Defined Goals for Health Behavior Change","created":"2023-11-16","cited_by_count":0,"area":null},{"id":"2408.07629","title":"Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2408.08024","title":"Adaptive User Journeys in Pharma E-Commerce with Reinforcement Learning: Insights from SwipeRx","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2509.05864","title":"Beyond ATE: Multi-Criteria Design for A/B Testing","created":"2025-09-06","cited_by_count":0,"area":null},{"id":"2510.01020","title":"The Good, the Bad, and the Sampled: a No-Regret Approach to Safe Online Classification","created":"2025-10-01","cited_by_count":0,"area":null},{"id":"2512.09850","title":"Conformal bandits: bringing statistical validity and reward efficiency under weak arm separability","created":"2025-12-10","cited_by_count":0,"area":null}],"next_cursor":null}