{"total":17,"rows":[{"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":"2304.02572","title":"Evaluating Online Bandit Exploration In Large-Scale Recommender System","created":"2023-04-05","cited_by_count":7,"area":null},{"id":"2105.14586","title":"Kolmogorov-Smirnov Test-Based Actively-Adaptive Thompson Sampling for Non-Stationary Bandits","created":"2021-05-30","cited_by_count":4,"area":null},{"id":"2207.06030","title":"Contextual Active Model Selection","created":"2022-07-13","cited_by_count":4,"area":null},{"id":"2108.00236","title":"Debiasing Samples from Online Learning Using Bootstrap","created":"2021-07-31","cited_by_count":3,"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":"2109.05278","title":"Existence conditions for hidden feedback loops in online recommender systems","created":"2021-09-11","cited_by_count":1,"area":null},{"id":"2205.09584","title":"Multi-Armed Bandits in Brain-Computer Interfaces","created":"2022-05-19","cited_by_count":1,"area":null},{"id":"2402.15442","title":"GROS: A General Robust Aggregation Strategy","created":"2024-02-23","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":"2510.12152","title":"Follow-the-Perturbed-Leader for Decoupled Bandits: Best-of-Both-Worlds and Practicality","created":"2025-10-14","cited_by_count":1,"area":null},{"id":"2101.06592","title":"TSEC: a framework for online experimentation under experimental constraints","created":"2021-01-17","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":"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":"2409.11442","title":"A Green Multi-Attribute Client Selection for Over-The-Air Federated Learning: A Grey-Wolf-Optimizer Approach","created":"2024-09-16","cited_by_count":0,"area":null},{"id":"2503.15962","title":"Information maximization for a broad variety of multi-armed bandit games","created":"2025-03-20","cited_by_count":0,"area":null}],"next_cursor":null}