{"total":20,"rows":[{"id":"2108.06422","title":"Metadata-based Multi-Task Bandits with Bayesian Hierarchical Models","created":"2021-08-13","cited_by_count":24,"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":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2202.06891","title":"Counterfactual inference in sequential experiments","created":"2022-02-14","cited_by_count":13,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2202.11296","title":"Reinforcement Learning in Practice: Opportunities and Challenges","created":"2022-02-23","cited_by_count":6,"area":null},{"id":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"area":null},{"id":"2211.08998","title":"Data-pooling Reinforcement Learning for Personalized Healthcare Intervention","created":"2022-11-16","cited_by_count":6,"area":null},{"id":"2312.06403","title":"RoME: A Robust Mixed-Effects Bandit Algorithm for Optimizing Mobile Health Interventions","created":"2023-12-11","cited_by_count":5,"area":null},{"id":"2601.01069","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits and MDPs","created":"2026-01-03","cited_by_count":5,"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":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2205.02944","title":"A Deep Bayesian Bandits Approach for Anticancer Therapy: Exploration via Functional Prior","created":"2022-05-05","cited_by_count":0,"area":null},{"id":"2303.02691","title":"Revisiting Weighted Strategy for Non-stationary Parametric Bandits","created":"2023-03-05","cited_by_count":0,"area":null},{"id":"2309.14156","title":"Designing and evaluating an online reinforcement learning agent for physical exercise recommendations in N-of-1 trials","created":"2023-09-25","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":"2408.07897","title":"The Nah Bandit: Modeling User Non-compliance in Recommendation Systems","created":"2024-08-15","cited_by_count":0,"area":null},{"id":"2605.24261","title":"Optimizing Digital Therapeutic Interventions: Online Learning under Endogenous Adherence","created":"2026-05-22","cited_by_count":0,"area":null},{"id":"2605.25590","title":"Nonstationary Generalized Linear Bandits with Discounted Online Mirror Descent","created":"2026-05-25","cited_by_count":0,"area":null},{"id":"2608.01545","title":"Dominant Arm Identification with Mixing and Recycling Observed Samples","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}