{"total":14,"rows":[{"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":"2402.06122","title":"Peeking with PEAK: Sequential, Nonparametric Composite Hypothesis Tests for Means of Multiple Data Streams","created":"2024-02-09","cited_by_count":9,"area":null},{"id":"2505.23260","title":"Stable Thompson Sampling: Valid Inference via Variance Inflation","created":"2025-05-29","cited_by_count":8,"area":null},{"id":"2402.17739","title":"reBandit: Random Effects based Online RL algorithm for Reducing Cannabis Use","created":"2024-02-27","cited_by_count":6,"area":null},{"id":"2301.05491","title":"Efficient and robust transfer learning of optimal individualized treatment regimes with right-censored survival data","created":"2023-01-13","cited_by_count":5,"area":null},{"id":"2305.18511","title":"Contextual Bandits with Budgeted Information Reveal","created":"2023-05-29","cited_by_count":3,"area":null},{"id":"2306.11208","title":"The Unintended Consequences of Discount Regularization: Improving Regularization in Certainty Equivalence Reinforcement Learning","created":"2023-06-20","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":"2308.07843","title":"Dyadic Reinforcement Learning","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2407.14845","title":"Prompting the Unknown: Understanding Response Uncertainty in Large Language Models","created":"2024-07-20","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":"2509.13499","title":"Reproducible workflow for online AI in digital health","created":"2025-09-16","cited_by_count":1,"area":null},{"id":"2303.01954","title":"Synthetic Data Generator for Adaptive Interventions in Global Health","created":"2023-03-03","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}],"next_cursor":null}