{"total":11,"rows":[{"id":"2409.02069","title":"A Deployed Online Reinforcement Learning Algorithm In An Oral Health Clinical Trial","created":"2024-09-03","cited_by_count":11,"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":"2303.02534","title":"Semi-parametric inference based on adaptively collected data","created":"2023-03-05","cited_by_count":7,"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":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2402.03110","title":"Non-Stationary Latent Auto-Regressive Bandits","created":"2024-02-05","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":"2305.11942","title":"OPTWIN: Drift identification with optimal sub-windows","created":"2023-05-19","cited_by_count":1,"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}],"next_cursor":null}