{"total":19,"rows":[{"id":"2205.14309","title":"Federated Neural Bandits","created":"2022-05-28","cited_by_count":17,"area":null},{"id":"2112.00195","title":"Efficient Online Bayesian Inference for Neural Bandits","created":"2021-12-01","cited_by_count":15,"area":null},{"id":"2304.04341","title":"Regret Distribution in Stochastic Bandits: Optimal Trade-off between Expectation and Tail Risk","created":"2023-04-10","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":"2203.02605","title":"Reinforcement Learning in Modern Biostatistics: Constructing Optimal Adaptive Interventions","created":"2022-03-04","cited_by_count":6,"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":"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":"2205.08295","title":"Semi-Parametric Contextual Bandits with Graph-Laplacian Regularization","created":"2022-05-17","cited_by_count":4,"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":"2301.08781","title":"GBOSE: Generalized Bandit Orthogonalized Semiparametric Estimation","created":"2023-01-20","cited_by_count":1,"area":null},{"id":"2308.09248","title":"Active and Passive Causal Inference Learning","created":"2023-08-18","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":"2411.12154","title":"Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2506.13390","title":"Experimental Design for Semiparametric Bandits","created":"2025-06-16","cited_by_count":1,"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":"2407.16062","title":"Artificial Intelligence-based Decision Support Systems for Precision and Digital Health","created":"2024-07-22","cited_by_count":0,"area":null},{"id":"2604.03969","title":"Nearly Optimal Best Arm Identification for Semiparametric Bandits","created":"2026-04-05","cited_by_count":0,"area":null},{"id":"2609.01999","title":"Posterior Tempering Explains Variance Inflation in Linear and Generalized Linear Thompson Sampling","created":"2026-09-02","cited_by_count":0,"area":null},{"id":"2609.19709","title":"Odds-Ratio Thompson Sampling: A Specification and Design Guide for Contrast-Based Multi-Armed Bandits","created":"2026-09-17","cited_by_count":0,"area":null}],"next_cursor":null}