{"total":56,"rows":[{"id":"2109.08075","title":"Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health","created":"2021-09-16","cited_by_count":43,"area":null},{"id":"2104.14074","title":"Statistical Inference with M-Estimators on Adaptively Collected Data","created":"2021-04-29","cited_by_count":40,"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":"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":"2303.16292","title":"XAIR: A Framework of Explainable AI in Augmented Reality","created":"2023-03-28","cited_by_count":17,"area":null},{"id":"2110.13052","title":"Can Q-Learning be Improved with Advice?","created":"2021-10-25","cited_by_count":13,"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":"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":"2211.14297","title":"Doubly robust nearest neighbors in factor models","created":"2022-11-25","cited_by_count":9,"area":null},{"id":"2303.12206","title":"Policy Optimization for Personalized Interventions in Behavioral Health","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2402.08658","title":"The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Conceptual Cardiac Rehabilitation Setting","created":"2024-02-13","cited_by_count":7,"area":null},{"id":"2502.13920","title":"Exploring Personalized Health Support through Data-Driven, Theory-Guided LLMs: A Case Study in Sleep Health","created":"2025-02-19","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":"2211.08998","title":"Data-pooling Reinforcement Learning for Personalized Healthcare Intervention","created":"2022-11-16","cited_by_count":6,"area":null},{"id":"2304.05365","title":"Did we personalize? Assessing personalization by an online reinforcement learning algorithm using resampling","created":"2023-04-11","cited_by_count":6,"area":null},{"id":"2307.07320","title":"Adaptive Linear Estimating Equations","created":"2023-07-14","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":"2403.05584","title":"Time2Stop: Adaptive and Explainable Human-AI Loop for Smartphone Overuse Intervention","created":"2024-03-03","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":"2307.13916","title":"Online learning in bandits with predicted context","created":"2023-07-26","cited_by_count":4,"area":null},{"id":"2502.05783","title":"WatchGuardian: Enabling User-Defined Personalized Just-in-Time Intervention on Smartwatch","created":"2025-02-09","cited_by_count":4,"area":null},{"id":"2211.03983","title":"Doubly Inhomogeneous Reinforcement Learning","created":"2022-11-08","cited_by_count":3,"area":null},{"id":"2305.09913","title":"Assessing the Impact of Context Inference Error and Partial Observability on RL Methods for Just-In-Time Adaptive Interventions","created":"2023-05-17","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":"2312.11551","title":"Probabilistic Offline Policy Ranking with Approximate Bayesian Computation","created":"2023-12-17","cited_by_count":3,"area":null},{"id":"2406.18848","title":"Temporally Multi-Scale Sparse Self-Attention for Physical Activity Data Imputation","created":"2024-06-27","cited_by_count":3,"area":null},{"id":"2407.20241","title":"NudgeRank: Digital Algorithmic Nudging for Personalized Health","created":"2024-07-16","cited_by_count":3,"area":null},{"id":"2106.00589","title":"Improving Long-Term Metrics in Recommendation Systems using Short-Horizon Reinforcement Learning","created":"2021-06-01","cited_by_count":2,"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":"2502.15345","title":"Efficiently Solving Discounted MDPs with Predictions on Transition Matrices","created":"2025-02-21","cited_by_count":2,"area":null},{"id":"2606.02595","title":"Human-in-the-Loop Contextual Bandits for Short-Term Rental Dynamic Pricing: Structural Equivalence of Historical Warm-Up and Approval-Gated Live Learning","created":"2026-05-22","cited_by_count":2,"area":null},{"id":"2103.06160","title":"Using Cognitive Models to Train Warm Start Reinforcement Learning Agents for Human-Computer Interactions","created":"2021-03-10","cited_by_count":1,"area":null},{"id":"2208.00250","title":"A Bayesian Approach to Learning Bandit Structure in Markov Decision Processes","created":"2022-07-30","cited_by_count":1,"area":null},{"id":"2301.07835","title":"Decision-Focused Evaluation: Analyzing Performance of Deployed Restless Multi-Arm Bandits","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2306.10983","title":"Effect-Invariant Mechanisms for Policy Generalization","created":"2023-06-19","cited_by_count":1,"area":null},{"id":"2308.07843","title":"Dyadic Reinforcement Learning","created":"2023-08-15","cited_by_count":1,"area":null},{"id":"2505.16311","title":"Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions","created":"2025-05-22","cited_by_count":1,"area":null},{"id":"2106.08881","title":"Nonparametric Empirical Bayes Estimation and Testing for Sparse and Heteroscedastic Signals","created":"2021-06-16","cited_by_count":0,"area":null},{"id":"2107.09949","title":"Online structural kernel selection for mobile health","created":"2021-07-21","cited_by_count":0,"area":null},{"id":"2109.10231","title":"SalienTrack: providing salient information for semi-automated self-tracking feedback with model explanations","created":"2021-09-21","cited_by_count":0,"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},{"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":"2407.03674","title":"Short-Long Policy Evaluation with Novel Actions","created":"2024-07-04","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":"2506.04166","title":"N$^2$: A Unified Python Package and Test Bench for Nearest Neighbor-Based Matrix Completion","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2508.00846","title":"Cognitive Exoskeleton: Augmenting Human Cognition with an AI-Mediated Intelligent Visual Feedback","created":"2025-07-09","cited_by_count":0,"area":null},{"id":"2508.02817","title":"Real-World Receptivity to Adaptive Mental Health Interventions: Findings from an In-the-Wild Study","created":"2025-07-10","cited_by_count":0,"area":null},{"id":"2508.20923","title":"Finite-Time Guarantees for Multi-Agent Combinatorial Bandits with Nonstationary Rewards","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2510.09908","title":"Learning with Incomplete Context: Linear Contextual Bandits with Pretrained Imputation","created":"2025-10-10","cited_by_count":0,"area":null},{"id":"2511.06189","title":"Counterfactual Forecasting for Panel Data","created":"2025-11-09","cited_by_count":0,"area":null},{"id":"2603.06330","title":"Structured Exploration vs. Generative Flexibility: A Field Study Comparing Bandit and LLM Architectures for Personalised Health Behaviour Interventions","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.07384","title":"Decisions and Deployment: The Five-Year SAHELI Project (2020-2025) on Restless Multi-Armed Bandits for Improving Maternal and Child Health","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.00913","title":"Bandit Simulation for Average Reward Inference","created":"2026-05-30","cited_by_count":0,"area":null},{"id":"2608.22023","title":"Spectral Pre-Filtering for Context-Adaptive Sensor Fusion: A Four-Role FFT-GDCB Integration for High-Stakes Decision Systems","created":"2026-08-22","cited_by_count":0,"area":null}],"next_cursor":null}