{"total":15,"rows":[{"id":"2205.14988","title":"Quantum Multi-Armed Bandits and Stochastic Linear Bandits Enjoy Logarithmic Regrets","created":"2022-05-30","cited_by_count":19,"area":null},{"id":"2201.09910","title":"Learning Neural Contextual Bandits Through Perturbed Rewards","created":"2022-01-24","cited_by_count":17,"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":"2107.00948","title":"From Personalized Medicine to Population Health: A Survey of mHealth Sensing Techniques","created":"2021-07-02","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":"2211.11869","title":"Examining Policy Entropy of Reinforcement Learning Agents for Personalization Tasks","created":"2022-11-21","cited_by_count":3,"area":null},{"id":"2204.12764","title":"Bounded Memory Adversarial Bandits with Composite Anonymous Delayed Feedback","created":"2022-04-27","cited_by_count":1,"area":null},{"id":"2210.10631","title":"Simulated Contextual Bandits for Personalization Tasks from Recommendation Datasets","created":"2022-10-12","cited_by_count":1,"area":null},{"id":"2602.07767","title":"BFTS: Thompson Sampling with Bayesian Additive Regression Trees","created":"2026-02-08","cited_by_count":1,"area":null},{"id":"2205.04528","title":"Selectively Contextual Bandits","created":"2022-05-09","cited_by_count":0,"area":null},{"id":"2208.09819","title":"Robust Tests in Online Decision-Making","created":"2022-08-21","cited_by_count":0,"area":null},{"id":"2306.14297","title":"Inference for relative sparsity","created":"2023-06-25","cited_by_count":0,"area":null},{"id":"2310.05324","title":"Increasing Entropy to Boost Policy Gradient Performance on Personalization Tasks","created":"2023-10-09","cited_by_count":0,"area":null},{"id":"2406.10795","title":"Improving Reward-Conditioned Policies for Multi-Armed Bandits using Normalized Weight Functions","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2606.20022","title":"Set Membership Estimation for Stochastic Linear Contextual Bandits","created":"2026-06-18","cited_by_count":0,"area":null}],"next_cursor":null}