{"total":21,"rows":[{"id":"2209.06983","title":"Double Doubly Robust Thompson Sampling for Generalized Linear Contextual Bandits","created":"2022-09-15","cited_by_count":14,"area":null},{"id":"2108.04782","title":"Bandit Algorithms for Precision Medicine","created":"2021-08-10","cited_by_count":12,"area":null},{"id":"2206.03520","title":"Finite-Time Regret of Thompson Sampling Algorithms for Exponential Family Multi-Armed Bandits","created":"2022-06-07","cited_by_count":11,"area":null},{"id":"2206.05404","title":"Squeeze All: Novel Estimator and Self-Normalized Bound for Linear Contextual Bandits","created":"2022-06-11","cited_by_count":6,"area":null},{"id":"2306.00096","title":"Learning the Pareto Front Using Bootstrapped Observation Samples","created":"2023-05-31","cited_by_count":5,"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":"2201.04469","title":"Optimal Best Arm Identification in Two-Armed Bandits with a Fixed Budget under a Small Gap","created":"2022-01-12","cited_by_count":4,"area":null},{"id":"2502.06142","title":"Linear Bandits with Partially Observable Features","created":"2025-02-10","cited_by_count":4,"area":null},{"id":"2605.10405","title":"Valid Best-Model Identification for LLM Evaluation via Low-Rank Factorization","created":"2026-05-11","cited_by_count":4,"area":null},{"id":"2209.07330","title":"Best Arm Identification with Contextual Information under a Small Gap","created":"2022-09-15","cited_by_count":3,"area":null},{"id":"2302.02988","title":"Asymptotically Optimal Fixed-Budget Best Arm Identification with Variance-Dependent Bounds","created":"2023-02-06","cited_by_count":3,"area":null},{"id":"2310.15286","title":"A Doubly Robust Approach to Sparse Reinforcement Learning","created":"2023-10-23","cited_by_count":3,"area":null},{"id":"2404.12219","title":"A Quadrature Approach for General-Purpose Batch Bayesian Optimization via Probabilistic Lifting","created":"2024-04-18","cited_by_count":3,"area":null},{"id":"2301.13791","title":"Improved Algorithms for Multi-period Multi-class Packing Problems with Bandit Feedback","created":"2023-01-31","cited_by_count":2,"area":null},{"id":"2401.03756","title":"Adaptive Experimental Design for Policy Learning","created":"2024-01-08","cited_by_count":2,"area":null},{"id":"2209.07154","title":"Risk-aware linear bandits with convex loss","created":"2022-09-15","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":"2506.14479","title":"Adaptive Data Augmentation for Thompson Sampling","created":"2025-06-17","cited_by_count":0,"area":null},{"id":"2602.05139","title":"Adaptive Exploration for Latent-State Bandits","created":"2026-02-04","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},{"id":"2608.01545","title":"Dominant Arm Identification with Mixing and Recycling Observed Samples","created":"2026-08-02","cited_by_count":0,"area":null}],"next_cursor":null}