{"total":27,"rows":[{"id":"2111.06929","title":"Hierarchical Bayesian Bandits","created":"2021-11-12","cited_by_count":35,"area":null},{"id":"2202.10066","title":"Multi-task Representation Learning with Stochastic Linear Bandits","created":"2022-02-21","cited_by_count":21,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2307.09943","title":"Impatient Bandits: Optimizing Recommendations for the Long-Term Without Delay","created":"2023-07-19","cited_by_count":17,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2202.13227","title":"Towards Scalable and Robust Structured Bandits: A Meta-Learning Framework","created":"2022-02-26","cited_by_count":11,"area":null},{"id":"2202.12888","title":"Meta-Learning for Simple Regret Minimization","created":"2022-02-25","cited_by_count":10,"area":null},{"id":"2209.06129","title":"Hierarchical Conversational Preference Elicitation with Bandit Feedback","created":"2022-09-06","cited_by_count":10,"area":null},{"id":"2212.04720","title":"Multi-Task Off-Policy Learning from Bandit Feedback","created":"2022-12-09","cited_by_count":9,"area":null},{"id":"2307.02295","title":"Meta-Learning Adversarial Bandit Algorithms","created":"2023-07-05","cited_by_count":8,"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":"2502.07064","title":"Contextual Thompson Sampling via Generation of Missing Data","created":"2025-02-10","cited_by_count":6,"area":null},{"id":"2202.00602","title":"Meta-Learning Hypothesis Spaces for Sequential Decision-making","created":"2022-02-01","cited_by_count":5,"area":null},{"id":"2205.14128","title":"Meta-Learning Adversarial Bandits","created":"2022-05-27","cited_by_count":5,"area":null},{"id":"2210.14483","title":"Robust Contextual Linear Bandits","created":"2022-10-26","cited_by_count":4,"area":null},{"id":"2210.15513","title":"Lifelong Bandit Optimization: No Prior and No Regret","created":"2022-10-27","cited_by_count":4,"area":null},{"id":"2402.05878","title":"Prior-Dependent Allocations for Bayesian Fixed-Budget Best-Arm Identification in Structured Bandits","created":"2024-02-08","cited_by_count":4,"area":null},{"id":"2404.00688","title":"Meta Learning in Bandits within Shared Affine Subspaces","created":"2024-03-31","cited_by_count":4,"area":null},{"id":"2206.08556","title":"Thompson Sampling for Robust Transfer in Multi-Task Bandits","created":"2022-06-17","cited_by_count":3,"area":null},{"id":"2502.01226","title":"Adaptive Prior Selection in Gaussian Process Bandits with Thompson Sampling","created":"2025-02-03","cited_by_count":2,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2306.09136","title":"Finite-Time Logarithmic Bayes Regret Upper Bounds","created":"2023-06-15","cited_by_count":0,"area":null},{"id":"2309.01453","title":"Interactive Graph Convolutional Filtering","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2505.18269","title":"Representative Action Selection for Large Action Space Bandit Families","created":"2025-05-23","cited_by_count":0,"area":null},{"id":"2512.12693","title":"Co-Exploration and Co-Exploitation via Shared Structure in Multi-Task Bandits","created":"2025-12-14","cited_by_count":0,"area":null},{"id":"2603.20408","title":"Meta-Learning for Repeated Bayesian Persuasion","created":"2026-03-20","cited_by_count":0,"area":null},{"id":"2610.17203","title":"Online LLM Personalization from Pairwise Preferences Across Users","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}