{"total":13,"rows":[{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"id":"2202.01454","title":"Deep Hierarchy in Bandits","created":"2022-02-03","cited_by_count":19,"area":null},{"id":"2205.15124","title":"Mixed-Effect Thompson Sampling","created":"2022-05-30","cited_by_count":14,"area":null},{"id":"2109.04941","title":"Best-Arm Identification in Correlated Multi-Armed Bandits","created":"2021-09-10","cited_by_count":8,"area":null},{"id":"2109.01656","title":"Thompson Sampling for Bandits with Clustered Arms","created":"2021-09-06","cited_by_count":6,"area":null},{"id":"2404.17493","title":"Causally Abstracted Multi-armed Bandits","created":"2024-04-26","cited_by_count":6,"area":null},{"id":"2401.05193","title":"Experiment Planning with Function Approximation","created":"2024-01-10","cited_by_count":5,"area":null},{"id":"2301.13524","title":"Quantum contextual bandits and recommender systems for quantum data","created":"2023-01-31","cited_by_count":4,"area":null},{"id":"2110.03424","title":"Bad-Policy Density: A Measure of Reinforcement Learning Hardness","created":"2021-10-07","cited_by_count":2,"area":null},{"id":"2112.04083","title":"Best Arm Identification under Additive Transfer Bandits","created":"2021-12-08","cited_by_count":1,"area":null},{"id":"2504.04505","title":"A Classification View on Meta Learning Bandits","created":"2025-04-06","cited_by_count":1,"area":null},{"id":"2101.06592","title":"TSEC: a framework for online experimentation under experimental constraints","created":"2021-01-17","cited_by_count":0,"area":null},{"id":"2605.07304","title":"Latent Order Bandits","created":"2026-05-08","cited_by_count":0,"area":null}],"next_cursor":null}