{"total":32,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2102.04168","title":"Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature","created":"2021-02-08","cited_by_count":32,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2101.06197","title":"Deciding What to Learn: A Rate-Distortion Approach","created":"2021-01-15","cited_by_count":23,"area":null},{"id":"2205.01970","title":"Non-Stationary Bandit Learning via Predictive Sampling","created":"2022-05-04","cited_by_count":21,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2205.13924","title":"Lifting the Information Ratio: An Information-Theoretic Analysis of Thompson Sampling for Contextual Bandits","created":"2022-05-27","cited_by_count":19,"area":null},{"id":"2206.02072","title":"Deciding What to Model: Value-Equivalent Sampling for Reinforcement Learning","created":"2022-06-04","cited_by_count":19,"area":null},{"id":"2107.05320","title":"Metalearning Linear Bandits by Prior Update","created":"2021-07-12","cited_by_count":16,"area":null},{"id":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2103.05750","title":"Regret Bounds for Generalized Linear Bandits under Parameter Drift","created":"2021-03-09","cited_by_count":13,"area":null},{"id":"2103.11489","title":"UCB-based Algorithms for Multinomial Logistic Regression Bandits","created":"2021-03-21","cited_by_count":12,"area":null},{"id":"2107.13078","title":"A Payload Optimization Method for Federated Recommender Systems","created":"2021-07-27","cited_by_count":10,"area":null},{"id":"2302.12202","title":"A Definition of Non-Stationary Bandits","created":"2023-02-23","cited_by_count":9,"area":null},{"id":"2310.20007","title":"Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning","created":"2023-10-30","cited_by_count":7,"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":"2102.09488","title":"A Bit Better? Quantifying Information for Bandit Learning","created":"2021-02-18","cited_by_count":5,"area":null},{"id":"2201.01902","title":"Gaussian Imagination in Bandit Learning","created":"2022-01-06","cited_by_count":5,"area":null},{"id":"2304.13593","title":"Thompson Sampling Regret Bounds for Contextual Bandits with sub-Gaussian rewards","created":"2023-04-26","cited_by_count":5,"area":null},{"id":"2306.01990","title":"Incentivizing Exploration with Linear Contexts and Combinatorial Actions","created":"2023-06-03","cited_by_count":5,"area":null},{"id":"2109.14412","title":"Apple Tasting Revisited: Bayesian Approaches to Partially Monitored Online Binary Classification","created":"2021-09-29","cited_by_count":3,"area":null},{"id":"2306.14872","title":"Geometry-Aware Approaches for Balancing Performance and Theoretical Guarantees in Linear Bandits","created":"2023-06-26","cited_by_count":3,"area":null},{"id":"2205.14829","title":"Adaptive Sampling for Discovery","created":"2022-05-30","cited_by_count":2,"area":null},{"id":"2401.11565","title":"Thompson Sampling for Stochastic Bandits with Noisy Contexts: An Information-Theoretic Regret Analysis","created":"2024-01-21","cited_by_count":2,"area":null},{"id":"2102.07987","title":"The Elliptical Potential Lemma for General Distributions with an Application to Linear Thompson Sampling","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2412.02861","title":"An Information-Theoretic Analysis of Thompson Sampling for Logistic Bandits","created":"2024-12-03","cited_by_count":1,"area":null},{"id":"2508.13749","title":"Order Optimal Regret Bounds for Sharpe Ratio Optimization under Thompson Sampling","created":"2025-08-19","cited_by_count":1,"area":null},{"id":"2601.02022","title":"Prior Diffusiveness and Regret in the Linear-Gaussian Bandit","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2403.03361","title":"Chained Information-Theoretic bounds and Tight Regret Rate for Linear Bandit Problems","created":"2024-03-05","cited_by_count":0,"area":null},{"id":"2502.02140","title":"An Information-Theoretic Analysis of Thompson Sampling with Infinite Action Spaces","created":"2025-02-04","cited_by_count":0,"area":null},{"id":"2506.01685","title":"Geometry Meets Incentives: Sample-Efficient Incentivized Exploration with Linear Contexts","created":"2025-06-02","cited_by_count":0,"area":null},{"id":"2606.04845","title":"Bayesian learning for the stochastic shortest path problem","created":"2026-06-03","cited_by_count":0,"area":null}],"next_cursor":null}