{"total":23,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2210.10768","title":"Anytime-valid off-policy inference for contextual bandits","created":"2022-10-19","cited_by_count":37,"area":null},{"id":"2302.09739","title":"A Blackbox Approach to Best of Both Worlds in Bandits and Beyond","created":"2023-02-20","cited_by_count":30,"area":null},{"id":"2202.04985","title":"Generalization Bounds via Convex Analysis","created":"2022-02-10","cited_by_count":27,"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":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"area":null},{"id":"2105.14260","title":"Understanding Bandits with Graph Feedback","created":"2021-05-29","cited_by_count":14,"area":null},{"id":"2202.10997","title":"Minimax Regret for Partial Monitoring: Infinite Outcomes and Rustichini's Regret","created":"2022-02-22","cited_by_count":14,"area":null},{"id":"2206.06810","title":"Adversarially Robust Multi-Armed Bandit Algorithm with Variance-Dependent Regret Bounds","created":"2022-06-14","cited_by_count":12,"area":null},{"id":"2403.00715","title":"Adaptive Learning Rate for Follow-the-Regularized-Leader: Competitive Analysis and Best-of-Both-Worlds","created":"2024-03-01","cited_by_count":11,"area":null},{"id":"2403.05134","title":"Follow-the-Perturbed-Leader with Fr\\'{e}chet-type Tail Distributions: Optimality in Adversarial Bandits and Best-of-Both-Worlds","created":"2024-03-08","cited_by_count":10,"area":null},{"id":"2305.15383","title":"On the Minimax Regret for Online Learning with Feedback Graphs","created":"2023-05-24","cited_by_count":8,"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":"2301.12038","title":"STEERING: Stein Information Directed Exploration for Model-Based Reinforcement Learning","created":"2023-01-28","cited_by_count":4,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2307.07264","title":"On Interpolating Experts and Multi-Armed Bandits","created":"2023-07-14","cited_by_count":4,"area":null},{"id":"2310.06069","title":"Optimal Exploration is no harder than Thompson Sampling","created":"2023-10-09","cited_by_count":3,"area":null},{"id":"2405.20028","title":"A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds","created":"2024-05-30","cited_by_count":3,"area":null},{"id":"2504.07307","title":"Follow-the-Perturbed-Leader Approaches Best-of-Both-Worlds for the m-Set Semi-Bandit Problems","created":"2025-04-09","cited_by_count":2,"area":null},{"id":"2110.13400","title":"Scale-Free Adversarial Multi-Armed Bandit with Arbitrary Feedback Delays","created":"2021-10-26","cited_by_count":1,"area":null},{"id":"2205.15076","title":"Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition","created":"2022-05-30","cited_by_count":1,"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}],"next_cursor":null}