{"total":22,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"area":null},{"id":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2105.14260","title":"Understanding Bandits with Graph Feedback","created":"2021-05-29","cited_by_count":14,"area":null},{"id":"2210.04229","title":"Learning on the Edge: Online Learning with Stochastic Feedback Graphs","created":"2022-10-09","cited_by_count":12,"area":null},{"id":"2302.03683","title":"Linear Partial Monitoring for Sequential Decision-Making: Algorithms, Regret Bounds and Applications","created":"2023-02-07","cited_by_count":12,"area":null},{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"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":"2402.08127","title":"Efficient Contextual Bandits with Uninformed Feedback Graphs","created":"2024-02-12","cited_by_count":6,"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":"2405.16581","title":"On Bits and Bandits: Quantifying the Regret-Information Trade-off","created":"2024-05-26","cited_by_count":3,"area":null},{"id":"2106.08441","title":"Online Learning with Uncertain Feedback Graphs","created":"2021-06-15","cited_by_count":2,"area":null},{"id":"2404.19292","title":"Provably Efficient Information-Directed Sampling Algorithms for Multi-Agent Reinforcement Learning","created":"2024-04-30","cited_by_count":2,"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":"2308.15107","title":"Stochastic Graph Bandit Learning with Side-Observations","created":"2023-08-29","cited_by_count":1,"area":null},{"id":"2402.15127","title":"Asymptotically and Minimax Optimal Regret Bounds for Multi-Armed Bandits with Abstention","created":"2024-02-23","cited_by_count":1,"area":null},{"id":"2601.00461","title":"Laplacian Kernelized Bandit","created":"2026-01-01","cited_by_count":1,"area":null},{"id":"2503.20975","title":"Competitive Multi-armed Bandit Games for Resource Sharing","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2505.10698","title":"Asymptotically-Optimal Gaussian Bandits with Side Observations","created":"2025-05-15","cited_by_count":0,"area":null},{"id":"2508.14311","title":"Online Learning with Multiple Fairness Regularizers via Graph-Structured Feedback","created":"2025-08-19","cited_by_count":0,"area":null},{"id":"2602.07273","title":"Hybrid Feedback-Guided Optimal Learning for Wireless Interactive Panoramic Scene Delivery","created":"2026-02-06","cited_by_count":0,"area":null}],"next_cursor":null}