{"total":31,"rows":[{"id":"2103.04047","title":"Reinforcement Learning, Bit by Bit","created":"2021-03-06","cited_by_count":59,"area":null},{"id":"2206.13063","title":"On the Complexity of Adversarial Decision Making","created":"2022-06-27","cited_by_count":33,"area":null},{"id":"2102.05295","title":"An Efficient Pessimistic-Optimistic Algorithm for Stochastic Linear Bandits with General Constraints","created":"2021-02-10","cited_by_count":29,"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":"2110.13973","title":"The Value of Information When Deciding What to Learn","created":"2021-10-26","cited_by_count":15,"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":"2111.01479","title":"Dealing With Misspecification In Fixed-Confidence Linear Top-m Identification","created":"2021-11-02","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":"2105.11802","title":"Bias-Robust Bayesian Optimization via Dueling Bandits","created":"2021-05-25","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":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"area":null},{"id":"2406.04137","title":"Optimal Batched Linear Bandits","created":"2024-06-06","cited_by_count":7,"area":null},{"id":"2209.02211","title":"Multi-Armed Bandits with Self-Information Rewards","created":"2022-09-06","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":"2203.09784","title":"The price of unfairness in linear bandits with biased feedback","created":"2022-03-18","cited_by_count":3,"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":"2212.09429","title":"On the Complexity of Representation Learning in Contextual Linear Bandits","created":"2022-12-19","cited_by_count":2,"area":null},{"id":"2403.10379","title":"Regret Minimization via Saddle Point Optimization","created":"2024-03-15","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":"2405.15200","title":"Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits","created":"2024-05-24","cited_by_count":2,"area":null},{"id":"2507.08438","title":"Optimal and Practical Batched Linear Bandit Algorithm","created":"2025-07-11","cited_by_count":2,"area":null},{"id":"2606.00984","title":"Practical and Optimal Algorithm for Linear Contextual Bandits with Rare Parameter Updates","created":"2026-05-31","cited_by_count":2,"area":null},{"id":"2202.11735","title":"Truncated LinUCB for Stochastic Linear Bandits","created":"2022-02-23","cited_by_count":1,"area":null},{"id":"2208.09372","title":"Non-Stationary Dynamic Pricing Via Actor-Critic Information-Directed Pricing","created":"2022-08-19","cited_by_count":1,"area":null},{"id":"2209.07154","title":"Risk-aware linear bandits with convex loss","created":"2022-09-15","cited_by_count":1,"area":null},{"id":"2510.24234","title":"Sparse Optimistic Information Directed Sampling","created":"2025-10-28","cited_by_count":1,"area":null},{"id":"2201.08832","title":"Occupancy Information Ratio: Infinite-Horizon, Information-Directed, Parameterized Policy Search","created":"2022-01-21","cited_by_count":0,"area":null},{"id":"2503.05098","title":"Empirical Bound Information-Directed Sampling for Norm-Agnostic Bandits","created":"2025-03-07","cited_by_count":0,"area":null},{"id":"2512.20096","title":"Information-directed sampling for bandits: a primer","created":"2025-12-23","cited_by_count":0,"area":null}],"next_cursor":null}