{"total":37,"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":"2206.04640","title":"Regret Bounds for Information-Directed Reinforcement Learning","created":"2022-06-09","cited_by_count":24,"area":null},{"id":"2101.08534","title":"Efficient Pure Exploration for Combinatorial Bandits with Semi-Bandit Feedback","created":"2021-01-21","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":"2205.10895","title":"Contextual Information-Directed Sampling","created":"2022-05-22","cited_by_count":16,"area":null},{"id":"2106.01660","title":"Bandit Phase Retrieval","created":"2021-06-03","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":"2210.06380","title":"Near-Optimal Multi-Agent Learning for Safe Coverage Control","created":"2022-10-12","cited_by_count":11,"area":null},{"id":"2402.15411","title":"Optimistic Information Directed Sampling","created":"2024-02-23","cited_by_count":7,"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":"2402.10289","title":"Thompson Sampling in Partially Observable Contextual Bandits","created":"2024-02-15","cited_by_count":5,"area":null},{"id":"2310.18601","title":"Online Decision Mediation","created":"2023-10-28","cited_by_count":4,"area":null},{"id":"2403.07591","title":"Robustifying and Boosting Training-Free Neural Architecture Search","created":"2024-03-12","cited_by_count":4,"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":"2402.05002","title":"Randomized Confidence Bounds for Stochastic Partial Monitoring","created":"2024-02-07","cited_by_count":3,"area":null},{"id":"2405.20677","title":"Provably Efficient Interactive-Grounded Learning with Personalized Reward","created":"2024-05-31","cited_by_count":3,"area":null},{"id":"2401.11563","title":"Distributed Multi-Task Learning for Stochastic Bandits with Context Distribution and Stage-wise Constraints","created":"2024-01-21","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":"2405.15200","title":"Indexed Minimum Empirical Divergence-Based Algorithms for Linear Bandits","created":"2024-05-24","cited_by_count":2,"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":"2405.08921","title":"Neural Active Learning Meets the Partial Monitoring Framework","created":"2024-05-14","cited_by_count":1,"area":null},{"id":"2411.12154","title":"Tangential Randomization in Linear Bandits (TRAiL): Guaranteed Inference and Regret Bounds","created":"2024-11-19","cited_by_count":1,"area":null},{"id":"2510.19158","title":"Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring","created":"2025-10-22","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":"2510.07424","title":"Best-of-Both Worlds for linear contextual bandits with paid observations","created":"2025-10-08","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},{"id":"2602.08307","title":"Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback","created":"2026-02-09","cited_by_count":0,"area":null},{"id":"2609.33981","title":"Future Information-Directed Sampling for Bayesian Nonstationary Bandits","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2610.01377","title":"Minimax Optimal Regret for Causal Logistic Bandits with Counterfactual Fairness","created":"2026-10-01","cited_by_count":0,"area":null},{"id":"2610.17760","title":"Gaussian Process Bandits for AI System Optimization with Selectively Verified Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}