{"total":40,"rows":[{"id":"2110.00871","title":"Feel-Good Thompson Sampling for Contextual Bandits and Reinforcement Learning","created":"2021-10-02","cited_by_count":66,"area":null},{"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":"2105.14267","title":"Information Directed Sampling for Sparse Linear Bandits","created":"2021-05-29","cited_by_count":20,"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":"2310.00806","title":"Bayesian Design Principles for Frequentist Sequential Learning","created":"2023-10-01","cited_by_count":18,"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":"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":"2410.05117","title":"Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability","created":"2024-10-07","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":"2302.06025","title":"Statistical Complexity and Optimal Algorithms for Non-linear Ridge Bandits","created":"2023-02-12","cited_by_count":7,"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":"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":"2306.01990","title":"Incentivizing Exploration with Linear Contexts and Combinatorial Actions","created":"2023-06-03","cited_by_count":5,"area":null},{"id":"2305.03263","title":"Bayesian Reinforcement Learning with Limited Cognitive Load","created":"2023-05-05","cited_by_count":4,"area":null},{"id":"2305.19394","title":"Synaptic Weight Distributions Depend on the Geometry of Plasticity","created":"2023-05-30","cited_by_count":4,"area":null},{"id":"2405.19752","title":"Understanding Memory-Regret Trade-Off for Streaming Stochastic Multi-Armed Bandits","created":"2024-05-30","cited_by_count":4,"area":null},{"id":"2106.00444","title":"Minimax Regret for Bandit Convex Optimisation of Ridge Functions","created":"2021-06-01","cited_by_count":3,"area":null},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2202.05767","title":"A PDE-Based Analysis of the Symmetric Two-Armed Bernoulli Bandit","created":"2022-02-11","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":"2402.08321","title":"Exploration by Optimization with Hybrid Regularizers: Logarithmic Regret with Adversarial Robustness in Partial Monitoring","created":"2024-02-13","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":"2204.04773","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","created":"2022-04-10","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":"2205.15076","title":"Improved Algorithms for Bandit with Graph Feedback via Regret Decomposition","created":"2022-05-30","cited_by_count":1,"area":null},{"id":"2506.02980","title":"Non-stationary Bandit Convex Optimization: A Comprehensive Study","created":"2025-06-03","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":"2605.29645","title":"The Sample Complexity of Multiclass and Sparse Contextual Bandits","created":"2026-05-28","cited_by_count":1,"area":null},{"id":"2309.02425","title":"On the Minimax Regret in Online Ranking with Top-k Feedback","created":"2023-09-05","cited_by_count":0,"area":null},{"id":"2504.11866","title":"On the Problem of Best Arm Retention","created":"2025-04-16","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":"2607.12389","title":"Thompson Sampling Is 2-Competitive for Mistakes","created":"2026-07-14","cited_by_count":0,"area":null},{"id":"2610.19804","title":"Efficient contextual partial monitoring with general function approximation","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}