{"total":26,"rows":[{"id":"2211.16275","title":"A survey on multi-player bandits","created":"2022-11-29","cited_by_count":19,"area":null},{"id":"2101.01086","title":"Be Greedy in Multi-Armed Bandits","created":"2021-01-04","cited_by_count":7,"area":null},{"id":"2302.07425","title":"Bandit Social Learning: Exploration under Myopic Behavior","created":"2023-02-15","cited_by_count":6,"area":null},{"id":"2105.10590","title":"Parallelizing Contextual Bandits","created":"2021-05-21","cited_by_count":4,"area":null},{"id":"2201.12975","title":"Rotting Infinitely Many-armed Bandits","created":"2022-01-31","cited_by_count":4,"area":null},{"id":"2210.00340","title":"Speed Up the Cold-Start Learning in Two-Sided Bandits with Many Arms","created":"2022-10-01","cited_by_count":4,"area":null},{"id":"2305.10718","title":"Discounted Thompson Sampling for Non-Stationary Bandit Problems","created":"2023-05-18","cited_by_count":4,"area":null},{"id":"2310.07320","title":"Byzantine-Resilient Decentralized Multi-Armed Bandits","created":"2023-10-11","cited_by_count":3,"area":null},{"id":"2202.01011","title":"Auto-Transfer: Learning to Route Transferrable Representations","created":"2022-02-02","cited_by_count":2,"area":null},{"id":"2404.14202","title":"An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints","created":"2024-04-22","cited_by_count":2,"area":null},{"id":"2503.04010","title":"Greedy Algorithm for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure","created":"2025-03-06","cited_by_count":2,"area":null},{"id":"2108.13810","title":"Max-Utility Based Arm Selection Strategy For Sequential Query Recommendations","created":"2021-08-31","cited_by_count":1,"area":null},{"id":"2207.08130","title":"Discover Life Skills for Planning with Bandits via Observing and Learning How the World Works","created":"2022-07-17","cited_by_count":1,"area":null},{"id":"2502.00108","title":"Tracking Most Significant Shifts in Infinite-Armed Bandits","created":"2025-01-31","cited_by_count":1,"area":null},{"id":"2511.10661","title":"Sequential Bayesian Evaluation of Large Language Model Behavior","created":"2025-11-04","cited_by_count":1,"area":null},{"id":"2603.21716","title":"Mixture-Greedy for Online Generative Model Selection: Is UCB Necessary in Diversity-Aware Multi-Armed Bandits?","created":"2026-03-23","cited_by_count":1,"area":null},{"id":"2205.06297","title":"Improving Sequential Query Recommendation with Immediate User Feedback","created":"2022-05-12","cited_by_count":0,"area":null},{"id":"2310.12563","title":"Approximate information maximization for bandit games","created":"2023-10-19","cited_by_count":0,"area":null},{"id":"2310.17538","title":"Little Exploration is All You Need","created":"2023-10-26","cited_by_count":0,"area":null},{"id":"2504.03926","title":"An Exploration-free Method for a Linear Stochastic Bandit Driven by a Linear Gaussian Dynamical System","created":"2025-04-04","cited_by_count":0,"area":null},{"id":"2506.06334","title":"Preference-based learning for news headline recommendation","created":"2025-05-31","cited_by_count":0,"area":null},{"id":"2511.22273","title":"UCB for Large-Scale Pure Exploration: Beyond Sub-Gaussianity","created":"2025-11-27","cited_by_count":0,"area":null},{"id":"2601.20694","title":"Is Pure Exploitation Sufficient in Exogenous MDPs with Linear Function Approximation?","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2605.31034","title":"Annealed Softmax Greedy in Many-Armed Bayesian Bandits","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2609.38659","title":"Bandits with Multiple Optimal Arms: Minimax Regret and Non-Adaptivity","created":"2026-09-29","cited_by_count":0,"area":null},{"id":"2610.13407","title":"Accelerating Linear Bandits with Persistent Candidate Sets","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}