{"total":29,"rows":[{"id":"2102.08462","title":"Multi-Agent Multi-Armed Bandits with Limited Communication","created":"2021-02-10","cited_by_count":29,"area":null},{"id":"2404.13895","title":"Optimal Design for Human Preference Elicitation","created":"2024-04-22","cited_by_count":17,"area":null},{"id":"2305.08629","title":"A Unified Analysis of Nonstochastic Delayed Feedback for Combinatorial Semi-Bandits, Linear Bandits, and MDPs","created":"2023-05-15","cited_by_count":15,"area":null},{"id":"2203.12577","title":"Minimax Regret for Cascading Bandits","created":"2022-03-23","cited_by_count":10,"area":null},{"id":"2103.00368","title":"PairRank: Online Pairwise Learning to Rank by Divide-and-Conquer","created":"2021-02-28","cited_by_count":6,"area":null},{"id":"2305.17071","title":"Adversarial Attacks on Online Learning to Rank with Click Feedback","created":"2023-05-26","cited_by_count":6,"area":null},{"id":"2305.19218","title":"Adversarial Attacks on Online Learning to Rank with Stochastic Click Models","created":"2023-05-30","cited_by_count":6,"area":null},{"id":"2103.10321","title":"Learning How to Optimize Black-Box Functions With Extreme Limits on the Number of Function Evaluations","created":"2021-03-18","cited_by_count":5,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2502.09257","title":"From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards","created":"2025-02-13","cited_by_count":4,"area":null},{"id":"2311.05975","title":"Sum-max Submodular Bandits","created":"2023-11-10","cited_by_count":3,"area":null},{"id":"2110.02248","title":"Contextual Combinatorial Bandits with Changing Action Sets via Gaussian Processes","created":"2021-10-05","cited_by_count":2,"area":null},{"id":"2207.05437","title":"Simultaneously Learning Stochastic and Adversarial Bandits under the Position-Based Model","created":"2022-07-12","cited_by_count":2,"area":null},{"id":"2311.04528","title":"Bandit Learning to Rank with Position-Based Click Models: Personalized and Equal Treatments","created":"2023-11-08","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":"2103.04387","title":"CORe: Capitalizing On Rewards in Bandit Exploration","created":"2021-03-07","cited_by_count":1,"area":null},{"id":"2111.00735","title":"Calibrating Explore-Exploit Trade-off for Fair Online Learning to Rank","created":"2021-11-01","cited_by_count":1,"area":null},{"id":"2201.06658","title":"Learning Neural Ranking Models Online from Implicit User Feedback","created":"2022-01-17","cited_by_count":1,"area":null},{"id":"2301.10651","title":"Overcoming Prior Misspecification in Online Learning to Rank","created":"2023-01-25","cited_by_count":1,"area":null},{"id":"2402.14013","title":"Misalignment, Learning, and Ranking: Harnessing Users Limited Attention","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2502.18826","title":"Adversarial Combinatorial Semi-bandits with Graph Feedback","created":"2025-02-26","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":"2106.03546","title":"On Learning to Rank Long Sequences with Contextual Bandits","created":"2021-06-07","cited_by_count":0,"area":null},{"id":"2208.01515","title":"UniRank: Unimodal Bandit Algorithm for Online Ranking","created":"2022-08-02","cited_by_count":0,"area":null},{"id":"2305.01202","title":"Exploration of Unranked Items in Safe Online Learning to Re-Rank","created":"2023-05-02","cited_by_count":0,"area":null},{"id":"2305.15193","title":"Adaptive Policy Learning to Additional Tasks","created":"2023-05-24","cited_by_count":0,"area":null},{"id":"2406.05017","title":"Adaptively Learning to Select-Rank in Online Platforms","created":"2024-06-07","cited_by_count":0,"area":null},{"id":"2509.22855","title":"Observation-Free Attacks on Online Learning to Rank","created":"2025-09-26","cited_by_count":0,"area":null},{"id":"2606.29221","title":"A Linear Matching Bandit Approach to Online Multi-Human Multi-Robot Teaming","created":"2026-06-28","cited_by_count":0,"area":null}],"next_cursor":null}