{"total":24,"rows":[{"id":"2501.17513","title":"Sequential Learning of the Pareto Front for Multi-objective Bandits","created":"2025-01-29","cited_by_count":15,"area":null},{"id":"2204.06521","title":"Optimizing generalized Gini indices for fairness in rankings","created":"2022-04-02","cited_by_count":13,"area":null},{"id":"2212.00884","title":"Pareto Regret Analyses in Multi-objective Multi-armed Bandit","created":"2022-12-01","cited_by_count":13,"area":null},{"id":"2309.11518","title":"Ad-load Balancing via Off-policy Learning in a Content Marketplace","created":"2023-09-19","cited_by_count":12,"area":null},{"id":"2405.02141","title":"Multi-Objective Recommendation via Multivariate Policy Learning","created":"2024-05-03","cited_by_count":10,"area":null},{"id":"2306.09995","title":"Fairness in Preference-based Reinforcement Learning","created":"2023-06-16","cited_by_count":9,"area":null},{"id":"2405.20678","title":"No-Regret Learning for Fair Multi-Agent Social Welfare Optimization","created":"2024-05-31","cited_by_count":8,"area":null},{"id":"2307.03288","title":"Optimal Scalarizations for Sublinear Hypervolume Regret","created":"2023-07-06","cited_by_count":7,"area":null},{"id":"2502.13457","title":"Provably Efficient Multi-Objective Bandit Algorithms under Preference-Centric Customization","created":"2025-02-19","cited_by_count":5,"area":null},{"id":"2508.18708","title":"Skill-Aligned Fairness in Multi-Agent Learning for Collaboration in Healthcare","created":"2025-08-26","cited_by_count":3,"area":null},{"id":"2210.09957","title":"Contextual bandits with concave rewards, and an application to fair ranking","created":"2022-10-18","cited_by_count":2,"area":null},{"id":"2608.04324","title":"Efficient Online Lexicographic Generalized Low-Rank Matrix Bandits","created":"2026-08-05","cited_by_count":2,"area":null},{"id":"2503.10386","title":"Multi-thresholding Good Arm Identification with Bandit Feedback","created":"2025-03-13","cited_by_count":1,"area":null},{"id":"2506.13125","title":"Stochastic Multi-Objective Multi-Armed Bandits: Regret Definition and Algorithm","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2601.15552","title":"BanditLP: Large-Scale Stochastic Optimization for Personalized Recommendations","created":"2026-01-22","cited_by_count":1,"area":null},{"id":"2605.06864","title":"Multi-Objective Multi-Agent Bandits: From Learning Efficiency to Fairness Optimization","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2406.11984","title":"Online Pareto-Optimal Decision-Making for Complex Tasks using Active Inference","created":"2024-06-17","cited_by_count":0,"area":null},{"id":"2601.10600","title":"Procedural Fairness in Multi-Agent Bandits","created":"2026-01-15","cited_by_count":0,"area":null},{"id":"2604.07096","title":"Are Stochastic Multi-objective Bandits Harder than Single-objective Bandits?","created":"2026-04-08","cited_by_count":0,"area":null},{"id":"2606.21929","title":"Selective Ensemble Based on Preference-Directed Multi-Objective Bandits","created":"2026-06-20","cited_by_count":0,"area":null},{"id":"2607.19357","title":"Stochastic Primal-Dual Decoding for Multiobjective Generative Recommender Systems","created":"2026-05-26","cited_by_count":0,"area":null},{"id":"2607.26273","title":"Top-$k$ Pareto Bandits: Hypervolume Regret for Multi-Objective Slate Selection","created":"2026-07-28","cited_by_count":0,"area":null},{"id":"2608.00175","title":"Inference-Time Policy Alignment for Fair Reinforcement Learning","created":"2026-07-31","cited_by_count":0,"area":null},{"id":"2610.18577","title":"When More Objectives Make Identification Easier: The Role of Preferences and Feedback","created":"2026-10-13","cited_by_count":0,"area":null}],"next_cursor":null}