{"total":19,"rows":[{"id":"2103.09568","title":"A Practical Guide to Multi-Objective Reinforcement Learning and Planning","created":"2021-03-17","cited_by_count":256,"area":null},{"id":"2201.10142","title":"Almost Optimal Variance-Constrained Best Arm Identification","created":"2022-01-25","cited_by_count":16,"area":null},{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2110.12311","title":"Vector Optimization with Stochastic Bandit Feedback","created":"2021-10-23","cited_by_count":12,"area":null},{"id":"2204.11910","title":"Integrating Reward Maximization and Population Estimation: Sequential Decision-Making for Internal Revenue Service Audit Selection","created":"2022-04-25","cited_by_count":5,"area":null},{"id":"2412.02988","title":"Preference-based Pure Exploration","created":"2024-12-04","cited_by_count":5,"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":"2512.00930","title":"Thompson Sampling for Multi-Objective Linear Contextual Bandit","created":"2025-11-30","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":"2409.16098","title":"The Digital Transformation in Health: How AI Can Improve the Performance of Health Systems","created":"2024-09-24","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":"2206.02666","title":"Robust Pareto Set Identification with Contaminated Bandit Feedback","created":"2022-06-06","cited_by_count":0,"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":"2411.00156","title":"Unlocking the Potential of Global Human Expertise","created":"2024-10-31","cited_by_count":0,"area":null},{"id":"2508.15966","title":"Vector preference-based contextual bandits under distributional shifts","created":"2025-08-21","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":"2606.08410","title":"Provably Efficient Personalized Multi-Objective Bandits with Proactive Conversational Queries","created":"2026-06-07","cited_by_count":0,"area":null},{"id":"2610.16840","title":"Few-for-Many Best-Arm Identification in Multi-Objective Bandits","created":"2026-10-12","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}