{"total":14,"rows":[{"id":"2304.06701","title":"Learning Personalized Decision Support Policies","created":"2023-04-13","cited_by_count":14,"area":null},{"id":"2211.14768","title":"Constrained Pure Exploration Multi-Armed Bandits with a Fixed Budget","created":"2022-11-27","cited_by_count":9,"area":null},{"id":"2108.01152","title":"Maximizing and Satisficing in Multi-armed Bandits with Graph Information","created":"2021-08-02","cited_by_count":5,"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":"2302.05257","title":"Piecewise-Stationary Multi-Objective Multi-Armed Bandit with Application to Joint Communications and Sensing","created":"2023-02-10","cited_by_count":3,"area":null},{"id":"2302.12676","title":"Towards Computationally Efficient Responsibility Attribution in Decentralized Partially Observable MDPs","created":"2023-02-24","cited_by_count":3,"area":null},{"id":"2408.11240","title":"Asymmetric Graph Error Control with Low Complexity in Causal Bandits","created":"2024-08-20","cited_by_count":2,"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":"2511.05802","title":"Beyond the Lower Bound: Bridging Regret Minimization and Best Arm Identification in Lexicographic Bandits","created":"2025-11-08","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":"2206.02666","title":"Robust Pareto Set Identification with Contaminated Bandit Feedback","created":"2022-06-06","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":"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}