{"total":20,"rows":[{"id":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"area":null},{"id":"2212.03798","title":"Stochastic Rising Bandits","created":"2022-12-07","cited_by_count":18,"area":null},{"id":"2310.02147","title":"Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation","created":"2023-10-03","cited_by_count":14,"area":null},{"id":"2312.10303","title":"Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2303.12206","title":"Policy Optimization for Personalized Interventions in Behavioral Health","created":"2023-03-21","cited_by_count":9,"area":null},{"id":"2202.13187","title":"Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2107.01689","title":"Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning","created":"2021-07-04","cited_by_count":7,"area":null},{"id":"2302.14686","title":"Approximately Stationary Bandits with Knapsacks","created":"2023-02-28","cited_by_count":6,"area":null},{"id":"2310.13393","title":"Optimal Best Arm Identification with Fixed Confidence in Restless Bandits","created":"2023-10-20","cited_by_count":3,"area":null},{"id":"2501.00924","title":"On the Low-Complexity of Fair Learning for Combinatorial Multi-Armed Bandit","created":"2025-01-01","cited_by_count":3,"area":null},{"id":"2106.08771","title":"Reinforcement Learning for Markovian Bandits: Is Posterior Sampling more Scalable than Optimism?","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2301.07835","title":"Decision-Focused Evaluation: Analyzing Performance of Deployed Restless Multi-Arm Bandits","created":"2023-01-19","cited_by_count":1,"area":null},{"id":"2406.07992","title":"A Federated Online Restless Bandit Framework for Cooperative Resource Allocation","created":"2024-06-12","cited_by_count":1,"area":null},{"id":"2409.04605","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes","created":"2024-09-06","cited_by_count":1,"area":null},{"id":"2506.18186","title":"Online Learning of Whittle Indices for Restless Bandits with Non-Stationary Transition Kernels","created":"2025-06-22","cited_by_count":1,"area":null},{"id":"2109.09855","title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits","created":"2021-09-20","cited_by_count":0,"area":null},{"id":"2405.09584","title":"Restless Bandit Problem with Rewards Generated by a Linear Gaussian Dynamical System","created":"2024-05-15","cited_by_count":0,"area":null},{"id":"2502.05145","title":"From Restless to Contextual: A Thresholding Bandit Reformulation For Finite-horizon Improvement","created":"2025-02-07","cited_by_count":0,"area":null},{"id":"2602.01400","title":"Online Social Welfare Function-based Resource Allocation","created":"2026-02-01","cited_by_count":0,"area":null},{"id":"2603.16755","title":"A Practical Algorithm for Feature-Rich, Non-Stationary Bandit Problems","created":"2026-03-17","cited_by_count":0,"area":null}],"next_cursor":null}