{"total":31,"rows":[{"id":"2109.08075","title":"Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health","created":"2021-09-16","cited_by_count":43,"area":null},{"id":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"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":"2106.07677","title":"Planning to Fairly Allocate: Probabilistic Fairness in the Restless Bandit Setting","created":"2021-06-14","cited_by_count":12,"area":null},{"id":"2302.04452","title":"An Information-Theoretic Analysis of Nonstationary Bandit Learning","created":"2023-02-09","cited_by_count":11,"area":null},{"id":"2202.03463","title":"On learning Whittle index policy for restless bandits with scalable regret","created":"2022-02-07","cited_by_count":10,"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":"2302.12202","title":"A Definition of Non-Stationary Bandits","created":"2023-02-23","cited_by_count":9,"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":"2402.04933","title":"Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits","created":"2024-02-07","cited_by_count":6,"area":null},{"id":"2212.05144","title":"Networked Restless Bandits with Positive Externalities","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2101.03641","title":"Learning Augmented Index Policy for Optimal Service Placement at the Network Edge","created":"2021-01-10","cited_by_count":4,"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":"2402.06348","title":"Fairness of Exposure in Online Restless Multi-armed Bandits","created":"2024-02-09","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":"2501.06103","title":"Finite-Horizon Single-Pull Restless Bandits: An Efficient Index Policy For Scarce Resource Allocation","created":"2025-01-10","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":"2403.05683","title":"Efficient Public Health Intervention Planning Using Decomposition-Based Decision-Focused Learning","created":"2024-03-08","cited_by_count":0,"area":null},{"id":"2403.10638","title":"A resource-constrained stochastic scheduling algorithm for homeless street outreach and gleaning edible food","created":"2024-03-15","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":"2508.10804","title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2512.05680","title":"Meta-Learning Multi-armed Bandits for Beam Tracking in 5G and 6G Networks","created":"2025-12-05","cited_by_count":0,"area":null},{"id":"2512.14930","title":"Restless Multi-Process Multi-Armed Bandits with Applications to Self-Driving Microscopies","created":"2025-12-16","cited_by_count":0,"area":null},{"id":"2606.27448","title":"Learning in Markovian bandits with non-observable states and constrained decision epochs","created":"2026-06-25","cited_by_count":0,"area":null},{"id":"2608.24167","title":"From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}