{"total":30,"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":"2110.02128","title":"NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2106.12024","title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","created":"2021-06-22","cited_by_count":21,"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":"2206.03883","title":"Efficient Resource Allocation with Fairness Constraints in Restless Multi-Armed Bandits","created":"2022-06-08","cited_by_count":11,"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":"2203.15853","title":"Near-optimality for infinite-horizon restless bandits with many arms","created":"2022-03-29","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":"2310.14526","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","created":"2023-10-23","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":"2201.12408","title":"Networked Restless Multi-Armed Bandits for Mobile Interventions","created":"2022-01-28","cited_by_count":7,"area":null},{"id":"2209.08646","title":"DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs","created":"2022-09-18","cited_by_count":6,"area":null},{"id":"2211.08998","title":"Data-pooling Reinforcement Learning for Personalized Healthcare Intervention","created":"2022-11-16","cited_by_count":6,"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":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"area":null},{"id":"2302.02570","title":"Improved Policy Evaluation for Randomized Trials of Algorithmic Resource Allocation","created":"2023-02-06","cited_by_count":4,"area":null},{"id":"2412.12641","title":"Lagrangian Index Policy for Restless Bandits with Average Reward","created":"2024-12-17","cited_by_count":4,"area":null},{"id":"2502.06072","title":"Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2406.14122","title":"EduQate: Generating Adaptive Curricula through RMABs in Education Settings","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2408.09882","title":"GINO-Q: Learning an Asymptotically Optimal Index Policy for Restless Multi-armed Bandits","created":"2024-08-19","cited_by_count":1,"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":"2506.18186","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":"2408.07629","title":"Optimizing HIV Patient Engagement with Reinforcement Learning in Resource-Limited Settings","created":"2024-08-14","cited_by_count":0,"area":null},{"id":"2408.08024","title":"Adaptive User Journeys in Pharma E-Commerce with Reinforcement Learning: Insights from SwipeRx","created":"2024-08-15","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":"2505.14137","title":"Memory Assignment for Finite-Memory Strategies in Adversarial Patrolling Games","created":"2025-05-20","cited_by_count":0,"area":null},{"id":"2506.02385","title":"Multi-agent Markov Entanglement","created":"2025-06-03","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}],"next_cursor":null}