{"total":42,"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":"2105.07965","title":"Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2307.07539","title":"On the Sublinear Regret of GP-UCB","created":"2023-07-14","cited_by_count":26,"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":"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":"2202.00916","title":"Scalable Decision-Focused Learning in Restless Multi-Armed Bandits with Application to Maternal and Child Health","created":"2022-02-02","cited_by_count":12,"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":"2210.16386","title":"Non-Stationary Bandits with Auto-Regressive Temporal Dependency","created":"2022-10-28","cited_by_count":10,"area":null},{"id":"2211.00112","title":"Indexability is Not Enough for Whittle: Improved, Near-Optimal Algorithms for Restless Bandits","created":"2022-10-31","cited_by_count":10,"area":null},{"id":"2303.08271","title":"Act-Then-Measure: Reinforcement Learning for Partially Observable Environments with Active Measuring","created":"2023-03-14","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":"2103.09052","title":"Selective Intervention Planning using Restless Multi-Armed Bandits to Improve Maternal and Child Health Outcomes","created":"2021-03-07","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":"2103.04730","title":"Efficient Algorithms for Finite Horizon and Streaming Restless Multi-Armed Bandit Problems","created":"2021-03-08","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":"2406.00738","title":"Global Rewards in Restless Multi-Armed Bandits","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2207.13343","title":"Towards Soft Fairness in Restless Multi-Armed Bandits","created":"2022-07-27","cited_by_count":5,"area":null},{"id":"2212.05144","title":"Networked Restless Bandits with Positive Externalities","created":"2022-12-09","cited_by_count":5,"area":null},{"id":"2402.11771","title":"Evaluating the Effectiveness of Index-Based Treatment Allocation","created":"2024-02-19","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":"2106.03279","title":"Learning MDPs from Features: Predict-Then-Optimize for Sequential Decision Problems by Reinforcement Learning","created":"2021-06-06","cited_by_count":3,"area":null},{"id":"2303.00799","title":"Fairness for Workers Who Pull the Arms: An Index Based Policy for Allocation of Restless Bandit Tasks","created":"2023-03-01","cited_by_count":3,"area":null},{"id":"2305.06426","title":"Planning a Community Approach to Diabetes Care in Low- and Middle-Income Countries Using Optimization","created":"2023-05-10","cited_by_count":3,"area":null},{"id":"2407.11973","title":"Preliminary Study of the Impact of AI-Based Interventions on Health and Behavioral Outcomes in Maternal Health Programs","created":"2024-05-23","cited_by_count":2,"area":null},{"id":"2407.12131","title":"Improving Health Information Access in the World's Largest Maternal Mobile Health Program via Bandit Algorithms","created":"2024-05-14","cited_by_count":2,"area":null},{"id":"2408.07205","title":"Deep Index Policy for Multi-Resource Restless Matching Bandit and Its Application in Multi-Channel Scheduling","created":"2024-08-13","cited_by_count":2,"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":"2312.11227","title":"Robust Active Measuring under Model Uncertainty","created":"2023-12-18","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":"2406.14122","title":"EduQate: Generating Adaptive Curricula through RMABs in Education Settings","created":"2024-06-20","cited_by_count":1,"area":null},{"id":"2502.00045","title":"Optimizing Urban Service Allocation with Time-Constrained Restless Bandits","created":"2025-01-27","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":"2510.26284","title":"Empirical Bayesian Multi-Bandit Learning","created":"2025-10-30","cited_by_count":1,"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":"2508.10804","title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2509.00415","title":"Lagrangian Relaxation for Multi-Action Partially Observable Restless Bandits: Heuristic Policies and Indexability","created":"2025-08-30","cited_by_count":0,"area":null},{"id":"2509.10777","title":"Contextual Budget Bandit for Food Rescue Volunteer Engagement","created":"2025-09-13","cited_by_count":0,"area":null},{"id":"2605.06564","title":"Dynamic Treatment on Networks","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2608.10936","title":"Threshold Structure of Optimal Policies in Restart POMDPs","created":"2026-08-11","cited_by_count":0,"area":null}],"next_cursor":null}