{"total":18,"rows":[{"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":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"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":"2310.18803","title":"Weakly Coupled Deep Q-Networks","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2404.16281","title":"Timely Communications for Remote Inference","created":"2024-04-25","cited_by_count":6,"area":null},{"id":"2305.12640","title":"Limited Resource Allocation in a Non-Markovian World: The Case of Maternal and Child Healthcare","created":"2023-05-22","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":"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":"2608.01128","title":"MA-HEAD-Net: Adaptive Rule-Guided Multi-Agent DRL for AoI Minimization in UAV-Assisted Emergency Networks","created":"2026-08-02","cited_by_count":2,"area":null},{"id":"2307.01366","title":"Minimizing Age of Information for Mobile Edge Computing Systems: A Nested Index Approach","created":"2023-07-03","cited_by_count":0,"area":null},{"id":"2509.12457","title":"On the Regularity and Fairness of Combinatorial Multi-Armed Bandit","created":"2025-09-15","cited_by_count":0,"area":null},{"id":"2509.18654","title":"Online Learning for Optimizing AoI-Energy Tradeoff under Unknown Channel Statistics","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.09324","title":"MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2601.08760","title":"Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2604.10177","title":"A Modularized Framework for Piecewise-Stationary Restless Bandits","created":"2026-04-11","cited_by_count":0,"area":null},{"id":"2607.27626","title":"Real-Time Hard Peak Age-of-Information Safety with No-Regret Learning","created":"2026-07-30","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}