{"total":19,"rows":[{"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":"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":"2105.13383","title":"An Online Learning Approach to Optimizing Time-Varying Costs of AoI","created":"2021-05-27","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":"2408.05686","title":"The Bandit Whisperer: Communication Learning for Restless Bandits","created":"2024-08-11","cited_by_count":5,"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":"2208.06948","title":"How Does Data Freshness Affect Real-time Supervised Learning?","created":"2022-08-15","cited_by_count":3,"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":"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":"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":"2508.07555","title":"Multimodal Remote Inference","created":"2025-08-11","cited_by_count":1,"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":"2310.15705","title":"Learning-based Scheduling for Information Accuracy and Freshness in Wireless Networks","created":"2023-10-24","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":"2601.08760","title":"Adaptive Requesting in Decentralized Edge Networks via Non-Stationary Bandits","created":"2026-01-13","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},{"id":"2609.37932","title":"Learning When to Update: A Near-Optimal Timing Bandit Approach","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}