{"total":14,"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":"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":"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":"2403.15640","title":"Contextual Restless Multi-Armed Bandits with Application to Demand Response Decision-Making","created":"2024-03-22","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":"2310.18803","title":"Weakly Coupled Deep Q-Networks","created":"2023-10-28","cited_by_count":6,"area":null},{"id":"2506.10872","title":"The Gittins Index: A Design Principle for Decision-Making Under Uncertainty","created":"2025-06-12","cited_by_count":6,"area":null},{"id":"2304.03729","title":"Full Gradient Deep Reinforcement Learning for Average-Reward Criterion","created":"2023-04-07","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":"2502.06072","title":"Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs","created":"2025-02-09","cited_by_count":3,"area":null},{"id":"2507.20755","title":"Beyond Listenership: AI-Predicted Interventions Drive Improvements in Maternal Health Behaviours","created":"2025-07-28","cited_by_count":2,"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":"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":"2607.23772","title":"Outcome-Fair Restless Multi-Armed Bandits for Stochastic Deadline Scheduling","created":"2026-07-26","cited_by_count":0,"area":null}],"next_cursor":null}