{"total":11,"rows":[{"id":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"area":null},{"id":"2202.03463","title":"On learning Whittle index policy for restless bandits with scalable regret","created":"2022-02-07","cited_by_count":10,"area":null},{"id":"2406.00738","title":"Global Rewards in Restless Multi-Armed Bandits","created":"2024-06-02","cited_by_count":6,"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":"2305.00410","title":"Indexability of Finite State Restless Multi-Armed Bandit and Rollout Policy","created":"2023-04-30","cited_by_count":1,"area":null},{"id":"2409.04605","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes","created":"2024-09-06","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":"2511.08097","title":"Model Predictive Control is almost Optimal for Heterogeneous Restless Multi-armed Bandits","created":"2025-11-11","cited_by_count":1,"area":null},{"id":"2410.23029","title":"Risk-Aware Decision Making in Restless Bandits: Theory and Algorithms for Planning and Learning","created":"2024-10-30","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":"2510.22069","title":"Neural Index Policies for Restless Multi-Action Bandits with Heterogeneous Budgets","created":"2025-10-24","cited_by_count":0,"area":null}],"next_cursor":null}