{"total":19,"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":"2107.11911","title":"Restless Bandits with Many Arms: Beating the Central Limit Theorem","created":"2021-07-25","cited_by_count":18,"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":"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":"2312.10303","title":"Online Restless Multi-Armed Bandits with Long-Term Fairness Constraints","created":"2023-12-16","cited_by_count":10,"area":null},{"id":"2203.15853","title":"Near-optimality for infinite-horizon restless bandits with many arms","created":"2022-03-29","cited_by_count":9,"area":null},{"id":"2306.00196","title":"Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption","created":"2023-05-31","cited_by_count":9,"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":"2402.05689","title":"Unichain and Aperiodicity are Sufficient for Asymptotic Optimality of Average-Reward Restless Bandits","created":"2024-02-08","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":"2405.17882","title":"Achieving Exponential Asymptotic Optimality in Average-Reward Restless Bandits without Global Attractor Assumption","created":"2024-05-28","cited_by_count":5,"area":null},{"id":"2108.03812","title":"Low-Complexity Algorithm for Restless Bandits with Imperfect Observations","created":"2021-08-09","cited_by_count":3,"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":"2110.12118","title":"Bandits with Dynamic Arm-acquisition Costs","created":"2021-10-23","cited_by_count":1,"area":null},{"id":"2410.06307","title":"Model Predictive Control is Almost Optimal for Restless Bandit","created":"2024-10-08","cited_by_count":1,"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":"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":"2109.09855","title":"Reinforcement Learning for Finite-Horizon Restless Multi-Armed Multi-Action Bandits","created":"2021-09-20","cited_by_count":0,"area":null}],"next_cursor":null}