{"total":16,"rows":[{"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":"2310.14526","title":"Towards a Pretrained Model for Restless Bandits via Multi-arm Generalization","created":"2023-10-23","cited_by_count":9,"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":"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":"2502.06072","title":"Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs","created":"2025-02-09","cited_by_count":3,"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},{"id":"2502.03725","title":"Optimal Control of Fluid Restless Multi-armed Bandits: A Machine Learning Approach","created":"2025-02-06","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":"2506.02385","title":"Multi-agent Markov Entanglement","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2609.38132","title":"Achieving an $O(1/N)$ Optimality Gap in Average-Reward Weakly-Coupled MDPs","created":"2026-09-29","cited_by_count":0,"area":null}],"next_cursor":null}