{"total":10,"rows":[{"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":"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":"2402.04933","title":"Context in Public Health for Underserved Communities: A Bayesian Approach to Online Restless Bandits","created":"2024-02-07","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":"2408.16147","title":"Improving the Prediction of Individual Engagement in Recommendations Using Cognitive Models","created":"2024-08-28","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":"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":"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":"2511.09324","title":"MARBLE: Multi-Armed Restless Bandits in Latent Markovian Environment","created":"2025-11-12","cited_by_count":0,"area":null},{"id":"2608.24167","title":"From Relaxed Indexability to Exact Indexability: A $t$-Step Approach for Partially Observable Restless Bandits","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}