{"total":12,"rows":[{"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":"2406.00738","title":"Global Rewards in Restless Multi-Armed Bandits","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2305.11942","title":"OPTWIN: Drift identification with optimal sub-windows","created":"2023-05-19","cited_by_count":1,"area":null},{"id":"2402.06348","title":"Fairness of Exposure in Online Restless Multi-armed Bandits","created":"2024-02-09","cited_by_count":1,"area":null},{"id":"2406.07992","title":"A Federated Online Restless Bandit Framework for Cooperative Resource Allocation","created":"2024-06-12","cited_by_count":1,"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":"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":"2403.10638","title":"A resource-constrained stochastic scheduling algorithm for homeless street outreach and gleaning edible food","created":"2024-03-15","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":"2508.10804","title":"Non-Stationary Restless Multi-Armed Bandits with Provable Guarantee","created":"2025-08-14","cited_by_count":0,"area":null},{"id":"2604.10177","title":"A Modularized Framework for Piecewise-Stationary Restless Bandits","created":"2026-04-11","cited_by_count":0,"area":null}],"next_cursor":null}