{"total":18,"rows":[{"id":"2402.14807","title":"A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health","created":"2024-02-22","cited_by_count":24,"area":null},{"id":"2205.15372","title":"Optimistic Whittle Index Policy: Online Learning for Restless Bandits","created":"2022-05-30","cited_by_count":20,"area":null},{"id":"2310.02147","title":"Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation","created":"2023-10-03","cited_by_count":14,"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":"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":"2209.08646","title":"DeepTOP: Deep Threshold-Optimal Policy for MDPs and RMABs","created":"2022-09-18","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":"2304.03729","title":"Full Gradient Deep Reinforcement Learning for Average-Reward Criterion","created":"2023-04-07","cited_by_count":5,"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":"2412.12641","title":"Lagrangian Index Policy for Restless Bandits with Average Reward","created":"2024-12-17","cited_by_count":4,"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":"2409.04605","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes","created":"2024-09-06","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":"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":"2506.02385","title":"Multi-agent Markov Entanglement","created":"2025-06-03","cited_by_count":0,"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}],"next_cursor":null}