{"total":31,"rows":[{"id":"2109.08075","title":"Field Study in Deploying Restless Multi-Armed Bandits: Assisting Non-Profits in Improving Maternal and Child Health","created":"2021-09-16","cited_by_count":43,"area":null},{"id":"2105.07965","title":"Learn to Intervene: An Adaptive Learning Policy for Restless Bandits in Application to Preventive Healthcare","created":"2021-05-17","cited_by_count":35,"area":null},{"id":"2110.02128","title":"NeurWIN: Neural Whittle Index Network For Restless Bandits Via Deep RL","created":"2021-10-05","cited_by_count":27,"area":null},{"id":"2106.12024","title":"Q-Learning Lagrange Policies for Multi-Action Restless Bandits","created":"2021-06-22","cited_by_count":21,"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":"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":"2202.03463","title":"On learning Whittle index policy for restless bandits with scalable regret","created":"2022-02-07","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":"2303.12206","title":"Policy Optimization for Personalized Interventions in Behavioral Health","created":"2023-03-21","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":"2202.13187","title":"Whittle Index based Q-Learning for Wireless Edge Caching with Linear Function Approximation","created":"2022-02-26","cited_by_count":8,"area":null},{"id":"2107.01689","title":"Restless and Uncertain: Robust Policies for Restless Bandits via Deep Multi-Agent Reinforcement Learning","created":"2021-07-04","cited_by_count":7,"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":"2101.03641","title":"Learning Augmented Index Policy for Optimal Service Placement at the Network Edge","created":"2021-01-10","cited_by_count":4,"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":"2106.08771","title":"Reinforcement Learning for Markovian Bandits: Is Posterior Sampling more Scalable than Optimism?","created":"2021-06-16","cited_by_count":1,"area":null},{"id":"2305.00410","title":"Indexability of Finite State Restless Multi-Armed Bandit and Rollout Policy","created":"2023-04-30","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":"2409.04605","title":"Whittle Index Learning Algorithms for Restless Bandits with Constant Stepsizes","created":"2024-09-06","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":"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":"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":"2212.03291","title":"Caching Contents with Varying Popularity using Restless Bandits","created":"2022-10-31","cited_by_count":0,"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":"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}