{"total":16,"rows":[{"id":"2405.05950","title":"Federated Combinatorial Multi-Agent Multi-Armed Bandits","created":"2024-05-09","cited_by_count":11,"area":null},{"id":"2406.00738","title":"Global Rewards in Restless Multi-Armed Bandits","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2501.19300","title":"Offline Learning for Combinatorial Multi-armed Bandits","created":"2025-01-31","cited_by_count":5,"area":null},{"id":"2412.10682","title":"Stochastic $k$-Submodular Bandits with Full Bandit Feedback","created":"2024-12-14","cited_by_count":3,"area":null},{"id":"2502.04290","title":"Every Call is Precious: Global Optimization of Black-Box Functions with Unknown Lipschitz Constants","created":"2025-02-06","cited_by_count":3,"area":null},{"id":"2405.12439","title":"No-Regret M${}^{\\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and Hardness of Adversarial Full-Information Setting","created":"2024-05-21","cited_by_count":1,"area":null},{"id":"2602.11491","title":"Exploring Multiple High-Scoring Subspaces in Generative Flow Networks","created":"2026-02-12","cited_by_count":1,"area":null},{"id":"2502.13467","title":"On the Sublinear Regret of Continuous K-Max Bandits","created":"2025-02-19","cited_by_count":0,"area":null},{"id":"2503.12285","title":"A Resilience Framework for Bi-Criteria Combinatorial Optimization with Bandit Feedback","created":"2025-03-15","cited_by_count":0,"area":null},{"id":"2602.16183","title":"Multi-Agent Combinatorial-Multi-Armed-Bandit framework for the Submodular Welfare Problem under Bandit Feedback","created":"2026-02-18","cited_by_count":0,"area":null},{"id":"2603.06810","title":"Multi-Agent Reinforcement Learning with Submodular Reward","created":"2026-03-06","cited_by_count":0,"area":null},{"id":"2604.09423","title":"Offline Local Search for Online Stochastic Bandits","created":"2026-04-10","cited_by_count":0,"area":null},{"id":"2605.10151","title":"Learning to Sparsify Stochastic Linear Bandits","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2608.12134","title":"Adversarial Resilience of Poisson-Process Submodular Maximization over Matroids, and Full-Bandit Learning","created":"2026-08-12","cited_by_count":0,"area":null},{"id":"2608.16375","title":"Multinomial Subset Routing with Sum-Max Rewards and Operational Constraints","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.24627","title":"Bandit Submodular Maximization under Matroid Constraints: Learning Compressed Exchange Policy","created":"2026-08-25","cited_by_count":0,"area":null}],"next_cursor":null}