{"total":10,"rows":[{"id":"2402.06562","title":"Safe Guaranteed Exploration for Non-linear Systems","created":"2024-02-09","cited_by_count":8,"area":null},{"id":"2602.16796","title":"Efficient Tail-Aware Generative Optimization via Flow Model Fine-Tuning","created":"2026-02-18","cited_by_count":8,"area":null},{"id":"2406.00738","title":"Global Rewards in Restless Multi-Armed Bandits","created":"2024-06-02","cited_by_count":6,"area":null},{"id":"2503.07127","title":"Performance-driven Constrained Optimal Auto-Tuner for MPC","created":"2025-03-10","cited_by_count":6,"area":null},{"id":"2505.07594","title":"Finite-Sample-Based Reachability for Safe Control with Gaussian Process Dynamics","created":"2025-05-12","cited_by_count":5,"area":null},{"id":"2309.03710","title":"A State Representation for Diminishing Rewards","created":"2023-09-07","cited_by_count":3,"area":null},{"id":"2410.16600","title":"Convex Markov Games: A New Frontier for Multi-Agent Reinforcement Learning","created":"2024-10-22","cited_by_count":3,"area":null},{"id":"2403.08199","title":"Deep Submodular Peripteral Networks","created":"2024-03-13","cited_by_count":1,"area":null},{"id":"2509.16650","title":"Safe and Near-Optimal Control with Online Dynamics Learning","created":"2025-09-20","cited_by_count":1,"area":null},{"id":"2511.02254","title":"Fast Approximation Algorithm for Non-Monotone DR-submodular Maximization under Size Constraint","created":"2025-11-04","cited_by_count":0,"area":null}],"next_cursor":null}