{"total":14,"rows":[{"id":"2407.17226","title":"Sublinear Regret for a Class of Continuous-Time Linear-Quadratic Reinforcement Learning Problems","created":"2024-07-24","cited_by_count":12,"area":"deeprl"},{"id":"2405.07637","title":"Near-Optimal Regret in Linear MDPs with Aggregate Bandit Feedback","created":"2024-05-13","cited_by_count":10,"area":"deeprl"},{"id":"2511.20066","title":"SOMBRL: Scalable and Optimistic Model-Based RL","created":"2025-11-25","cited_by_count":7,"area":"deeprl"},{"id":"2402.03792","title":"No-Regret Reinforcement Learning in Smooth MDPs","created":"2024-02-06","cited_by_count":6,"area":"deeprl"},{"id":"2501.15910","title":"The Sample Complexity of Online Reinforcement Learning: A Multi-model Perspective","created":"2025-01-27","cited_by_count":6,"area":"deeprl"},{"id":"2405.06363","title":"Projection by Convolution: Optimal Sample Complexity for Reinforcement Learning in Continuous-Space MDPs","created":"2024-05-10","cited_by_count":5,"area":"deeprl"},{"id":"2505.03706","title":"Policy Gradient Adaptive Control for the LQR: Indirect and Direct Approaches","created":"2025-05-06","cited_by_count":5,"area":"deeprl"},{"id":"2406.01175","title":"NeoRL: Efficient Exploration for Nonepisodic RL","created":"2024-06-03","cited_by_count":4,"area":"deeprl"},{"id":"2410.24071","title":"Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs","created":"2024-10-31","cited_by_count":4,"area":"deeprl"},{"id":"2505.01041","title":"Global Optimality of Single-Timescale Actor-Critic under Continuous State-Action Space: A Study on Linear Quadratic Regulator","created":"2025-05-02","cited_by_count":2,"area":"deeprl"},{"id":"2403.05367","title":"Stability-Certified On-Policy Data-Driven LQR via Recursive Learning and Policy Gradient","created":"2024-03-08","cited_by_count":1,"area":"deeprl"},{"id":"2601.19284","title":"Model-Free Output Feedback Stabilization via Policy Gradient Methods","created":"2026-01-27","cited_by_count":1,"area":"deeprl"},{"id":"2603.28938","title":"Optimistic Online LQR via Intrinsic Rewards","created":"2026-03-30","cited_by_count":1,"area":"deeprl"},{"id":"2601.03016","title":"Adaptive Control of Unknown Linear Switched Systems via Policy Gradient Methods","created":"2026-01-06","cited_by_count":0,"area":"deeprl"}],"next_cursor":null}