{"total":12,"rows":[{"id":"2109.00157","title":"A Survey of Exploration Methods in Reinforcement Learning","created":"2021-09-01","cited_by_count":73,"area":null},{"id":"2107.03635","title":"Sublinear Regret for Learning POMDPs","created":"2021-07-08","cited_by_count":19,"area":null},{"id":"2205.14035","title":"Learning to Control Linear Systems can be Hard","created":"2022-05-27","cited_by_count":11,"area":null},{"id":"2201.10542","title":"Augmented RBMLE-UCB Approach for Adaptive Control of Linear Quadratic Systems","created":"2022-01-25","cited_by_count":5,"area":null},{"id":"2212.06251","title":"Autoregressive Bandits","created":"2022-12-12","cited_by_count":3,"area":null},{"id":"2110.12276","title":"Coarse-Grained Smoothness for RL in Metric Spaces","created":"2021-10-23","cited_by_count":2,"area":null},{"id":"2307.11655","title":"Preferences Evolve And So Should Your Bandits: Bandits with Evolving States for Online Platforms","created":"2023-07-21","cited_by_count":2,"area":null},{"id":"2410.01331","title":"Efficient Learning of POMDPs with Known Observation Model in Average-Reward Setting","created":"2024-10-02","cited_by_count":1,"area":null},{"id":"2502.14043","title":"Safe Learning Under Irreversible Dynamics via Asking for Help","created":"2025-02-19","cited_by_count":1,"area":null},{"id":"2106.08477","title":"Fundamental Limits of Reinforcement Learning in Environment with Endogeneous and Exogeneous Uncertainty","created":"2021-06-15","cited_by_count":0,"area":null},{"id":"2501.18790","title":"Achieving $\\widetilde{\\mathcal{O}}(\\sqrt{T})$ Regret in Average-Reward POMDPs with Known Observation Models","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2509.19695","title":"DyBBT: Dynamic Balance via Bandit-inspired Targeting for Dialog Policy with Cognitive Dual-Systems","created":"2025-09-24","cited_by_count":0,"area":null}],"next_cursor":null}