{"total":11,"rows":[{"id":"2209.05423","title":"Statistical Learning Theory for Control: A Finite Sample Perspective","created":"2022-09-12","cited_by_count":53,"area":null},{"id":"2102.05214","title":"Task-Optimal Exploration in Linear Dynamical Systems","created":"2021-02-10","cited_by_count":15,"area":null},{"id":"2111.07018","title":"Identification and Adaptive Control of Markov Jump Systems: Sample Complexity and Regret Bounds","created":"2021-11-13","cited_by_count":14,"area":null},{"id":"2201.01680","title":"Regret Lower Bounds for Learning Linear Quadratic Gaussian Systems","created":"2022-01-05","cited_by_count":11,"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":"2206.08520","title":"Thompson Sampling Achieves $\\tilde O(\\sqrt{T})$ Regret in Linear Quadratic Control","created":"2022-06-17","cited_by_count":8,"area":null},{"id":"2105.12358","title":"Certainty Equivalent Quadratic Control for Markov Jump Systems","created":"2021-05-26","cited_by_count":3,"area":null},{"id":"2108.07970","title":"Scalable regret for learning to control network-coupled subsystems with unknown dynamics","created":"2021-08-18","cited_by_count":2,"area":null},{"id":"2309.02815","title":"Near-continuous time Reinforcement Learning for continuous state-action spaces","created":"2023-09-06","cited_by_count":2,"area":null},{"id":"2108.08502","title":"A relaxed technical assumption for posterior sampling-based reinforcement learning for control of unknown linear systems","created":"2021-08-19","cited_by_count":1,"area":null},{"id":"2206.02507","title":"Learning to Control under Time-Varying Environment","created":"2022-06-06","cited_by_count":0,"area":null}],"next_cursor":null}