{"total":20,"rows":[{"id":"2112.10955","title":"Joint Learning of Linear Time-Invariant Dynamical Systems","created":"2021-12-21","cited_by_count":16,"area":null},{"id":"2201.11211","title":"Learning Mixtures of Linear Dynamical Systems","created":"2022-01-26","cited_by_count":15,"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":"2110.12175","title":"Analysis of Thompson Sampling for Partially Observable Contextual Multi-Armed Bandits","created":"2021-10-23","cited_by_count":10,"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":"2112.10753","title":"Strong Consistency and Rate of Convergence of Switched Least Squares System Identification for Autonomous Markov Jump Linear Systems","created":"2021-12-20","cited_by_count":6,"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":"2108.11959","title":"Finite-time System Identification and Adaptive Control in Autoregressive Exogenous Systems","created":"2021-08-26","cited_by_count":4,"area":null},{"id":"2201.01387","title":"Joint Learning-Based Stabilization of Multiple Unknown Linear Systems","created":"2022-01-01","cited_by_count":3,"area":null},{"id":"2202.00867","title":"Efficient Algorithms for Learning to Control Bandits with Unobserved Contexts","created":"2022-02-02","cited_by_count":3,"area":null},{"id":"2103.10620","title":"Towards a Dimension-Free Understanding of Adaptive Linear Control","created":"2021-03-19","cited_by_count":2,"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":"2112.15094","title":"Bayesian Algorithms Learn to Stabilize Unknown Continuous-Time Systems","created":"2021-12-30","cited_by_count":2,"area":null},{"id":"2204.04773","title":"Worst-case Performance of Greedy Policies in Bandits with Imperfect Context Observations","created":"2022-04-10","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":"2103.13278","title":"Safe Linear-Quadratic Dual Control with Almost Sure Performance Guarantee","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2109.07630","title":"Reinforcement Learning Policies in Continuous-Time Linear Systems","created":"2021-09-16","cited_by_count":0,"area":null},{"id":"2206.04434","title":"Regret Analysis of Certainty Equivalence Policies in Continuous-Time Linear-Quadratic Systems","created":"2022-06-09","cited_by_count":0,"area":null},{"id":"2301.05537","title":"Almost Surely $\\sqrt{T}$ Regret for Adaptive LQR","created":"2023-01-13","cited_by_count":0,"area":null},{"id":"2305.16974","title":"Finite Time Regret Bounds for Minimum Variance Control of Autoregressive Systems with Exogenous Inputs","created":"2023-05-26","cited_by_count":0,"area":null}],"next_cursor":null}