{"total":9,"rows":[{"id":"2106.05335","title":"Online Learning for Stochastic Shortest Path Model via Posterior Sampling","created":"2021-06-09","cited_by_count":16,"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":"2309.14648","title":"Learning the Uncertainty Sets for Control Dynamics via Set Membership: A Non-Asymptotic Analysis","created":"2023-09-26","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":"2312.05465","title":"On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR","created":"2023-12-09","cited_by_count":1,"area":null},{"id":"2405.17370","title":"Model-Agnostic Zeroth-Order Policy Optimization for Meta-Learning of Ergodic Linear Quadratic Regulators","created":"2024-05-27","cited_by_count":1,"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},{"id":"2506.22186","title":"Thompson Sampling-Based Learning and Control for Unknown Dynamic Systems","created":"2025-06-27","cited_by_count":0,"area":null},{"id":"2608.13651","title":"Consistent Model Chasing Is Minimax Optimal: The Exact Value of Scalar Adversarial Adaptive Control under Large Parametric Uncertainty","created":"2026-08-13","cited_by_count":0,"area":null}],"next_cursor":null}