Learning Linear-Quadratic Regulators Efficiently with only \√(T)\n Regret

2019/02/17 by Alon Cohen, Cohen, Alon, Tomer Koren +3 · 6 citations
Computer Science · Decision Sciences · #Adaptive Dynamic Programming Control #Advanced Bandit Algorithms Research #FOS: Computer and information sciences #Gaussian Processes and Bayesian Inference #Machine Learning (cs.LG) #Machine Learning (stat.ML) #Machine Learning and Algorithms #Reinforcement Learning in Robotics

paper · pdf · doi:10.48550/arxiv.1902.06223

openalex publication_date 2019/02/17 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We present the first computationally-efficient algorithm with widetilde\nO(\√(T)) regret for learning in Linear Quadratic Control systems with\nunknown dynamics. By that, we resolve an open question of Abbasi-Yadkori and\nSzepesv 'ari (2011) and Dean, Mania, Matni, Recht, and Tu (2018).\n

Citations

• On the Sample Complexity of the Linear Quadratic Regulator
• Global Convergence of Policy Gradient Methods for the Linear Quadratic Regulator
• Regret Bounds for Robust Adaptive Control of the Linear Quadratic Regulator

Cited by

• Adapt and Stabilize, Then Learn and Optimize: A New Approach to Adaptive LQR
• SOMBRL: Scalable and Optimistic Model-Based RL
• Stability of Certainty-Equivalent Adaptive LQR for Linear Systems with Unknown Time-Varying Parameters
• Adversarially Robust Multitask Adaptive Control
• Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control
• A Modified Adaptive Data-Enabled Policy Optimization Control to Resolve State Perturbations

Related

• Logarithmic Regret for Learning Linear Quadratic Regulators Efficiently
• Rate-matching the regret lower-bound in the linear quadratic regulator with unknown dynamics
• Online Policy Gradient for Model Free Learning of Linear Quadratic Regulators with √(T) Regret
• Minimal Expected Regret in Linear Quadratic Control
• Safe Adaptive Learning-based Control for Constrained Linear Quadratic Regulators with Regret Guarantees