Litcius/Paper detail

Efficient Off-Policy Q-Learning for Data-Based Discrete-Time LQR Problems

Victor G. Lopez, Mohammad Alsalti, Matthias A. Müller

2023IEEE Transactions on Automatic Control49 citationsDOIOpen Access PDF

Abstract

This article introduces and analyzes an improved Q-learning algorithm for discrete-time linear time-invariant systems. The proposed method does not require any knowledge of the system dynamics, and it enjoys significant efficiency advantages over other data-based optimal control methods in the literature. This algorithm can be fully executed offline, as it does not require to apply the current estimate of the optimal input to the system as in on-policy algorithms. It is shown that a PE input, defined from an easily tested matrix rank condition, guarantees the convergence of the algorithm. A data-based method is proposed to design the initial stabilizing feedback gain that the algorithm requires. Robustness of the algorithm in the presence of noisy measurements is analyzed. We compare the proposed algorithm in simulation to different direct and indirect data-based control design methods.

Topics & Concepts

Robustness (evolution)Computer scienceConvergence (economics)Discrete time and continuous timeAlgorithmControl theory (sociology)Algorithm designMathematical optimizationControl (management)MathematicsArtificial intelligenceEconomic growthBiochemistryEconomicsStatisticsChemistryGeneAdaptive Dynamic Programming ControlControl Systems and IdentificationFault Detection and Control Systems
Efficient Off-Policy Q-Learning for Data-Based Discrete-Time LQR Problems | Litcius