An algorithm is proposed to determine output feedback policies that solve finite-horizon linear-quadratic (LQ) optimal control problems without requiring knowledge of the system dynamical matrices. To reach this goal, the Q -factors arising from finite-horizon LQ problems are first characterized in the state feedback case. It is then shown how they can be parameterized as functions of the input-output vectors. A procedure is then proposed for estimating these functions from input/output data and using these estimates for computing the optimal control via the measured inputs and outputs.
Calafiore, G.c., Possieri, C. (2021). Output feedback Q-learning for linear-quadratic discrete-time finite-horizon control problems. IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 32(7), 3274-3281 [10.1109/TNNLS.2020.3010304].
Output feedback Q-learning for linear-quadratic discrete-time finite-horizon control problems
Possieri C.
2021-01-01
Abstract
An algorithm is proposed to determine output feedback policies that solve finite-horizon linear-quadratic (LQ) optimal control problems without requiring knowledge of the system dynamical matrices. To reach this goal, the Q -factors arising from finite-horizon LQ problems are first characterized in the state feedback case. It is then shown how they can be parameterized as functions of the input-output vectors. A procedure is then proposed for estimating these functions from input/output data and using these estimates for computing the optimal control via the measured inputs and outputs.| File | Dimensione | Formato | |
|---|---|---|---|
|
Output_Feedback_Q-Learning_for_Linear-Quadratic_Discrete-Time_Finite-Horizon_Control_Problems.pdf
solo utenti autorizzati
Tipologia:
Versione Editoriale (PDF)
Licenza:
Copyright dell'editore
Dimensione
416.51 kB
Formato
Adobe PDF
|
416.51 kB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
