This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal Control Problem (OCP), even if based on an inexact model. This can be achieved by selecting a proper stage cost and terminal cost for the OCP. A very useful particular case of OCP is a Model Predictive Control (MPC) scheme where a deterministic (possibly nonlinear) model is used to reduce the computational complexity. This observation leads us to parameterize an MPC scheme fully, including the cost function. In practice, Reinforcement Learning algorithms can then be used to tune the parameterized MPC scheme. We verify the developed theorems analytically in an LQR case and we investigate some other nonlinear examples in simulations.
Equivalence of Optimality Criteria for Markov Decision Process and Model Predictive Control
Mario Zanon;
2024-01-01
Abstract
This paper shows that the optimal policy and value functions of a Markov Decision Process (MDP), either discounted or not, can be captured by a finite-horizon undiscounted Optimal Control Problem (OCP), even if based on an inexact model. This can be achieved by selecting a proper stage cost and terminal cost for the OCP. A very useful particular case of OCP is a Model Predictive Control (MPC) scheme where a deterministic (possibly nonlinear) model is used to reduce the computational complexity. This observation leads us to parameterize an MPC scheme fully, including the cost function. In practice, Reinforcement Learning algorithms can then be used to tune the parameterized MPC scheme. We verify the developed theorems analytically in an LQR case and we investigate some other nonlinear examples in simulations.File | Dimensione | Formato | |
---|---|---|---|
EMDP.pdf
accesso aperto
Tipologia:
Documento in Post-print
Licenza:
Copyright dell'editore
Dimensione
1.08 MB
Formato
Adobe PDF
|
1.08 MB | Adobe PDF | Visualizza/Apri |
Equivalence_of_Optimality_Criteria_for_Markov_Decision_Process_and_Model_Predictive_Control.pdf
non disponibili
Tipologia:
Versione Editoriale (PDF)
Licenza:
Copyright dell'editore
Dimensione
1.02 MB
Formato
Adobe PDF
|
1.02 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.