We propose an efficient technique for performing data-driven optimal control of discrete-time systems. In particular, we show that log-sum-exp ($lse$) neural networks, which are smooth and convex universal approximators of convex functions, can be efficiently used to approximate Q-factors arising from finite-horizon optimal control problems with continuous state space. The key advantage of these networks over classical approximation techniques is that they are convex and hence readily amenable to efficient optimization.
Calafiore, G., Possieri, C. (2020). Efficient model-free Q-factor approximation in value space via log-sum-exp neural networks. In Proceedings of the 18th European Control Conference. IFAC [10.23919/ECC51009.2020.9143765].
Efficient model-free Q-factor approximation in value space via log-sum-exp neural networks
Corrado Possieri
2020-01-01
Abstract
We propose an efficient technique for performing data-driven optimal control of discrete-time systems. In particular, we show that log-sum-exp ($lse$) neural networks, which are smooth and convex universal approximators of convex functions, can be efficiently used to approximate Q-factors arising from finite-horizon optimal control problems with continuous state space. The key advantage of these networks over classical approximation techniques is that they are convex and hence readily amenable to efficient optimization.File | Dimensione | Formato | |
---|---|---|---|
Calafiore-Efficient.pdf
solo utenti autorizzati
Tipologia:
Documento in Post-print
Licenza:
Copyright dell'editore
Dimensione
272.44 kB
Formato
Adobe PDF
|
272.44 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.