Neural approximations of the optimal stationary closed-loop control strategies for discounted infinite-horizon stochastic optimal control problems are investigated. It is shown that for a family of such problems, the minimal number of network parameters needed to achieve a desired accuracy of the approximate solution does not grow exponentially with the number of state variables. In such a way, neural-network approximation mitigates the so-called “curse of dimensionality”. The obtained theoretical results point out the potentialities of neural-network based approximation in the framework of sequential decision problems with continuous state, control, and disturbance spaces.

Neural approximations in discounted infinite-horizon stochastic optimal control problems

G. Gnecco;
2018-01-01

Abstract

Neural approximations of the optimal stationary closed-loop control strategies for discounted infinite-horizon stochastic optimal control problems are investigated. It is shown that for a family of such problems, the minimal number of network parameters needed to achieve a desired accuracy of the approximate solution does not grow exponentially with the number of state variables. In such a way, neural-network approximation mitigates the so-called “curse of dimensionality”. The obtained theoretical results point out the potentialities of neural-network based approximation in the framework of sequential decision problems with continuous state, control, and disturbance spaces.
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S0952197618301489-main.pdf

non disponibili

Tipologia: Versione Editoriale (PDF)
Licenza: Nessuna licenza
Dimensione 768.47 kB
Formato Adobe PDF
768.47 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.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11771/11065
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 3
social impact