The policy iteration method is a classical algorithm for solving optimal control problems. We introduce a policy iteration method for Mean Field Games systems and we prove, under a classical monotonicity assumption on the coupling cost, the convergence of this procedure to the solution of the problem.
A policy iteration method for mean field games / Camilli, Fabio. - In: IFAC PAPERSONLINE. - ISSN 2405-8971. - 55:30(2022), pp. 406-411. (Intervento presentato al convegno 25th IFAC Symposium on Mathematical Theory of Networks and Systems, MTNS 2022 tenutosi a Bayreuth, Germania) [10.1016/j.ifacol.2022.11.087].
A policy iteration method for mean field games
Fabio Camilli
2022
Abstract
The policy iteration method is a classical algorithm for solving optimal control problems. We introduce a policy iteration method for Mean Field Games systems and we prove, under a classical monotonicity assumption on the coupling cost, the convergence of this procedure to the solution of the problem.File allegati a questo prodotto
File | Dimensione | Formato | |
---|---|---|---|
Camilli_a policy iteration_2022.pdf
accesso aperto
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
3.86 MB
Formato
Adobe PDF
|
3.86 MB | Adobe PDF |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.