bei Google ScholarTitelangaben
Sperl, Mario ; Saluzzi, Luca ; Grüne, Lars ; Kalise, Dante:
Separable approximations of optimal value functions under a decaying sensitivity assumption.
In:
62nd IEEE Conference on Decision and Control (CDC) 2023. -
Singapore, Singapore
,
2023
. - S. 259-264
DOI: https://doi.org/10.1109/CDC49753.2023.10383497
Dies ist die aktuelle Version des Eintrags.
Volltext
Angaben zu Projekten
| Projekttitel: |
Offizieller Projekttitel Projekt-ID Curse-of-dimensionality-free nonlinear optimal feedback control with deep neural networks. A compositionality-based approach via Hamilton-Jacobi-Bellman PDEs 463912816 |
|---|---|
| Projektfinanzierung: |
Deutsche Forschungsgemeinschaft |
Abstract
An efficient approach for the construction of separable approximations of optimal value functions from interconnected optimal control problems is presented. The approach is based on assuming decaying sensitivities between subsystems, enabling a curse-of-dimensionality free approximation, for instance by deep neural networks.
Weitere Angaben
Zu diesem Eintrag verfügbare Versionen
-
Separable approximations of optimal value functions under a decaying sensitivity assumption. (deposited 17 Apr 2023 07:43)
- Separable approximations of optimal value functions under a decaying sensitivity assumption. (deposited 02 Feb 2024 11:10) [Aktuelle Anzeige]