Title data
Sperl, Mario ; Saluzzi, Luca ; Grüne, Lars ; Kalise, Dante:
Separable approximations of optimal value functions under a decaying sensitivity assumption.
Bayreuth
,
2023
DOI: https://doi.org/10.48550/arXiv.2304.06379
Project information
Project title: |
Project's official title Project's id Curse-of-dimensionality-free nonlinear optimal feedback control with deep neural networks. A compositionality-based approach via Hamilton-Jacobi-Bellman PDEs 463912816 |
---|---|
Project financing: |
Deutsche Forschungsgemeinschaft |
Abstract in another language
A new 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.