Separable approximations of optimal value functions under a decaying sensitivity assumption
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2023
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929676101877760 |
|---|---|
| author | Sperl, Mario Saluzzi, Luca Grüne, Lars Kalise, Dante |
| author_facet | Sperl, Mario Saluzzi, Luca Grüne, Lars Kalise, Dante |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2304_06379 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Separable approximations of optimal value functions under a decaying sensitivity assumption Sperl, Mario Saluzzi, Luca Grüne, Lars Kalise, Dante Optimization and Control 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. |
| title | Separable approximations of optimal value functions under a decaying sensitivity assumption |
| topic | Optimization and Control |
| url | https://arxiv.org/abs/2304.06379 |