Publications

BibTex format

@inproceedings{Sperl:2023:10.1109/CDC49753.2023.10383497,
author = {Sperl, M and Saluzzi, L and Grune, L and Kalise, D},
doi = {10.1109/CDC49753.2023.10383497},
pages = {259--264},
title = {Separable Approximations of Optimal Value Functions Under a Decaying Sensitivity Assumption},
url = {http://dx.doi.org/10.1109/CDC49753.2023.10383497},
year = {2023}
}

Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - 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.
AU  - Sperl,M
AU  - Saluzzi,L
AU  - Grune,L
AU  - Kalise,D
DO  - 10.1109/CDC49753.2023.10383497
EP  - 264
PY  - 2023///
SN  - 0743-1546
SP  - 259
TI  - Separable Approximations of Optimal Value Functions Under a Decaying Sensitivity Assumption
UR  - http://dx.doi.org/10.1109/CDC49753.2023.10383497
ER  -

Download

Dr Dante Kalise

Contact

Location

Summary

Citation

BibTex format

RIS format (EndNote, RefMan)