4 papers
Decaying Sensitivity of the Zero Solution for a Class of Nonlinear Optimal Control Problems
Lars Grüne, Mario Sperl
We study spatial decay properties of sensitivities in a nonlinear optimal control problem with a graph-structured interaction topology. For a problem with nonlinear decoupled dynam…
Convexity and strict convexity for compositional neural networks in high-dimensional optimal control
Lars Grüne, Konrad Kleinberg, Thomas Kruse +1
Neural networks (NNs) have emerged as powerful tools for solving high-dimensional optimal control problems. In particular, their compositional structure has been shown to enable ef…
Separable Approximations of Optimal Value Functions and Their Representation by Neural Networks
Mario Sperl, Luca Saluzzi, Dante Kalise +1
The use of separable approximations is proposed to mitigate the curse of dimensionality related to the approximation of high-dimensional value functions in optimal control. The sep…
Separable approximations of optimal value functions under a decaying sensitivity assumption
Mario Sperl, Luca Saluzzi, Lars Grüne +1
An efficient approach for the construction of separable approximations of optimal value functions from interconnected optimal control problems is presented. The approach is based o…