1 citations · 4 across the 7 of their papers we have counts for
5 papers · 1 filter
Recovery of the optimal control value function in reproducing kernel Hilbert spaces from verification conditions
Tobias Ehring, Behzad Azmi, Bernard Haasdonk
Approximating the optimal value function for infinite-horizon, nonlinear, autonomous optimal control problems is both challenging and essential for synthesizing real-time opt…
Escaping the native space of Sobolev kernels by interpolation
Tobias Ehring, Max-Paul Vogel, Bernard Haasdonk
Classical convergence analysis for kernel interpolation typically assumes that the target function lies in the reproducing kernel Hilbert space …
Solving Approximation Tasks with Greedy Deep Kernel Methods
Marian Klink, Tobias Ehring, Robin Herkert +3
Kernel methods are versatile tools for function approximation and surrogate modeling. In particular, greedy techniques offer computational efficiency and reliability through inhere…
On the Convergence of the Policy Iteration for Infinite-Horizon Nonlinear Optimal Control Problems
Tobias Ehring, Behzad Azmi, Bernard Haasdonk
Policy iteration (PI) is a widely used algorithm for synthesizing optimal feedback control policies across many engineering and scientific applications. When PI is deployed on infi…
A trust-region framework for optimization using Hermite kernel surrogate models
Sven Ullmann, Tobias Ehring, Robin Herkert +1
In this work, we present a trust-region optimization framework that employs Hermite kernel surrogate models. The method targets optimization problems with computationally demanding…