Picture for Sebastian Peitz

Sebastian Peitz

MOREL: Enhancing Adversarial Robustness through Multi-Objective Representation Learning

Add code
Oct 02, 2024
Viaarxiv icon

Common pitfalls to avoid while using multiobjective optimization in machine learning

Add code
May 02, 2024
Viaarxiv icon

Predicting PDEs Fast and Efficiently with Equivariant Extreme Learning Machines

Add code
Apr 29, 2024
Viaarxiv icon

On the continuity and smoothness of the value function in reinforcement learning and optimal control

Add code
Mar 21, 2024
Viaarxiv icon

A multiobjective continuation method to compute the regularization path of deep neural networks

Add code
Aug 24, 2023
Viaarxiv icon

Partial observations, coarse graining and equivariance in Koopman operator theory for large-scale dynamical systems

Add code
Jul 28, 2023
Viaarxiv icon

Learning a model is paramount for sample efficiency in reinforcement learning control of PDEs

Add code
Feb 14, 2023
Viaarxiv icon

Distributed Control of Partial Differential Equations Using Convolutional Reinforcement Learning

Add code
Jan 25, 2023
Viaarxiv icon

Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories

Add code
Sep 20, 2022
Figure 1 for Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories
Figure 2 for Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories
Figure 3 for Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories
Figure 4 for Learning Bilinear Models of Actuated Koopman Generators from Partially-Observed Trajectories
Viaarxiv icon

Efficient time stepping for numerical integration using reinforcement learning

Add code
Apr 08, 2021
Figure 1 for Efficient time stepping for numerical integration using reinforcement learning
Figure 2 for Efficient time stepping for numerical integration using reinforcement learning
Figure 3 for Efficient time stepping for numerical integration using reinforcement learning
Figure 4 for Efficient time stepping for numerical integration using reinforcement learning
Viaarxiv icon