3 papers
cs.LG2025
Stable Port-Hamiltonian Neural Networks
Fabian J. Roth, Dominik K. Klein, Maximilian Kannapinn +2
In recent years, nonlinear dynamic system identification using artificial neural networks has garnered attention due to its broad potential applications across science and engineer…
cs.LG2025
DIME:Diffusion-Based Maximum Entropy Reinforcement Learning
Onur Celik, Zechu Li, Denis Blessing +5
Maximum entropy reinforcement learning (MaxEnt-RL) has become the standard approach to RL due to its beneficial exploration properties. Traditionally, policies are parameterized us…
cs.LG2023
Domain Randomization via Entropy Maximization
Gabriele Tiboni, Pascal Klink, Jan Peters +3
Varying dynamics parameters in simulation is a popular Domain Randomization (DR) approach for overcoming the reality gap in Reinforcement Learning (RL). Nevertheless, DR heavily hi…