no code implementations • 12 Jul 2023 • Andreas Metzger, Tristan Kley, Aristide Rothweiler, Klaus Pohl
This means that acting on less accurate predictions may lead to unnecessary adaptations or missed adaptations.
no code implementations • 9 Jul 2023 • Andreas Metzger, Jan Laufer, Felix Feit, Klaus Pohl
However, Online RL requires the definition of an effective and correct reward function, which quantifies the feedback to the RL algorithm and thereby guides learning.
no code implementations • 12 Oct 2022 • Felix Feit, Andreas Metzger, Klaus Pohl
Online reinforcement learning, i. e., employing reinforcement learning (RL) at runtime, is an emerging approach to realizing self-adaptive systems in the presence of design time uncertainty.
no code implementations • 24 Feb 2022 • Tsung-Hao Huang, Andreas Metzger, Klaus Pohl
We thus see growing interest in explainable predictive business process monitoring, which aims to increase the interpretability of prediction models.
no code implementations • 22 Jul 2019 • Andreas Metzger, Clément Quinton, Zoltán Ádám Mann, Luciano Baresi, Klaus Pohl
Existing online learning techniques randomly explore the possible adaptation actions, but this can lead to slow convergence of the learning process.