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.