Autonomous and learning systems based on Deep Reinforcement Learning have firmly established themselves as a foundation for approaches to creating resilient and efficient Cyber-Physical Energy Systems. However, most current approaches suffer from two distinct problems: Modern model-free algorithms such as Soft Actor Critic need a high number of samples to learn a meaningful policy, as well as a fallback to ward against concept drifts (e. g., catastrophic forgetting). In this paper, we present the work in progress towards a hybrid agent architecture that combines model-based Deep Reinforcement Learning with imitation learning to overcome both problems.
@article{arxiv.2404.01794,
title = {Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid},
author = {Eric MSP Veith and Torben Logemann and Aleksandr Berezin and Arlena Wellßow and Stephan Balduin},
journal= {arXiv preprint arXiv:2404.01794},
year = {2024}
}