Paper ID: 2404.01794

Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid

Eric MSP Veith, Torben Logemann, Aleksandr Berezin, Arlena Wellßow, Stephan Balduin

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.

Submitted: Apr 2, 2024