Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid
| Autor: | Veith, Eric MSP, Logemann, Torben, Berezin, Aleksandr, Wellßow, Arlena, Balduin, Stephan |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | 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. Comment: Accepted as publication at MSCPES '24 |
| Databáze: | arXiv |
| Externí odkaz: |
|