تقرير
Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid
العنوان: | Imitation Game: A Model-based and Imitation Learning Deep Reinforcement Learning Hybrid |
---|---|
المؤلفون: | Veith, Eric MSP, Logemann, Torben, Berezin, Aleksandr, Wellßow, Arlena, Balduin, Stephan |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Artificial Intelligence |
الوصف: | 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 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2404.01794 |
رقم الأكسشن: | edsarx.2404.01794 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |