Cocktail: Learn a Better Neural Network Controller from Multiple Experts via Adaptive Mixing and Robust Distillation
TimeTuesday, December 7th4:00pm - 4:30pm PST
Design of Cyber-physical Systems and IoT
DescriptionNeural networks are being increasingly applied to control and decision making for learning-enabled cyber-physical systems (LE-CPSs). They have shown promising performance without requiring the development of complex physical models; however, their adoption is significantly hindered by the concerns on their safety, robustness, and efficiency. In this work, we propose Cocktail, a novel design framework that automatically learns a neural network based controller from multiple existing control methods (experts) that could be either model-based or neural network based.
Experiments on three non-linear systems demonstrate significant advantages of our approach on these properties over various baseline methods.