Safe DNN-type Controller Synthesis for Nonlinear Systems via Meta Reinforcement Learning

There is a pressing need to synthesize provable safety controllers for nonlinear systems as they are embedded in many safety-critical applications. In this paper, we propose a safe Meta Reinforcement Learning (Meta-RL) approach to synthesize deep neural network (DNN) controllers for nonlinear system...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2023 60th ACM/IEEE Design Automation Conference (DAC) S. 1 - 6
Hauptverfasser:	Zhao, Hanrui, Zeng, Xia, Qi, Niuniu, Yang, Zhengfeng, Zeng, Zhenbing
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 09.07.2023
Schlagworte:	Artificial neural networks Benchmark testing controller synthesis formal verification meta learning Metalearning Pressing Reinforcement learning Safety Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!