Cloud-Edge Training Architecture for Sim-to-Real Deep Reinforcement Learning

Deep reinforcement learning (DRL) is a promising approach to solve complex control tasks by learning policies through interactions with the environment. However, the training of DRL policies requires large amounts of training experiences, making it impractical to learn the policy directly on physica...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2022-07
Hauptverfasser:	Cao, Hongpeng, Theile, Mirco, Wyrwal, Federico G, Caccamo, Marco
Format:	Artikel
Sprache:	eng
Schlagworte:	Cloud computing Computer Science - Learning Computer Science - Robotics Control tasks Deep learning Domains Performance degradation Policies Real time Simulation Task complexity Training
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!