RMBench: Benchmarking Deep Reinforcement Learning for Robotic Manipulator Control

Reinforcement learning is applied to solve actual complex tasks from high-dimensional, sensory inputs. The last decade has developed a long list of reinforcement learning algorithms. Recent progress benefits from deep learning for raw sensory signal representation. One question naturally arises: how...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	arXiv.org 2023-03
Hauptverfasser:	Xiang, Yanfei, Wang, Xin, Hu, Shu, Zhu, Bin, Huang, Xiaomeng, Wu, Xi, Lyu, Siwei
Format:	Artikel
Sprache:	eng
Schlagworte:	Algorithms Benchmarks Computer Science - Artificial Intelligence Computer Science - Robotics Deep learning Learning curves Machine learning Performance measurement Robot arms Robot control Robotics Stability Stability augmentation Task complexity
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!