Improve exploration in deep reinforcement learning for UAV path planning using state and action entropy

Despite being a widely adopted development framework for unmanned aerial vehicle (UAV), deep reinforcement learning is often considered sample inefficient. Particularly, UAV struggles to fully explore the state and action space in environments with sparse rewards. While some exploration algorithms h...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Measurement science & technology 2024-05, Vol.35 (5), p.56206
Hauptverfasser:	Lv, Hui, Chen, Yadong, Li, Shibo, Zhu, Baolong, Li, Min
Format:	Artikel
Sprache:	eng
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!