Centralizing State-Values in Dueling Networks for Multi-Robot Reinforcement Learning Mapless Navigation

We study the problem of multi-robot mapless navigation in the popular Centralized Training and Decentralized Execution (CTDE) paradigm. This problem is challenging when each robot considers its path without explicitly sharing observations with other robots and can lead to non-stationary issues in De...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Proceedings of the ... IEEE/RSJ International Conference on Intelligent Robots and Systems S. 4583 - 4588
Hauptverfasser:	Marchesini, Enrico, Farinelli, Alessandro
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 27.09.2021
Schlagworte:	Computational modeling Computer architecture Estimation Navigation Reinforcement learning Task analysis Training
ISSN:	2153-0866
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!