Reinforcement Learning-Based Multihop Relaying: A Decentralized Q-Learning Approach

Conventional optimization-based relay selection for multihop networks cannot resolve the conflict between performance and cost. The optimal selection policy is centralized and requires local channel state information (CSI) of all hops, leading to high computational complexity and signaling overhead....

Ausführliche Beschreibung

Bibliografische Detailangaben

Hauptverfasser:	Xiaowei Wang, Xin Wang
Format:	Artigo
Sprache:	Inglês
Veröffentlicht:	MDPI AG 2021-10-01
Schriftenreihe:	Entropy
Schlagworte:	reinforcement learning Q-learning multihop network relay selection
Online-Zugang:	https://www.mdpi.com/1099-4300/23/10/1310
Tags:	Tag hinzufügen Keine Tags, Fügen Sie das erste Tag hinzu!