Salvato in:
Dettagli Bibliografici
Autori principali: Xu, Kaidi, Zhou, Shenglong, Li, Geoffrey Ye
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:https://arxiv.org/abs/2405.01961
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
Sommario:
  • Federated Reinforcement Learning (FRL) offers a promising solution to various practical challenges in resource allocation for vehicle-to-everything (V2X) networks. However, the data discrepancy among individual agents can significantly degrade the performance of FRL-based algorithms. To address this limitation, we exploit the node-wise invariance property of ReLU-activated neural networks, with the aim of reducing data discrepancy to improve learning performance. Based on this property, we introduce a backward rescale-invariant operation to develop a rescale-invariant FRL algorithm. Simulation results demonstrate that the proposed algorithm notably enhances both convergence speed and convergent performance.