Over-the-air Federated Policy Gradient

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Yang, Huiwen, Huang, Lingying, Dey, Subhrakanti, Shi, Ling
Formato: Preprint
Publicado: 2023
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917596730753024
author Yang, Huiwen
Huang, Lingying
Dey, Subhrakanti
Shi, Ling
author_facet Yang, Huiwen
Huang, Lingying
Dey, Subhrakanti
Shi, Ling
contents In recent years, over-the-air aggregation has been widely considered in large-scale distributed learning, optimization, and sensing. In this paper, we propose the over-the-air federated policy gradient algorithm, where all agents simultaneously broadcast an analog signal carrying local information to a common wireless channel, and a central controller uses the received aggregated waveform to update the policy parameters. We investigate the effect of noise and channel distortion on the convergence of the proposed algorithm, and establish the complexities of communication and sampling for finding an $ε$-approximate stationary point. Finally, we present some simulation results to show the effectiveness of the algorithm.
format Preprint
id arxiv_https___arxiv_org_abs_2310_16592
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Over-the-air Federated Policy Gradient
Yang, Huiwen
Huang, Lingying
Dey, Subhrakanti
Shi, Ling
Machine Learning
Distributed, Parallel, and Cluster Computing
Signal Processing
In recent years, over-the-air aggregation has been widely considered in large-scale distributed learning, optimization, and sensing. In this paper, we propose the over-the-air federated policy gradient algorithm, where all agents simultaneously broadcast an analog signal carrying local information to a common wireless channel, and a central controller uses the received aggregated waveform to update the policy parameters. We investigate the effect of noise and channel distortion on the convergence of the proposed algorithm, and establish the complexities of communication and sampling for finding an $ε$-approximate stationary point. Finally, we present some simulation results to show the effectiveness of the algorithm.
title Over-the-air Federated Policy Gradient
topic Machine Learning
Distributed, Parallel, and Cluster Computing
Signal Processing
url https://arxiv.org/abs/2310.16592