Federated TD Learning Over Finite-Rate Erasure Channels: Linear Speedup Under Markovian Sampling-Reference-Cited by-同舟云学术

Federated TD Learning Over Finite-Rate Erasure Channels: Linear Speedup Under Markovian Sampling

Published:2023 Issue: Volume:7 Page:2461-2466
ISSN:2475-1456
Container-title:IEEE Control Systems Letters
language:
Short-container-title:IEEE Control Syst. Lett.

Author:

Dal Fabbro Nicolò¹^ORCID,Mitra Aritra²^ORCID,Pappas George J.³^ORCID

Affiliation:

1. Department of Information Engineering, University of Padova, Venice, Italy

2. Electrical and Computer Engineering Department, North Carolina State University, Raleigh, NC, USA

3. Electrical and Systems Engineering Department, University of Pennsylvania, Philadelphia, PA, USA

Funder

NSF

Italian Ministry of Education, University and Research through the PRIN Project

Publisher

Institute of Electrical and Electronics Engineers (IEEE)

Subject

Control and Optimization,Control and Systems Engineering

Link

https://ieeexplore.ieee.org/ielam/7782633/9828546/10158993-aam.pdf

Reference22 articles.

1. Finite-time analysis of distributed TD(0) with linear function approximation on multi-agent reinforcement learning;doan;Proc Int Conf Mach Learn,2019

2. Finite time analysis of temporal difference learning with linear function approximation: Tail averaging and regularisation;patil;Proc Int Conf Artif Intell Statist,2023

3. Federated reinforcement learning: Linear speedup under Markovian sampling;khodadadian;Proc ICML,2022

4. Distributed TD(0) with almost no communication;liu;arXiv 2104 07855,2021

5. Markov Chains and Mixing Times

Cited by 3 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Finite- Time Analysis of Asynchronous Multi-Agent TD Learning;2024 American Control Conference (ACC);2024-07-10

2. Compressed Federated Reinforcement Learning with a Generative Model;Lecture Notes in Computer Science;2024

3. Federated TD Learning Over Finite-Rate Erasure Channels: Linear Speedup Under Markovian Sampling;IEEE Control Systems Letters;2023