跳到正文
arXiv cs.MA· Mohammadreza Rostami, Shahriar Talebi, Solmaz S. Kia·· 23 小时前AI 评分18

ResiFedLQR:在噪声与丢包上行链路中通过标量通信实现弹性联邦 LQR

Resilient Federated LQR over Noisy and Lossy Uplinks via Scalar Communication

AI 导读

研究提出 ResiFedLQR,一种面向相似系统集群的免模型联邦 LQR 控制方案:每个智能体每包只发送一个实数(梯度坐标、随机方向投影或 rollout 成本)并加冗余,替代完整梯度估计,以应对有限带宽、丢包和加性噪声。

正文 · 原文

View PDF HTML (experimental)

Abstract:This paper studies model-free federated learning of a common LQR controller for a fleet of similar systems that communicate with a server over an uplink subject to limited bandwidth, packet dropout, and additive noise. We propose \textsc{ResiFedLQR}, a scalar communication scheme in which each agent sends one real number per packet, with redundancy, instead of full gradient estimates. The scalars can be gradient coordinates, projections of the gradient onto random directions reproduced at the server from a shared seed, or the rollout costs themselves. For the projection encoding, we prove that, with high probability, every iterate stabilizes all agents and the fleet-average cost converges linearly to a neighborhood of the optimum whose radius separates heterogeneity, sampling, and communication effects, and we derive a rule for choosing the number of transmissions from the channel parameters and the fleet size. We then compare the encodings with full-gradient transmission under the same uplink budget and identify the signal-to-noise regime and power constraint under which each is preferable. Numerical experiments on a heterogeneous fleet evaluate stability and convergence under varying noise levels and dropout probabilities.
Subjects: Multiagent Systems (cs.MA)
Cite as: arXiv:2611.23913 [cs.MA]
  (or arXiv:2611.23913v1 [cs.MA] for this version)
  https://doi.org/10.48550/arXiv.2611.23913

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Mohammadreza Rostami [view email]
[v1] Wed, 18 Nov 2026 06:03:43 UTC (6,473 KB)

来源:arXiv cs.MA · arxiv.org