paper-with-me

Papers

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates

2023-10-09 · NeurIPS 2023 11

Federated reinforcement learning (FedRL) enables agents to collaboratively train a global policy without sharing their individual data. However, high communication overhead remains a critical bottleneck, particularly for natural policy gradient (NPG) methods, which are second-order. To address this issue, we propose the FedNPG-ADMM framework, which leverages the alternating direction method of multipliers (ADMM) to approximate global NPG directions efficiently. We theoretically demonstrate that using ADMM-based gradient updates reduces communication complexity from ${O}({d^{2}})$ to ${O}({d})$ at each iteration, where $d$ is the number of model parameters. Furthermore, we show that achieving an $\epsilon$-error stationary convergence requires ${O}(\frac{1}{(1-\gamma)^{2}{\epsilon}})$ iterations for discount factor $\gamma$, demonstrating that FedNPG-ADMM maintains the same convergence rate as the standard FedNPG. Through evaluation of the proposed algorithms in MuJoCo environments, we demonstrate that FedNPG-ADMM maintains the reward performance of standard FedNPG, and that its convergence rate improves when the number of federated agents increases.

📄 PDF Abstract BibTeX arXiv:2310.19807

Code (0)

등록된 구현이 없습니다.

Tasks

MuJoCo

Similar Papers 제목 키워드 기반

Federated Learning over Wireless IoT Networks with Optimized Communication and Resources

2021-10-22 · Hao Chen, Shaocheng Huang, Deyou Zhang, Ming Xiao 외

To leverage massive distributed data and computation resources, machine learning in the network edge is considered to be a promising technique especially for large-scale model training. Federated learning (FL), as a para…

Federated LearningScheduling

PubSwap: Public-Data Off-Policy Coordination for Federated RLVR

2026-04-14 · Anupam Nayak, Baris Askin, Muhammed Ustaomeroglu, Carlee Joe-Wong 외 arxiv

Reasoning post-training with reinforcement learning from verifiable rewards (RLVR) is typically studied in centralized settings, yet many realistic applications involve decentralized private data distributed across organ…

Reinforcement Learning

Compressed Federated Reinforcement Learning with a Generative Model

2024-03-26 · Ali Beikmohammadi, Sarit Khirirat, Sindri Magnússon

Reinforcement learning has recently gained unprecedented popularity, yet it still grapples with sample inefficiency. Addressing this challenge, federated reinforcement learning (FedRL) has emerged, wherein agents collabo…

modelQ-Learningreinforcement-learningReinforcement Learning

Joint Channel Selection using FedDRL in V2X

2024-10-03 · Lorenzo Mancini, Safwan Labbi, Karim Abed Meraim, Fouzi Boukhalfa 외

Vehicle-to-everything (V2X) communication technology is revolutionizing transportation by enabling interactions between vehicles, devices, and infrastructures. This connectivity enhances road safety, transportation effic…

channel selectionDecision MakingDeep Reinforcement Learning

Federated LoRA with Sparse Communication

2024-06-07 · Kevin Kuo, Arian Raje, Kousik Rajesh, Virginia Smith

Low-rank adaptation (LoRA) is a natural method for finetuning in communication-constrained machine learning settings such as cross-device federated learning. Prior work that has studied LoRA in the context of federated l…

Federated Learning