[2506.02668] FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems

Computer Science > Artificial Intelligence arXiv:2506.02668 (cs) [Submitted on 3 Jun 2025 (v1), last revised 28 Feb 2026 (this version, v2)] Title:FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems Authors:Frederico Metelo, Alexandre Oliveira, Stevo Racković, Pedro Ákos Costa, Cláudia Soares View a PDF of the paper titled FAuNO: Semi-Asynchronous Federated Reinforcement Learning Framework for Task Offloading in Edge Systems, by Frederico Metelo and 4 other authors View PDF HTML (experimental) Abstract:Edge computing addresses the growing data demands of connected-device networks by placing computational resources closer to end users through decentralized infrastructures. This decentralization challenges traditional, fully centralized orchestration, which suffers from latency and resource bottlenecks. We present \textbf{FAuNO} -- \emph{Federated Asynchronous Network Orchestrator} -- a buffered, asynchronous \emph{federated reinforcement-learning} (FRL) framework for decentralized task offloading in edge systems. FAuNO adopts an actor-critic architecture in which local actors learn node-specific dynamics and peer interactions, while a federated critic aggregates experience across agents to encourage efficient cooperation and improve overall system performance. Experiments in the \emph{PeersimGym} environment show that FAuNO consistently matches or exceeds heuristic and federated multi-agent RL baselines in reducing task lo...