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

ICLR 2026 Conference Submission17021 Authors

Keywords: Task Offloading, Edge Systems, Partial Observability, Multi-Agent Federated Reinforcemtent Learning, Actor-Critic Methods

TL;DR: We developed a framework for orchestrating edge systems using a federated multi-agent reinforcement learning approach.

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 loss and latency, underscoring its adaptability to dynamic edge-computing scenarios.

Primary Area: reinforcement learning

Submission Number: 17021