Vendredi 14 novembre, 11h30 – Salle C057.
Title: Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
Abstract: In edge computing systems, autonomous agents must make rapid local decisions while competing for shared resources. Existing MARL approaches often rely on centralized critics or frequent inter-agent communication, which breaks down under limited observability and communication constraints. We propose a decentralized framework in which agents coordinate implicitly through a shared constraint on resource usage. This constraint is updated infrequently, requiring minimal communication, while each agent independently solves a local constrained Markov decision process (CMDP) to learn its behavior. Leveraging safe reinforcement learning, agents learn policies that satisfy both local and global objectives. We provide theoretical guarantees under mild assumptions and validate our approach experimentally, demonstrating superior performance to centralized and independent baselines, particularly in large-scale settings.
Title: Multi-Agent Reinforcement Learning for Task Offloading in Wireless Edge Networks
Abstract: In edge computing systems, autonomous agents must make rapid local decisions while competing for shared resources. Existing MARL approaches often rely on centralized critics or frequent inter-agent communication, which breaks down under limited observability and communication constraints. We propose a decentralized framework in which agents coordinate implicitly through a shared constraint on resource usage. This constraint is updated infrequently, requiring minimal communication, while each agent independently solves a local constrained Markov decision process (CMDP) to learn its behavior. Leveraging safe reinforcement learning, agents learn policies that satisfy both local and global objectives. We provide theoretical guarantees under mild assumptions and validate our approach experimentally, demonstrating superior performance to centralized and independent baselines, particularly in large-scale settings.