Guido Marchetto

MARS: Multi-Agent Deep Reinforcement Learning for Complex Environment Exploration

Adaptive SDN Autoscaling via Generalizable Multi-Agent Reinforcement Learning With EAGLE

This work proposes EAGLE, a Multi-Agent Reinforcement Learning (MARL) system that autonomously orchestrates the scaling of network resources to meet flow demands and reduce power consumption, and shows that the trained model can “zero-shot generalize” to unseen network topologies that share structural or statistical si...

Packets in P4 Switches With Multi-Agent Decisions Logic

ROAR is proposed, a novel architectural solution that implements Deep Reinforcement Learning (DRL) inside P4 programmable switches to perform adaptive routing policies based on network conditions and traffic patterns that show both a throughput and delay improvement in the transmission compared to traditional approache...