Open access
Jul 2026
MARL-Converge: Decentralized Multi-Agent Reinforcement Learning for Failure-Aware Routing Convergence
A reproducible discrete-time link-state convergence proxy with independent topology views, stochastic failure detection and link-state advertisement diffusion, shortest-path recomputation, and forwarding-loop/drop checks is implemented.
David Clarke, Mei Huang, Jonas Eriksen
· International journal of inf... · 0 citations