Decentralized graph attention multi-agent reinforcement learning for adaptive urban traffic routing

Abstract Urban traffic congestion incurs high economic and environmental costs, including fuel wastage, increased greenhouse gas emissions, and driver frustration. Current genetic algorithm-based traffic routing systems do not adapt when real-time conditions deviate from their offline optimization a...

Descrizione completa

Dettagli Bibliografici

Autori principali:	Muhammad Mahmoud, Souham Meshoul, Mohamed Batouche, Mohamed Hammad
Natura:	Artigo
Lingua:	Inglês
Pubblicazione:	Nature Portfolio 2026-06-01
Serie:	Scientific Reports
Soggetti:	Multi-agent reinforcement learning Graph attention networks Traffic routing Intelligent transportation systems Decentralized control
Accesso online:	https://doi.org/10.1038/s41598-026-56204-2
Tags:	Aggiungi Tag Nessun Tag, puoi essere il primo ad aggiungerne!!