Salvato in:
Dettagli Bibliografici
Autori principali: Su, Haoran, Sun, Yandong, Deng, Hanxiao
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:https://arxiv.org/abs/2602.02903
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912871333494784
author Su, Haoran
Sun, Yandong
Deng, Hanxiao
author_facet Su, Haoran
Sun, Yandong
Deng, Hanxiao
contents Traffic signal control is a critical challenge in urban transportation, requiring coordination among multiple intersections to optimize network-wide traffic flow. While reinforcement learning has shown promise for adaptive signal control, existing methods struggle with multi-agent coordination and sample efficiency. We introduce MADT (Multi-Agent Decision Transformer), a novel approach that reformulates multi-agent traffic signal control as a sequence modeling problem. MADT extends the Decision Transformer paradigm to multi-agent settings by incorporating: (1) a graph attention mechanism for modeling spatial dependencies between intersections, (2) a|temporal transformer encoder for capturing traffic dynamics, and (3) return-to-go conditioning for target performance specification. Our approach enables offline learning from historical traffic data, with architecture design that facilitates potential online fine-tuning. Experiments on synthetic grid networks and real-world traffic scenarios demonstrate that MADT achieves state-of-the-art performance, reducing average travel time by 5-6% compared to the strongest baseline while exhibiting superior coordination among adjacent intersections.
format Preprint
id arxiv_https___arxiv_org_abs_2602_02903
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Spatiotemporal Decision Transformer for Traffic Coordination
Su, Haoran
Sun, Yandong
Deng, Hanxiao
Machine Learning
Artificial Intelligence
Systems and Control
Traffic signal control is a critical challenge in urban transportation, requiring coordination among multiple intersections to optimize network-wide traffic flow. While reinforcement learning has shown promise for adaptive signal control, existing methods struggle with multi-agent coordination and sample efficiency. We introduce MADT (Multi-Agent Decision Transformer), a novel approach that reformulates multi-agent traffic signal control as a sequence modeling problem. MADT extends the Decision Transformer paradigm to multi-agent settings by incorporating: (1) a graph attention mechanism for modeling spatial dependencies between intersections, (2) a|temporal transformer encoder for capturing traffic dynamics, and (3) return-to-go conditioning for target performance specification. Our approach enables offline learning from historical traffic data, with architecture design that facilitates potential online fine-tuning. Experiments on synthetic grid networks and real-world traffic scenarios demonstrate that MADT achieves state-of-the-art performance, reducing average travel time by 5-6% compared to the strongest baseline while exhibiting superior coordination among adjacent intersections.
title Spatiotemporal Decision Transformer for Traffic Coordination
topic Machine Learning
Artificial Intelligence
Systems and Control
url https://arxiv.org/abs/2602.02903