Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning

In recent years, rapid urbanization has led to increased traffic congestion, rendering traditional traffic light control methods ineffective. Deep Reinforcement Learning (DRL) has emerged as a promising approach to sequential decision-making, offering adaptive and efficient solutions for traffic man...

Full description

Saved in:
Bibliographic Details
Main Authors: Zahra Fereidooni, Luciano Alessandro Ipsaro Palesi, Paolo Nesi
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/11029249/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849682783002165248
author Zahra Fereidooni
Luciano Alessandro Ipsaro Palesi
Paolo Nesi
author_facet Zahra Fereidooni
Luciano Alessandro Ipsaro Palesi
Paolo Nesi
author_sort Zahra Fereidooni
collection DOAJ
description In recent years, rapid urbanization has led to increased traffic congestion, rendering traditional traffic light control methods ineffective. Deep Reinforcement Learning (DRL) has emerged as a promising approach to sequential decision-making, offering adaptive and efficient solutions for traffic management. This paper aims to develop an optimal traffic light planning strategy that integrates seamlessly with urban transportation systems, including trams and Bus Rapid Transit Systems (BRTS). The study explores three DRL-based approaches: Single-Agent Deep Reinforcement Learning (SADRL), Multi-Agent Deep Reinforcement Learning (MADRL) with fixed traffic lights, and an actuated control approach. System for Managing Actuated and Real-Time Traffic, referred to as SMART, dynamically adjusts traffic signals based on real-time conditions to enhance traffic flow efficiency. The proposed methods are evaluated and compared against the Webster method, Simulation of Urban Mobility (SUMO)-based control, and a genetic algorithm-based multi-objective traffic light optimization method (MamoTLO). The results demonstrate that DRL-based solutions improve traffic flow and reduce congestion.
format Article
id doaj-art-2d0a13d45bf4485d86810beb396ffc6a
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-2d0a13d45bf4485d86810beb396ffc6a2025-08-20T03:24:06ZengIEEEIEEE Access2169-35362025-01-011310697410698810.1109/ACCESS.2025.357851811029249Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement LearningZahra Fereidooni0Luciano Alessandro Ipsaro Palesi1https://orcid.org/0000-0001-8992-2084Paolo Nesi2https://orcid.org/0000-0003-1044-3107Department of Information Engineering, DISIT Laboratory, University of Florence, Florence, ItalyDepartment of Information Engineering, DISIT Laboratory, University of Florence, Florence, ItalyDepartment of Information Engineering, DISIT Laboratory, University of Florence, Florence, ItalyIn recent years, rapid urbanization has led to increased traffic congestion, rendering traditional traffic light control methods ineffective. Deep Reinforcement Learning (DRL) has emerged as a promising approach to sequential decision-making, offering adaptive and efficient solutions for traffic management. This paper aims to develop an optimal traffic light planning strategy that integrates seamlessly with urban transportation systems, including trams and Bus Rapid Transit Systems (BRTS). The study explores three DRL-based approaches: Single-Agent Deep Reinforcement Learning (SADRL), Multi-Agent Deep Reinforcement Learning (MADRL) with fixed traffic lights, and an actuated control approach. System for Managing Actuated and Real-Time Traffic, referred to as SMART, dynamically adjusts traffic signals based on real-time conditions to enhance traffic flow efficiency. The proposed methods are evaluated and compared against the Webster method, Simulation of Urban Mobility (SUMO)-based control, and a genetic algorithm-based multi-objective traffic light optimization method (MamoTLO). The results demonstrate that DRL-based solutions improve traffic flow and reduce congestion.https://ieeexplore.ieee.org/document/11029249/Deep reinforcement learningsmart citiestraffic controltraffic lightmulti-agentsingle-agent
spellingShingle Zahra Fereidooni
Luciano Alessandro Ipsaro Palesi
Paolo Nesi
Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
IEEE Access
Deep reinforcement learning
smart cities
traffic control
traffic light
multi-agent
single-agent
title Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
title_full Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
title_fullStr Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
title_full_unstemmed Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
title_short Multi-Agent Optimizing Traffic Light Signals Using Deep Reinforcement Learning
title_sort multi agent optimizing traffic light signals using deep reinforcement learning
topic Deep reinforcement learning
smart cities
traffic control
traffic light
multi-agent
single-agent
url https://ieeexplore.ieee.org/document/11029249/
work_keys_str_mv AT zahrafereidooni multiagentoptimizingtrafficlightsignalsusingdeepreinforcementlearning
AT lucianoalessandroipsaropalesi multiagentoptimizingtrafficlightsignalsusingdeepreinforcementlearning
AT paolonesi multiagentoptimizingtrafficlightsignalsusingdeepreinforcementlearning