• Home
  • Search
  • Adaptive Traffic Signal Control Based on Multi-Agent Soft Actor-Critic
  • https://doi.org/10.1109/jiot.2026.3653949Copy DOI Icon

Adaptive Traffic Signal Control Based on Multi-Agent Soft Actor-Critic

Show More
  • Abstract
  • Literature Map
  • Similar Papers
Abstract

In IoT-centric adaptive traffic signal control, existing multi-agent deep reinforcement learning methods are constrained by insufficient communication mechanisms. These limitations become particularly evident when handling the dynamic traffic networks and high-dimensional action spaces, leading to unstable environmental observability and diminished control effectiveness. Motivated by the idea of policy entropy maximization and the paradigm of centralized training and decentralized execution, the MASAC (Multi-Agent Soft Actor-Critic) algorithm was developed. However, the algorithm exhibited issues such as unstable training and low sample efficiency during its application. To enhance MASAC’s training speed and stability, the prioritized experience replay was introduced, leading to the development of a Multi-Agent Soft Actor-Critic algorithm based on prioritized experience replay(MPER-SAC), which improves the model’s learning efficiency. Joint simulation experiments using SUMO and Carla demonstrated that the proposed algorithm increased the average reward in the traffic environment by 9.55%, boosted average vehicle speed by 14.52%, and reduced average queue length and average intersection delay by 15.35% and 11.26%, respectively. Additionally, the ablation study displayed significant performance improvements, with an 11.36% increase in average reward, a 11.65% reduction in average queue length, and a 8.12% decrease in total travel delay. Additional performance metrics also exhibited varying degrees of enhancement.

Similar Papers
  • Conference Article
  • Citations5

Closed Loop Optimal Adaptive Traffic Signal and Ramp Control: A Case Study on Downtown Toronto

  • Sep 01, 2015
  • Samah El-Tantawy +2
  • Research Article

FPA-DQN: A Fairness- and Pressure-Aware Dueling Deep Q-Network for Adaptive Traffic Signal Control Using UAV-Based Trajectory Data

  • Jul 30, 2025
  • Indian Journal Of Science And Technology
  • Mihir Panchal +1
  • Conference Article
  • Citations24

RA-TSC: Learning Adaptive Traffic Signal Control Strategy via Deep Reinforcement Learning

  • Oct 01, 2019
  • Yu Du +3
  • Conference Article

Mitigating Congestion with Physics-Informed Neural Networks and Adaptive Traffic Signal Control

  • Nov 02, 2025
  • Ntemi Masanja +4
  • Research Article
  • Citations82

Real-Time Optimization for Adaptive Traffic Signal Control Using Genetic Algorithms

  • Jul 01, 2005
  • Journal of Intelligent Transportation Systems
  • Jinwoo Lee +3
  • Research Article
  • Citations552

Multiagent Reinforcement Learning for Integrated Network of Adaptive Traffic Signal Controllers (MARLIN-ATSC): Methodology and Large-Scale Application on Downtown Toronto

  • Sep 01, 2013
  • IEEE Transactions on Intelligent Transportation Systems
  • Samah El-Tantawy +2
  • Conference Article
  • Citations4

An Innovative Attack Modeling and Attack Detection Approach for a Waiting Time-Based Adaptive Traffic Signal Controller

  • Aug 31, 2022
  • Sagar Dasgupta +4
  • Research Article
  • Citations7

CAV-enabled data analytics for enhancing adaptive signal control safety environment

  • Sep 12, 2023
  • Accident Analysis & Prevention
  • Wei Lin +1
  • Research Article
  • Citations120

Distributed and adaptive traffic signal control within a realistic traffic simulation

  • May 22, 2012
  • Engineering Applications of Artificial Intelligence
  • Dave Mckenney +1
  • Conference Article

Exploiting domain constraints for exemplar based bus detection for traffic scheduling

  • Oct 01, 2014
  • Aravindh Mahendran +2
  • Conference Article

Efficiency of Adaptive Traffic Signal Control in a Partially Connected Vehicle Environment

  • Apr 17, 2023
  • Anton Agafonov +2
  • Research Article
  • Citations6

Elevating adaptive traffic signal control in semi‐autonomous traffic dynamics by using connected and automated vehicles as probes

  • Jan 21, 2024
  • IET Intelligent Transport Systems
  • Yurong Li +1
  • Research Article
  • Citations964

Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

  • Feb 20, 2019
  • IEEE Transactions on Intelligent Transportation Systems
  • Tianshu Chu +3
  • Research Article

Multi-Agent Adaptive Traffic Signal Control Based on Q-Learning and Speed Transition Matrices.

  • Dec 02, 2025
  • Sensors (Basel, Switzerland)
  • Željko Majstorović +3
  • Conference Article
  • Citations1

SCMA: A Sparse Cooperative Multi-Agent Framework for Adaptive Traffic Signal Control

  • Dec 01, 2019
  • Mahmoud Nawar +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.