Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations

• URL: http://arxiv.org/abs/2511.00549v1
• Date: Sat, 01 Nov 2025 13:18:50 GMT
• Title: Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
• Authors: Qiang Li, Jin Niu, Lina Yu,
• Abstract summary: Traffic congestion, primarily driven by intersection queuing, significantly impacts urban living standards, safety, environmental quality, and economic efficiency.<n>This study introduces a novel single-agent reinforcement learning framework for regional adaptive TSC.<n>The framework exhibits robust anti-fluctuation capability and significantly reduces queue lengths.
• Score: 5.784337914162491
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Traffic congestion, primarily driven by intersection queuing, significantly impacts urban living standards, safety, environmental quality, and economic efficiency. While Traffic Signal Control (TSC) systems hold potential for congestion mitigation, traditional optimization models often fail to capture real-world traffic complexity and dynamics. This study introduces a novel single-agent reinforcement learning (RL) framework for regional adaptive TSC, circumventing the coordination complexities inherent in multi-agent systems through a centralized decision-making paradigm. The model employs an adjacency matrix to unify the encoding of road network topology, real-time queue states derived from probe vehicle data, and current signal timing parameters. Leveraging the efficient learning capabilities of the DreamerV3 world model, the agent learns control policies where actions sequentially select intersections and adjust their signal phase splits to regulate traffic inflow/outflow, analogous to a feedback control system. Reward design prioritizes queue dissipation, directly linking congestion metrics (queue length) to control actions. Simulation experiments conducted in SUMO demonstrate the model's effectiveness: under inference scenarios with multi-level (10%, 20%, 30%) Origin-Destination (OD) demand fluctuations, the framework exhibits robust anti-fluctuation capability and significantly reduces queue lengths. This work establishes a new paradigm for intelligent traffic control compatible with probe vehicle technology. Future research will focus on enhancing practical applicability by incorporating stochastic OD demand fluctuations during training and exploring regional optimization mechanisms for contingency events.

Related papers

• Spatiotemporal Decision Transformer for Traffic Coordination [1.2099551931618155]
  MADT (Multi-Agent Decision Transformer) is a novel approach that reformulates multi-agent traffic signal control as a sequence modeling problem.<n>Our approach enables offline learning from historical traffic data, with architecture design that facilitates potential online fine-tuning.
  arXiv  Detail & Related papers  (2026-02-02T23:19:13Z)
• Wireless Traffic Prediction with Large Language Model [54.07581399989292]
  TIDES is a novel framework that captures spatial-temporal correlations for wireless traffic prediction.<n> TIDES achieves efficient adaptation to domain-specific patterns without incurring excessive training overhead.<n>Our results indicate that integrating spatial awareness into LLM-based predictors is the key to unlocking scalable and intelligent network management in future 6G systems.
  arXiv  Detail & Related papers  (2025-12-19T04:47:40Z)
• Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control [5.170416022609791]
  This work proposes a single-agent RL-based regional traffic signal control model compatible with probe vehicle technology.<n>Key components of the RL design include state, action, and reward function definitions.<n> Experimental results demonstrate that the proposed model effectively mitigates large-scale regional congestion levels via coordinated multi-intersection control.
  arXiv  Detail & Related papers  (2025-11-01T13:29:13Z)
• Reinforcement Learning Based Traffic Signal Design to Minimize Queue Lengths [15.439906983758808]
  We propose a novel adaptive TSC framework that leverages Reinforcement Learning (RL) to minimize total queue lengths across all signal phases.<n>The proposed algorithm has been implemented using the Simulation of Urban Mobility (SUMO) traffic simulator.<n>The best performing configuration achieves an approximately 29% reduction in average queue lengths compared to the traditional Webster method.
  arXiv  Detail & Related papers  (2025-09-26T01:23:30Z)
• Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies [0.0]
  Urban traffic congestion, particularly at intersections, significantly impacts travel time, fuel consumption, and emissions.<n>Traditional fixed-time signal control systems often lack the adaptability to manage dynamic traffic patterns effectively.<n>This study explores the application of multi-agent reinforcement learning to optimize traffic signal coordination across multiple intersections.
  arXiv  Detail & Related papers  (2025-05-20T15:59:44Z)
• Improving Traffic Flow Predictions with SGCN-LSTM: A Hybrid Model for Spatial and Temporal Dependencies [55.2480439325792]
  This paper introduces the Signal-Enhanced Graph Convolutional Network Long Short Term Memory (SGCN-LSTM) model for predicting traffic speeds across road networks. Experiments on the PEMS-BAY road network traffic dataset demonstrate the SGCN-LSTM model's effectiveness.
  arXiv  Detail & Related papers  (2024-11-01T00:37:00Z)
• A Holistic Framework Towards Vision-based Traffic Signal Control with Microscopic Simulation [53.39174966020085]
  Traffic signal control (TSC) is crucial for reducing traffic congestion that leads to smoother traffic flow, reduced idling time, and mitigated CO2 emissions. In this study, we explore the computer vision approach for TSC that modulates on-road traffic flows through visual observation. We introduce a holistic traffic simulation framework called TrafficDojo towards vision-based TSC and its benchmarking.
  arXiv  Detail & Related papers  (2024-03-11T16:42:29Z)
• Real-Time Network-Level Traffic Signal Control: An Explicit Multiagent Coordination Method [9.761657423863706]
  Efficient traffic signal control (TSC) has been one of the most useful ways for reducing urban road congestion. Recent efforts that applied reinforcement learning (RL) methods can query policies by mapping the traffic state to the signal decision in real-time. We propose an explicit multiagent coordination (EMC)-based online planning methods that can satisfy adaptive, real-time and network-level TSC.
  arXiv  Detail & Related papers  (2023-06-15T04:08:09Z)
• Language-Guided Traffic Simulation via Scene-Level Diffusion [46.47977644226296]
  We present CTG++, a scene-level conditional diffusion model that can be guided by language instructions. We first propose a scene-level diffusion model equipped with atemporal backbone which generates realistic and controllable traffic. We then harness a large language model (LLM) to convert a users query into a loss function guiding the diffusion model towards query-compliant generation.
  arXiv  Detail & Related papers  (2023-06-10T05:20:30Z)
• AI-aided Traffic Control Scheme for M2M Communications in the Internet of Vehicles [61.21359293642559]
  The dynamics of traffic and the heterogeneous requirements of different IoV applications are not considered in most existing studies. We consider a hybrid traffic control scheme and use proximal policy optimization (PPO) method to tackle it.
  arXiv  Detail & Related papers  (2022-03-05T10:54:05Z)
• A Deep Reinforcement Learning Approach for Traffic Signal Control Optimization [14.455497228170646]
  Inefficient traffic signal control methods may cause numerous problems, such as traffic congestion and waste of energy. This paper first proposes a multi-agent deep deterministic policy gradient (MADDPG) method by extending the actor-critic policy gradient algorithms.
  arXiv  Detail & Related papers  (2021-07-13T14:11:04Z)
• Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline [85.9210953301628]
  Control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. Because of the high complexity of modelling the problem, experimental settings of current works are often inconsistent. We propose a novel and strong baseline model based on deep reinforcement learning with the encoder-decoder structure.
  arXiv  Detail & Related papers  (2021-01-24T03:55:39Z)
• MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Control [54.162449208797334]
  Traffic signal control aims to coordinate traffic signals across intersections to improve the traffic efficiency of a district or a city. Deep reinforcement learning (RL) has been applied to traffic signal control recently and demonstrated promising performance where each traffic signal is regarded as an agent. We propose a novel Meta Variationally Intrinsic Motivated (MetaVIM) RL method to learn the decentralized policy for each intersection that considers neighbor information in a latent way.
  arXiv  Detail & Related papers  (2021-01-04T03:06:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.