mlsanityData to 14 Oct 2026

Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse

arXiv 2503.08728 ↗First posted 11 Mar 2025cs.MA cs.AIcited by 0

On the map: Deep reinforcement learning methods → RL for autonomous driving and traffic

Abstract (arXiv)

Multi-agent reinforcement learning (MARL) has shown significant potential in traffic signal control (TSC). However, current MARL-based methods often suffer from insufficient generalization due to the fixed traffic patterns and road network conditions used during training. This limitation results in poor adaptability to new traffic scenarios, leading to high retraining costs and complex deployment. To address this challenge, we propose two algorithms: PLight and PRLight. PLight employs a model-based reinforcement learning approach, pretraining control policies and environment models using predefined source-domain traffic scenarios. The environment model predicts the state transitions, which facilitates the comparison of environmental features. PRLight further enhances adaptability by adaptively selecting pre-trained PLight agents based on the similarity between the source and target domains to accelerate the learning process in the target domain. We evaluated the algorithms through two transfer settings: (1) adaptability to different traffic scenarios within the same road network, and (2) generalization across different road networks. The results show that PRLight significantly reduces the adaptation time compared to learning from scratch in new TSC scenarios, achieving optimal performance using similarities between available and target scenarios.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for autonomous driving and traffic, one of 15 directions in Deep reinforcement learning methods. Builds on 15 of its 29 references that are in the map. First posted on arXiv 11 Mar 2025.

Builds on

15 of 29 references.

References · 15

  1. 2020Transfer Learning in Deep Reinforcement Learning: A Surveycited by 265
  2. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 164
  3. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  4. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 98
  5. 2019Learning Phase Competition for Traffic Signal Controlcited by 87
  6. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 62
  7. 2021Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlcited by 29
  8. 2021Multi-Agent MDP Homomorphic Networkscited by 25
  9. 2020IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Controlcited by 22
  10. 2020GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learningcited by 17
  11. 2022SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Controlcited by 15
  12. 2017An Optimal Online Method of Selecting Source Policies for Reinforcement Learningcited by 13
3 more
  1. 2022EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control Systemcited by 9
  2. 2021Leveraging Queue Length and Attention Mechanisms for Enhanced Traffic Signal Control Optimizationcited by 7
  3. 2021Model-Augmented Q-learningcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control
  2. 2025A Constrained Multi-Agent Reinforcement Learning Approach to Autonomous Traffic Signal Control
  3. 2024Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
  4. 2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
  5. 2025Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control
  6. 2024PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Control
  7. 2025Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control
  8. 2025Reinforcement Learning Based Traffic Signal Design to Minimize Queue Lengths