mlsanityData to 14 Oct 2026

Topology-Assisted Spatio-Temporal Pattern Disentangling for Scalable MARL in Large-scale Autonomous Traffic Control

arXiv 2506.12453 ↗First posted 14 Jun 2025cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Intelligent Transportation Systems (ITSs) have emerged as a promising solution towards ameliorating urban traffic congestion, with Traffic Signal Control (TSC) identified as a critical component. Although Multi-Agent Reinforcement Learning (MARL) algorithms have shown potential in optimizing TSC through real-time decision-making, their scalability and effectiveness often suffer from large-scale and complex environments. Typically, these limitations primarily stem from a fundamental mismatch between the exponential growth of the state space driven by the environmental heterogeneities and the limited modeling capacity of current solutions. To address these issues, this paper introduces a novel MARL framework that integrates Dynamic Graph Neural Networks (DGNNs) and Topological Data Analysis (TDA), aiming to enhance the expressiveness of environmental representations and improve agent coordination. Furthermore, inspired by the Mixture of Experts (MoE) architecture in Large Language Models (LLMs), a topology-assisted spatial pattern disentangling (TSD)-enhanced MoE is proposed, which leverages topological signatures to decouple graph features for specialized processing, thus improving the model's ability to characterize dynamic and heterogeneous local observations. The TSD module is also integrated into the policy and value networks of the Multi-agent Proximal Policy Optimization (MAPPO) algorithm, further improving decision-making efficiency and robustness. Extensive experiments conducted on real-world traffic scenarios, together with comprehensive theoretical analysis, validate the superior performance of the proposed framework, highlighting the model's scalability and effectiveness in addressing the complexities of large-scale TSC tasks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 35 of its 59 references that are in the map. First posted on arXiv 14 Jun 2025.

Builds on

35 of 59 references.

References · 35

  1. 2017Graph Attention Networkscited by 8,923
  2. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,509
  3. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  4. 2021Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsitycited by 3,073
  5. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,367
  6. 2015High-Dimensional Continuous Control Using Generalized Advantage Estimationcited by 2,026
  7. 2021How Attentive are Graph Attention Networks?cited by 835
  8. 2022Mixture-of-Experts with Expert Choice Routingcited by 623
  9. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 567
  10. 2020Temporal Graph Networks for Deep Learning on Dynamic Graphscited by 530
  11. 2021BASE Layers: Simplifying Training of Large, Sparse Modelscited by 320
  12. 2023From Sparse to Soft Mixtures of Expertscited by 248
23 more
  1. 2021Hash Layers For Large Sparse Modelscited by 237
  2. 2024A Survey on Mixture of Experts in Large Language Modelscited by 237
  3. 2015Conditional Computation in Neural Networks for faster modelscited by 167
  4. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  5. 2019PersLay: A Neural Network Layer for Persistence Diagrams and New Graph Topological Signaturescited by 126
  6. 2020Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A surveycited by 124
  7. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 98
  8. 2021Scaling Multi-Agent Reinforcement Learning with Selective Parameter Sharingcited by 87
  9. 2021Topological Graph Neural Networkscited by 87
  10. 2024LLaVA-MoLE: Sparse Mixture of LoRA Experts for Mitigating Data Conflicts in Instruction Finetuning MLLMscited by 84
  11. 2024Mixtures of Experts Unlock Parameter Scaling for Deep RLcited by 78
  12. 2017Flow: A Modular Learning Framework for Mixed Autonomy Trafficcited by 73
  13. 2018Deep Reinforcement Learning for Traffic Light Control in Vehicular Networkscited by 52
  14. 2022Gradient Gating for Deep Multi-Rate Learning on Graphscited by 49
  15. 2024Bridging the Divide: Reconsidering Softmax and Linear Attentioncited by 48
  16. 2021Federated Mixture of Expertscited by 28
  17. 2023The Expressive Power of Graph Neural Networks: A Surveycited by 27
  18. 2020IG-RL: Inductive Graph Reinforcement Learning for Massive-Scale Traffic Signal Controlcited by 22
  19. 2024Mixture of Experts in a Mixture of RL settingscited by 21
  20. 2019Learning an Interpretable Traffic Signal Control Policycited by 20
  21. 2022CoTV: Cooperative Control for Traffic Light Signals and Connected Autonomous Vehicles using Deep Reinforcement Learningcited by 6
  22. 2019A Mobility-Aware Vehicular Caching Scheme in Content Centric Networks: Model and Optimizationcited by 2
  23. 2023Semantics-enhanced Temporal Graph Networks for Content Popularity Predictioncited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs
  2. 2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
  3. 2025Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies
  4. 2025Convergence of Multiagent Learning Systems for Traffic control
  5. 2025Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control
  6. 2025Large-scale Regional Traffic Signal Control Based on Single-Agent Reinforcement Learning
  7. 2026LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
  8. 2025Single-agent Reinforcement Learning Model for Regional Adaptive Traffic Signal Control