mlsanityData to 14 Oct 2026

Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Control

arXiv 2507.15174 ↗First posted 21 Jul 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Traffic Signal Control (TSC) is essential for managing urban traffic flow and reducing congestion. Reinforcement Learning (RL) offers an adaptive method for TSC by responding to dynamic traffic patterns, with multi-agent RL (MARL) gaining traction as intersections naturally function as coordinated agents. However, due to shifts in environmental dynamics, implementing MARL-based TSC policies in the real world often leads to a significant performance drop, known as the sim-to-real gap. Grounded Action Transformation (GAT) has successfully mitigated this gap in single-agent RL for TSC, but real-world traffic networks, which involve numerous interacting intersections, are better suited to a MARL framework. In this work, we introduce JL-GAT, an application of GAT to MARL-based TSC that balances scalability with enhanced grounding capability by incorporating information from neighboring agents. JL-GAT adopts a decentralized approach to GAT, allowing for the scalability often required in real-world traffic networks while still capturing key interactions between agents. Comprehensive experiments on various road networks under simulated adverse weather conditions, along with ablation studies, demonstrate the effectiveness of JL-GAT. The code is publicly available at https://github.com/DaRL-LibSignal/JL-GAT/.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 21 Jul 2025.

Builds on

26 of 46 references.

References · 26

  1. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  2. 2020A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challengescited by 819
  3. 2014Deep Domain Confusion: Maximizing for Domain Invariancecited by 600
  4. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 413
  5. 2014A Survey of Multi-Objective Sequential Decision-Makingcited by 242
  6. 2014Robots that can adapt like animalscited by 204
  7. 2018Sim-to-Real via Sim-to-Sim: Data-efficient Robotic Grasping via Randomized-to-Canonical Adaptation Networkscited by 174
  8. 2017Using Simulation and Domain Adaptation to Improve Efficiency of Deep Robotic Graspingcited by 144
  9. 2020Uncertainty Quantification and Deep Ensemblescited by 139
  10. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 115
  11. 2025Uncertainty Quantification and Confidence Calibration in Large Language Models: A Surveycited by 95
  12. 2019A Survey on Traffic Signal Control Methodscited by 79
14 more
  1. 2023Uncertainty Estimation by Fisher Information-based Evidential Deep Learningcited by 58
  2. 2025A Survey of Sim-to-Real Methods in RL: Progress, Prospects and Challenges with Foundation Modelscited by 38
  3. 2017Multi-Task Domain Adaptation for Deep Learning of Instance Grasping from Simulationcited by 36
  4. 2023Prompt to Transfer: Sim-to-Real Transfer for Traffic Signal Control with Prompt Learningcited by 36
  5. 2019Diagnosing Reinforcement Learning for Traffic Signal Controlcited by 33
  6. 2022Honor of Kings Arena: an Environment for Generalization in Competitive Reinforcement Learningcited by 28
  7. 2020Reinforced Grounded Action Transformation for Sim-to-Real Transfercited by 18
  8. 2020Stochastic Grounded Action Transformation for Robot Learning in Simulationcited by 16
  9. 2022LibSignal: An Open Library for Traffic Signal Controlcited by 16
  10. 2024X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learnercited by 10
  11. 2021Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Controlcited by 6
  12. 2024CityFlowER: An Efficient and Realistic Traffic Simulator with Embedded Machine Learning Modelscited by 4
  13. 2023Uncertainty-aware Grounded Action Transformation towards Sim-to-Real Transfer for Traffic Signal Controlcited by 3
  14. 2023Probabilistic Offline Policy Ranking with Approximate Bayesian Computationcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Toward Dependency Dynamics in Multi-Agent Reinforcement Learning for Traffic Signal Control
  2. 2026A Robust and Efficient Multi-Agent Reinforcement Learning Framework for Traffic Signal Control
  3. 2025Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse
  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. 2026Sim2Signal: Sim-to-Real Benchmarks for Traffic Signal Control
  7. 2025Convergence of Multiagent Learning Systems for Traffic control
  8. 2025Smart Traffic Signals: Comparing MARL and Fixed-Time Strategies