mlsanityData to 7 Oct 2026

The Real Deal: A Review of Challenges and Opportunities in Moving Reinforcement Learning-Based Traffic Signal Control Systems Towards Reality

arXiv 2206.11996 ↗First posted 23 Jun 2022cs.AI cs.LG cs.SYcited by 8

Not on the map. Why?

Abstract (arXiv)

Traffic signal control (TSC) is a high-stakes domain that is growing in importance as traffic volume grows globally. An increasing number of works are applying reinforcement learning (RL) to TSC; RL can draw on an abundance of traffic data to improve signalling efficiency. However, RL-based signal controllers have never been deployed. In this work, we provide the first review of challenges that must be addressed before RL can be deployed for TSC. We focus on four challenges involving (1) uncertainty in detection, (2) reliability of communications, (3) compliance and interpretability, and (4) heterogeneous road users. We show that the literature on RL-based TSC has made some progress towards addressing each challenge. However, more work should take a systems thinking approach that considers the impacts of other pipeline components on RL.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 140 references that are in the map. First posted on arXiv 23 Jun 2022.

Builds on

34 of 140 references.

References · 34

  1. 2017Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real Worldcited by 1,401
  2. 2020Deep Reinforcement Learning for Autonomous Driving: A Surveycited by 698
  3. 2018Learning Dexterous In-Hand Manipulationcited by 643
  4. 2019Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithmscited by 555
  5. 2020Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Surveycited by 388
  6. 2021Safe Learning in Robotics: From Learning-Based Control to Safe Reinforcement Learningcited by 337
  7. 2018Reinforcement Learning for Solving the Vehicle Routing Problemcited by 327
  8. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  9. 2019Reinforcement Learning in Healthcare: A Surveycited by 308
  10. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 159
  11. 2020SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learningcited by 150
  12. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
22 more
  1. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 114
  2. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 94
  3. 2019Learning Phase Competition for Traffic Signal Controlcited by 84
  4. 2019A Survey on Traffic Signal Control Methodscited by 78
  5. 2022Constrained Variational Policy Optimization for Safe Reinforcement Learningcited by 69
  6. 2021Collaboration Challenges in Building ML-Enabled Systems: Communication, Documentation, Engineering, and Processcited by 56
  7. 2018Deep Reinforcement Learning for Traffic Light Control in Vehicular Networkscited by 51
  8. 2019Value constrained model-free continuous controlcited by 34
  9. 2017Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learningcited by 33
  10. 2019Diagnosing Reinforcement Learning for Traffic Signal Controlcited by 33
  11. 2016Using a Deep Reinforcement Learning Agent for Traffic Signal Controlcited by 26
  12. 2019Learning an Interpretable Traffic Signal Control Policycited by 20
  13. 2021Network-wide traffic signal control optimization using a multi-agent deep reinforcement learningcited by 12
  14. 2021CVLight: Decentralized Learning for Adaptive Traffic Signal Control with Connected Vehiclescited by 11
  15. 2022Multi-Agent Reinforcement Learning for Traffic Signal Control through Universal Communication Methodcited by 10
  16. 2021A Decentralized Reinforcement Learning Framework for Efficient Passage of Emergency Vehiclescited by 8
  17. 2017Intelligent Traffic Light Control Using Distributed Multi-agent Q Learningcited by 7
  18. 2019A Reinforcement Learning Approach for Intelligent Traffic Signal Control at Urban Intersectionscited by 6
  19. 2020Quantifying the Impact of Non-Stationarity in Reinforcement Learning-Based Traffic Signal Controlcited by 6
  20. 2021Towards Real-World Deployment of Reinforcement Learning for Traffic Signal Controlcited by 6
  21. 2019Towards Robust Deep Reinforcement Learning for Traffic Signal Control: Demand Surges, Incidents and Sensor Failurescited by 5
  22. 2019AI for Social Impact: Learning and Planning in the Data-to-Deployment Pipelinecited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 2; 2026: 2.

8 papers.

  1. 2025Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systemscited by 12
  2. 2024OffLight: An Offline Multi-Agent Reinforcement Learning Framework for Traffic Signal Controlcited by 3
  3. 2023Bridging the Reality Gap of Reinforcement Learning based Traffic Signal Control using Domain Randomization and Meta Learningcited by 2
  4. 2024PyTSC: A Unified Platform for Multi-Agent Reinforcement Learning in Traffic Signal Controlcited by 1
  5. 2024An Offline Meta Black-box Optimization Framework for Adaptive Design of Urban Traffic Light Management Systemscited by 0
  6. 2025Robustness of Reinforcement Learning-Based Traffic Signal Control under Incidents: A Comparative Studycited by 0
  7. 2026Active Inference for Adaptive Traffic Signal Control in Noisy Nonstationary IoT Environmentscited by 0
  8. 2026EvoSignal: LLM-Guided Evolutionary Design of Modular Traffic Signal Control Programscited by 0