mlsanityData to 7 Oct 2026

ModelLight: Model-Based Meta-Reinforcement Learning for Traffic Signal Control

arXiv 2111.08067 ↗First posted 15 Nov 2021cs.LG eess.SPcited by 8

Not on the map. Why?

Abstract (arXiv)

Traffic signal control is of critical importance for the effective use of transportation infrastructures. The rapid increase of vehicle traffic and changes in traffic patterns make traffic signal control more and more challenging. Reinforcement Learning (RL)-based algorithms have demonstrated their potential in dealing with traffic signal control. However, most existing solutions require a large amount of training data, which is unacceptable for many real-world scenarios. This paper proposes a novel model-based meta-reinforcement learning framework (ModelLight) for traffic signal control. Within ModelLight, an ensemble of models for road intersections and the optimization-based meta-learning method are used to improve the data efficiency of an RL-based traffic light control method. Experiments on real-world datasets demonstrate that ModelLight can outperform state-of-the-art traffic light control algorithms while substantially reducing the number of required interactions with the real-world environment.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 18 of its 41 references that are in the map. First posted on arXiv 15 Nov 2021.

Builds on

18 of 41 references.

References · 18

  1. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  2. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 748
  3. 2019Model-Based Reinforcement Learning for Ataricited by 495
  4. 2017Neural Network Dynamics for Model-Based Deep Reinforcement Learning with Model-Free Fine-Tuningcited by 288
  5. 2018Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learningcited by 270
  6. 2018Model-Ensemble Trust-Region Policy Optimizationcited by 214
  7. 2019Benchmarking Model-Based Reinforcement Learningcited by 158
  8. 2018Algorithmic Framework for Model-based Deep Reinforcement Learning with Theoretical Guaranteescited by 138
  9. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
  10. 2018Model-Based Reinforcement Learning via Meta-Policy Optimizationcited by 99
  11. 2019Learning Phase Competition for Traffic Signal Controlcited by 84
  12. 2019Learning to Paint With Model-based Deep Reinforcement Learningcited by 70
6 more
  1. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 60
  2. 2019Low Level Control of a Quadrotor with Deep Model-Based Reinforcement Learningcited by 40
  3. 2019Diagnosing Reinforcement Learning for Traffic Signal Controlcited by 33
  4. 2019Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learningcited by 33
  5. 2020GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learningcited by 17
  6. 2016Path Integral Guided Policy Searchcited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 4; 2024: 2; 2025: 0; 2026: 1.

8 papers.

  1. 2023Reinforcement Learning Approaches for Traffic Signal Control under Missing Datacited by 13
  2. 2024Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory controlcited by 7
  3. 2022Time Series Anomaly Detection via Reinforcement Learning-Based Model Selectioncited by 4
  4. 2023Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approachcited by 3
  5. 2023Policy Reuse for Communication Load Balancing in Unseen Traffic Scenarioscited by 1
  6. 2023Communication Load Balancing via Efficient Inverse Reinforcement Learningcited by 0
  7. 2024MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Controlcited by 0
  8. 2026Few-Shot Learning for Dynamic Operations of Automated Electric Taxi Fleets under Evolving Charging Infrastructure: A Meta-Deep Reinforcement Learning Approachcited by 0