mlsanityData to 7 Oct 2026

Multi-intersection Traffic Optimisation: A Benchmark Dataset and a Strong Baseline

arXiv 2101.09640 ↗First posted 24 Jan 2021eess.SY cs.LG cs.SYcited by 4

Not on the map. Why?

Abstract (arXiv)

The control of traffic signals is fundamental and critical to alleviate traffic congestion in urban areas. However, it is challenging since traffic dynamics are complicated in real-world scenarios. Because of the high complexity of the optimisation problem for modelling the traffic, experimental settings of existing works are often inconsistent. Moreover, it is not trivial to control multiple intersections properly in real complex traffic scenarios due to its vast state and action space. Failing to take intersection topology relations into account also results in inferior solutions. To address these issues, in this work we carefully design our settings and propose a new dataset including both synthetic and real traffic data in more complex scenarios. Additionally, we propose a novel baseline model with strong performance. It is based on deep reinforcement learning with an encoder-decoder structure: an edge-weighted graph convolutional encoder to excavate multi-intersection relations; and an unified structure decoder to jointly model multiple junctions in a comprehensive manner, which significantly reduces the number of the model parameters. By doing so, the proposed model is able to effectively deal with the multi-intersection traffic optimisation problem. Models are trained/tested on both synthetic and real maps and traffic data with the Simulation of Urban Mobility (SUMO) simulator. Experimental results show that the proposed model surpasses multiple competitive methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 16 of its 31 references that are in the map. First posted on arXiv 24 Jan 2021.

Builds on

16 of 31 references.

References · 16

  1. 2017Proximal Policy Optimization Algorithmscited by 14,441
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  4. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,704
  5. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  6. 2015Prioritized Experience Replaycited by 1,070
  7. 2016Geometric deep learning: going beyond Euclidean datacited by 1,042
  8. 2017Emergence of Locomotion Behaviours in Rich Environmentscited by 159
  9. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 159
  10. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
  11. 2017Traffic Light Control Using Deep Policy-Gradient and Value-Function Based Reinforcement Learningcited by 33
  12. 2019Large-Scale Traffic Signal Control Using a Novel Multi-Agent Reinforcement Learningcited by 33
4 more
  1. 2016Using a Deep Reinforcement Learning Agent for Traffic Signal Controlcited by 26
  2. 2019A Reinforcement Learning Approach for Intelligent Traffic Signal Control at Urban Intersectionscited by 6
  3. 2018Deep Reinforcement Learning for Intelligent Transportation Systemscited by 2
  4. 2017Traffic Lights with Auction-Based Controllers: Algorithms and Real-World Datacited by 1

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1.

4 papers.

  1. 2023Fairness-enhancing deep learning for ride-hailing demand predictioncited by 9
  2. 2022Model-based graph reinforcement learning for inductive traffic signal controlcited by 5
  3. 2023Improving the generalizability and robustness of large-scale traffic signal controlcited by 5
  4. 2024Mitigating Metropolitan Carbon Emissions with Dynamic Eco-driving at Scalecited by 2