mlsanityData to 7 Oct 2026

X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner

arXiv 2404.12090 ↗First posted 18 Apr 2024cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

The effectiveness of traffic light control has been significantly improved by current reinforcement learning-based approaches via better cooperation among multiple traffic lights. However, a persisting issue remains: how to obtain a multi-agent traffic signal control algorithm with remarkable transferability across diverse cities? In this paper, we propose a Transformer on Transformer (TonT) model for cross-city meta multi-agent traffic signal control, named as X-Light: We input the full Markov Decision Process trajectories, and the Lower Transformer aggregates the states, actions, rewards among the target intersection and its neighbors within a city, and the Upper Transformer learns the general decision trajectories across different cities. This dual-level approach bolsters the model's robust generalization and transferability. Notably, when directly transferring to unseen scenarios, ours surpasses all baseline methods with +7.91% on average, and even +16.3% in some cases, yielding the best results.

Key facts. Cited by 10 papers in the map (data through 7 Oct 2026). Builds on 25 of its 50 references that are in the map. First posted on arXiv 18 Apr 2024.

Builds on

25 of 50 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2021ViViT: A Video Vision Transformercited by 1,610
  6. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  7. 2021The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Gamescited by 903
  8. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  9. 2021Transformer in Transformercited by 632
  10. 2016RL2: Fast Reinforcement Learning via Slow Reinforcement Learningcited by 490
  11. 2019Multi-Agent Deep Reinforcement Learning for Large-scale Traffic Signal Controlcited by 159
  12. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 143
13 more
  1. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 133
  2. 2019Learning Phase Competition for Traffic Signal Controlcited by 84
  3. 2019Meta reinforcement learning as task inferencecited by 75
  4. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 60
  5. 2018Deep Reinforcement Learning for Traffic Light Control in Vehicular Networkscited by 51
  6. 2022Transformers are Meta-Reinforcement Learnerscited by 39
  7. 2022Cascade Transformers for End-to-End Person Searchcited by 31
  8. 2017Using Task Descriptions in Lifelong Machine Learning for Improved Performance and Zero-Shot Transfercited by 19
  9. 2020GeneraLight: Improving Environment Generalization of Traffic Signal Control via Meta Reinforcement Learningcited by 17
  10. 2021DualFormer: Local-Global Stratified Transformer for Efficient Video Recognitioncited by 11
  11. 2023DuaLight: Enhancing Traffic Signal Control by Leveraging Scenario-Specific and Scenario-Shared Knowledgecited by 9
  12. 2021MetaVIM: Meta Variationally Intrinsic Motivated Reinforcement Learning for Decentralized Traffic Signal Controlcited by 6
  13. 2023PDiT: Interleaving Perception and Decision-making Transformers for Deep Reinforcement Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 3; 2026: 3.

10 papers.

  1. 2024MalLight: Influence-Aware Coordinated Traffic Signal Control for Traffic Signal Malfunctionscited by 5
  2. 2024GuideLight: "Industrial Solution" Guidance for More Practical Traffic Signal Control Agentscited by 1
  3. 2025Unicorn: A Universal and Collaborative Reinforcement Learning Approach Towards Generalizable Network-Wide Traffic Signal Controlcited by 1
  4. 2026LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Controlcited by 1
  5. 2024Transformer-based Drum-level Prediction in a Boiler Plant with Delayed Relations among Multivariatescited by 0
  6. 2024Exploring Genre and Success Classification through Song Lyrics using DistilBERT: A Fun NLP Venturecited by 0
  7. 2025HALO: Hierarchical Reinforcement Learning for Large-Scale Adaptive Traffic Signal Controlcited by 0
  8. 2025Joint-Local Grounded Action Transformation for Sim-to-Real Transfer in Multi-Agent Traffic Controlcited by 0
  9. 2026Spatiotemporal Decision Transformer for Traffic Coordinationcited by 0
  10. 2026Emergency Preemption Without Online Exploration: A Decision Transformer Approachcited by 0