mlsanityData to 14 Oct 2026

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data

arXiv 2410.22938 ↗First posted 30 Oct 2024eess.SY cs.AI cs.LGcited by 4

On the map: Diffusion models → Diffusion and flow policies for robotics

also in 1 more
Abstract (arXiv)

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i.e., traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https://github.com/lokol5579/DiffLight-release.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Placed in Diffusion and flow policies for robotics, one of 14 directions in Diffusion models. Builds on 34 of its 48 references that are in the map. First posted on arXiv 30 Oct 2024.

Builds on

34 of 48 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Reasoning with Latent Diffusion in Offline Reinforcement Learning12 Sep
  2. 2023Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning29 May
  3. 2023MADiff: Offline Multi-agent Learning with Diffusion Models27 May
  4. 2022Is Conditional Generative Modeling all you need for Decision-Making?28 Nov
  5. 2022Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning12 Aug

Other references · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,863
  4. 2020Denoising Diffusion Implicit Modelscited by 9,781
  5. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,058
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,809
  9. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  10. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,061
  11. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 899
  12. 2021CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputationcited by 582
17 more
  1. 2016Recurrent Neural Networks for Multivariate Time Series with Missing Valuescited by 554
  2. 2018Behavioral Cloning from Observationcited by 492
  3. 2018BRITS: Bidirectional Recurrent Imputation for Time Seriescited by 290
  4. 2019CoLight: Learning Network-level Cooperation for Traffic Signal Controlcited by 138
  5. 2023PDFormer: Propagation Delay-Aware Dynamic Long-Range Transformer for Traffic Flow Predictioncited by 137
  6. 2019CityFlow: A Multi-Agent Reinforcement Learning Environment for Large Scale City Traffic Scenariocited by 115
  7. 2023Compositional 3D Scene Generation using Locally Conditioned Diffusioncited by 101
  8. 2019Learning Phase Competition for Traffic Signal Controlcited by 87
  9. 2017Estimating Missing Data in Temporal Data Streams Using Multi-directional Recurrent Neural Networkscited by 86
  10. 2023PriSTI: A Conditional Diffusion Framework for Spatiotemporal Imputationcited by 66
  11. 2020AttendLight: Universal Attention-Based Reinforcement Learning Model for Traffic Signal Controlcited by 62
  12. 2021Expression might be enough: representing pressure and demand for reinforcement learning based traffic signal controlcited by 29
  13. 2021Efficient Pressure: Improving efficiency for signalized intersectionscited by 24
  14. 2022Adaptive Graph Spatial-Temporal Transformer Network for Traffic Flow Forecastingcited by 17
  15. 2024A Survey of Generative Techniques for Spatial-Temporal Data Miningcited by 14
  16. 2023Reinforcement Learning Approaches for Traffic Signal Control under Missing Datacited by 13
  17. 2024Move Anything with Layered Scene Diffusioncited by 12

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 3.

4 papers.

  1. 2025Unraveling Spatio-Temporal Foundation Models via the Pipeline Lens: A Comprehensive Reviewcited by 10
  2. 2025VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecturecited by 3
  3. 2025Incomplete Data, Complete Dynamics: A Diffusion Approachcited by 3
  4. 2024A Survey and Benchmarking of Spatial-Temporal Traffic Data Imputation Modelscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023A Fully Data-Driven Approach for Realistic Traffic Signal Control Using Offline Reinforcement Learning
  2. 2024MoveLight: Enhancing Traffic Signal Control through Movement-Centric Deep Reinforcement Learning
  3. 2024Reinforcement Learning for Adaptive Traffic Signal Control: Turn-Based and Time-Based Approaches to Reduce Congestion
  4. 2023Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach
  5. 2025Robust Single-Agent Reinforcement Learning for Regional Traffic Signal Control Under Demand Fluctuations
  6. 2024X-Light: Cross-City Traffic Signal Control Using Transformer on Transformer as Meta Multi-Agent Reinforcement Learner
  7. 2025Enhancing Traffic Signal Control through Model-based Reinforcement Learning and Policy Reuse
  8. 2024MTLight: Efficient Multi-Task Reinforcement Learning for Traffic Signal Control