mlsanityData to 7 Oct 2026

Can ChatGPT Enable ITS? The Case of Mixed Traffic Control via Reinforcement Learning

arXiv 2306.08094 ↗First posted 13 Jun 2023cs.AI cs.HC cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

The surge in Reinforcement Learning (RL) applications in Intelligent Transportation Systems (ITS) has contributed to its growth as well as highlighted key challenges. However, defining objectives of RL agents in traffic control and management tasks, as well as aligning policies with these goals through an effective formulation of Markov Decision Process (MDP), can be challenging and often require domain experts in both RL and ITS. Recent advancements in Large Language Models (LLMs) such as GPT-4 highlight their broad general knowledge, reasoning capabilities, and commonsense priors across various domains. In this work, we conduct a large-scale user study involving 70 participants to investigate whether novices can leverage ChatGPT to solve complex mixed traffic control problems. Three environments are tested, including ring road, bottleneck, and intersection. We find ChatGPT has mixed results. For intersection and bottleneck, ChatGPT increases number of successful policies by 150% and 136% compared to solely beginner capabilities, with some of them even outperforming experts. However, ChatGPT does not provide consistent improvements across all scenarios.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 23 of its 48 references that are in the map. First posted on arXiv 13 Jun 2023.

Builds on

23 of 48 references.

References · 23

  1. 2023GPT-4 Technical Reportcited by 18,132
  2. 2022Training language models to follow instructions with human feedbackcited by 15,712
  3. 2017Proximal Policy Optimization Algorithmscited by 14,441
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2022Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedbackcited by 3,634
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,579
  7. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  8. 2023Guiding Pretraining in Reinforcement Learning with Large Language Modelscited by 185
  9. 2023Foundation Models for Decision Making: Problems, Methods, and Opportunitiescited by 160
  10. 2022ChatGPT Makes Medicine Easy to Swallow: An Exploratory Case Study on Simplified Radiology Reportscited by 100
  11. 2020Deep Reinforcement Learning for Intelligent Transportation Systems: A Surveycited by 94
  12. 2023Do Embodied Agents Dream of Pixelated Sheep: Embodied Decision Making using Language Guided World Modellingcited by 88
11 more
  1. 2023Can an Embodied Agent Find Your "Cat-shaped Mug"? LLM-Guided Exploration for Zero-Shot Object Navigationcited by 74
  2. 2017Flow: A Modular Learning Framework for Mixed Autonomy Trafficcited by 67
  3. 2023Language Instructed Reinforcement Learning for Human-AI Coordinationcited by 61
  4. 2021Reinforcement Learning for Mixed Autonomy Intersectionscited by 14
  5. 2019ADAPS: Autonomous Driving Via Principled Simulationscited by 13
  6. 2021A Generic Graph Sparsification Framework using Deep Reinforcement Learningcited by 8
  7. 2020Predicting Station-Level Bike-Sharing Demands Using Graph Convolutional Neural Networkcited by 7
  8. 2021Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Modelscited by 6
  9. 2021Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learningcited by 4
  10. 2022AutoJoin: Efficient Adversarial Training against Gradient-Free Perturbations for Robust Maneuvering via Denoising Autoencoder and Joint Learningcited by 3
  11. 2023Efficient Quality-Diversity Optimization through Diverse Quality Speciescited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 3; 2024: 6; 2025: 8; 2026: 1.

18 papers.

Sort:

By area:

  1. 2023TrafficGPT: Viewing, Processing and Interacting with Traffic Foundation Modelscited by 45
  2. 2025Exploring the Roles of Large Language Models in Reshaping Transportation Systems: A Survey, Framework, and Roadmapcited by 26
  3. 2024Towards Urban General Intelligence: A Review and Outlook of Urban Foundation Modelscited by 23
  4. 2025Integrating LLMs with ITS: Recent Advances, Potentials, Challenges, and Future Directionscited by 23
  5. 2025Mixture-of-Personas Language Models for Population Simulationcited by 20
  6. 2024BIGCity: A Universal Spatiotemporal Model for Unified Trajectory and Traffic State Data Analysiscited by 16
  7. 2023EnduRL: Enhancing Safety, Stability, and Efficiency of Mixed Traffic Under Real-World Perturbations Via Reinforcement Learningcited by 7
  8. 2024CityGPT: Towards Urban IoT Learning, Analysis and Interaction with Multi-Agent Systemcited by 3
  9. 2024TrafficGPT: Towards Multi-Scale Traffic Analysis and Generation with Spatial-Temporal Agent Frameworkcited by 2
  10. 2025Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learningcited by 2
  11. 2024Exploring Transformer-Augmented LSTM for Temporal and Spatial Feature Learning in Trajectory Predictioncited by 1
  12. 2023Analyzing Behaviors of Mixed Traffic via Reinforcement Learning at Unsignalized Intersectionscited by 0
6 more
  1. 2024Neighbor-Aware Reinforcement Learning for Mixed Traffic Optimization in Large-scale Networkscited by 0
  2. 2025LDGNet: A Lightweight Difference Guiding Network for Remote Sensing Change Detectioncited by 0
  3. 2025GraphTrafficGPT: Enhancing Traffic Management Through Graph-Based AI Agent Coordinationcited by 0
  4. 2025Multi-Objective Reinforcement Learning for Large-Scale Mixed Traffic Controlcited by 0
  5. 2025Learning to Design City-scale Transit Routescited by 0
  6. 2026Large Language Models in Transportation Systems Management and Operations: From Text Reasoning to Multi-modal Decision Supportcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Traffic Performance GPT (TP-GPT): Real-Time Data Informed Intelligent ChatBot for Transportation Surveillance and Management
  2. 2025ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
  3. 2022Offline Reinforcement Learning for Road Traffic Control
  4. 2026LATS: Large Language Model Assisted Teacher-Student Framework for Multi-Agent Reinforcement Learning in Traffic Signal Control
  5. 2026OracleTSC: Oracle-Informed Reward Hurdle and Uncertainty Regularization for Traffic Signal Control
  6. 2023LLMLight: Large Language Models as Traffic Signal Control Agents
  7. 2025LLM-Guided Reinforcement Learning with Representative Agents for Traffic Modeling
  8. 2025Traffic-R1: Reinforced LLMs Bring Human-Like Reasoning to Traffic Signal Control Systems