# GARLIC: GPT-Augmented Reinforcement Learning with Intelligent Control for Vehicle Dispatching

arXiv: https://arxiv.org/abs/2408.10286 · HTML: https://mlsanity.com/paper/2408.10286/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 49 references that are in the map.
- First posted on arXiv 19 Aug 2024.

## Builds on (most cited first, 15 of 15)

- [Conservative Q-Learning for Offline Reinforcement Learning](https://mlsanity.com/paper/2006.04779/) (2020)
- [Decision Transformer: Reinforcement Learning via Sequence Modeling](https://mlsanity.com/paper/2106.01345/) (2021)
- [A Minimalist Approach to Offline Reinforcement Learning](https://mlsanity.com/paper/2106.06860/) (2021)
- [Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL](https://mlsanity.com/paper/2209.03993/) (2022)
- [Reinforcement Learning for Ridesharing: An Extended Survey](https://mlsanity.com/paper/2105.01099/) (2021)
- [Semi-Supervised Offline Reinforcement Learning with Action-Free Trajectories](https://mlsanity.com/paper/2210.06518/) (2022)
- [MLPST: MLP is All You Need for Spatio-Temporal Prediction](https://mlsanity.com/paper/2309.13363/) (2023)
- [UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction](https://mlsanity.com/paper/2306.11443/) (2023)
- [PromptST: Prompt-Enhanced Spatio-Temporal Multi-Attribute Prediction](https://mlsanity.com/paper/2309.09500/) (2023)
- [A Survey on Machine Learning-based Misbehavior Detection Systems for 5G and Beyond Vehicular Networks](https://mlsanity.com/paper/2201.10500/) (2022)
- [Rethinking Sensors Modeling: Hierarchical Information Enhanced Traffic Forecasting](https://mlsanity.com/paper/2309.11284/) (2023)
- [Autonomous Vehicles in 5G and Beyond: A Survey](https://mlsanity.com/paper/2207.10510/) (2022)
- [Real-Time Dispatching of Large-Scale Ride-Sharing Systems: Integrating Optimization, Machine Learning, and Model Predictive Control](https://mlsanity.com/paper/2003.10942/) (2020)
- [i-Rebalance: Personalized Vehicle Repositioning for Supply Demand Balance](https://mlsanity.com/paper/2401.04429/) (2024)
- [Optimizing V2V Unicast Communication Transmission with Reinforcement Learning and Vehicle Clustering](https://mlsanity.com/paper/2309.12052/) (2023)

## Built on by (most cited first, 5 of 5)

- [Swarm Intelligence in Geo-Localization: A Multi-Agent Large Vision-Language Model Collaborative Framework](https://mlsanity.com/paper/2408.11312/) (2024)
- [Large Language Model Powered Intelligent Urban Agents: Concepts, Capabilities, and Applications](https://mlsanity.com/paper/2507.00914/) (2025)
- [LLM-ODDR: A Large Language Model Framework for Joint Order Dispatching and Driver Repositioning](https://mlsanity.com/paper/2505.22695/) (2025)
- [Multimodal Trajectory Representation Learning for Travel Time Estimation](https://mlsanity.com/paper/2510.05840/) (2025)
- [MobiWave: Dispatch-Oriented Graph Wavelets and Drift-Guided Selective Optimization for Autonomous Fleet Rebalancing](https://mlsanity.com/paper/2607.24365/) (2026)

## Abstract (arXiv)

As urban residents demand higher travel quality, vehicle dispatch has become a critical component of online ride-hailing services. However, current vehicle dispatch systems struggle to navigate the complexities of urban traffic dynamics, including unpredictable traffic conditions, diverse driver behaviors, and fluctuating supply and demand patterns. These challenges have resulted in travel difficulties for passengers in certain areas, while many drivers in other areas are unable to secure orders, leading to a decline in the overall quality of urban transportation services. To address these issues, this paper introduces GARLIC: a framework of GPT-Augmented Reinforcement Learning with Intelligent Control for vehicle dispatching. GARLIC utilizes multiview graphs to capture hierarchical traffic states, and learns a dynamic reward function that accounts for individual driving behaviors. The framework further integrates a GPT model trained with a custom loss function to enable high-precision predictions and optimize dispatching policies in real-world scenarios. Experiments conducted on two real-world datasets demonstrate that GARLIC effectively aligns with driver behaviors while reducing the empty load rate of vehicles.