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

TL;DR

GARLIC is a novel framework combining GPT and reinforcement learning to improve vehicle dispatching by modeling traffic dynamics and driver behaviors, leading to more efficient ride-hailing services.

Contribution

It introduces a GPT-augmented reinforcement learning framework with hierarchical traffic modeling and dynamic reward functions for urban vehicle dispatching.

Findings

Reduces vehicle empty load rate in real-world datasets

Aligns dispatching with driver behaviors effectively

Enhances ride-hailing service quality

Abstract

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.