Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?

Zijian Zhao, Sen Li

Keywords: Reinforcement Learning, Order Dispatching, Ride Sharing

TL;DR: This paper proposes a novel centralized reinforcement learning framework for large-scale order dispatching tasks in ride-sharing scenarios, achieving better cooperation among workers compared to previous multi-agent methods.

Abstract: On-demand ride-sharing platforms, such as Uber and Lyft, face the intricate real-time challenge of bundling and matching passengers—each with distinct origins and destinations—to available vehicles, all while navigating significant system uncertainties. Due to the extensive observation space arising from the large number of drivers and orders, order dispatching, though fundamentally a centralized task, is often addressed using Multi-Agent Reinforcement Learning (MARL). However, independent MARL methods fail to capture global information and exhibit poor cooperation among workers, while Centralized Training Decentralized Execution (CTDE) MARL methods suffer from the curse of dimensionality. To overcome these challenges, we propose Triple-BERT, a centralized method designed specifically for large-scale order dispatching on ride-sharing platforms. Built on TD3, our approach addresses the vast action space through an action decomposition strategy that breaks down the joint action probability into individual driver action probabilities. To handle the extensive observation space, we introduce a novel BERT-based network, where parameter reuse mitigates parameter growth as the number of drivers and orders increases, and the attention mechanism effectively captures the complex relationships among the large pool of driver and orders. We validate our method using a real-world ride-hailing dataset from Manhattan. Triple-BERT achieves approximately an 11.95\% improvement over current state-of-the-art methods, with a 4.26\% increase in served orders and a 22.25\% reduction in pickup times. Our code, trained model parameters, and processed data are publicly available at the anonymous repository https://anonymous.4open.science/r/Triple-BERT .

Primary Area: Reinforcement learning (e.g., decision and control, planning, hierarchical RL, robotics)

Submission Number: 10344