Value Function is All You Need: A Unified Learning Framework for Ride Hailing Platforms
| Autor: | Fan Zhang, Bingchen Song, Jieping Ye, Zhiwei Qin, Yongxin Tong, Xiaocheng Tang, Dingyuan Shi, Yansheng Wang, Hongtu Zhu |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
FOS: Computer and information sciences
Scheme (programming language) education.field_of_study Computer Science - Machine Learning Artificial neural network Computer science business.industry Computer Science - Artificial Intelligence media_common.quotation_subject Distributed computing Population Machine Learning (cs.LG) Artificial Intelligence (cs.AI) User experience design Robustness (computer science) Reinforcement learning Function (engineering) education business computer media_common computer.programming_language Fleet management |
| Zdroj: | KDD |
| Popis: | Large ride-hailing platforms, such as DiDi, Uber and Lyft, connect tens of thousands of vehicles in a city to millions of ride demands throughout the day, providing great promises for improving transportation efficiency through the tasks of order dispatching and vehicle repositioning. Existing studies, however, usually consider the two tasks in simplified settings that hardly address the complex interactions between the two, the real-time fluctuations between supply and demand, and the necessary coordinations due to the large-scale nature of the problem. In this paper we propose a unified value-based dynamic learning framework (V1D3) for tackling both tasks. At the center of the framework is a globally shared value function that is updated continuously using online experiences generated from real-time platform transactions. To improve the sample-efficiency and the robustness, we further propose a novel periodic ensemble method combining the fast online learning with a large-scale offline training scheme that leverages the abundant historical driver trajectory data. This allows the proposed framework to adapt quickly to the highly dynamic environment, to generalize robustly to recurrent patterns and to drive implicit coordinations among the population of managed vehicles. Extensive experiments based on real-world datasets show considerably improvements over other recently proposed methods on both tasks. Particularly, V1D3 outperforms the first prize winners of both dispatching and repositioning tracks in the KDD Cup 2020 RL competition, achieving state-of-the-art results on improving both total driver income and user experience related metrics. KDD 2021; Ride-hailing marketplace open simulation platform: https://outreach.didichuxing.com/Simulation/ |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|