Enregistré dans:
Détails bibliographiques
Auteurs principaux: Yue, Xinlang, Liu, Yiran, Shi, Fangzhou, Luo, Sihong, Zhong, Chen, Lu, Min, Xu, Zhe
Format: Preprint
Publié: 2024
Sujets:
Accès en ligne:https://arxiv.org/abs/2408.10479
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866914917640044544
author Yue, Xinlang
Liu, Yiran
Shi, Fangzhou
Luo, Sihong
Zhong, Chen
Lu, Min
Xu, Zhe
author_facet Yue, Xinlang
Liu, Yiran
Shi, Fangzhou
Luo, Sihong
Zhong, Chen
Lu, Min
Xu, Zhe
contents Assigning orders to drivers under localized spatiotemporal context (micro-view order-dispatching) is a major task in Didi, as it influences ride-hailing service experience. Existing industrial solutions mainly follow a two-stage pattern that incorporate heuristic or learning-based algorithms with naive combinatorial methods, tackling the uncertainty of both sides' behaviors, including emerging timings, spatial relationships, and travel duration, etc. In this paper, we propose a one-stage end-to-end reinforcement learning based order-dispatching approach that solves behavior prediction and combinatorial optimization uniformly in a sequential decision-making manner. Specifically, we employ a two-layer Markov Decision Process framework to model this problem, and present \underline{D}eep \underline{D}ouble \underline{S}calable \underline{N}etwork (D2SN), an encoder-decoder structure network to generate order-driver assignments directly and stop assignments accordingly. Besides, by leveraging contextual dynamics, our approach can adapt to the behavioral patterns for better performance. Extensive experiments on Didi's real-world benchmarks justify that the proposed approach significantly outperforms competitive baselines in optimizing matching efficiency and user experience tasks. In addition, we evaluate the deployment outline and discuss the gains and experiences obtained during the deployment tests from the view of large-scale engineering implementation.
format Preprint
id arxiv_https___arxiv_org_abs_2408_10479
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing
Yue, Xinlang
Liu, Yiran
Shi, Fangzhou
Luo, Sihong
Zhong, Chen
Lu, Min
Xu, Zhe
Machine Learning
Artificial Intelligence
Assigning orders to drivers under localized spatiotemporal context (micro-view order-dispatching) is a major task in Didi, as it influences ride-hailing service experience. Existing industrial solutions mainly follow a two-stage pattern that incorporate heuristic or learning-based algorithms with naive combinatorial methods, tackling the uncertainty of both sides' behaviors, including emerging timings, spatial relationships, and travel duration, etc. In this paper, we propose a one-stage end-to-end reinforcement learning based order-dispatching approach that solves behavior prediction and combinatorial optimization uniformly in a sequential decision-making manner. Specifically, we employ a two-layer Markov Decision Process framework to model this problem, and present \underline{D}eep \underline{D}ouble \underline{S}calable \underline{N}etwork (D2SN), an encoder-decoder structure network to generate order-driver assignments directly and stop assignments accordingly. Besides, by leveraging contextual dynamics, our approach can adapt to the behavioral patterns for better performance. Extensive experiments on Didi's real-world benchmarks justify that the proposed approach significantly outperforms competitive baselines in optimizing matching efficiency and user experience tasks. In addition, we evaluate the deployment outline and discuss the gains and experiences obtained during the deployment tests from the view of large-scale engineering implementation.
title An End-to-End Reinforcement Learning Based Approach for Micro-View Order-Dispatching in Ride-Hailing
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2408.10479