1,707 Hits in 8.5 sec

A Deep Value-network Based Approach for Multi-Driver Order Dispatching [article]

Xiaocheng Tang, Zhiwei Qin, Fan Zhang, Zhaodong Wang, Zhe Xu, Yintai Ma, Hongtu Zhu, Jieping Ye
2021 arXiv   pre-print
In this work, we propose a deep reinforcement learning based solution for order dispatching and we conduct large scale online A/B tests on DiDi's ride-dispatching platform to show that the proposed method  ...  Recent works on ride-sharing order dispatching have highlighted the importance of taking into account both the spatial and temporal dynamics in the dispatching process for improving the transportation  ...  To improve the sample complexity of reinforcement learning, a novel transfer learning method is also proposed for order dispatching to leverage knowledge transfer across multiple cities.  ... 
arXiv:2106.04493v1 fatcat:slzvx3ash5hhhj3wo7uf4ezy7a

Optimizing Online Matching for Ride-Sourcing Services with Multi-Agent Deep Reinforcement Learning [article]

Jintao Ke, Feng Xiao, Hai Yang, Jieping Ye
2019 arXiv   pre-print
Two reinforcement learning methods, spatio-temporal multi-agent deep Q learning (ST-M-DQN) and spatio-temporal multi-agent actor-critic (ST-M-A2C) are developed.  ...  Online matching between idle drivers and waiting passengers is one of the most key components in a ride-sourcing system.  ...  [10] combined a deep Q-network with transfer learning techniques in a large-scale online order dispatching system.  ... 
arXiv:1902.06228v1 fatcat:uwl2xwgeffcd5jwojjggm4yzim

Pattern Transfer Learning for Reinforcement Learning in Order Dispatching [article]

Runzhe Wan, Sheng Zhang, Chengchun Shi, Shikai Luo, Rui Song
2021 arXiv   pre-print
value-based reinforcement learning in the order dispatch problem.  ...  Order dispatch is one of the central problems to ride-sharing platforms. Recently, value-based reinforcement learning algorithms have shown promising performance on this problem.  ...  Acknowledgement We thank Didi Chuxing for sharing the datasets for public research.  ... 
arXiv:2105.13218v2 fatcat:ekwxo32ouzfc7koj6uxrm4xmee

Multi-Agent Reinforcement Learning for Order-dispatching via Order-Vehicle Distribution Matching

Ming Zhou, Jiarui Jin, Weinan Zhang, Zhiwei Qin, Yan Jiao, Chenxi Wang, Guobin Wu, Yong Yu, Jieping Ye
2019 Proceedings of the 28th ACM International Conference on Information and Knowledge Management - CIKM '19  
Improving the efficiency of dispatching orders to vehicles is a research hotspot in online ride-hailing systems.  ...  In this paper, we propose a decentralized execution order-dispatching method based on multi-agent reinforcement learning to address the large-scale order-dispatching problem.  ...  Another two related work using multi-agent to learn order-dispatching is based on mean-eld MARL [13] and knowledge transferring [35] . ere are some challenges to be solved when we apply the MARL to  ... 
doi:10.1145/3357384.3357799 dblp:conf/cikm/ZhouJZQJWWYY19 fatcat:2ylyniwu6jas7bdrwiva4umene

FlexPool: A Distributed Model-Free Deep Reinforcement Learning Algorithm for Joint Passengers Goods Transportation [article]

Kaushik Manchella and Abhishek K. Umrawal and Vaneet Aggarwal
2020 arXiv   pre-print
We propose FlexPool, a distributed model-free deep reinforcement learning algorithm that jointly serves passengers & goods workloads by learning optimal dispatch policies from its interaction with the  ...  On the other hand, ride-sharing has been on the rise with the success of ride-sharing platforms and increased research on using autonomous vehicle technologies for routing and matching.  ...  The authors would like to thank Intel for giving us access to the Intel DevCloud cluster for this project.  ... 
arXiv:2007.13699v2 fatcat:cjwo6gun4zbojfcjgggpevgsvu

Deep Reinforcement Learning for Demand Driven Services in Logistics and Transportation Systems: A Survey [article]

Zefang Zong, Tao Feng, Tong Xia, Depeng Jin, Yong Li
2022 arXiv   pre-print
Meanwhile, deep reinforcement learning (DRL) has been developed rapidly in recent years.  ...  serving orders within the constructed loops.  ...  To tackle such a problem, deep learning (DL) is introduced in RL to form deep reinforcement learning (DRL), which utilizes deep neural networks for function approximation in the traditional RL model and  ... 
arXiv:2108.04462v2 fatcat:y3ogh3v4rbhbjfoymql3yku4ty

Real-world Ride-hailing Vehicle Repositioning using Deep Reinforcement Learning [article]

Yan Jiao, Xiaocheng Tang, Zhiwei Qin, Shuaiji Li, Fan Zhang, Hongtu Zhu, Jieping Ye
2021 arXiv   pre-print
We present a new practical framework based on deep reinforcement learning and decision-time planning for real-world vehicle repositioning on ride-hailing (a type of mobility-on-demand, MoD) platforms.  ...  Our approach learns the spatiotemporal state-value function using a batch training algorithm with deep value networks.  ...  their support and efforts in product, platform, and operations for the experiment program of this research.  ... 
arXiv:2103.04555v3 fatcat:mrbw3736bvdqdhfxlxk3heyqim

A Spatiotemporal Thermo Guidance based Real-time Online Ride-hailing Dispatch Framework

Yuhan Guo, Yu Zhang, Junyu Yu, Xueli Shen
2020 IEEE Access  
INDEX TERMS Transportation, vehicle dispatching, online ride-hailing, spatiotemporal thermo, dynamic timeframe.  ...  In this paper, we propose a real-time service vehicle dispatching framework in the context of large-scale online ride-hailing, which considers all the main issues involved in the problem in a unified and  ...  For example, Lin et al. proposed a multi-agent reinforcement learning framework.  ... 
doi:10.1109/access.2020.3003942 fatcat:a3tgsgifojgstljiluuzfk25va

Guest Editorial: Introduction to the Special Section on Machine Learning-Based Internet of Vehicles: Theory, Methodology, and Applications

Jun Guo, Sunwoo Kim, Henk Wymeersch, Walid Saad, Wei Chen
2019 IEEE Transactions on Vehicular Technology  
Finally, in the work by Peng et al., "Decentralized Scheduling for Cooperative Localization With Deep Reinforcement Learning," reinforcement learning is applied for deciding when to perform measurements  ...  In the work by Yang et al., "Intelligent Resource Management Based on Efficient Transfer Actor-Critic Reinforcement Learning for IoV Communication Networks," they investigate the policy for jointly communication  ... 
doi:10.1109/tvt.2019.2914747 fatcat:rrpckr7cczfdzmqy7nkbcnsdua

Reinforcement Learning in the Wild: Scalable RL Dispatching Algorithm Deployed in Ridehailing Marketplace [article]

Soheil Sadeghi Eshkevari, Xiaocheng Tang, Zhiwei Qin, Jinhan Mei, Cheng Zhang, Qianying Meng, Jia Xu
2022 arXiv   pre-print
In this study, a real-time dispatching algorithm based on reinforcement learning is proposed and for the first time, is deployed in large scale.  ...  The present study proposes a standalone RL-based dispatching solution that is equipped with multiple mechanisms to ensure robust and efficient on-policy learning and inference while being adaptable for  ...  REINFORCEMENT LEARNING IN THE WILD When proposed mechanisms are combined, a full picture of the online reinforcement learning algorithm will be established.  ... 
arXiv:2202.05118v1 fatcat:az7cdp2ixbfatgq5wgofp5yriu

Table of Contents

2021 IEEE Transactions on Network Science and Engineering  
Chen 1862 Resource Allocation for Delay-Sensitive Vehicle-to-Multi-Edges (V2Es) Communications in Vehicular Networks: A Multi-Agent Deep Reinforcement Learning Approach . . . . . . . . . . . . . . . .  ...  Yu 1070 FedSteg: A Federated Transfer Learning Framework for Secure Image Steganalysis . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . .  ... 
doi:10.1109/tnse.2021.3063959 fatcat:gsx7gl6eezcjlauapp2gxpbp5u

Modeling and Optimization of Multiaction Dynamic Dispatching Problem for Shared Autonomous Electric Vehicles

Ning Wang, Jiahui Guo, Zhihong Yao
2021 Journal of Advanced Transportation  
the first model; (3) and integrating combinatorial optimization theory with reinforcement learning theory is a perfect package for solving the multiaction dynamic dispatching problem of SAEVs.  ...  After that, the Kuhn–Munkres algorithm is set as the baseline method to solve the first model to achieve optimal multiaction allocation instructions for SAEVs, and the combination of deep Q-learning algorithm  ...  In addition, part of the order and trajectory data used to train value function in the dispatching simulator of the case study were obtained from Didi Chuxing, which can be applied on the website https  ... 
doi:10.1155/2021/1368286 fatcat:4dw2u4fedfdjbkvkqnna2zbpvq

Reinforcement Learning in Practice: Opportunities and Challenges [article]

Yuxi Li
2022 arXiv   pre-print
In this article, we first give a brief introduction to reinforcement learning (RL), and its relationship with deep learning, machine learning and AI.  ...  This article is a gentle discussion about the field of reinforcement learning in practice, about opportunities and challenges, touching a broad range of topics, with perspectives and without technical  ...  Facebook/Meta has open-sourced ReAgent (Gauci et al., 2019) , an RL platform for products and services like notification delivery. 6 Didi has applied RL to ride sharing order dispatching (Qin et al.,  ... 
arXiv:2202.11296v2 fatcat:xdtsmme22rfpfn6rgfotcspnhy

A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation

Haitao Yuan, Guoliang Li
2021 Data Science and Engineering  
With the development of mobile Internet and position technologies, it is reasonable to collect spatio-temporal data and then leverage these data to achieve the goal of intelligent transportation, and here  ...  [191] address the order dispatching problem using multi-agent reinforcement learning (MARL), which follows the distributed nature of the peer-to-peer ride sharing problem and possesses the ability to  ...  -Travel demand prediction: Transportation companies provide online taxi service for users. They need to predict people's travel demands in order to better dispatch vehicles for different regions.  ... 
doi:10.1007/s41019-020-00151-z fatcat:nnnnxnpo3bgk3l4hpr7kk2n4xa

Autonomous Taxi Driving Environment Using Reinforcement Learning Algorithms

Showkat A. Dar, Department of Computer Science and Engineering, Annamalai University, India, S. Palanivel, M. Kalaiselvi Geetha
2022 International Journal of Modern Education and Computer Science  
RL (Reinforcement Learning) has evolved into a robust learning model which can learn about complications in high dimensional settings, owing to the advent of deep representation learning.  ...  For performing this task, RL methods like DQNs (Deep Q Networks), Q-LNs (Q-Learning networks) , SARSAs (state action reward state actions), and ConvDQNs (convolution DQNs) are proposed for driving Taxis  ...  To answer taxi dispatch problems, Mao et al [26] explored unique model free DRL DRL (Deep Reinforcement Learning) architecture.  ... 
doi:10.5815/ijmecs.2022.03.06 fatcat:sjbawudl5ncytkhhj3erbc6vuq
« Previous Showing results 1 — 15 out of 1,707 results