中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
HMDRL: Hierarchical Mixed Deep Reinforcement Learning to Balance Vehicle Supply and Demand

文献类型：期刊论文

作者Xi, Jinhao1,2; Zhu, Fenghua1,2; Ye, Peijun1,2; Lv, Yisheng1,2; Tang, Haina1; Wang, Fei-Yue1,2
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2022-07-25
页码12
关键词Reinforcement learning Pricing Heuristic algorithms Supply and demand Surges Vehicle dynamics Vehicles Deep reinforcement learning online ride-hailing system hierarchical repositioning framework parallel coordination mechanism mixed state
ISSN号1524-9050
DOI10.1109/TITS.2022.3191752
通讯作者Zhu, Fenghua(fenghua.zhu@ia.ac.cn) ; Ye, Peijun(peijun_ye@hotmail.com)
英文摘要The imbalance of vehicle supply and demand is a common phenomenon that influences the efficiency of online ride-hailing systems greatly. To address this problem, a three-level hierarchical mixed deep reinforcement learning method (HMDRL) is proposed to reposition idle vehicles. A manager operates at the top level, where action-abstraction is conducted from the time dimension and is adaptive for spatially scalable and time-varying systems. Coordinators locate at the middle level and a parallel coordination mechanism that is independent of the decision order is designed to improve the efficiency of the repositioning. The bottom level is composed of executive workers to reposition vehicles with mixed states and the states contain spatiotemporal information of agents' neighbor areas. Two reward functions are designed for the manager and the coordinators, respectively, aiming to improve the training effect by avoiding sparse rewards. A simulator based on real orders is designed and HMDRL is compared with six methods. Experimental results demonstrate that HMDRL outperforms all the other methods. In three comparison experiments, the order response rate is increased by 0.62% to 8.29%, 1.5% to 7.78%, 1.18% to 4.75%, respectively.
资助项目Key-Area Research and Development Program of Guangdong Province[2020B0909050001] ; National Natural Science Foundation of China (NSFC)[U1811463] ; National Natural Science Foundation of China (NSFC)[U1909204] ; National Natural Science Foundation of China (NSFC)[61876011] ; National Natural Science Foundation of China (NSFC)[52071312] ; Chinese Academy of Sciences (CAS) Science and Technology Service Network Plan (STS) Dongguan Project[20201600200132]
WOS研究方向Engineering ; Transportation
语种英语
WOS记录号WOS:000833052300001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构Key-Area Research and Development Program of Guangdong Province ; National Natural Science Foundation of China (NSFC) ; Chinese Academy of Sciences (CAS) Science and Technology Service Network Plan (STS) Dongguan Project
源URL[http://ir.ia.ac.cn/handle/173211/49761]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Zhu, Fenghua; Ye, Peijun
作者单位1.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 100049, Peoples R China
2.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Xi, Jinhao,Zhu, Fenghua,Ye, Peijun,et al. HMDRL: Hierarchical Mixed Deep Reinforcement Learning to Balance Vehicle Supply and Demand[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:12.
APA Xi, Jinhao,Zhu, Fenghua,Ye, Peijun,Lv, Yisheng,Tang, Haina,&Wang, Fei-Yue.(2022).HMDRL: Hierarchical Mixed Deep Reinforcement Learning to Balance Vehicle Supply and Demand.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,12.
MLA Xi, Jinhao,et al."HMDRL: Hierarchical Mixed Deep Reinforcement Learning to Balance Vehicle Supply and Demand".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):12.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。