東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

FindBook

Google Book

Amazon

博客來

Multiagent Modeling of Delivery Trucks Logistics.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Multiagent Modeling of Delivery Trucks Logistics./
作者:	Tushmanluei, Atefeh Morsali.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2021,
面頁冊數:	135 p.
附註:	Source: Dissertations Abstracts International, Volume: 83-05, Section: A.
Contained By:	Dissertations Abstracts International83-05A.
標題:	Scheduling. -
電子資源:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28747762
ISBN:	9798494446978

Multiagent Modeling of Delivery Trucks Logistics.
Tushmanluei, Atefeh Morsali.

Multiagent Modeling of Delivery Trucks Logistics. - Ann Arbor : ProQuest Dissertations & Theses, 2021 - 135 p.

Source: Dissertations Abstracts International, Volume: 83-05, Section: A.

Thesis (Ph.D.)--North Carolina State University, 2021.

This item must not be sold to any third party vendors.

Technological trends have the potential to derive machine intelligence to perform immediate decision-making at all times with no human interference. This research studies such autonomy in the freight transportation domain. We propose a multi-agent learning framework and use reinforcement learning techniques to model delivery trucks logistics. That is, each truck itself is empowered with computational intelligence to self-determine its itinerary and reschedule it in real time to handle revealed, stochastic customer requests. In our proposed self-organizing setting, truck agents learn joint bidding and routing strategies (JBR) to maximize their expected profit and minimize service delays. Hence, truck agents - interacting on an online platform - autonomously place bids on customer requests considering their itinerary, customer profile, service constraints, and future dynamics; this enables them to perform in-situation bidding and routing decisions without intervention, oversight, or control by humans as well as other truck agents. We also present a relational module which takes advantage of flexible statistical learning and advanced structured approaches to learn informative representations from agents' itinerary and observations. The relational module employs deep neural networks and applies an iterative message passing procedure to exploit and discover informative representations. In addition, the customized reward function developed in this study, which helps ensure realistic operation of the trucks and allows various behavioral patterns - cooperative and/or selfish - to emerge among the agents. However, despite the potential for competition between agents, it merely affects their profitability and forces them to adjust their strategies. We conduct comprehensive experiments and evaluate our proposed framework in a simulation environment and compare with other competing methods in the literatures. Our experiment results show significant improvement in agents' performance and decision making. In addition, our model offers advantages in efficiency and generalization to unseen dynamics.

ISBN: 9798494446978Subjects--Topical Terms:

750729
Scheduling.

Multiagent Modeling of Delivery Trucks Logistics.
LDR:03208nmm a2200361 4500 001 2342421
005 20220318093140.5
008 241004s2021 ||||||||||||||||| ||eng d
020 $a 9798494446978
035 $a (MiAaPQ)AAI28747762
035 $a (MiAaPQ)NCState_Univ18402038917
035 $a AAI28747762
040 $a MiAaPQ $c MiAaPQ
100 1 $a Tushmanluei, Atefeh Morsali. $3 3680793
245 1 0 $a Multiagent Modeling of Delivery Trucks Logistics.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2021
300 $a 135 p.
500 $a Source: Dissertations Abstracts International, Volume: 83-05, Section: A.
500 $a Advisor: List, George.
502 $a Thesis (Ph.D.)--North Carolina State University, 2021.
506 $a This item must not be sold to any third party vendors.
520 $a Technological trends have the potential to derive machine intelligence to perform immediate decision-making at all times with no human interference. This research studies such autonomy in the freight transportation domain. We propose a multi-agent learning framework and use reinforcement learning techniques to model delivery trucks logistics. That is, each truck itself is empowered with computational intelligence to self-determine its itinerary and reschedule it in real time to handle revealed, stochastic customer requests. In our proposed self-organizing setting, truck agents learn joint bidding and routing strategies (JBR) to maximize their expected profit and minimize service delays. Hence, truck agents - interacting on an online platform - autonomously place bids on customer requests considering their itinerary, customer profile, service constraints, and future dynamics; this enables them to perform in-situation bidding and routing decisions without intervention, oversight, or control by humans as well as other truck agents. We also present a relational module which takes advantage of flexible statistical learning and advanced structured approaches to learn informative representations from agents' itinerary and observations. The relational module employs deep neural networks and applies an iterative message passing procedure to exploit and discover informative representations. In addition, the customized reward function developed in this study, which helps ensure realistic operation of the trucks and allows various behavioral patterns - cooperative and/or selfish - to emerge among the agents. However, despite the potential for competition between agents, it merely affects their profitability and forces them to adjust their strategies. We conduct comprehensive experiments and evaluate our proposed framework in a simulation environment and compare with other competing methods in the literatures. Our experiment results show significant improvement in agents' performance and decision making. In addition, our model offers advantages in efficiency and generalization to unseen dynamics.
590 $a School code: 0155.
650 4 $a Scheduling. $3 750729
650 4 $a Monte Carlo simulation. $3 3564916
650 4 $a Integer programming. $3 648270
650 4 $a Dynamic programming. $3 641303
650 4 $a Planning. $3 552734
650 4 $a Optimization. $3 891104
650 4 $a Decision making. $3 517204
650 4 $a Trucks. $3 573590
650 4 $a Probability. $3 518898
650 4 $a Prices. $3 652651
650 4 $a Travel. $3 585743
650 4 $a Linear programming. $3 560448
650 4 $a Algorithms. $3 536374
650 4 $a Bids. $3 3561817
650 4 $a Markov analysis. $3 3562906
650 4 $a Vehicles. $3 2145288
650 4 $a Computer science. $3 523869
650 4 $a Mathematics. $3 515831
650 4 $a Operations research. $3 547123
650 4 $a Recreation. $3 535376
650 4 $a Statistics. $3 517247
650 4 $a Transportation. $3 555912
690 $a 0984
690 $a 0405
690 $a 0796
690 $a 0814
690 $a 0463
690 $a 0709
710 2 $a North Carolina State University. $3 1018772
773 0 $t Dissertations Abstracts International $g 83-05A.
790 $a 0155
791 $a Ph.D.
792 $a 2021
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28747762