文章快速检索 高级检索

1. 北京化工大学 经济管理学院, 北京 100029;
2. 北京化工大学 理学院, 北京 100029

Game analysis of hazardous chemicals transport route selection based on reinforcement learning-model
WU Jun1, WANG Dan1, LI Jian1, YANG Feng-mei2
1. School of Economics and Management, Beijing University of Chemical Technology, Beijing 100029, China;
2. School of Science, Beijing University of Chemical Technology, Beijing 100029, China
Abstract:Many hazardous chemicals transportation accidents occur in China in recent years. One of the reasons is that the transport company often ignores the transportation safety when transporting the hazardous chemicals. In order to improve the transportation safety, one of the effective policies for the government is to set the tax policy for the different routes. In this paper, the model of hazardous chemicals transport route selection with tax policy is established. Reinforcement learning is introduced into this paper to model the behavior of transport company. The simulation example illustrated that the transport company is willing to choose the road with tax policy, which reduces the risk of hazardous chemicals transport.
Key words: hazardous chemicals     tax policy     reinforcement learning     evolutionary game     route selection

0 引言

 [1] Frieze M, Galbiati G, Maffioli F. On the worst-case performance of some algorithms for the asymmetric traveling salesman problem[J]. Networks, 1982, 12(1): 23-39. [2] Bläser M. A new approximation algorithm for the asymmetric TSP with triangle inequality[C]// Proceedings of the 14th annual ACM-SIAM symposium on discrete algorithms. PA, USA: Society for Industrial and Applied Mathematics Philadelphia, 2003: 638-645. [3] Kaplan H, Lewenstein M, Shafrir N, et al. Approximation algorithms for asymmetric TSP by decomposing directed regular multigraphs[C]// Proceedings of the 44th Annual IEEE Symposium on Foundations of Computer Science. Washington, DC, USA: IEEE Computer Society, 2003: 56. [4] Ausiello G, Feuerstein E, Leonardi S, et al. Algorithms for the on-line travelling salesman[J]. Algorithmica, 2001, 29(4): 560-581. [5] Lipmann M. The online traveling salesman problem on the line[D]. Amsterdam, Netherlands: University of Amsterdam, 1999. [6] Blom M, Krumke S O, De-Paepe W E, et al. The online-TSP against fair adversaries[J]. Informs Journal on Computing, 2001, 13(2): 138-148. [7] Jaillet P, Wagner M. Generalized online routing: New competitive ratios, resource augmentation and asymptotic analyses[J]. Operations Research, 2008, 56(3): 745-757. [8] Jaillet P, Wagner M. Online routing problems: Value of advanced information as improved competitive ratios[J]. Transportation Science, 2006, 40(2): 200-210. [9] Allulli L, Ausiello G, Bonifaci V, et al. On the power of lookahead in on-line server routing problems[J]. Theoretical Computer Science, 2008, 408(2): 116-128. [10] 温新刚,徐寅峰,丁黎黎. 基于预知信息的占线Nomadic TSP问题[J]. 系统工程理论与实践, 2013, 33(1): 1-7. Wen Xingang, Xu Yinfeng, Ding Lili. Online nomadic TSP based on the advanced information[J]. Systems Engineering —— Theory & Practice, 2013, 33(1): 1-7. [11] Wen X G, Xu Y F, Zhang H L. Online traveling salesman problem with deadline and advanced information[J]. Computers & Industrial Engineering, 2012, 63(4): 1048-1053. [12] Ausiello G, Bonifaci V, Laura L. The on-line asymmetric traveling salesman problem[J]. Journal of Discrete Algorithms, 2008, 6(2): 290-298. [13] Borodin A, El-Yaniv R. Online computation and competitive analysis[M]. Cambridge: Cambridge University Press, 1998.
0

#### 文章信息

WU Jun, WANG Dan, LI Jian, YANG Feng-mei

Game analysis of hazardous chemicals transport route selection based on reinforcement learning-model

Systems Engineering - Theory & practice, 2015, 35(2): 388-393.