基于逆向强化学习的装船时堆场翻箱智能决策
CSTR:
作者:
作者单位:

武汉理工大学 交通与物流工程学院,湖北 武汉 430063

作者简介:

张艳伟(1977—),女,副教授,工学博士,主要研究方向为智慧港航、港口物流、智能决策与算法。 E-mail:zywtg@whut.edu.cn

中图分类号:

U695.22

基金项目:

国家自然科学基金(60904067)


An Inverse Reinforcement Learning Method for Container Relocation in Container Terminal Yard During Loading
Author:
Affiliation:

School of Transportation and Logistics Engineering, Wuhan University of Technology, Wuhan 430063, China

  • 摘要
  • | |
  • 访问统计
  • |
  • 参考文献 [25]
  • |
  • 相似文献 [14]
  • | | |
  • 文章评论
    摘要:

    集装箱码头装船时堆场翻箱具有时序性与动态性,属于NP(non?deterministic polynomial)难问题。针对常见的顺岸式集装箱码头堆场,以最小化总翻箱次数为优化目标,考虑翻箱对装船连续性及效率的影响,基于马尔科夫决策过程构建装船时堆场翻箱模型,设计逆向强化学习算法。为验证算法的有效性,以随机决策为基准,将设计的逆向强化学习算法与码头常见规则决策、随机决策对比。结果表明,贝位堆存状态不佳时,常见的规则决策不一定优于随机决策;逆向强化学习算法可有效挖掘隐含专家经验,收敛至最小翻箱次数的概率更高,且不同堆存状态下均能更好地限制单次发箱的翻箱次数,可实现装船时堆场翻箱智能决策。

    Abstract:

    The container relocation during loading in the terminal yard has sequential and dynamic characteristics, and belongs to the non-deterministic polynomial hard problem. This paper takes the common container terminal yard, which is parallel to the shoreline, as the research object. Considering the relocation effect on the continuity and efficiency of shipment, the model based on Markov decision processes for the container relocation in the yard during loading was proposed, with the optimization objective to minimize the total relocation times, and the algorithm based on inverse reinforcement learning was designed. To verify the effectiveness of the algorithm, taking the random decision as criterion, the inverse reinforcement learning algorithm was compared with the common rule decision-making and the random decision-making . The results show that when the initial state of the bay is unsatisfactory, the common rule decision-making is not necessarily superior to random decision-making. The inverse reinforcement learning algorithm can effectively mine and apply the expert experience, and the probability of converging to the minimum relocation times is obviously better than that of the others. In addition, it can better control the relocation times of a single loading in different state of the bay, and realize the intelligent decision-making of container relocation during loading.

    参考文献
    [1] 宓为建, 张晓华, 秦曌, 等. 集装箱码头装船贝内发箱顺序决策[J]. 中国工程机械学报, 2016, 14(4): 369.
    [2] 郑斯斯, 王爱虎. 路径优化算法求解集装箱码头堆场翻箱问题[J]. 工业工程与管理, 2017, 22(3): 31.
    [3] CASERTA M, SCHWARZE S, VO? S. A mathematical formulation and complexity considerations for the blocks relocation problem[J]. European Journal of Operational Research, 2012, 219(1): 96.
    [4] EXPóSITO-IZQUIERDO C, MELIáN-BATISTA B, MORENO-VEGA J M. An exact approach for the blocks relocation problem[J]. Expert Systems with Applications, 2015, 42(17/18): 6408.
    [5] ZEHENDNER E, CASERTA M, FEILLET D, et al. An improved mathematical formulation for the blocks relocation problem[J]. European Journal of Operational Research, 2015, 245(2): 415.
    [6] PETERING M E H, HUSSEIN M I. A new mixed integer program and extended look-ahead heuristic algorithm for the block relocation problem[J]. European Journal of Operational Research, 2013, 231(1): 120.
    [7] GALLE V, BARNHART C, JAILLET P. A new binary formulation of the restricted container relocation problem based on a binary encoding of configurations[J]. European Journal of Operational Research, 2018, 267(2): 467.
    [8] JIN B. On the integer programming formulation for the relaxed restricted container relocation problem[J]. European Journal of Operational Research, 2020, 281(2): 475.
    [9] TANAKA S, TAKII K. A faster branch-and-bound algorithm for the block relocation problem[J]. IEEE Transactions on Automation Science and Engineering, 2016, 13(1): 181.
    [10] TRICOIRE F, SCAGNETTI J, BEHAM A. New insights on the block relocation problem[J]. Computers and Operations Research, 2018, 89: 127.
    [11] FORSTER F, BORTFELDT A. A tree search procedure for the container relocation problem[J]. Computers and Operations Research, 2012, 39(2): 299.
    [12] TANAKA S, MIZUNO F. An exact algorithm for the unrestricted block relocation problem[J]. Computers and Operations Research, 2018, 95: 12.
    [13] TING C J, WU K C. Optimizing container relocation operations at container yards with beam search[J]. Transportation Research Part E: Logistics and Transportation Review, 2017, 103: 17.
    [14] BACCI T, MATTIA S, VENTURA P. The bounded beam search algorithm for the block relocation problem[J]. Computers and Operations Research, 2019, 103: 252.
    [15] FEILLET D, PARRAGH S N, TRICOIRE F. A local-search based heuristic for the unrestricted block relocation problem[J]. Computers and Operations Research, 2019, 108: 44.
    [16] BENGIO Y, LODI A, PROUVOST A. Machine learning for combinatorial optimization: a methodological tour d’horizon[J]. European Journal of Operational Research, 2021, 290(2): 405.
    [17] RUVOLO P, FASEL I, MOVELLAN J. Optimization on a budget: a reinforcement learning approach[C]//22nd Annual Conference on Neural Information Processing SystemsNIPS 2008.Vancouver:Currn Associates Inc, 2009: 1385–1392.
    [18] ZENG Y, XU K, YIN Q, et al. Inverse reinforcement learning based human behavior modeling for goal recognition in dynamic local network interdiction[J]. Indian Journal of Medical Research, 2016, 120(3): 151.
    [19] 陈希亮,曹雷,何明,等.深度逆向强化学习研究综述[J].计算机工程与应用, 2018, 54(5):24.
    [20] LIN J L, HWANG K S, SHI H, et al. An ensemble method for inverse reinforcement learning[J]. Information Sciences, 2020, 512: 518.
    [21] ABBEEL P, NG A Y. Apprenticeship learning via inverse reinforcement learning[C]//Proceedings, Twenty-First International Conference on Machine Learning,ICML 2004.Banff:Association for Computing Machinery, 2004: 1–8.
    [22] 杨放青,王超,姜滨,等.舰载机出动回收调度策略生成方法[J].北京理工大学学报, 2018, 38(10):1030.
    [23] KIM K H, HONG G P. A heuristic rule for relocating blocks[J]. Computers and Operations Research, 2006, 33(4): 940.
    [24] 徐亚,陈秋双,龙磊,等.集装箱倒箱问题的启发式算法研究[J].系统仿真学报, 2008, 20(14):3666.
    [25] 游鑫梦,梁承姬,张悦.进口集装箱堆存和翻箱策略两阶段规划模型[J].上海海事大学学报, 2020, 41(4): 1.
    引证文献
引用本文

张艳伟,蔡梦蝶.基于逆向强化学习的装船时堆场翻箱智能决策[J].同济大学学报(自然科学版),2021,49(10):1417~1425

复制
分享
文章指标
  • 点击次数:
  • 下载次数:
  • HTML阅读次数:
  • 引用次数:
历史
  • 收稿日期:2021-01-14
  • 在线发布日期: 2021-10-18
文章二维码