arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2301.01913cs.AIcs.LG
收藏

在约束规划求解器内部学习通用的值选择启发式

Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver

Polytechnique Montréal(蒙特利尔理工学院);Ecole Polytechnique(巴黎综合理工学院)

Tom Marty, Tristan François, Pierre Tessier, Louis Gauthier, Louis-Martin Rousseau, Quentin Cappart

AI总结:

针对约束规划中通用值选择启发式稀缺的问题,提出结合深度 Q-learning、定制奖励与异构图神经网络的学习流程,在多类图问题上以较少回溯获得接近最优的解。

摘要:

约束规划被认为是求解组合问题的一种高效方法。求解器中的重要设计选择是分支启发式,其旨在以最少时间引导搜索找到最佳解。然而,开发这些启发式是一个耗时过程,需要针对具体问题的专业知识。这一观察推动了大量利用机器学习在无需专家干预的情况下自动学习高效启发式的努力。据我们所知,这仍是一个开放的研究问题。尽管文献中已有若干通用的变量选择启发式,但通用值选择启发式的选择更为稀缺。本文中,我们提出通过引入一种通用学习流程来解决该问题,该流程可用于在约束规划求解器内部获得值选择启发式。这一成果得益于深度 Q-learning 算法、定制奖励信号以及异构图神经网络架构的结合。在图着色、最大独立集和最大割问题上的实验表明,我们的框架能够在保持通用性的同时,无需大量回溯即可找到接近最优的更优解。

英文摘要:

Constraint programming is known for being an efficient approach for solving combinatorial problems. Important design choices in a solver are the branching heuristics, which are designed to lead the search to the best solutions in a minimum amount of time. However, developing these heuristics is a time-consuming process that requires problem-specific expertise. This observation has motivated many efforts to use machine learning to automatically learn efficient heuristics without expert intervention. To the best of our knowledge, it is still an open research question. Although several generic variable-selection heuristics are available in the literature, the options for a generic value-selection heuristic are more scarce. In this paper, we propose to tackle this issue by introducing a generic learning procedure that can be used to obtain a value-selection heuristic inside a constraint programming solver. This has been achieved thanks to the combination of a deep Q-learning algorithm, a tailored reward signal, and a heterogeneous graph neural network architecture. Experiments on graph coloring, maximum independent set, and maximum cut problems show that our framework is able to find better solutions close to optimality without requiring a large amounts of backtracks while being generic.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑