arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.10026cs.LGstat.ML
收藏

分支定界算法中变量选择的强化学习

Reinforcement Learning for Variable Selection in a Branch and Bound Algorithm

EDF R&D(法国电力研发中心);CNAM Paris(巴黎国立工艺美术学院);ENSTA Paris(巴黎高等先进技术学院);Institut Polytechnique de Paris(巴黎理工学院)

Marc Etheve, Zacharie Alès, Côme Bissuel, Olivier Juan, Safia Kedad-Sidhoum

摘要:

混合整数线性规划问题通常采用分枝定界算法求解。最成功的商业求解器的效率的一个关键因素是它们的微调算法。在本文中,我们利用现实世界中的模式,从头开始学习一个新的分支策略,针对给定的问题进行优化,并将其与商业求解器进行比较。我们提出了FMSTS,一种新的强化学习方法,专门为这项任务而设计。我们的方法的优势在于局部价值函数和全局度量之间的一致性。此外,我们提供的见解适应已知的RL技术的分支和界限设置,并提出了一个新的神经网络架构的启发,从文献。据我们所知,这是第一次使用强化学习来完全优化分支策略。计算实验表明,我们的方法是适当的,能够很好地推广到新的情况。

英文摘要:

Mixed integer linear programs are commonly solved by Branch and Bound algorithms. A key factor of the efficiency of the most successful commercial solvers is their fine-tuned heuristics. In this paper, we leverage patterns in real-world instances to learn from scratch a new branching strategy optimised for a given problem and compare it with a commercial solver. We propose FMSTS, a novel Reinforcement Learning approach specifically designed for this task. The strength of our method lies in the consistency between a local value function and a global metric of interest. In addition, we provide insights for adapting known RL techniques to the Branch and Bound setting, and present a new neural network architecture inspired from the literature. To our knowledge, it is the first time Reinforcement Learning has been used to fully optimise the branching strategy. Computational experiments show that our method is appropriate and able to generalise well to new instances.

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。

↑