论文标题
学习通过深入的强化学习来派遣车间安排
Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
论文作者
论文摘要
优先派遣规则（PDR）广泛用于解决现实世界的工作店调度问题（JSSP）。但是，有效PDR的设计是一项繁琐的任务，需要无数的专业知识，并且经常提供有限的性能。在本文中，我们建议通过端到端的深度加固学习代理自动学习PDR。我们利用JSSP的分离图表示，并提出了一个基于图神经网络的方案，以嵌入求解过程中遇到的状态。由此产生的策略网络是尺寸不足的，有效地在大规模实例上概括了。实验表明，代理可以通过基本原始特征从头开始学习高质量的PDR，并在最佳现有PDR上展示了强劲的性能。学识渊博的政策在培训中看不见的更大实例上也表现出色。
Priority dispatching rule (PDR) is widely used for solving real-world Job-shop scheduling problem (JSSP). However, the design of effective PDRs is a tedious task, requiring a myriad of specialized knowledge and often delivering limited performance. In this paper, we propose to automatically learn PDRs via an end-to-end deep reinforcement learning agent. We exploit the disjunctive graph representation of JSSP, and propose a Graph Neural Network based scheme to embed the states encountered during solving. The resulting policy network is size-agnostic, effectively enabling generalization on large-scale instances. Experiments show that the agent can learn high-quality PDRs from scratch with elementary raw features, and demonstrates strong performance against the best existing PDRs. The learned policies also perform well on much larger instances that are unseen in training.
