Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning

TL;DR

This paper introduces a deep reinforcement learning approach using graph neural networks to automatically learn effective priority dispatching rules for job shop scheduling, demonstrating strong generalization and performance on large, unseen instances.

Contribution

It presents a novel end-to-end deep reinforcement learning framework with graph neural networks for automatic PDR learning, improving scalability and performance over traditional methods.

Findings

Learned policies outperform existing PDRs.

Effective on large, unseen instances.

Size-agnostic policy generalization.

Abstract

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.