Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
This addresses the tedious and knowledge-intensive task of creating scheduling rules for manufacturing and logistics, offering an automated solution with competitive results.
The paper tackles the problem of designing effective priority dispatching rules for job shop scheduling by proposing an end-to-end deep reinforcement learning agent that learns these rules from scratch, achieving strong performance against existing rules and generalizing well to larger unseen instances.
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.