Learning to schedule job-shop problems: Representation and policy learning using graph neural network and reinforcement learning

TL;DR

This paper introduces a novel framework combining graph neural networks and reinforcement learning to effectively learn and generalize scheduling policies for job-shop scheduling problems, outperforming traditional methods.

Contribution

It presents a new end-to-end learning approach using GNNs and PPO to model and solve JSSPs, demonstrating superior generalization and transferability.

Findings

GNN scheduler outperforms traditional dispatching rules.

The framework generalizes to new JSSP instances without retraining.

The approach achieves better solutions on benchmark problems.

Abstract

We propose a framework to learn to schedule a job-shop problem (JSSP) using a graph neural network (GNN) and reinforcement learning (RL). We formulate the scheduling process of JSSP as a sequential decision-making problem with graph representation of the state to consider the structure of JSSP. In solving the formulated problem, the proposed framework employs a GNN to learn that node features that embed the spatial structure of the JSSP represented as a graph (representation learning) and derive the optimum scheduling policy that maps the embedded node features to the best scheduling action (policy learning). We employ Proximal Policy Optimization (PPO) based RL strategy to train these two modules in an end-to-end fashion. We empirically demonstrate that the GNN scheduler, due to its superb generalization capability, outperforms practically favored dispatching rules and RL-based schedulers on various benchmark JSSP. We also confirmed that the proposed framework learns a transferable scheduling policy that can be employed to schedule a completely new JSSP (in terms of size and parameters) without further training.