# Learning-enabled Flexible Job-shop Scheduling for Scalable Smart Manufacturing

arXiv: https://arxiv.org/abs/2402.08979 · HTML: https://mlsanity.com/paper/2402.08979/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 32 references that are in the map.
- First posted on arXiv 14 Feb 2024.

## Builds on (most cited first, 7 of 7)

- [Instance Normalization: The Missing Ingredient for Fast Stylization](https://mlsanity.com/paper/1607.08022/) (2016)
- [Attention, Learn to Solve Routing Problems!](https://mlsanity.com/paper/1803.08475/) (2018)
- [Combinatorial optimization and reasoning with graph neural networks](https://mlsanity.com/paper/2102.09544/) (2021)
- [Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning](https://mlsanity.com/paper/2010.12367/) (2020)
- [Matrix Encoding Networks for Neural Combinatorial Optimization](https://mlsanity.com/paper/2106.11113/) (2021)
- [Graph Meta Learning via Local Subgraphs](https://mlsanity.com/paper/2006.07889/) (2020)
- [On the Generalization of Neural Combinatorial Optimization Heuristics](https://mlsanity.com/paper/2206.00787/) (2022)

## Built on by (most cited first, 1 of 1)

- [Variational Approach for Job Shop Scheduling](https://mlsanity.com/paper/2602.00408/) (2026)

## Abstract (arXiv)

In smart manufacturing systems (SMSs), flexible job-shop scheduling with transportation constraints (FJSPT) is essential to optimize solutions for maximizing productivity, considering production flexibility based on automated guided vehicles (AGVs). Recent developments in deep reinforcement learning (DRL)-based methods for FJSPT have encountered a scale generalization challenge. These methods underperform when applied to environment at scales different from their training set, resulting in low-quality solutions. To address this, we introduce a novel graph-based DRL method, named the Heterogeneous Graph Scheduler (HGS). Our method leverages locally extracted relational knowledge among operations, machines, and vehicle nodes for scheduling, with a graph-structured decision-making framework that reduces encoding complexity and enhances scale generalization. Our performance evaluation, conducted with benchmark datasets, reveals that the proposed method outperforms traditional dispatching rules, meta-heuristics, and existing DRL-based approaches in terms of makespan performance, even on large-scale instances that have not been experienced during training.