Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Soykan, Bulent, Mondesire, Sean, Rabadi, Ghaith, Bochenek, Grace
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914314506469376
author Soykan, Bulent
Mondesire, Sean
Rabadi, Ghaith
Bochenek, Grace
author_facet Soykan, Bulent
Mondesire, Sean
Rabadi, Ghaith
Bochenek, Grace
contents The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total Weighted Tardiness (TWT) and Total Setup Time (TST). This paper proposes a Deep Reinforcement Learning framework using Proximal Policy Optimization (PPO) and a Graph Neural Network (GNN). The GNN effectively represents the complex state of jobs, machines, and setups, allowing the PPO agent to learn a direct scheduling policy. Guided by a multi-objective reward function, the agent simultaneously minimizes TWT and TST. Experimental results on benchmark instances demonstrate that our PPO-GNN agent significantly outperforms a standard dispatching rule and a metaheuristic, achieving a superior trade-off between both objectives. This provides a robust and scalable solution for complex manufacturing scheduling.
format Preprint
id arxiv_https___arxiv_org_abs_2602_08052
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling
Soykan, Bulent
Mondesire, Sean
Rabadi, Ghaith
Bochenek, Grace
Artificial Intelligence
Emerging Technologies
The Unrelated Parallel Machine Scheduling Problem (UPMSP) with release dates, setups, and eligibility constraints presents a significant multi-objective challenge. Traditional methods struggle to balance minimizing Total Weighted Tardiness (TWT) and Total Setup Time (TST). This paper proposes a Deep Reinforcement Learning framework using Proximal Policy Optimization (PPO) and a Graph Neural Network (GNN). The GNN effectively represents the complex state of jobs, machines, and setups, allowing the PPO agent to learn a direct scheduling policy. Guided by a multi-objective reward function, the agent simultaneously minimizes TWT and TST. Experimental results on benchmark instances demonstrate that our PPO-GNN agent significantly outperforms a standard dispatching rule and a metaheuristic, achieving a superior trade-off between both objectives. This provides a robust and scalable solution for complex manufacturing scheduling.
title Graph-Enhanced Deep Reinforcement Learning for Multi-Objective Unrelated Parallel Machine Scheduling
topic Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2602.08052