A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling

Abstract To improve the scheduling efficiency of flexible job shops, this paper proposes a multi-objective collaborative intelligent agent reinforcement learning algorithm based on weight distribution. First, a mathematical model for flexible job shop scheduling optimization is established, with the...

Full description

Saved in:
Bibliographic Details
Main Authors: Jian Li, Shifa Li, Pengbo He, Huankun Li
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-03681-6
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849335303707295744
author Jian Li
Shifa Li
Pengbo He
Huankun Li
author_facet Jian Li
Shifa Li
Pengbo He
Huankun Li
author_sort Jian Li
collection DOAJ
description Abstract To improve the scheduling efficiency of flexible job shops, this paper proposes a multi-objective collaborative intelligent agent reinforcement learning algorithm based on weight distribution. First, a mathematical model for flexible job shop scheduling optimization is established, with the makespan and total energy consumption of the shop as optimization objectives, and a disjunctive-graph is introduced to represent state features. Second, two intelligent agents are designed to address the simultaneous decision making problems of jobs and machines. Encoder-decoder components are implemented to facilitate state recognition and action output by the agents. Reward parameters are computed based on temporal differences at various moments, constructing a multi-objective Markov decision-process training model. Using hypervolume, set coverage and inverted generational distance as evaluation metrics, the algorithm is compared with those proposed in other studies on standard instances. The results demonstrate that the proposed method significantly outperforms other algorithms in solving the flexible job shop scheduling problem. Finally, a real-world case study further validates the effectiveness and practicality of the proposed algorithm.
format Article
id doaj-art-c0264ad048264767ade78bf23993e72f
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-c0264ad048264767ade78bf23993e72f2025-08-20T03:45:19ZengNature PortfolioScientific Reports2045-23222025-07-0115111810.1038/s41598-025-03681-6A multi objective collaborative reinforcement learning algorithm for flexible job shop schedulingJian Li0Shifa Li1Pengbo He2Huankun Li3School of Mechatronics Engineering, Henan University of Science and TechnologySchool of Mechatronics Engineering, Henan University of Science and TechnologySchool of Mechatronics Engineering, Henan University of Science and TechnologySchool of Mechatronics Engineering, Henan University of Science and TechnologyAbstract To improve the scheduling efficiency of flexible job shops, this paper proposes a multi-objective collaborative intelligent agent reinforcement learning algorithm based on weight distribution. First, a mathematical model for flexible job shop scheduling optimization is established, with the makespan and total energy consumption of the shop as optimization objectives, and a disjunctive-graph is introduced to represent state features. Second, two intelligent agents are designed to address the simultaneous decision making problems of jobs and machines. Encoder-decoder components are implemented to facilitate state recognition and action output by the agents. Reward parameters are computed based on temporal differences at various moments, constructing a multi-objective Markov decision-process training model. Using hypervolume, set coverage and inverted generational distance as evaluation metrics, the algorithm is compared with those proposed in other studies on standard instances. The results demonstrate that the proposed method significantly outperforms other algorithms in solving the flexible job shop scheduling problem. Finally, a real-world case study further validates the effectiveness and practicality of the proposed algorithm.https://doi.org/10.1038/s41598-025-03681-6Flexible job shop scheduling problemCollaborative agent reinforcement learningMarkov decision process
spellingShingle Jian Li
Shifa Li
Pengbo He
Huankun Li
A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
Scientific Reports
Flexible job shop scheduling problem
Collaborative agent reinforcement learning
Markov decision process
title A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
title_full A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
title_fullStr A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
title_full_unstemmed A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
title_short A multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
title_sort multi objective collaborative reinforcement learning algorithm for flexible job shop scheduling
topic Flexible job shop scheduling problem
Collaborative agent reinforcement learning
Markov decision process
url https://doi.org/10.1038/s41598-025-03681-6
work_keys_str_mv AT jianli amultiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT shifali amultiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT pengbohe amultiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT huankunli amultiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT jianli multiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT shifali multiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT pengbohe multiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling
AT huankunli multiobjectivecollaborativereinforcementlearningalgorithmforflexiblejobshopscheduling