Reinforcement Learning Based Iterated Greedy for Parallel Machine Scheduling with Weighted Earliness Tardiness

Research output: Chapter in Book/Report/Conference proceedingsConference proceedingpeer-review

Abstract

On-time delivery is becoming more and more important for industrial companies, as their customers often require orders to meet specific deadlines. In this paper, we investigate the parallel machine scheduling problem with sequence-dependent setup times and due date windows. This problem has attracted attention due to its significance and relevance in real-world applications. To minimize total weighted earliness tardiness, we propose an efficient adaptive iterated greedy method enhanced with Q-learning (QIG). The performance of our approach is compared against six well selected metaheuristics from the literature. Computational experiments on a benchmark set of 600 instances demonstrate the efficiency of the proposed iterated greedy method.

Original languageEnglish
Title of host publicationAdvances and Trends in Artificial Intelligence. Theory and Applications - 38th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2025, Proceedings
EditorsHamido Fujita, Yutaka Watanobe, Moonis Ali, Yinglin Wang
PublisherSpringer Science and Business Media Deutschland GmbH
Pages15-26
Number of pages12
ISBN (Print)9789819688883
DOIs
Publication statusPublished - 2026
Event38th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2025 - Kitakyushu, Japan
Duration: 1 Jul 20254 Jul 2025

Publication series

NameLecture Notes in Computer Science
Volume15706 LNAI
ISSN (Print)0302-9743
ISSN (Electronic)1611-3349

Conference

Conference38th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems, IEA/AIE 2025
Country/TerritoryJapan
CityKitakyushu
Period1/07/254/07/25

Keywords

  • Iterated Greedy
  • Parallel Machine
  • Q-Learning
  • Setup times
  • Total Earliness Tardiness

Fingerprint

Dive into the research topics of 'Reinforcement Learning Based Iterated Greedy for Parallel Machine Scheduling with Weighted Earliness Tardiness'. Together they form a unique fingerprint.

Cite this