Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
July 22, 2026Machine LearningOpen Access

Reinforcement Learning Guided Neural Deconstruction Search for Flexible Job Scheduling

View Full Paper
Ask AI
Bookmark
Share

Authors

DZDavide ZagoUniversity of TurinAHAndré HottungBielefeld UniversityFGFynn Martin GilbertBielefeld University

Discussion

Loading...

Member takes

Overview

Randomized trial demonstrates improved job scheduling outcomes, suggesting new optimization strategies.

Key Points

  • The aim is to develop a learning-based method for scheduling that utilizes neural deconstruction to enhance solutions.
  • Introduced a learning-based improvement method for scheduling using a neural deconstruction framework.
  • Applied the method to classical and flexible job-shop scheduling problems.
  • Utilized a learned deconstruction policy and a simple repair strategy for solution enhancement.
  • Demonstrated the method outperformed existing end-to-end approaches on benchmark instances.
  • Achieved state-of-the-art results on flexible and classical job scheduling problems.

Cite This Study

Zago et al. (2026) studied this question.

synapsesocial.com/papers/6a605f464163e025518d8958https://doi.org/10.1007/s10994-026-07116-9
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Research on flexible job shop scheduling problems based on deep reinforcement learning2024 · 2 citations
  2. 2Dynamic scheduling of human-machine collaborative flexible job shops based on deep reinforcement learning2026
  3. 3A multiobjective flexible job shop scheduling method based on deep reinforcement learning2024 · 2 citations
  4. 4Beyond Training: Optimizing Reinforcement Learning Based Job Shop Scheduling Through Adaptive Action Sampling2024
  5. 5Multi-Agent Reinforcement Learning for Job Shop Scheduling in Dynamic Environments2024 · 28 citations