Synapse
⌘+K
Synapse
PulseExploreClubsResearchersJournals
Instagram
HomeClubsExplore
March 12, 2026MachinesOpen Access

PPO-Graph Explorer: A New Method for Flexible Job Shop Scheduling via Entropy-Guided Attention Networks

View Full Paper
Ask AI
Bookmark
Share

Authors

KTKaiguo TanYLYanwu LiNDNina Dai

Discussion

Loading...

Member takes

Overview

This research introduces PPO-Graph Explorer to enhance scheduling efficiency in intelligent manufacturing, implying improved operational stability.

Key Points

  • The central aim is to develop a novel scheduling framework that combines PPO stability with improved exploration for job-shop scheduling.
  • Integrates Graph Isomorphism Attention Network (GIAN) with Entropy-Adjusted PPO (EAE-PPO)
  • Applies hybrid design tailored for disjunctive graph topology
  • Conducts extensive experiments on standard benchmarks including Brandimarte, Hurink, and Dauzère–Pérès
  • Reduces average makespan gap by 5.1 percentage points compared to state-of-the-art DRL methods
  • Achieves an 8.95% reduction in makespan on representative instances
  • Increases average machine utilization from 89.0% to 98.1%

Cite This Study

Tan et al. (2026) studied this question.

synapsesocial.com/papers/69b2587296eeacc4fcec829bhttps://doi.org/10.3390/machines14030310
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. 1Flexible Job Shop Scheduling Problem Based on Deep Reinforcement Learning Using Dual Attention Network2026
  2. 2Dynamic flexible job shop scheduling using greedy actor–neural critic PPO reinforcement learning algorithm2026
  3. 3Dynamic Job-Shop Scheduling via Graph Attention Networks and Deep Reinforcement Learning2024 · 17 citations
  4. 4Solving Flexible Job-Shop Scheduling Problem with Heterogeneous Graph Neural Network Based on Relation and Deep Reinforcement Learning2024 · 19 citations
  5. 5Adaptive Lagrangian Penalty-Enhanced Proximal Policy Optimization for Flexible Job Shop Rescheduling with Worker Workload Constraints Under Concurrent Dynamic Disturbances2026