A multi-action deep reinforcement learning framework for flexible Job-shop scheduling problem
作者：
Highlights：
• An end-to-end DRL-based framework is introduced to solve the FJSP.
• Multi-PPO is used to learn job operation action and machine action sub-policies in MPGN.
• The proposed DRL shows its robustness via random and benchmark test instances.
摘要
•An end-to-end DRL-based framework is introduced to solve the FJSP.•Multi-PPO is used to learn job operation action and machine action sub-policies in MPGN.•The proposed DRL shows its robustness via random and benchmark test instances.
论文关键词：Flexible job-shop scheduling problem,Multi-action deep reinforcement learning,Graph neural network,Markov decision process,Multi-proximal policy optimization
论文评审过程：Received 5 February 2022, Revised 12 May 2022, Accepted 5 June 2022, Available online 8 June 2022, Version of Record 15 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117796
