Uncertain Interruptibility Multiobjective Flexible Job Shop via Deep Reinforcement Learning Based on Heterogeneous Graph Self-Attention
Zunxun Wang, Junqing Li, Xiaolong Chen, Peiyong Duan, Jiake Li
Abstract
Although an increasing number of studies have focused on the flexible job shop problem, there has been insufficient consideration of realistic constraints, such as the working hours of employees and the noninterruptible nature of certain operations. To address this issue, here an improved deep reinforcement learning (DRL) approach is presented that utilizes end-to-end multidecision-intelligent body proximal policy optimization (m-PPO). In the proposed framework, a heterogeneous graph self-attention neural network (HGAN) model is embedded, which efficiently extracts valuable features from the original state in heterogeneous graphs to capture intricate relationships. Within this framework, agents are divided into five rule-driven job decision agents and data-driven operation-machine ( $\mathcal {O}\text {-}\mathcal {M}$ ) pair decision agents, which incorporate problem-specific knowledge. To optimize the makespan, total costs, and total lateness concurrently, the weight parameters for the objectives are generated by the network and self-updated based on the current state. Numerical experiments demonstrate the effectiveness of the proposed method.