In dynamic manufacturing environments, multi-agent systems must coordinate effectively under frequent operational disturbances such as machine failures, urgent job arrivals, and processing time variations. Existing multi-agent reinforcement learning approaches treat each disturbance episode independently, discarding valuable coordination experience that could accelerate future adaptation.
This paper proposes a Graph-Structured Experiential Memory (GSEM) framework for multi-agent coordination in dynamic manufacturing. The framework encodes historical coordination episodes as heterogeneous relational graphs that capture task dependencies, machine states, and inter-agent collaboration patterns.
When a new disturbance occurs, a graph neural network-based retrieval mechanism identifies structurally similar past episodes, enabling experience-guided policy adaptation rather than learning from scratch.
Experiments on dynamic flexible job-shop scheduling benchmarks show that GSEM reduces makespan by 4.1%-10.0% and adaptation time by 33%-38% compared to the strongest memory-augmented baseline, with the advantage increasing under higher disturbance frequency.
Ablation studies and cross-disturbance transfer experiments further validate the necessity of graph-structured encoding and similarity-based retrieval and demonstrate the cross-disturbance generalizability of learned coordination patterns.
Blogger's Review: The GSEM framework introduced in this paper effectively integrates historical experiences using graph neural networks, significantly enhancing the adaptability of multi-agent systems in dynamic manufacturing environments. This approach not only reduces time costs but also provides a new perspective for future research, warranting deeper exploration in practical applications.