DRL-Survey published
We are delighted that the survey “A literature review on deep reinforcement learning for machine scheduling problems” written by our former colleague Dr.-Ing. Constantin Waubert de Puiseau, together with Furkan Ercan (Lehrstuhl für Produktionssysteme, Ruhr-Universität Bochum), Jannik Peters, Marvin Brune, Dr.-Ing. Hasan Tercan, Dr.-Ing. Christopher Prinz (LPS), Prof. Dr.-Ing. Tobias Meisen und Prof. Dr.-Ing. Bernd Kuhlenkötter (LPS) has been published in the Journal of Manufacturing Systems.
This survey presents a coprehensive review of 143 publications between 2018 and February 2025 that apply Deep Reinforcement Learning (DLR) to machine scheduling problems. They developed a structured framework to classify and compare problem settings, algorithmic designs, and evaluation methodologies. Key aspects such as action and observation space design, reward functions, neural network architectures, and experimental benchmarks are systematically analyzed.
The review identified current trends, outlines promising patterns, and highlights open research opportunities for DRL-based scheduling solutions. The goal of this survey was to make the rapidly evolving research landscape more accessible to both academics and practitioners and to identify the next steps in research and application. To facilitate reproducible research and customized analysis, they published the dataset underpinning this review, which includes 61 annotated features per publication, allowing for customizable filtering and further in-depth exploration of niches within the field.
Read the entire survey here
