Dynamic Job Shop Scheduling via Deep Reinforcement Learning

Created by W.Langdon from gp-bibliography.bib Revision:1.8051

@InProceedings{Liang:2023:ICTAI,

• author = "Xinjie Liang and Wen Song and Pengfei Wei",
• booktitle = "2023 IEEE 35th International Conference on Tools with Artificial Intelligence (ICTAI)",
• title = "Dynamic Job Shop Scheduling via Deep Reinforcement Learning",
• year = "2023",
• pages = "369--376",
• abstract = "Recently, deep reinforcement learning (DRL) is shown to be promising in learning dispatching rules end-to-end for complex scheduling problems. However, most research is limited to deterministic problems. In this paper, we focus on the dynamic job-shop scheduling problem (DJSP), which is a complex dynamic optimisation problem under uncertainty. We propose a DRL based method to learn dispatching policies for DJSP. Unlike existing DRL based dynamic scheduling methods that use a fixed number of dispatching rules as actions, our decision-making framework directly selects legitimate jobs, which is able to break the limitations imposed by priority dispatching rules. We design two training methods, including a gradient based algorithm with dense rewards, and an evolutionary strategy with sparse rewards. Extensive experiments show that our DRL method can learn high-quality DJSP dispatching policies, and can significantly outperform a state-of-the-art Genetic Programming (GP) based dispatching rule learning method.",
• keywords = "genetic algorithms, genetic programming, Deep learning, Training, Learning systems, Job shop scheduling, Uncertainty, Heuristic algorithms, Reinforcement learning, Deep Reinforcement Learning, Dynamic Job Shop Scheduling Problem, Evolutionary Strategy",
• DOI = "doi:10.1109/ICTAI59109.2023.00060",
• ISSN = "2375-0197",
• month = nov,
• notes = "Also known as \cite{10356485}",

}

Genetic Programming entries for Xinjie Liang Wen Song Pengfei Wei

Citations