Manufacturing Control in Job Shop Environments with Reinforcement Learning

Vladimir Samsonov, Marco Kemmerling, Maren Paegert, Daniel Lütticke, Frederick Sauermann, Andreas Gützlaff, Günther Schuh, Tobias Meisen

2021

Abstract

Computing solutions to job shop problems is a particularly challenging task due to the computational hardness of the underlying optimization problem as well as the often dynamic nature of given environments. To address such scheduling problems in a more flexible way, such that changing circumstances can be accommodated, we propose a reinforcement learning approach to solve job shop problems. As part of our approach, we propose a new reward shaping and devise a novel action space, from which a reinforcement learning agent can sample actions, which is independent of the job shop problem size. A number of experiments demonstrate that our approach outperforms commonly used scheduling heuristics with regard to the quality of the generated solutions. We further show that, once trained, the time required to compute solutions using our methodology increases less sharply as the problem size grows than exact solution methods making it especially suitable for online manufacturing control tasks.

Paper Citation

in Harvard Style

Samsonov V., Kemmerling M., Paegert M., Lütticke D., Sauermann F., Gützlaff A., Schuh G. and Meisen T. (2021). Manufacturing Control in Job Shop Environments with Reinforcement Learning.In Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART, ISBN 978-989-758-484-8, pages 589-597. DOI: 10.5220/0010202405890597

in Bibtex Style

@conference{icaart21,
author={Vladimir Samsonov and Marco Kemmerling and Maren Paegert and Daniel Lütticke and Frederick Sauermann and Andreas Gützlaff and Günther Schuh and Tobias Meisen},
title={Manufacturing Control in Job Shop Environments with Reinforcement Learning},
booktitle={Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,},
year={2021},
pages={589-597},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010202405890597},
isbn={978-989-758-484-8},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 13th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART,
TI - Manufacturing Control in Job Shop Environments with Reinforcement Learning
SN - 978-989-758-484-8
AU - Samsonov V.
AU - Kemmerling M.
AU - Paegert M.
AU - Lütticke D.
AU - Sauermann F.
AU - Gützlaff A.
AU - Schuh G.
AU - Meisen T.
PY - 2021
SP - 589
EP - 597
DO - 10.5220/0010202405890597