Curiosity Driven Reinforcement Learning for Job Shop Scheduling

Alexander Nasuta, Marco Kemmerling, Hans Zhou, Anas Abdelrazeq, Robert H. Schmitt

2025

Abstract

The Job Shop Problem (JSP) is a well-known NP-hard problem with numerous applications in manufacturing and other fields. Efficient scheduling is critical for producing customized products in the manufacturing industry in time. Typically, the quality metrics of a schedule, such as the makespan, can only be assessed after all tasks have been assigned, leading to sparse reward signals when framing JSP as a reinforcement learning (RL) problem. Sparse rewards pose significant challenges for many RL algorithms, often resulting in slow learning behavior. Curiosity algorithms, which introduce intrinsic reward signals, have been shown to acceler-ate learning in environments with sparse rewards. In this study, we explored the effectiveness of the Intrinsic Curiosity Module (ICM) and Episodic Curiosity (EC) by benchmarking them against state-of-the-art methods. Our experiments demonstrate that the use of curiosity significantly increases the amount of states encountered by the RL agent. When the intrinsic and extrinsic reward signals are of comparable magnitude, the agent is with ICM module are able to escape local optima and discover better solutions.

Paper Citation

in Harvard Style

Nasuta A., Kemmerling M., Zhou H., Abdelrazeq A. and Schmitt R. (2025). Curiosity Driven Reinforcement Learning for Job Shop Scheduling. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART; ISBN 978-989-758-737-5, SciTePress, pages 216-227. DOI: 10.5220/0013143800003890

in Bibtex Style

@conference{icaart25,
author={Alexander Nasuta and Marco Kemmerling and Hans Zhou and Anas Abdelrazeq and Robert H. Schmitt},
title={Curiosity Driven Reinforcement Learning for Job Shop Scheduling},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART},
year={2025},
pages={216-227},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013143800003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART
TI - Curiosity Driven Reinforcement Learning for Job Shop Scheduling
SN - 978-989-758-737-5
AU - Nasuta A.
AU - Kemmerling M.
AU - Zhou H.
AU - Abdelrazeq A.
AU - Schmitt R.
PY - 2025
SP - 216
EP - 227
DO - 10.5220/0013143800003890
PB - SciTePress