Abstract
In times of rapidly changing markets and increasing complexity the fast and precise adaption of production systems to new circumstances is key for the economic success of manufacturing companies. Given highly adaptable production systems, the control of these systems still has to be optimized for each configuration. One critical aspect is worker control. To enable an automatic control logic which is capable of adapting autonomously and anticipatory to new configurations of the production system, a combination of reinforcement learning (RL) with simulation is promising. Key to a successful implementation of RL in such a dynamic production system is that the RL agent is able to perform well independently of the present system configuration and not just in the one system he is originally trained in. This paper presents an approach to develop such generalized production control RL agents, which was tested and evaluated using a discrete event simulation of a real-world production system. The approach defines a methodology of hyperparameter tuning for generalization including training, agent selection and testing of the RL in independent configurations of the production system. The results indicate that the approach is very successful in creating a generalized production control RL agent, which is able to control the workers efficiently in various configurations of a production system and adapt rapidly to new circumstances.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Westkämper, E., Löffler, C.: Strategien der Produktion. Springer, Berlin (2016)
Pinedo, M.L.: Scheduling. Springer, US, Boston, MA (2012)
Overbeck, L., Hugues, A., May, M.C., et al.: Reinforcement learning based production control of semi-automated manufacturing systems. Procedia CIRP 103, 170–175 (2021). https://doi.org/10.1016/j.procir.2021.10.027
Belousov, B., Abdulsamad, H., Klink, P., et al.: Reinforcement Learning Algorithms: Analysis and Applications, vol. 883. Springer International Publishing, Cham (2021)
Kuhnle, A., Röhrig, N., Lanza, G.: Autonomous order dispatching in the semiconductor industry using reinforcement learning. Procedia CIRP 79, 391–396 (2019). https://doi.org/10.1016/j.procir.2019.02.101
Kuhnle, A., May, M.C., Schäfer, L., et al.: Explainable reinforcement learning in production control of job shop manufacturing system. Int. J. Prod. Res. 60, 5812–5834 (2022). https://doi.org/10.1080/00207543.2021.1972179
Cobbe, K., Klimov, O., Hesse, C., et al.: Quantifying Generalization in Reinforcement Learning (2018). https://arxiv.org/pdf/1812.02341
Wang, K., Kang, B., Shao, J., et al.: Improving Generalization in Reinforcement Learning with Mixture Regularization (2020)
Ripley, B.D.: Pattern Recognition and Neural Networks, 1. Paperback ed. 1997, reprinted 2009. Cambridge University Press, Cambridge (2009)
Pfeifer, T., Schmitt, R. (eds.): Masing Handbuch Qualitätsmanagement, 7. überarbeitete Auflage. Hanser eLibrary. Hanser, München (2021)
Schiefer, H., Schiefer, F.: Statistik für Ingenieure. Springer Fachmedien Wiesbaden, Wiesbaden (2018)
Zhou, Z.-H.: Machine Learning. Springer Singapore, Singapore (2021)
Kubat, M.: An Introduction to Machine Learning. Springer International Publishing, Cham (2021)
Kirk, R., Zhang, A., Grefenstette, E., et al.: A Survey of Generalisation in Deep Reinforcement Learning (2021)
Ahmed, Z., Le Roux, N., Norouzi, M., et al.: Understanding the impact of entropy on policy optimization (2018)
Dong, H., Ding, Z., Zhang, S.: Deep Reinforcement Learning. Springer Singapore, Singapore (2020)
Igl, M., Ciosek, K., Li, Y., et al.: Generalization in Reinforcement Learning with Selective Noise Injection and Information Bottleneck (2019)
Siebertz, K., van Bebber, D., Hochkirchen, T.: Statistische Versuchsplanung. Springer, Berlin (2017)
Plappert, M., Houthooft, R., Dhariwal, P., et al.: Parameter Space Noise for Exploration (2017)
Tensorforce Team: Proximal Policy Optimization (2022). https://tensorforce.readthedocs.io/en/latest/agents/ppo.html. Accessed 11 Jan 2023
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Overbeck, L., Glaser, V., May, M.C., Lanza, G. (2023). Generalization of Reinforcement Learning Agents for Production Control. In: Galizia, F.G., Bortolini, M. (eds) Production Processes and Product Evolution in the Age of Disruption. CARV 2023. Lecture Notes in Mechanical Engineering. Springer, Cham. https://doi.org/10.1007/978-3-031-34821-1_37
Download citation
DOI: https://doi.org/10.1007/978-3-031-34821-1_37
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34820-4
Online ISBN: 978-3-031-34821-1
eBook Packages: EngineeringEngineering (R0)