Reinforcement Learning

Automation of Production Planning and Control

Automation of Production Planning and Control

A deep dive into production control with intelligent agents
Jonas Schneider, Peter Nyhuis ORCID Icon, Matthias Schmidt
How can artificial intelligence (AI) automate production planning and control? This study examines its potential to enhance efficiency in modern production environments. The focus is on establishing a robust data infrastructure that integrates real-time, historical, and contextual data to create a solid basis for AI models. Reinforcement learning (RL) is applied to aid automation. A roadmap for implementation, focusing on practical application, is presented. This roadmap incorporates simulation-based training methods and outlines strategies for continuous improvement and adaptation of production processes.
Industry 4.0 Science | Volume 41 | 2025 | Edition 5 | Pages 86-93 | DOI 10.30844/I4SE.25.5.84
Potentials of Reinforcement Learning for Production

Potentials of Reinforcement Learning for Production

Marco Huber, Tobias Nagel, Raphael Lamprecht, Florian Eiling
Reinforcement learning (RL) can be more and more used for real-world decision problems in production. The article gives an introduction into the functionalities of RL as well as its preferred areas of application. It further describes project examples from everyday production. The presented knowledge of current research is intended to make this sub-area of artificial intelligence accessible to a broader audience and to increase the added value in production.
Industrie 4.0 Management | Volume 37 | 2021 | Edition 2 | Pages 25-29 | DOI 10.30844/I40M_21-2_S25-29
LearningGripper – Machine Learning in the Factory of the Future

LearningGripper – Machine Learning in the Factory of the Future

Grasping and orientation through independent learning
Arne Rost, Elias Maria Knubben, Nina Gaissert
The LearningGripper from Festo looks like an abstract form of the human hand. The four fingers of the compliant gripper are driven by 12 pneumatic bellows actuators with low-level pressurisation. Thanks to the process of machine learning, it is able to teach itself to carry out complex actions such as, for example, gripping and positioning an object. By means of the LearningGripper we demonstrate how the development of such complex systems will be accelerated in the production of the future. Furthermore, the specific usage of machine learning algorithms will increase the efficiency of whole production plants.
Industrie Management | Volume 31 | 2015 | Edition 1 | Pages 13-16
Reinforcement Learning for Planning Working Processes

Reinforcement Learning for Planning Working Processes

Anwendung von Reinforcement Learning Methoden zur Planung von Arbeitsaufgaben im industriellen Bereich
Helge Ülo Dinkelbach, Julia Schuster, Fred H. Hamker
One of the main purposes of the „Smart Virtual Worker“-project is the application of a digital human model for the simulation of industrial work tasks. This contribution focuses on the implementation of an autonomic action selection, such that a virtual agent is able to solve tasks under certain optimization criteria. To realize the autonomic action selection, we use the Q-Learning algorithm with different extensions. In this article, we describe these different learning algorithms and we briefly describe the performance of their implementation with regard to the industrial field.
Industrie Management | Volume 31 | 2015 | Edition 1 | Pages 9-12