TY  - CONF
A1  - Sarawinsky, Stefan
A1  - Schaller, Kai
A1  - Kandiah, Kajan
A2  - Herberger, David
A2  - Hübner, Marco
T1  - Reinforcement Learning for Intercropping Sequences
T2  - Proceedings of the Conference on Production Systems and Logistics CPSL 2026, 14th – 17th April 2026, Instituto Superior de Engenharia do Porto (ISEP), Porto, Portugal
N2  - Improving the sustainability of production systems requires decision support methods that can solve the problem of optimizing the combination of resources under ecological, operational, and compatibility constraints. This challenge arises in agriculture and manufacturing, particularly in Circular Industrial Production Systems (CIPS), where the creation of value depends on the coordinated use of materials, processes and resources, while minimizing waste and environmental impact. As production environments become more complex and dynamic, traditional rule-based or static optimization approaches struggle to cope with combinatorial decision spaces and evolving system constraints. To address this issue, the authors use intercropping as an example proxy domain with high complexity that mirrors these combinatorial challenges and compatibility constraints. This paper therefore presents a Deep Q-Network (DQN)-based Reinforcement Learning (RL) approach embedded in a domain-specific simulation environment for planning intercropping sequences. The RL-based Decision Support System (DSS) learns to maximize an aggregated reward comprising agronomic quality indicators and binary user preference feedback. Results from a simulation demonstrate a consistent convergence and structured long-term policy learning in complex combinatorial decision spaces. Beyond agriculture, this framework shows how RL-based sequencing policies can help CIPS facing similar optimization problems involving material combinations, process compatibility, and sustainability trade-offs.
KW  - Kreislaufwirtschaft
KW  - 03
KW  - Reinforcement Learning
KW  - Circular Economy
KW  - Decision Support Systems
KW  - Sustainable Sequence Optimization
Y1  - 2026
UR  - https://epub.fir.de/frontdoor/index/index/docId/4419
SN  - 2701-6277
N1  - SAAT: Sustainable Agriculture through Artificial Intelligence and Digital Technologies

The aim of the research project 'SAAT' is to demonstrate the technical and economic feasibility of sustainable mixed crops in agriculture. For this purpose, a field planning tool based on explainable AI as well as an AI-controlled sorting robotics module for field crop sorting on autonomous harvesting systems will be developed and the economic efficiency and sustainability of mixed crops compared to monocultures will be measured by means of multidimensional monitoring.

Duration: 01.05.2023 – 30.04.2026
Funding no.: 01MN23012B
Project homepage: projekt-saat.de
Funding: Federal Ministry of Research, Technology and Space (BMFTR)
Promoters: Deutsches Zentrum für Luft- und Raumfahrt e. V. (DLR)

Acknowledgment:
Federal Ministry of Research, Technology and Space (BMFTR) based on a resolution of the German Bundestag under the funding number 01MN23012B
SP  - 293
EP  - 303
PB  - publish-Ing.
CY  - Hannover
ER  -