University of Twente Student Theses
Deep reinforcement learning for solving job shop scheduling problems
Meijer, B.J. (2024) Deep reinforcement learning for solving job shop scheduling problems.
|
PDF
62MB |
| Abstract: | This thesis explores integrating machine learning, specifically deep reinforcement learning, into job shop scheduling to improve production efficiency. The study assesses DRL models in both static and dynamic settings, revealing that DRL can surpass traditional methods in well-defined scenarios. However, it faces challenges with computational demands, scalability, and generalization. DRL shows promise, especially with tailored environments and transfer learning, but its practical use is limited to specific cases. Recommendations include continuing with traditional methods for now and exploring advanced techniques that require more expertise to enhance performance and generalization, while also speeding up the training process. |
| Item Type: | Essay (Master) |
| Faculty: | ET: Engineering Technology |
| Subject: | 52 mechanical engineering |
| Programme: | Mechanical Engineering MSc (60439) |
| Link to this item: | https://purl.utwente.nl/essays/102769 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page