Seiteninhalt Kontaktlinks
  • Wissenschaftliche Publikationen

Veröffentlichungen der HSWT

Die chronologische Liste zeigt aktuelle Veröffentlichungen aus dem Forschungsbetrieb der Hochschule Weihenstephan-Triesdorf. Zuständig ist das Zentrum für Forschung und Wissenstransfer (ZFW).

8 Ergebnisse

  • Dr. Bernd Panassiti

    Climate change effects on agronomic performance and biodiversity in alpine pastures (2024) Vortrag auf der Forum Alpinum, Kranjska Gora, Slovenia, Juni 2024 .

  • Dr. Christina Hartung, Dr. Bernd Panassiti, Prof. Dr. Jörg Ewald

    Plant communities of mountain pastures in the Berchtesgaden region (2024)

  • Jonathan Pirnay, Prof. Dr. Dominik Grimm

    • Berechtigungen:  Open Access
    • Berechtigungen:  Peer Reviewed

    Self-Improvement for Neural Combinatorial Optimization: Sample Without Replacement, but Improvement (2024) Transactions on Machine Learning Research (TMLR) .

    Current methods for end-to-end constructive neural combinatorial optimization usually train a policy using behavior cloning from expert solutions or policy gradient methods from reinforcement learning. While behavior cloning is straightforward, it requires expensive expert solutions, and policy gradient methods are often computationally demanding and complex to fine-tune. In this work, we bridge the two and simplify the training process by sampling multiple solutions for random instances using the current model in each epoch and then selecting the best solution as an expert trajectory for supervised imitation learning. To achieve progressively improving solutions with minimal sampling, we introduce a method that combines round-wise Stochastic Beam Search with an update strategy derived from a provable policy improvement. This strategy refines the policy between rounds by utilizing the advantage of the sampled sequences with almost no computational overhead. We evaluate our approach on the Traveling Salesman Problem and the Capacitated Vehicle Routing Problem. The models trained with our method achieve comparable performance and generalization to those trained with expert data. Additionally, we apply our method to the Job Shop Scheduling Problem using a transformer-based architecture and outperform existing state-of-the-art methods by a wide margin.
    Mehr

  • Paulina Bosko, Wioletta Biel, Prof. Dr. Iryna Smetanska, Ewa Piatkowska

    • Berechtigungen:  Open Access
    • Berechtigungen:  Peer Reviewed

    Sea Buckthorn Leaves as a Potential Source of Antioxidant Substances (2024) MDPI 14 (12). DOI: 10.3390/app14125038

Betreuung der Publikationsseiten

Zentrum für Forschung und Wissenstransfer - Lageplan in Weihenstephan an der HSWT

Kontakt

Hochschule Weihenstephan-Triesdorf
Zentrum für Forschung und Wissenstransfer
Gebäude H21
Am Staudengarten 9
85354 Freising

nach oben