Patrick Ferber

Patrick Ferber
Address
Department of Mathematics and Computer Science
Spiegelgasse 5
CH - 4051 Basel, Switzerland
Room
04.001
Email
Phone
+41 61 207 05 35

In 2015 I received my bachelor degree in Computer Science at the University of Luxembourg. Afterward, I pursued my master studies at the Saarland University where I specialized on data mining and planning. During my master studies I worked with Dr. Jilles Vreeken on graph summarization using Information Theory. Since 2018 I am working on my PhD at the University of Basel supervised by Prof. Malte Helmert and Prof. Jörg Hoffmann

My research interests are planning, deep learning, and data mining. Currently, I am working on combining planning and neural networks.

Publications

(Show all abstracts) (Hide all abstracts)

2022

  • Patrick Ferber, Liat Cohen, Jendrik Seipp and Thomas Keller.
    Learning and Exploiting Progress States in Greedy Best-First Search.
    In Proceedings of the 31st International Joint Conference on Artificial Intelligence (IJCAI 2022). 2022.
    (Show abstract) (PDF) (code and data)

  • Daniel Heller, Patrick Ferber, Julian Bitterwolf, Matthias Hein and Jörg Hoffmann.
    Neural Network Heuristic Functions: Taking Confidence into Account.
    In Proceedings of the 15th International Symposium on Combinatorial Search (SoCS 2022). 2022.
    (Show abstract) (PDF) (code)

  • Patrick Ferber, Florian Geißer, Felipe Trevizan, Malte Helmert and Jörg Hoffmann.
    Neural Network Heuristic Functions for Classical Planning: Bootstrapping and Comparison to Other Methods.
    In Proceedings of the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022). 2022.
    (Show abstract) (PDF) (code and data)

  • Marcel Steinmetz, Daniel Fišer, Hasan Ferit Enişer, Patrick Ferber, Timo Gros, Philippe Heim, Daniel Höller, Xandra Schuler, Valentin Wüstholz, Maria Christakis and Joerg Hoffmann..
    Debugging a Policy: Automatic Action-Policy Testing in AI Planning.
    In Proceedings of the 32nd International Conference on Automated Planning and Scheduling (ICAPS 2022). 2022.
    (Show abstract)

  • Patrick Ferber and Jendrik Seipp.
    Explainable Planner Selection for Classical Planning.
    In Proceedings of the 36th AAAI Conference on Artificial Intelligence (AAAI 2022). 2022.
    (Show abstract) (PDF) (slides (long); PDF) (slides (short); PDF) (poster; PDF) (code)

2021

  • Patrick Ferber, Florian Geißer, Felipe Trevizan, Jörg Hoffmann and Malte Helmert.
    Neural Network Heuristic Functions for Classical Planning: Reinforcement Learning and Comparison to Other Methods.
    In Proceedings of the ICAPS 2021 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL 2021). 2021.
    (Show abstract) (PDF) (slides; PDF) (poster; PDF) (talk; MP4) (code and data)

2020

  • Patrick Ferber, Malte Helmert and Jörg Hoffmann.
    Reinforcement Learning for Planning Heuristics.
    In Proceedings of the ICAPS 2020 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL 2020). 2020.
    (Show abstract) (PDF) (poster; PDF) (code and data)

  • Patrick Ferber and Jendrik Seipp.
    Explainable Planner Selection.
    In Proceedings of the ICAPS 2020 Workshop on Explainable AI Planning (XAIP 2020). 2020.
    (Show abstract) (PDF) (slides; PDF) (recording; MP4) (poster; PDF) (code and data)

  • Patrick Ferber.
    Simplified Planner Selection.
    In Proceedings of the ICAPS 2020 Workshop on Heuristics and Search for Domain-Independent Planning (HSDIP 2020). 2020.
    (Show abstract) (PDF) (slides; PDF) (recording; MP4) (code and data)

  • Patrick Ferber, Malte Helmert and Jörg Hoffmann.
    Neural Network Heuristics for Classical Planning: A Study of Hyperparameter Space.
    In Frontiers in Artificial Intelligence and Applications 325 (ECAI 2020), pp. 2346-2353. 2020.
    (Show abstract) (PDF) (slides; PDF) (recording; MP4) (code) (models)

  • Tengfei Ma, Patrick Ferber, Siyu Huo, Jie Chen and Michael Katz.
    Online Planner Selection with Graph Neural Networks and Adaptive Scheduling.
    In Proceedings of the 34th AAAI Conference on Artificial Intelligence (AAAI 2020), pp. 5077-5084. 2020.
    (Show abstract) (PDF)

2019

  • Patrick Ferber, Tengfei Ma, Siyu Huo, Jie chen and Michael Katz.
    IPC: A Benchmark Data Set for Learning with Graph-Structured Data.
    In Proceedings of the ICML-2019 Workshop on Learning and Reasoning with Graph-Structured Representations(LRWSR 2019). 2019.
    (Show abstract) (PDF)

  • Silvan Sievers, Michael Katz, Shirin Sohrabi, Horst Samulowitz and Patrick Ferber.
    Deep Learning for Cost-Optimal Planning: Task-Dependent Planner Selection.
    In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI 2019), pp. 7715-7723. 2019.
    (Show abstract) (PDF) (slides; PDF) (poster; PDF)