Zobrazeno 1 - 10
of 27
pro vyhledávání: '"HÖLLER, DANIEL"'
Autor:
Köhn, Arne, Wichlacz, Julia, Torralba, Álvaro, Höller, Daniel, Hoffmann, Jörg, Koller, Alexander
When generating technical instructions, it is often convenient to describe complex objects in the world at different levels of abstraction. A novice user might need an object explained piece by piece, while for an expert, talking about the complex ob
Externí odkaz:
http://arxiv.org/abs/2010.03982
Learning-based approaches for solving large sequential decision making problems have become popular in recent years. The resulting agents perform differently and their characteristics depend on those of the underlying learning approach. Here, we cons
Externí odkaz:
http://arxiv.org/abs/2008.00766
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Höller, Daniel
Publikováno v:
Journal of Artificial Intelligence Research; 2024, Vol. 80, p613-663, 51p
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Steinmetz, Marcel, Fišer, Daniel, Enişer, Hasan Ferit, Ferber, Patrick, Gros, Timo, Heim, Philippe, Höller, Daniel, Schuler, Xandra, Wüstholz, Valentin, Christakis, Maria, Hoffmann, Jörg
Publikováno v:
Proceedings of the Thirty-Second International Conference on Automated Planning and Scheduling
Testing is a promising way to gain trust in neural action policies π. Previous work on policy testing in sequential decision making targeted environment behavior leading to failure conditions. But if the failure is unavoidable given that behavior, t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::80dd82f4590a8e2f65ea00a2b3342426
https://doi.org/10.1609/icaps.v32i1.19820
https://doi.org/10.1609/icaps.v32i1.19820
Autor:
Lauer, Pascal, Torralba, Alvaro, Fišer, Daniel, Höller, Daniel, Wichlacz, Julia, Hoffmann, Jörg
Publikováno v:
Lauer, P, Torralba, A, Fišer, D, Höller, D, Wichlacz, J & Hoffmann, J 2021, Polynomial-Time in PDDL Input Size : Making the Delete Relaxation Feasible for Lifted Planning . in Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence. IJCAI-21 . International Joint Conferences on Artificial Intelligence, pp. 4119-4126, Thirtieth International Joint Conference on Artificial Intelligence. IJCAI-21, Canada, 19/08/2021 . < https://www.ijcai.org/proceedings/2021/0567.pdf >
Polynomial-time heuristic functions for planningare commonplace since 20 years. But polynomialtime in which input? Almost all existing approaches are based on a grounded task representation, not on the actual PDDL input which is exponentially smaller
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::129296ec686aab4d3b858323b91c9425
https://vbn.aau.dk/da/publications/50e51831-819d-4a97-9ba4-bee72d4affaf
https://vbn.aau.dk/da/publications/50e51831-819d-4a97-9ba4-bee72d4affaf
Autor:
Bercher , Pascal, Höller, Daniel, Behnke , Gregor, Biundo, Susanne, Shivashankar, Vikas, Alford , Ron
Publikováno v:
AI Magazine; Vol. 42 No. 1: Spring 2021; 83-85
Hierarchical planning has attracted renewed interest in the last few years. Consequently, the time was right to establish a workshop devoted entirely to hierarchical planning — an insight shared by many supporters. In this article, we report on the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=issn07384602::304d33f2dc547b4ca0143a294d8e3120
https://ojs.aaai.org/index.php/aimagazine/article/view/7393
https://ojs.aaai.org/index.php/aimagazine/article/view/7393
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
KI: Künstliche Intelligenz; Nov2021, Vol. 35 Issue 3/4, p391-396, 6p