Zobrazeno 1 - 10
of 23 571
pro vyhledávání: '"A. Gürtler"'
Zero-shot imitation learning algorithms hold the promise of reproducing unseen behavior from as little as a single demonstration at test time. Existing practical approaches view the expert demonstration as a sequence of goals, enabling imitation with
Externí odkaz:
http://arxiv.org/abs/2410.08751
In this work we explore the relevance of dropout for modern language models, particularly in the context of models on the scale of <100M parameters. We explore it's relevance firstly in the regime of improving the sample efficiency of models given sm
Externí odkaz:
http://arxiv.org/abs/2409.05423
The rapid advancement of large language models (LLMs) has led to significant improvements in natural language processing but also poses challenges due to their high computational and energy demands. This paper introduces a series of research efforts
Externí odkaz:
http://arxiv.org/abs/2405.14159
Autor:
Britta Kallin
Publikováno v:
Journal of Austrian Studies. 56:109-112
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::0d47f0c5f1c3fa827662a16f525bb6e6
https://doi.org/10.1353/oas.2023.0016
https://doi.org/10.1353/oas.2023.0016
Autor:
Margarete Lamb-Faffelberger
Publikováno v:
German Studies Review. 46:171-174
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::b7be7abfa8a5277885d9fa5fcd78af8a
https://doi.org/10.1353/gsr.2023.0026
https://doi.org/10.1353/gsr.2023.0026
Publikováno v:
Schwäbische Heimat. 69:118-119
Frank Ebel, Franziska Gürtler, Bastian Schmidt und Gerald Richter: 50 historische Wirtshäuser Schwäbische Alb und Mittleres Neckartal. Verlag Friedrich Pustet Regensburg 2017. 192 Seiten mit farbigen Abbildungen. Fest gebunden € 24,95. ISBN 978-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::efa40d96179dc019475316ab50b61b5c
https://doi.org/10.53458/sh.v69i1.1436
https://doi.org/10.53458/sh.v69i1.1436
Autor:
Kallin, Britta
Publikováno v:
Journal of Austrian Studies (Project Muse); April 2023, Vol. 56 Issue: 1 p109-112, 4p
Autor:
Gürtler, Nico, Widmaier, Felix, Sancaktar, Cansu, Blaes, Sebastian, Kolev, Pavel, Bauer, Stefan, Wüthrich, Manuel, Wulfmeier, Markus, Riedmiller, Martin, Allshire, Arthur, Wang, Qiang, McCarthy, Robert, Kim, Hangyeol, Baek, Jongchan, Kwon, Wookyong, Qian, Shanliang, Toshimitsu, Yasunori, Michelis, Mike Yan, Kazemipour, Amirhossein, Raayatsanati, Arman, Zheng, Hehui, Cangan, Barnabas Gavin, Schölkopf, Bernhard, Martius, Georg
Experimentation on real robots is demanding in terms of time and costs. For this reason, a large part of the reinforcement learning (RL) community uses simulators to develop and benchmark algorithms. However, insights gained in simulation do not nece
Externí odkaz:
http://arxiv.org/abs/2308.07741
Autor:
Gürtler, Nico, Blaes, Sebastian, Kolev, Pavel, Widmaier, Felix, Wüthrich, Manuel, Bauer, Stefan, Schölkopf, Bernhard, Martius, Georg
Learning policies from previously recorded data is a promising direction for real-world robotics tasks, as online learning is often infeasible. Dexterous manipulation in particular remains an open problem in its general form. The combination of offli
Externí odkaz:
http://arxiv.org/abs/2307.15690
Autor:
Lamb-Faffelberger, Margarete
Publikováno v:
German Studies Review (Project Muse); February 2023, Vol. 46 Issue: 1 p171-174, 4p