Zobrazeno 1 - 10
of 152
pro vyhledávání: '"Boehmer, W."'
Agents trained with DQN rely on an observation at each timestep to decide what action to take next. However, in real world applications observations can change or be missing entirely. Examples of this could be a light bulb breaking down, or the wallp
Externí odkaz:
http://arxiv.org/abs/2312.02665
We calculate neutron capture cross sections for r-process nucleosynthesis in the $^{48}$Ca region, namely for the isotopes $^{40-44}$S, $^{46-50}$Ar, $^{56-66}$Ti, $^{62-68}$Cr, and $^{72-76}$Fe. While previously only cross sections resulting from th
Externí odkaz:
http://arxiv.org/abs/1504.04456
Autor:
Kratz, K. -L., Boehmer, W., Freiburghaus, C., Moeller, P., Pfeiffer, B., Rauscher, T., Thielemann, F. -K.
In the framework of our investigation to explain the nucleosynthesis origin of the correlated Ca-Ti-Cr isotopic anomalies in the Ca-Al-rich ''FUN'' inclusion EK-1-4-1 of the Allende meteorite, the nuclear-physics basis in the neutron-rich N=28 region
Externí odkaz:
http://arxiv.org/abs/astro-ph/0012217
Autor:
Hannawald, M., Kautzsch, T., Woehr, A., Walters, W. B., Kratz, K. -L., Fedoseyev, V. N., Mishin, V. L., Boehmer, W., Pfeiffer, B., Sebastian, V., Jading, Y., Koester, U., Lettry, J., Ravn, H. L., Collaboration, the ISOLDE
Publikováno v:
Phys.Rev.Lett. 82 (1999) 1391-1394
The use of chemically selective laser ionization combined with beta-delayed neutron counting at CERN/ISOLDE has permitted identification and half-life measurements for 623-ms Mn-61 up through 14-ms Mn-69. The measured half-lives are found to be signi
Externí odkaz:
http://arxiv.org/abs/nucl-ex/9812008
Using privileged information during training can improve the sample efficiency and performance of machine learning systems. This paradigm has been applied to reinforcement learning (RL), primarily in the form of distillation or auxiliary tasks, and l
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______1032::9c39ef6bb6f8965916420471183f818b
http://hdl.handle.net/10044/1/82425
http://hdl.handle.net/10044/1/82425
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
We propose a new objective, the counterfactual objective, unifying existing objectives for off-policy policy gradient algorithms in the continuing reinforcement learning (RL) setting. Compared to the commonly used excursion objective, which can be mi
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d80f72f5f6dcd5a980696a29d38d53d7