Zobrazeno 1 - 10
of 809
pro vyhledávání: '"Thomas Albert"'
Autor:
Rajput Tripti Singh, Thomas Albert
Publikováno v:
E3S Web of Conferences, Vol 396, p 02023 (2023)
One of the sustainable approaches to improving indoor thermal comfort and building ventilation efficiency, particularly in developing and populated countries, is to implement the optimum passive design solutions. However, the interaction between vent
Externí odkaz:
https://doaj.org/article/ee5c03be229342359b8ab5881c5e97b4
We address offline reinforcement learning with privacy guarantees, where the goal is to train a policy that is differentially private with respect to individual trajectories in the dataset. To achieve this, we introduce DP-MORL, an MBRL algorithm com
Externí odkaz:
http://arxiv.org/abs/2402.05525
A Multi-step Loss Function for Robust Learning of the Dynamics in Model-based Reinforcement Learning
In model-based reinforcement learning, most algorithms rely on simulating trajectories from one-step models of the dynamics learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as the length of the t
Externí odkaz:
http://arxiv.org/abs/2402.03146
We consider the problem of offline reinforcement learning where only a set of system transitions is made available for policy optimization. Following recent advances in the field, we consider a model-based reinforcement learning algorithm that infers
Externí odkaz:
http://arxiv.org/abs/2402.02858
Autor:
Amelie Alfert, Carolin Walter, Natalia Moreno, Viktoria Melcher, Monika Graf, Marc Hotfilder, Martin Dugas, Thomas Albert, Kornelius Kerl
Publikováno v:
Cells, Vol 11, Iss 8, p 1354 (2022)
The murine esBAF complex plays a major role in the regulation of gene expression during stem cell development and differentiation. As one of its core subunits, Smarcb1 is indispensable for its function and its loss is connected to neurodevelopmental
Externí odkaz:
https://doaj.org/article/0460225bf6f44bfe9744ab9f00ec9cfd
Autor:
Daniel Göhler, Stephan Große, Alexander Bellendorf, Thomas Albert Falkenstein, Mehdi Ouaissi, Jürgen Zieren, Michael Stintz, Urs Giger-Pabst
Publikováno v:
Beilstein Journal of Nanotechnology, Vol 8, Iss 1, Pp 2729-2740 (2017)
Background: The delivery of aerosolised chemotherapeutic substances into pressurised capnoperitonea has been reported to be more effective than conventional liquid chemotherapy for the treatment of peritoneal carcinomatosis. However, recent reports r
Externí odkaz:
https://doaj.org/article/f8fcb53cd5c444d28ae286655fc40f74
Publikováno v:
Smart and Sustainable Built Environment, 2023, Vol. 13, Issue 5, pp. 1213-1239.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/SASBE-09-2022-0210
In model-based reinforcement learning (MBRL), most algorithms rely on simulating trajectories from one-step dynamics models learned on data. A critical challenge of this approach is the compounding of one-step prediction errors as length of the traje
Externí odkaz:
http://arxiv.org/abs/2310.05672