2021-01-25 10:08 |
Details des Eintrags - Ähnliche Datensätze
|
2021-01-25 09:20 |
Details des Eintrags - Ähnliche Datensätze
|
2021-01-24 16:57 |
[FZJ-2021-00681]
Contribution to a conference proceedings/Contribution to a book
Pleines, M. ; Jitsev, J. ; Preuss, M. ; et al
Obstacle Tower Without Human Demonstrations: How Far a Deep Feed-Forward Network Goes with Reinforcement Learning
20202020 IEEE Conference on Games (CoG) : [Proceedings] - IEEE, 2020 2020 IEEE Conference on Games (CoG), OsakaOsaka, Japan, 24 Aug 2020 - 27 Aug 20202020-08-242020-08-27
IEEE 447 - 454 (2020) [10.1109/CoG47356.2020.9231802]2020
The Obstacle Tower Challenge is the task to master a procedurally generated chain of levels that subsequently get harder to complete. Whereas the most top performing entries of last year's competition used human demonstrations or reward shaping to learn how to cope with the challenge, we present an approach that performed competitively (placed 7th) but starts completely from scratch by means of Deep Reinforcement Learning with a relatively simple feed-forward deep network structure. [...]
OpenAccess: PDF;
Details des Eintrags - Ähnliche Datensätze
|
2021-01-23 12:45 |
[FZJ-2021-00670]
Journal Article
Valov, I. ; Yang, Y.
Memristors with alloyed electrodes
Nanoionic memrisitve devices are one of the most promising building blocks for next generation hardware architectures for cognitive type data processing. These highly scalable, low power, fast operating units offer a broad spectrum of functionalities at various operation conditions. [...]
Fulltext: PDF; Published on 2020-06-08. Available in OpenAccess from 2020-12-08.: PDF;
ddc:600
Details des Eintrags - Ähnliche Datensätze
|
2021-01-23 12:40 |
Details des Eintrags - Ähnliche Datensätze
|
2021-01-23 12:35 |
[FZJ-2021-00666]
Journal Article
Milano, G. ; Raffone, F. ; Luebben, M. ; et al
Water-Mediated Ionic Migration in Memristive Nanowires with a Tunable Resistive Switching Mechanism
Memristive devices based on electrochemical resistive switching effects have been proposed as promising candidates for in-memory computing and for the realization of artificial neural networks. Despite great efforts toward understanding the nanoionic processes underlying resistive switching phenomena, comprehension of the effect of competing redox processes on device functionalities from the materials perspective still represents a challenge. [...]
Fulltext: PDF; Published on 2020-10-14. Available in OpenAccess from 2021-10-14.: PDF;
ddc:600
Details des Eintrags - Ähnliche Datensätze
|
2021-01-22 18:01 |
Details des Eintrags - Ähnliche Datensätze
|
2021-01-22 16:37 |
[FZJ-2021-00653]
Lecture (Other)
Herten, A.
GPU Accelerators at JSC
2020Lecture at JSC at training course "Introduction to usage and programming the supercomputing resources at JSC" (Jülich / online, Germany), 20 May 20202020-05-20
OpenAccess: PDF;
Details des Eintrags - Ähnliche Datensätze
|
2021-01-22 16:34 |
Details des Eintrags - Ähnliche Datensätze
|
2021-01-22 16:32 |
Details des Eintrags - Ähnliche Datensätze
|
|
|