Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Roman Kalkreuth"'
Autor:
Wolfgang Banzhaf, James A. Foster, Simon Harding, Roman Kalkreuth, Gul Muhammad Khan, W. B. Langdon, Riccardo Poli, Stephen Smith, Susan Stepney, Martin Trefzer, Dennis G. Wilson
Publikováno v:
ACM SIGEVOlution. 15:1-7
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::9d17c5af7ec39a056b236a7342061b06
https://doi.org/10.1145/3532942.3532943
https://doi.org/10.1145/3532942.3532943
Autor:
Roman Kalkreuth
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::262b1e76bfb82c1bf7af38c8671a575b
https://doi.org/10.1145/3520304.3529065
https://doi.org/10.1145/3520304.3529065
Publikováno v:
Proceedings of the Genetic and Evolutionary Computation Conference Companion.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ccabd62c75aec617418e9029ae3f1210
https://doi.org/10.1145/3520304.3533657
https://doi.org/10.1145/3520304.3533657
Autor:
Marco Pleines, Konstantin Ramthun, Yannik Wegener, Hendrik Meyer, Matthias Pallasch, Sebastian Prior, Jannik Drogemuller, Leon Buttinghaus, Thilo Rothemeyer, Alexander Kaschwig, Oliver Chmurzynski, Frederik Rohkrahmer, Roman Kalkreuth, Frank Zimmer, Mike Preuss
Autonomously trained agents that are supposed to play video games reasonably well rely either on fast simulation speeds or heavy parallelization across thousands of machines running concurrently. This work explores a third way that is established in
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::d7580c584ebadf9c839c790e6a03f800
http://arxiv.org/abs/2205.05061
http://arxiv.org/abs/2205.05061
Autor:
James McDermott, Gabriel Kronberger, Patryk Orzechowski, Leonardo Vanneschi, Luca Manzoni, Roman Kalkreuth, Mauro Castelli
In 2011, something which was latent in discussions of Genetic Programming (GP) was crystallised by Sean Luke in an email to the GP mailing list: “I think GP has a toy problem”. There was a damaging mismatch between the problems used to test GP pe
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b39a6bb530e5324a1701b8900a90bb04
https://dl.acm.org/toc/sigevo/2022/15/3
https://dl.acm.org/toc/sigevo/2022/15/3
Autor:
Roman Kalkreuth
Publikováno v:
Lecture Notes in Computer Science ISBN: 9783031147203
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::8fe49a491210fa34ec6c08d0352ceec4
https://doi.org/10.1007/978-3-031-14721-0_5
https://doi.org/10.1007/978-3-031-14721-0_5
Autor:
Roman Kalkreuth
Publikováno v:
Proceedings of the 14th International Joint Conference on Computational Intelligence.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::cf4a664725df1c77ce324c796d085863
https://doi.org/10.5220/0011551000003332
https://doi.org/10.5220/0011551000003332
Autor:
Márcio P. Basgalupp, Paul Kaufmann, Roman Kalkreuth, Léo Françoso Dal Piccol Sotto, Timothy Atkinson
Graph representations promise several desirable properties for genetic programming (GP); multiple-output programs, natural representations of code reuse and, in many cases, an innate mechanism for neutral drift. Each graph GP technique provides a pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::8b895afa8f47274fe18d3ec68305548a
https://publica.fraunhofer.de/handle/publica/270605
https://publica.fraunhofer.de/handle/publica/270605
Autor:
Roman Kalkreuth
Publikováno v:
Studies in Computational Intelligence ISBN: 9783030705930
The most commonly used genetic operator in Cartesian Genetic Programming (CGP) is the genotypic point mutation. Since CGP suffers from a lack of knowledge about the possibilities and effectiveness of advanced genetic operators, the point mutation is
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::622c9c30b0284577e004a19f25d89a96
https://doi.org/10.1007/978-3-030-70594-7_4
https://doi.org/10.1007/978-3-030-70594-7_4
Autor:
Roman Kalkreuth, Paul Kaufmann
Publikováno v:
CEC
In this work, we present a detailed analysis of Cartesian Genetic Programming (CGP) parametrization of the selection scheme ($\mu+\lambda$), and the levels back parameter l. We also investigate CGP’s mutation operator by decomposing it into a self-
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2a77cc66d814b52ddcc301c42005471e
https://doi.org/10.1109/cec48606.2020.9185492
https://doi.org/10.1109/cec48606.2020.9185492