Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Onken, Derek"'
Publikováno v:
IEEE Transactions on Control Systems Technology 2022
We propose a neural network approach that yields approximate solutions for high-dimensional optimal control problems and demonstrate its effectiveness using examples from multi-agent path finding. Our approach yields controls in a feedback form, wher
Externí odkaz:
http://arxiv.org/abs/2104.03270
Publikováno v:
2021 European Control Conference; copyright 2021 IEEE
We propose a neural network approach for solving high-dimensional optimal control problems. In particular, we focus on multi-agent control problems with obstacle and collision avoidance. These problems immediately become high-dimensional, even for mo
Externí odkaz:
http://arxiv.org/abs/2011.04757
Publikováno v:
Proceedings of the 2021 AAAI Conference on Artificial Intelligence, 35(10), 9223-9232
A normalizing flow is an invertible mapping between an arbitrary probability distribution and a standard normal distribution; it can be used for density estimation and statistical inference. Computing the flow follows the change of variables formula
Externí odkaz:
http://arxiv.org/abs/2006.00104
Autor:
Onken, Derek, Ruthotto, Lars
We compare the discretize-optimize (Disc-Opt) and optimize-discretize (Opt-Disc) approaches for time-series regression and continuous normalizing flows (CNFs) using neural ODEs. Neural ODEs are ordinary differential equations (ODEs) with neural netwo
Externí odkaz:
http://arxiv.org/abs/2005.13420
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Vigfusson, Ymir, Karlsson, Thorgeir A., Onken, Derek, Song, Congzheng, Einarsson, Atli F., Kishore, Nishant, Mitchell, Rebecca M., Brooks-Pollock, Ellen, Sigmundsdottir, Gudrun, Danon, Leon
Publikováno v:
Proceedings of the National Academy of Sciences of the United States of America, 2021 Feb 01. 118(6), 1-6.
Externí odkaz:
https://www.jstor.org/stable/27006285
Autor:
Onken, Derek, Marty, Eric, Palomares, Roberto, Xie, Rui, Zhang, Leyao, Arnold, Jonathan, Gutierrez, Juan B.
The lunar cycle has long been suspected to influence biological phenomena. Folklore alludes to such a relationship, but previous scientific analyses have failed to find significant associations. It has been shown that lunar cycles indeed have effects
Externí odkaz:
http://arxiv.org/abs/1706.08151
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
2021 European Control Conference (ECC).
We propose a neural network approach for solving high-dimensional optimal control problems. In particular, we focus on multi-agent control problems with obstacle and collision avoidance. These problems immediately become high-dimensional, even for mo
Publikováno v:
IEEE Transactions on Control Systems Technology; January 2023, Vol. 31 Issue: 1 p235-251, 17p