Zobrazeno 1 - 4
of 4
pro vyhledávání: '"Lopera, Daniela Sánchez"'
Autor:
Ott, Julius, Servadei, Lorenzo, Arjona-Medina, Jose, Rinaldi, Enrico, Mauro, Gianfranco, Lopera, Daniela Sánchez, Stephan, Michael, Stadelmayer, Thomas, Santra, Avik, Wille, Robert
Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do
Externí odkaz:
http://arxiv.org/abs/2210.13545
Autor:
Servadei, Lorenzo, Sun, Huawei, Ott, Julius, Stephan, Michael, Hazra, Souvik, Stadelmayer, Thomas, Lopera, Daniela Sanchez, Wille, Robert, Santra, Avik
In this paper, we introduce the Label-Aware Ranked loss, a novel metric loss function. Compared to the state-of-the-art Deep Metric Learning losses, this function takes advantage of the ranked ordering of the labels in regression problems. To this en
Externí odkaz:
http://arxiv.org/abs/2110.05876
Autor:
Ott, Julius, Servadei, Lorenzo, Arjona-Medina, Jose, Rinaldi, Enrico, Mauro, Gianfranco, Lopera, Daniela Sánchez, Stephan, Michael, Stadelmayer, Thomas, Santra, Avik, Wille, Robert
Publikováno v:
ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).
Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve the performance of the Reinforcement Learning agent. However, they do
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::1bcc5475718a53b6e720313d09f2d8f4
https://doi.org/10.1109/icassp49357.2023.10095236
https://doi.org/10.1109/icassp49357.2023.10095236
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.