Zobrazeno 1 - 10
of 25
pro vyhledávání: '"Korkmaz, Ezgi"'
Autor:
Korkmaz, Ezgi
Deep neural policies have recently been installed in a diverse range of settings, from biotechnology to automated financial systems. However, the utilization of deep neural networks to approximate the value function leads to concerns on the decision
Externí odkaz:
http://arxiv.org/abs/2406.16979
Autor:
Korkmaz, Ezgi
Reinforcement learning research obtained significant success and attention with the utilization of deep neural networks to solve problems in high dimensional state or action spaces. While deep reinforcement learning policies are currently being deplo
Externí odkaz:
http://arxiv.org/abs/2401.02349
Autor:
Korkmaz, Ezgi, Brown-Cohen, Jonah
Learning in MDPs with highly complex state representations is currently possible due to multiple advancements in reinforcement learning algorithm design. However, this incline in complexity, and furthermore the increase in the dimensions of the obser
Externí odkaz:
http://arxiv.org/abs/2306.05873
Autor:
Korkmaz, Ezgi
Learning from raw high dimensional data via interaction with a given environment has been effectively achieved through the utilization of deep neural networks. Yet the observed degradation in policy performance caused by imperceptible worst-case poli
Externí odkaz:
http://arxiv.org/abs/2301.07487
Autor:
Korkmaz, Ezgi
The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision boundary geometry and the loss landscape of neural policies is still
Externí odkaz:
http://arxiv.org/abs/2112.09025
Autor:
Korkmaz, Ezgi
Reinforcement learning policies based on deep neural networks are vulnerable to imperceptible adversarial perturbations to their inputs, in much the same way as neural network image classifiers. Recent work has proposed several methods to improve the
Externí odkaz:
http://arxiv.org/abs/2108.13093
Autor:
Çalışkan, Meltem1 meltem_alts@hotmail.com, Korkmaz, Ezgi1 korkmaze@yildiz.edu.tr
Publikováno v:
Urban Academy/ Kent Akademisi. Spring2023, Vol. 16 Issue 1, p632-661. 30p.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Autor:
Korkmaz, Ezgi
Publikováno v:
Proceedings of the AAAI Conference on Artificial Intelligence. 36:7229-7238
The use of deep neural networks as function approximators has led to striking progress for reinforcement learning algorithms and applications. Yet the knowledge we have on decision boundary geometry and the loss landscape of neural policies is still
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::18df8bccd7e0aab713a81c3a8ab8d2b8
https://doi.org/10.1609/aaai.v36i7.20684
https://doi.org/10.1609/aaai.v36i7.20684
Autor:
Cengiz, Hasan Tunay1 tunaycengiz@halic.edu.tr, Gedik, Gülay Zorer2 gzorer@hotmail.com, Korkmaz, Ezgi2 korkmaz.ezgi@gmail.com
Publikováno v:
Journal of the Faculty of Engineering & Architecture of Gazi University / Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi,. 2024, Vol. 39 Issue 4, p2395-2408. 15p.