Zobrazeno 1 - 10
of 21
pro vyhledávání: '"Freire, Ismael T."'
The hippocampus has been associated with both spatial cognition and episodic memory formation, but integrating these functions into a unified framework remains challenging. Here, we demonstrate that forming discrete memories of visual events in spars
Externí odkaz:
http://arxiv.org/abs/2405.14600
State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspired by the mammalian hippocampus
Externí odkaz:
http://arxiv.org/abs/2112.14734
The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes. Recent studies have tried to overcome this limitation by a
Externí odkaz:
http://arxiv.org/abs/2012.13779
A major challenge in cognitive science and AI has been to understand how autonomous agents might acquire and predict behavioral and mental states of other agents in the course of complex social interactions. How does such an agent model the goals, be
Externí odkaz:
http://arxiv.org/abs/1905.13225
Autor:
Freire, Ismael T., Moulin-Frier, Clement, Sanchez-Fibla, Marti, Arsiwalla, Xerxes D., Verschure, Paul
What is the role of real-time control and learning in the formation of social conventions? To answer this question, we propose a computational model that matches human behavioral data in a social decision-making game that was analyzed both in discret
Externí odkaz:
http://arxiv.org/abs/1802.06108
Autor:
Freire, Ismael T.1 (AUTHOR) ismael.freire@donders.ru.nl, Arsiwalla, Xerxes D.2 (AUTHOR) ismael.freire@donders.ru.nl, Puigbò, Jordi-Ysard2 (AUTHOR), Verschure, Paul1 (AUTHOR) ismael.freire@donders.ru.nl
Publikováno v:
Information (2078-2489). Aug2023, Vol. 14 Issue 8, p441. 20p.
Publikováno v:
In Procedia Computer Science 2021 190:256-262
Autor:
Freire, Ismael T., Guerrero-Rosado, Oscar, Amil, Adrián F., Verschure, Paul F. M. J., Fraboni, Federico, Sziebig, Gabor, Rosen, Patricia Helen
Publikováno v:
Frontiers in Robotics & AI; 2024, p1-19, 19p
Autor:
Freire, Ismael T.1 (AUTHOR) ifreire@ibecbarcelona.eu, Moulin-Frier, Clement2 (AUTHOR), Sanchez-Fibla, Marti3 (AUTHOR), Arsiwalla, Xerxes D.1 (AUTHOR), Verschure, Paul F. M. J.1,4,5 (AUTHOR)
Publikováno v:
PLoS ONE. 6/22/2020, Vol. 15 Issue 6, p1-22. 22p.
State of the art deep reinforcement learning algorithms are sample inefficient due to the large number of episodes they require to achieve asymptotic performance. Episodic Reinforcement Learning (ERL) algorithms, inspired by the mammalian hippocampus
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::683d452d3baf9f597ef7e3daf352502a