Zobrazeno 1 - 10
of 1 025
pro vyhledávání: '"Laterre, P"'
Leveraging planning during learning and decision-making is central to the long-term development of intelligent agents. Recent works have successfully combined tree-based search methods and self-play learning mechanisms to this end. However, these met
Externí odkaz:
http://arxiv.org/abs/2402.07963
Autor:
Chalumeau, Felix, Surana, Shikha, Bonnet, Clement, Grinsztajn, Nathan, Pretorius, Arnu, Laterre, Alexandre, Barrett, Thomas D.
Combinatorial Optimization underpins many real-world applications and yet, designing performant algorithms to solve these complex, typically NP-hard, problems remains a significant research challenge. Reinforcement Learning (RL) provides a versatile
Externí odkaz:
http://arxiv.org/abs/2311.13569
Autor:
Benoît Misset, Anh Nguyet Diep, Axelle Bertrand, Michael Piagnerelli, Eric Hoste, Isabelle Michaux, Elisabeth De Waele, Alexander Dumoulin, Philippe G. Jorens, Emmanuel van der Hauwaert, Frédéric Vallot, Walter Swinnen, Nicolas De Schryver, Nathalie de Mey, Nathalie Layios, Jean-Baptiste Mesland, Sébastien Robinet, Etienne Cavalier, Anne-Françoise Donneau, Michel Moutschen, Pierre-François Laterre
Publikováno v:
Annals of Intensive Care, Vol 14, Iss 1, Pp 1-11 (2024)
Abstract Background Convalescent plasma (CP) reduced the mortality in COVID-19 induced ARDS (C-ARDS) patients treated in the CONFIDENT trial. As patients are immunologically heterogeneous, we hypothesized that clusters may differ in their treatment r
Externí odkaz:
https://doaj.org/article/11cbf2802403454c91f23784e9bf64b7
Autor:
Bonnet, Clément, Luo, Daniel, Byrne, Donal, Surana, Shikha, Abramowitz, Sasha, Duckworth, Paul, Coyette, Vincent, Midgley, Laurence I., Tegegn, Elshadai, Kalloniatis, Tristan, Mahjoub, Omayma, Macfarlane, Matthew, Smit, Andries P., Grinsztajn, Nathan, Boige, Raphael, Waters, Cemlyn N., Mimouni, Mohamed A., Sob, Ulrich A. Mbou, de Kock, Ruan, Singh, Siddarth, Furelos-Blanco, Daniel, Le, Victor, Pretorius, Arnu, Laterre, Alexandre
Open-source reinforcement learning (RL) environments have played a crucial role in driving progress in the development of AI algorithms. In modern RL research, there is a need for simulated environments that are performant, scalable, and modular to e
Externí odkaz:
http://arxiv.org/abs/2306.09884
Autor:
Javier Mendoza-Revilla, Evan Trop, Liam Gonzalez, Maša Roller, Hugo Dalla-Torre, Bernardo P. de Almeida, Guillaume Richard, Jonathan Caton, Nicolas Lopez Carranza, Marcin Skwark, Alex Laterre, Karim Beguir, Thomas Pierrot, Marie Lopez
Publikováno v:
Communications Biology, Vol 7, Iss 1, Pp 1-18 (2024)
Abstract Significant progress has been made in the field of plant genomics, as demonstrated by the increased use of high-throughput methodologies that enable the characterization of multiple genome-wide molecular phenotypes. These findings have provi
Externí odkaz:
https://doaj.org/article/8af619509e904512a946b50928ccabd2
Meta-gradient Reinforcement Learning (RL) allows agents to self-tune their hyper-parameters in an online fashion during training. In this paper, we identify a bias in the meta-gradient of current meta-gradient RL approaches. This bias comes from usin
Externí odkaz:
http://arxiv.org/abs/2211.10550
Publikováno v:
AAAI'23: Proceedings of the Thirty-Seventh AAAI Conference on Artificial Intelligence, 2023
Combinatorial optimisation problems framed as mixed integer linear programmes (MILPs) are ubiquitous across a range of real-world applications. The canonical branch-and-bound algorithm seeks to exactly solve MILPs by constructing a search tree of inc
Externí odkaz:
http://arxiv.org/abs/2205.14345
From logistics to the natural sciences, combinatorial optimisation on graphs underpins numerous real-world applications. Reinforcement learning (RL) has shown particular promise in this setting as it can adapt to specific problem structures and does
Externí odkaz:
http://arxiv.org/abs/2205.14105
Autor:
Jonathan Dugernier, Déborah Le Pennec, Guillaume Maerckx, Laurine Allimonnier, Michel Hesse, Diego Castanares-Zapatero, Virginie Depoortere, Laurent Vecellio, Gregory Reychler, Jean-Bernard Michotte, Pierre Goffette, Marie-Agnes Docquier, Christian Raftopoulos, François Jamar, Pierre-François Laterre, Stephan Ehrmann, Xavier Wittebole
Publikováno v:
Annals of Intensive Care, Vol 13, Iss 1, Pp 1-13 (2023)
Abstract Background The administration technique for inhaled drug delivery during invasive ventilation remains debated. This study aimed to compare in vivo and in vitro the deposition of a radiolabeled aerosol generated through four configurations du
Externí odkaz:
https://doaj.org/article/633d13f21753458a8fc6212c33724093
Self-tuning algorithms that adapt the learning process online encourage more effective and robust learning. Among all the methods available, meta-gradients have emerged as a promising approach. They leverage the differentiability of the learning rule
Externí odkaz:
http://arxiv.org/abs/2111.00206