Zobrazeno 1 - 10
of 535
pro vyhledávání: '"A Castanyer"'
Extrinsic rewards can effectively guide reinforcement learning (RL) agents in specific tasks. However, extrinsic rewards frequently fall short in complex environments due to the significant human effort needed for their design and annotation. This li
Externí odkaz:
http://arxiv.org/abs/2405.19548
Both entropy-minimizing and entropy-maximizing (curiosity) objectives for unsupervised reinforcement learning (RL) have been shown to be effective in different environments, depending on the environment's level of natural entropy. However, neither me
Externí odkaz:
http://arxiv.org/abs/2405.17243
Exploration bonuses in reinforcement learning guide long-horizon exploration by defining custom intrinsic objectives. Several exploration objectives like count-based bonuses, pseudo-counts, and state-entropy maximization are non-stationary and hence
Externí odkaz:
http://arxiv.org/abs/2310.18144
Autor:
Castanyer, Roger Creus
Multi-agent Reinforcement learning (MARL) studies the behaviour of multiple learning agents that coexist in a shared environment. MARL is more challenging than single-agent RL because it involves more complex learning dynamics: the observations and r
Externí odkaz:
http://arxiv.org/abs/2304.13004
Publikováno v:
Beilstein Journal of Organic Chemistry, Vol 20, Iss 1, Pp 272-279 (2024)
The regioselective functionalization of fullerenes holds significant promise for applications in the fields of medicinal chemistry, materials science, and photovoltaics. In this study, we investigate the regioselectivity of the rhodium(I)-catalyzed [
Externí odkaz:
https://doaj.org/article/cce4c2f638ae41b09515118bcd196630
Autor:
López Castillo, Eva Maria, López-Bultó, Oriol, Berrocal Barberà, Anna, Castanyer Masoliver, Pere, Pera Isern, Joaquim, Rodrigo Requena, Esther, Piqué Huerta, Raquel
Publikováno v:
In Quaternary International 30 July 2024 699:35-46
Autor:
François Alexandre, Virginie Molinier, Louis Hognon, Laurène Charbonnel, Amandine Calvat, Adriana Castanyer, Thomas Henry, Aurélien Marcenac, Morgane Jollive, Antonin Vernet, Nicolas Oliver, Nelly Heraud
Publikováno v:
COPD, Vol 20, Iss 1, Pp 55-63 (2023)
This study aimed to assess the time-course of changes in multidimensional fatigue and functional exercise capacity and their associations during an inpatient pulmonary rehabilitation (PR) program. Seventy COPD patients from three centres were enrolle
Externí odkaz:
https://doaj.org/article/ad173d4a51134e1b8ef7d5019a9feb44
Background: The construction, evolution and usage of complex artificial intelligence (AI) models demand expensive computational resources. While currently available high-performance computing environments support well this complexity, the deployment
Externí odkaz:
http://arxiv.org/abs/2109.15284
Autor:
Travé Allepuz, Esther, Espona, Montserrat de Rocafiguera, Castanyer, Imma Ollich, Sala, Albert Pratdesaba, Subirana, Maria Ocaña
Publikováno v:
In Journal of Archaeological Science: Reports February 2024 53
When building Deep Learning (DL) models, data scientists and software engineers manage the trade-off between their accuracy, or any other suitable success criteria, and their complexity. In an environment with high computational power, a common pract
Externí odkaz:
http://arxiv.org/abs/2103.07286