Zobrazeno 1 - 10
of 106 337
pro vyhledávání: '"A. Frans"'
In offline reinforcement learning, deriving an effective policy from a pre-collected set of experiences is challenging due to the distribution mismatch between the target policy and the behavioral policy used to collect the data, as well as the limit
Externí odkaz:
http://arxiv.org/abs/2412.06486
Motivated by understanding the nonlinear gravitational dynamics of spacetimes admitting stably trapped null geodesics, such as ultracompact objects and black string solutions to general relativity, we explore the dynamics of nonlinear scalar waves on
Externí odkaz:
http://arxiv.org/abs/2411.17445
Autor:
Riccius, Leon, Rocha, Iuri B. C. M., Bierkens, Joris, Kekkonen, Hanne, van der Meer, Frans P.
Recent advancements in Markov chain Monte Carlo (MCMC) sampling and surrogate modelling have significantly enhanced the feasibility of Bayesian analysis across engineering fields. However, the selection and integration of surrogate models and cutting
Externí odkaz:
http://arxiv.org/abs/2411.13361
Publikováno v:
Frontiers in Artificial Intelligence and Applications, vol. 392, ECAI 2024, pp. 2919-2926
Multi-objective reinforcement learning (MORL) is used to solve problems involving multiple objectives. An MORL agent must make decisions based on the diverse signals provided by distinct reward functions. Training an MORL agent yields a set of soluti
Externí odkaz:
http://arxiv.org/abs/2411.04784
Medical Image Analysis (MedIA) has become indispensable in modern healthcare, enhancing clinical diagnostics and personalized treatment. Despite the remarkable advancements supported by deep learning (DL) technologies, their practical deployment face
Externí odkaz:
http://arxiv.org/abs/2411.05824
Autor:
Hernanz, Margarita, Feroci, Marco, Evangelista, Yuri, Meuris, Aline, Schanne, Stéphane, Zampa, Gianluigi, Tenzer, Chris, Bayer, Jörg, Nowosielski, Witold, Michalska, Malgorzata, Kalemci, Emrah, Sungur, Müberra, Brandt, Søren, Kuvvetli, Irfan, Franco, Daniel Alvarez, Carmona, Alex, Gálvez, José-Luis, Patruno, Alessandro, Zand, Jean in' t, Zwart, Frans, Santangelo, Andrea, Bozzo, Enrico, Zhang, Shuang-Nan, Lu, Fangjun, Xu, Yupeng, Campana, Riccardo, Del Monte, Ettore, Ceraudo, Francesco, Nuti, Alessio, Della Casa, Giovanni, Argan, Andrea, Minervini, Gabriele, Antonelli, Matias, Bonvicini, Valter, Boezio, Mirko, Cirrincione, Daniela, Munini, Riccardo, Rachevski, Alexandre, Vacchi, Andrea, Zampa, Nicola, Rashevskaya, Irina, Ficorella, Francesco, Picciotto, Antonino, Zorzi, Nicola, Baudin, David, Bouyjou, Florent, Gevin, Olivier, Limousin, Olivier, Hedderman, Paul, Pliego, Samuel, Xiong, Hao, de la Rie, Rob, Laubert, Phillip, Aitink-Kroes, Gabby, Kuiper, Lucien, Orleanski, Piotr, Skup, Konrad, Tcherniak, Denis, Turhan, Onur, Bozkurt, Ayhan, Onat, Ahmet
Publikováno v:
Proc. of SPIE 2024 Vol. 13093 130931Y
The eXTP mission is a major project of the Chinese Academy of Sciences (CAS), with a large involvement of Europe. Its scientific payload includes four instruments: SFA, PFA, LAD and WFM. They offer an unprecedented simultaneous wide-band Xray timing
Externí odkaz:
http://arxiv.org/abs/2411.03050
Offline goal-conditioned reinforcement learning (GCRL) is a major problem in reinforcement learning (RL) because it provides a simple, unsupervised, and domain-agnostic way to acquire diverse behaviors and representations from unlabeled data without
Externí odkaz:
http://arxiv.org/abs/2410.20092
Sample-efficient online reinforcement learning often uses replay buffers to store experience for reuse when updating the value function. However, uniform replay is inefficient, since certain classes of transitions can be more relevant to learning. Wh
Externí odkaz:
http://arxiv.org/abs/2410.18082
Unsupervised pretraining has been transformative in many supervised domains. However, applying such ideas to reinforcement learning (RL) presents a unique challenge in that fine-tuning does not involve mimicking task-specific data, but rather explori
Externí odkaz:
http://arxiv.org/abs/2410.18076
Autor:
Afshordi, Niayesh, Ashtekar, Abhay, Barausse, Enrico, Berti, Emanuele, Brito, Richard, Buoninfante, Luca, Carballo-Rubio, Raúl, Cardoso, Vitor, Carullo, Gregorio, Dafermos, Mihalis, De Laurentis, Mariafelicia, del Rio, Adrian, Di Filippo, Francesco, Eichhorn, Astrid, Emparan, Roberto, Gregory, Ruth, Herdeiro, Carlos A. R., Kunz, Jutta, Lehner, Luis, Liberati, Stefano, Mathur, Samir D., Nissanke, Samaya, Pani, Paolo, Platania, Alessia, Pretorius, Frans, Sasaki, Misao, Tiede, Paul, Unruh, William, Visser, Matt, Wald, Robert M.
The gravitational physics landscape is evolving rapidly, driven by our ability to study strong-field regions, in particular black holes. Black Holes Inside and Out gathered world experts to discuss the status of the field and prospects ahead. We hope
Externí odkaz:
http://arxiv.org/abs/2410.14414