Zobrazeno 1 - 10
of 9 101
pro vyhledávání: '"Laidlaw A"'
Autor:
Rivera, Gabriela Calistro, Heirich, Oliver, Shrestha, Amita, Ferenczi, Agnes, Duliu, Alexandru, Eppinger, Jakob, Castella, Bruno Femenia, Fuchs, Christian, Garbagnati, Elisa, Laidlaw, Douglas, Lützen, Pia, De Marco, Innocenzo, Moll, Florian, Prell, Johannes, Reeves, Andrew, Nonay, Jorge Rosano, Roubal, Christian, Torres, Joana S., Wagner, Matthias
The EAGLE-1 mission aims to develop Europe's first sovereign, end-to-end space-based quantum key distribution (QKD) system. The mission is led by the European Space Agency (ESA) and SES in collaboration with several European National Space Agencies a
Externí odkaz:
http://arxiv.org/abs/2412.03222
Autor:
Larsen, Thomas, Royer, John R., Laidlaw, Fraser H. J., Poon, Wilson C. K., Larsen, Tom, Andreasen, Søren J., Christiansen, Jesper de C.
A unique bistable transition has been identified in granular/colloidal gel-composites, resulting from shear-induced phase separation of the gel phase into dense blobs. In energy applications, it is critical to understand how this transition influence
Externí odkaz:
http://arxiv.org/abs/2405.06974
Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using flawed proxy rewards that seem to capture the true objective. However, optimizing proxy rewards frequently leads to reward hack
Externí odkaz:
http://arxiv.org/abs/2403.03185
Publikováno v:
Powder Technology 441 (2024) 119791
Cement is an essential construction material due to its ability to flow before later setting, however the rheological properties must be tightly controlled. Despite this, much understanding remains empirical. Using a combination of continuous and osc
Externí odkaz:
http://arxiv.org/abs/2401.09377
Autor:
Cooke, Lauren H., Klyne, Harvey, Zhang, Edwin, Laidlaw, Cassidy, Tambe, Milind, Doshi-Velez, Finale
Inverse reinforcement learning (IRL) is computationally challenging, with common approaches requiring the solution of multiple reinforcement learning (RL) sub-problems. This work motivates the use of potential-based reward shaping to reduce the compu
Externí odkaz:
http://arxiv.org/abs/2312.09983
Publikováno v:
ICLR 2024 (Spotlight)
Reinforcement learning (RL) theory has largely focused on proving minimax sample complexity bounds. These require strategic exploration algorithms that use relatively limited function classes for representing the policy or value function. Our goal is
Externí odkaz:
http://arxiv.org/abs/2312.08369
In practice, preference learning from human feedback depends on incomplete data with hidden context. Hidden context refers to data that affects the feedback received, but which is not represented in the data used to train a preference model. This cap
Externí odkaz:
http://arxiv.org/abs/2312.08358
Autor:
Larsen, Thomas, Royer, John R., Laidlaw, Fraser H. J., Poon, Wilson C. K., Larsen, Tom, Andreasen, Søren J., Christiansen, Jesper de C.
The ability to manipulate rheological and electrical properties of colloidal carbon black gels makes them attractive in composites for energy applications such as batteries and fuel cells, where they conduct electricity and prevent sedimentation of `
Externí odkaz:
http://arxiv.org/abs/2311.05302
Autor:
Picetti, Francesco, Deshpande, Shrinath, Leban, Jonathan, Shahtalebi, Soroosh, Patel, Jay, Jing, Peifeng, Wang, Chunpu, Metze III, Charles, Sun, Cameron, Laidlaw, Cera, Warren, James, Huynh, Kathy, Page, River, Hogins, Jonathan, Crespi, Adam, Ganguly, Sujoy, Ebadi, Salehe Erfanian
We present a novel human body model formulated by an extensive set of anthropocentric measurements, which is capable of generating a wide range of human body shapes and poses. The proposed model enables direct modeling of specific human identities th
Externí odkaz:
http://arxiv.org/abs/2309.03812
Publikováno v:
NeurIPS 2023 (Oral)
Deep reinforcement learning (RL) works impressively in some environments and fails catastrophically in others. Ideally, RL theory should be able to provide an understanding of why this is, i.e. bounds predictive of practical performance. Unfortunatel
Externí odkaz:
http://arxiv.org/abs/2304.09853