Zobrazeno 1 - 10
of 11 188
pro vyhledávání: '"Gros, P"'
Safe reinforcement learning (RL) is a promising approach for many real-world decision-making problems where ensuring safety is a critical necessity. In safe RL research, while expected cumulative safety constraints (ECSCs) are typically the first cho
Externí odkaz:
http://arxiv.org/abs/2410.06474
We propose an extension of the reinforcement learning architecture that enables moral decision-making of reinforcement learning agents based on normative reasons. Central to this approach is a reason-based shield generator yielding a moral shield tha
Externí odkaz:
http://arxiv.org/abs/2409.15014
In this paper, we present a novel method to compute the determinant of a link using Fourier-Hadamard transforms of Boolean functions. We also investigate the determinant of centrally symmetric links (a special class of strong achiral links). In parti
Externí odkaz:
http://arxiv.org/abs/2409.14133
Autor:
Sándor, Bulcsú, Gros, Claudius
Publikováno v:
Artificial Neural Networks and Machine Learning - ICANN 2024. Wand, M., Malinovska, K., Schmidhuber, J., Tetko, I.V. (eds), ICANN 2024. Lecture Notes in Computer Science, vol 15025. Springer, Cham
Locomotion may be induced on three levels. On a classical level, actuators and limbs follow the sequence of open-loop top-down control signals they receive. Limbs may move alternatively on their own, which implies that interlimb coordination must be
Externí odkaz:
http://arxiv.org/abs/2409.13581
This paper proposes a model predictive controller for discrete-time linear systems with additive, possibly unbounded, stochastic disturbances and subject to chance constraints. By computing a polytopic probabilistic positively invariant set for const
Externí odkaz:
http://arxiv.org/abs/2409.13032
Autor:
Arora, M. M., Balogh, L., Beaufort, C., Brossard, A., Chapellier, M., Clarke, J., Corcoran, E. C., Coquillat, J. -M., Dastgheibi-Fard, A., Deng, Y., Durnford, D., Garrah, C., Gerbier, G., Giomataris, I., Giroux, G., Gorel, P., Gros, M., Gros, P., Guillaudin, O., Hoppe, E. W., Katsioulas, I., Kelly, F., Knights, P., Lautridou, P., Makowski, A., Manthos, I., Martin, R. D., Matthews, J., McCallum, H. M., Meadows, H., Millins, L., Muraz, J. -F., Neep, T., Nikolopoulos, K., Panchal, N., Piro, M. -C., Rowe, N., Santos, D., Savvidis, G., Savvidis, I., Spathara, D., Fernandez, F. Vazquez de Sola, Ward, R.
The NEWS-G direct detection experiment uses spherical proportional counters to search for light dark matter candidates. New results from a 10 day physics run with a $135\,\mathrm{cm}$ in diameter spherical proportional counter at the Laboratoire Sout
Externí odkaz:
http://arxiv.org/abs/2407.12769
Autor:
Gros, Claudius
Attention involves comparing query and key vectors in terms of a scalar product, $\mathbf{Q}^T\mathbf{K}$, together with a subsequent softmax normalization. Classicaly, parallel/orthogonal/antiparallel queries and keys lead to large/intermediate/smal
Externí odkaz:
http://arxiv.org/abs/2407.18601
Markov Decision Processes (MDPs) offer a fairly generic and powerful framework to discuss the notion of optimal policies for dynamic systems, in particular when the dynamics are stochastic. However, computing the optimal policy of an MDP can be very
Externí odkaz:
http://arxiv.org/abs/2407.16500
In this chapter, we report on our experience with domestic flexible electric energy demand based on a regular commercial (HVAC)-based heating system in a house. Our focus is on investigating the predictability of the energy demand of the heating syst
Externí odkaz:
http://arxiv.org/abs/2407.16475
The factors contributing to the persistence and stability of life are fundamental for understanding complex living systems. Organisms are commonly challenged by harsh and fluctuating environments that are suboptimal for growth and reproduction, which
Externí odkaz:
http://arxiv.org/abs/2406.13765