Zobrazeno 1 - 10
of 1 903
pro vyhledávání: '"Blonde, A."'
In this paper, we introduce MAAD, a novel, sample-efficient on-policy algorithm for Imitation Learning from Observations. MAAD utilizes a surrogate reward signal, which can be derived from various sources such as adversarial games, trajectory matchin
Externí odkaz:
http://arxiv.org/abs/2306.09805
Autor:
Vivian A Fonseca, John B Buse, Julio Rosenstock, Richard E Pratley, Lawrence Blonde, Irina Bancos, Iulia Cristina Tudor, Ralph A DeFronzo, Richard J Auchus, Robert S Busch, James W Findling, Juan P Frias, Oksana Hamidi, Yehuda Handelsman, Andreas G Moraitis, Daniel Einhorn
Publikováno v:
BMJ Open, Vol 14, Iss 7 (2024)
Introduction Even with recent treatment advances, type 2 diabetes (T2D) remains poorly controlled for many patients, despite the best efforts to adhere to therapies and lifestyle modifications. Although estimates vary, studies indicate that in >10% o
Externí odkaz:
https://doaj.org/article/519af66c56274a5fb81b50cbc366808d
Publikováno v:
In Applied Acoustics 15 January 2025 228
Publikováno v:
In Physiology & Behavior 15 May 2024 279
The performance of state-of-the-art offline RL methods varies widely over the spectrum of dataset qualities, ranging from far-from-optimal random data to close-to-optimal expert demonstrations. We re-implement these methods to test their reproducibil
Externí odkaz:
http://arxiv.org/abs/2107.01407
In this work, we want to learn to model the dynamics of similar yet distinct groups of interacting objects. These groups follow some common physical laws that exhibit specificities that are captured through some vectorial description. We develop a mo
Externí odkaz:
http://arxiv.org/abs/2106.11083
Autor:
Acharya, A., Adhikary, H., Allison, K. K., Amin, N., Andronov, E. V., Antičić, T., Babkin, V., Baszczyk, M., Bhosale, S., Blonde, A., Bogomilov, M., Bondar, Y., Brandin, A., Bravar, A., Brylinski, W., Brzychczyk, J., Buryakov, M., Busygina, O., Bzdak, A., Cherif, H., Ćirković, M., Csanad, M., Cybowska, J., Czopowicz, T., Damyanova, A., Davis, N., Deliyergiyev, M., Deveaux, M., Dmitriev, A., Dominik, W., Dorosz, P., Dumarchez, J., Enge, R., Feofilov, G. A., Fields, L., Fodor, Z., Garibov, A., Gazdzicki, M., Golosov, O., Golovatyuk, V., Golubeva, M., Grebieszkow, K., Guber, F., Haesler, A., Igolkin, S. N., Ilieva, S., Ivashkin, A., Johnson, S. R., Kadija, K., Kargin, N., Kashirin, E., Kiełbowicz, M., Kireyeu, V. A., Klochkov, V., Kolesnikov, V. I., Kolev, D., Korzenev, A., Kovalenko, V. N., Kowalski, S., Kozie, M., Kozłowski, B., Krasnoperov, A., Kucewicz, W., Kuich, M., Kurepin, A., Larsen, D., László, A., Lazareva, T. V., Lewicki, M., Łojek, K., Lyubushkin, V. V., Mackowiak-Pawłowska, M., Majka, Z., Maksiak, B., Malakhov, A. I., Marcinek, A., Marino, A. D., Marton, K., Mathes, H. -J., Matulewicz, T., Matveev, V., Melkumov, G. L., Merzlaya, A. O., Messerly, B., Mik, Ł., Morozov, S., Nagai, Y., Naskret, M., Ozvenchuk, V., Panova, O., Paolone, V., Petukhov, O., Pidhurskyi, I., Płaneta, R., Podlaski, P., Popov, B. A., Porfy, B., Posiadała-Zezula, M., Prokhorova, D. S., Pszczel, D., Puławski, S., Puzović, J., Ravonel, M., Renfordt, R., Röhrich, D., Rondio, E., Rumberger, B. T., Rumyantsev, M., Rustamov, A., Rybczynski, M., Rybicki, A., Sadhu, S., Sadovsky, A., Schmidt, K., Selyuzhenkov, I., Seryakov, A. Yu., Seyboth, P., Słodkowski, M., Staszel, P., Stefanek, G., Stepaniak, J., Strikhanov, M., Ströbele, H., Šuša, T., Taranenko, A., Tefelska, A., Tefelski, D., Tereshchenko, V., Toia, A., Tsenov, R., Turko, L., Unger, M., Uzhva, D., Valiev, F. F., Veberič, D., Vechernin, V. V., Wickremasinghe, A., Wójcik, K., Wyszynski, O., Zaitsev, A., Zimmerman, E. D., Zwaska, R.
The production of $K^{0}_{S}$ mesons in inelastic $\textit{p+p}$ collisions at beam momentum 158 GeV/c ($\sqrt{s_{NN}}=17.3$ GeV) was measured with the NA61/SHINE spectrometer at the CERN Super Proton Synchrotron. Double-differential distributions we
Externí odkaz:
http://arxiv.org/abs/2106.07535
Despite the recent success of reinforcement learning in various domains, these approaches remain, for the most part, deterringly sensitive to hyper-parameters and are often riddled with essential engineering feats allowing their success. We consider
Externí odkaz:
http://arxiv.org/abs/2006.16785
In this work, we introduce a new method for imitation learning from video demonstrations. Our method, Relational Mimic (RM), improves on previous visual imitation learning methods by combining generative adversarial networks and relational learning.
Externí odkaz:
http://arxiv.org/abs/1912.08444
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.