Zobrazeno 1 - 6
of 6
pro vyhledávání: '"Parag, Amit"'
Autor:
Parag, Amit
Publikováno v:
Automatic. INSA de Toulouse, 2023. English. ⟨NNT : 2023ISAT0008⟩
L'apprentissage profond par renforcement utilise des simulateurs comme oracles abstraits pour interagir avec l'environnement. Dans les domaines continus des systèmes robotiques multi-corps, des simulateurs différentiables ont récemment été propo
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______4074::635f5cee61ad6d1331f1e5cd6145caee
https://theses.hal.science/tel-04164722
https://theses.hal.science/tel-04164722
Autor:
Parag, Amit
Publikováno v:
Automatic. INSA TOULOUSE, 2023. English. ⟨NNT : ⟩
National audience; Deep reinforcement learning uses simulators as abstract oracles to interact with the environment. In continuous domains of multi-body robotic systems, differentiable simulators have recently been proposed, still, they are yet under
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=od______4074::1a8fc32150cbfbddcec235b39a2b3fc6
https://hal.laas.fr/tel-04121962
https://hal.laas.fr/tel-04121962
Autor:
Parag, Amit, Mansard, Nicolas
Deep reinforcement learning uses simulators as abstract oracles to interact with the environment. In continuous domains of multi body robotic systems, differentiable simulators have recently been proposed but are yet under utilized, even though we ha
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::e40b14bd38864812ff017ec358f0a17e
https://hal.science/hal-03674092
https://hal.science/hal-03674092
Autor:
Parag, Amit, Belle, Vaishak
Cosmological simulations aim to understand the matter distribution in the universe either by following a semi-analytic approach or by formulating a hydrodynamical version of the matter distribution. Both approaches describe the evolution of baryonic
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::3467b2ab668e5fb2fadbd6e0e5d71b23
https://hal.science/hal-03744489/document
https://hal.science/hal-03744489/document
Autor:
Budhiraja, Rohan, Parag, Amit, Dantec, Ewen, Carpentier, Justin, Mastalli, Carlos, Mansard, Nicolas
Publikováno v:
Journées Nationales de la Robotique Humanoïde
Journées Nationales de la Robotique Humanoïde, May 2020, Paris (virtual), France
Journées Nationales de la Robotique Humanoïde, May 2020, Paris (virtual), France
7 pages; National audience; For a given motion task, an ideal Optimal Control (OC) solver could plan the entire future motion trajectory of arobot in real-time. However, this ideal scenario cannot bereached because of a few factores. (i) These OC pro
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=dedup_wf_001::c4c5dcb1d2aead57743746b6f265fe14
https://hal.laas.fr/hal-02898916
https://hal.laas.fr/hal-02898916
Publikováno v:
International Journal of Advanced Research in Computer Science; Sep/Oct2017, Vol. 8 Issue 8, p307-311, 5p
