Alexander Pashevich

photo
Pashevich Alexander, PhD student
Member of THOTH Team (INRIA Rhone-Alpes, Grenoble, France)

INRIA Rhone-Alpes
655 Avenue de l'Europe
38330 Montbonnot
France
Phone
Fax
Office
E-mail
:
:
:
:
-
-
H117
firstname.lastname@inria.fr

I am currently a Research Intern at Google and a third year PhD student at Inria, under Cordelia Schmid's and Ivan Laptev's supervision. My research interests include Reinforcement Learning, Robotics, Imitation Learning, Sim2Real transfer and Control Theory. Please take a look at my CV and a list of publications below.



Publications

Publications HAL de pashevich

titre
Learning visual policies for building 3D shape categories
auteur
Alexander Pashevich, Igor Kalevatykh, Ivan Laptev, Cordelia Schmid
article
IROS 2020, Oct 2020, Las Vegas, United States
Accès au bibtex
https://arxiv.org/pdf/2004.07950 BibTex
titre
Learning to combine primitive skills: A step towards versatile robotic manipulation
auteur
Robin Strudel, Alexander Pashevich, Igor Kalevatykh, Ivan Laptev, Josef Sivic, Cordelia Schmid
article
ICRA 2020 - IEEE International Conference on Robotics and Automation, May 2020, Paris / Virtuel, France
Accès au bibtex
https://arxiv.org/pdf/1908.00722 BibTex
titre
Learning to Augment Synthetic Images for Sim2Real Policy Transfer
auteur
Alexander Pashevich, Robin Strudel, Igor Kalevatykh, Ivan Laptev, Cordelia Schmid
article
IROS 2019 - IEEE/RSJ International Conference on Intelligent Robots and Systems, Nov 2019, Macao, China. pp.2651-2657, ⟨10.1109/IROS40897.2019.8967622⟩
Accès au bibtex
https://arxiv.org/pdf/1903.07740 BibTex
titre
Modulated Policy Hierarchies
auteur
Alexander Pashevich, Danijar Hafner, James Davidson, Rahul Sukthankar, Cordelia Schmid
article
Deep Reinforcement Learning Workshop at NeurIPS 2018, Dec 2018, Montreal, Canada
Accès au bibtex
https://arxiv.org/pdf/1812.00025 BibTex
titre
Plane-extraction from depth-data using a Gaussian mixture regression model
auteur
Richard Marriott, Alexander Pashevich, Radu Horaud
article
Pattern Recognition Letters, Elsevier, 2018, 110, pp.44-50. ⟨10.1016/j.patrec.2018.03.024⟩
Accès au texte intégral et bibtex
https://hal.inria.fr/hal-01663984/file/Mariott-arXiv-v2.pdf BibTex