Paavo Parmas
Paavo Parmas
Project Assistant Professor, The University of Tokyo
Joined
July 2019
Names
Emails
****@gmail.com (Confirmed)
****@weblab.t.u-tokyo.ac.jp (Confirmed)
****@sys.i.kyoto-u.ac.jp (Confirmed)
Personal Links
Career & Education History
Project Assistant Professor
The University of Tokyo (t.u-tokyo.ac.jp)
2024 – Present
Program Specific Assistant Professor
Kyoto University (kyoto-u.ac.jp)
2020 – 2024
PhD student
Okinawa Institute of Science and Technology (OIST) (oist.jp)
2014 – 2020
Intern
DeepMind (google.com)
2019 – 2019
Intern
RIKEN AIP (riken.jp)
2019 – 2019
Undergrad student
University of Cambridge (cam.ac.uk)
2010 – 2014
Advisors, Relations & Conflicts
Expertise
Monte Carlo gradient estimation
2017 – Present
Policy gradients
2017 – Present
Model-based reinforcement learning
2014 – Present
Reinforcement learning
2014 – Present
Gaussian processes
2014 – 2020
Publications
Co-Authors
- Akihiro Kubo
- Arnob Ghosh
- Audrunas Gruslys
- Carl Edward Rasmussen
- Daniel Hennes
- Dustin Morrill
- Edgar A. Duéñez-Guzmán
- Jan Peters
- Jean-Baptiste Lespiau
- Julien Pérolat
- Karl Tuyls
- Kazumi Kasaura
- Kenji Doya
- Kenta Hoshino
- Ku Onoda
- Manato Yaguchi
- Marc Lanctot
- Masashi Hamaya
- Masashi Sugiyama
- Rémi Munos
- Shayegan Omidshafiei
- Shin Ishii
- Soichiro Nishimori
- Sotetsu Koyamada
- Tadashi Kozuno