Jonas Degrave

Universidade Federal do Rio de Janeiro — Brazil

Computer Science · Physical Sciences

16h-index1.8kcitations39works5.92yr avg
OpenAlex↗ORCID↗Google Scholar↗Lab page↗

Accepting Students?

No reports yet. Know if this professor is taking students?

Research Topics

Reinforcement Learning in Robotics(9), Robotic Locomotion and Control(8), Magnetic confinement fusion research(5), Advanced Control Systems Optimization(4), Biomimetic flight and propulsion mechanisms(4)

Publications39 total

Sensor fusion applications in atmospheric sounding rockets
National repository of research data in engineering·2025Open Access
Improving cosmological reach of a gravitational wave observatory using Deep Loop Shaping
Science·2025· 3 citedOpen Access
Experimental research on the TCV tokamak
Nuclear Fusion·2024· 25 citedOpen Access
X-point radiator and power exhaust control in configurations with multiple X-points in TCV
Physics of Plasmas·2024· 6 citedOpen Access
TORAX: A Fast and Differentiable Tokamak Transport Simulator in JAX
arXiv (Cornell University)·2024· 6 citedOpen Access
X-point radiator and power exhaust control in configurations with multiple X-points in TCV
Zenodo (CERN European Organization for Nuclear Research)·2024· 1 citedOpen Access
X-point radiator and power exhaust control in configurations with multiple X-points in TCV
Zenodo (CERN European Organization for Nuclear Research)·2024Open Access
Magnetic control of tokamak plasmas through deep reinforcement learning
Nature·2022· 654 citedOpen Access
Shaking the foundations: delusions in sequence models for interaction and control
arXiv (Cornell University)·2021· 7 citedOpen Access
Shaking the foundations: delusions in sequence models for interaction\n and control
arXiv (Cornell University)·2021· 19 citedOpen Access
Local Search for Policy Iteration in Continuous Control
arXiv (Cornell University)·2020· 8 citedOpen Access
Exchangeable Models in Meta Reinforcement Learning
2020
Quinoa: a Q-function You Infer Normalized Over Actions
arXiv (Cornell University)·2019· 4 citedOpen Access
A Differentiable Physics Engine for Deep Learning in Robotics
Frontiers in Neurorobotics·2019· 164 citedOpen Access
Self-supervised Learning of Image Embedding for Continuous Control
arXiv (Cornell University)·2019· 30 citedOpen Access
Relative Entropy Regularized Policy Iteration
arXiv (Cornell University)·2018· 45 citedOpen Access
Dual Rectified Linear Units (DReLUs): A replacement for tanh activation functions in Quasi-Recurrent Neural Networks
Pattern Recognition Letters·2018· 47 citedOpen Access
Learning by Playing - Solving Sparse Reward Tasks from Scratch
International Conference on Machine Learning·2018· 152 cited
Learning by Playing - Solving Sparse Reward Tasks from Scratch
arXiv (Cornell University)·2018· 154 citedOpen Access
BRUNO: A Deep Recurrent Model for Exchangeable Data
arXiv (Cornell University)·2018· 16 citedOpen Access
page 1 of 2Next →

Frequent Co-authors

Joni Dambre(14), Francis wyffels(11), Martin Riedmiller(9), F. Felici(6), Jonas Buchli(6), Abbas Abdolmaleki(6), Nicolas Heess(6), Jost Tobias Springenberg(6), Brendan Tracey(5), Timo Ewalds(5), B.P. Duval(5), Iryna Korshunova(5), Benjamin Schrauwen(5), Roland Hafner(4), Craig Donner(4), A. Merle(4), G. Durr-Legoupil-Nicoud(4), O. Février(4), Tim Waegeman(4), Michael Neunert(3)