J
Jonas Degrave
Researcher at Ghent University
Publications - 33
Citations - 1778
Jonas Degrave is an academic researcher from Ghent University. The author has contributed to research in topics: Reinforcement learning & Robot. The author has an hindex of 15, co-authored 32 publications receiving 1199 citations. Previous affiliations of Jonas Degrave include Google.
Papers
More filters
Lasagne: First release.
Sander Dieleman,Michael Heilman,Jack Kelly,Martin Thoma,Kashif Rasul,Eric Battenberg,Hendrik Weideman,Søren Kaae Sønderby,instagibbs,Britefury,Colin Raffel,Jonas Degrave,peterderivaz,Jon,Jeffrey De Fauw,diogo,Daniel Nouri,Jan Schlüter,Daniel Maturana,CongLiu,Eben M. Olson,Brian McFee,takacsg +22 more
Journal ArticleDOI
Magnetic control of tokamak plasmas through deep reinforcement learning
Jonas Degrave,Federico Felici,Jonas Buchli,Michael Neunert,Brendan D. Tracey,Francesco Carpanese,Timo Ewalds,Roland Hafner,Abbas Abdolmaleki,Diego de Las Casas,Craig Donner,Leslie Fritz,C. Galperti,Andrea Huber,James Keeling,Maria Tsimpoukell,Jackie Kay,Antoine Merle,Jean-Marc Moret,Seb Noury,F. Pesamosca,D. Pfau,Olivier Sauter,C. Sommariva,Stefano Coda,B. P. Duval,Ambrogio Fasoli,Pushmeet Kohli,Koray Kavukcuoglu,Demis Hassabis,Martin Riedmiller +30 more
TL;DR: In this paper , a novel architecture for tokamak magnetic controller design that autonomously learns to command the full set of control coils is presented. But this approach has unprecedented flexibility and generality in problem specification and yields a notable reduction in design effort to produce new plasma configurations.
Proceedings Article
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Martin Riedmiller,Roland Hafner,Thomas Lampe,Michael Neunert,Jonas Degrave,Tom Van de Wiele,Volodymyr Mnih,Nicolas Heess,Jost Tobias Springenberg +8 more
TL;DR: Scheduled auxiliary control (SAC-X) as discussed by the authors enables learning of complex behaviors from scratch in the presence of multiple sparse reward signals, where the agent is equipped with a set of general auxiliary tasks, that it attempts to learn simultaneously via off-policy RL.
Posted Content
Learning by Playing - Solving Sparse Reward Tasks from Scratch
Martin Riedmiller,Roland Hafner,Thomas Lampe,Michael Neunert,Jonas Degrave,Tom Van de Wiele,Volodymyr Mnih,Nicolas Heess,Jost Tobias Springenberg +8 more
TL;DR: The key idea behind the method is that active (learned) scheduling and execution of auxiliary policies allows the agent to efficiently explore its environment - enabling it to excel at sparse reward RL.
Journal ArticleDOI
A Differentiable Physics Engine for Deep Learning in Robotics
TL;DR: In this article, the authors propose a physics engine that can differentiate control parameters, which is implemented for both CPU and GPU and shows how such an engine can speed up the optimization process, even for small problems.