Guillaume Desjardins

Research Scientist, DeepMind

Joined

November 2016

Names

Guillaume Desjardins (Preferred)

Emails

****@gmail.com (Confirmed)

****@google.com

Personal Links

Career & Education History

Research Scientist

DeepMind (google.com)

2014 – Present

PhD student

University of Montreal (umontreal.ca)

2009 – 2014

Advisors, Relations & Conflicts

No relations added

Expertise

reinforcement learning

rl as inference

intrinsic rewards

hierarchical reinforcement learning

2017 – Present

optimization

fisher information matrix

natural gradient

2013 – Present

deep learning

generative models

RNNs

optimization

2009 – Present

Publications

Imitating Language via Scalable Inverse Reinforcement Learning
Markus Wulfmeier, Michael Bloesch, Nino Vieillard, Arun Ahuja, Jorg Bornschein, Sandy Huang, Artem Sokolov, Matt Barnes, Guillaume Desjardins, Alex Bewley, Sarah Maria Elisabeth Bechtle, Jost Tobias Springenberg, Nikola Momchev, Olivier Bachem, Matthieu Geist, Martin Riedmiller
- NeurIPS 2024 poster
- Readers: Everyone
APART: Diverse Skill Discovery using All Pairs with Ascending Reward and DropouT
Hadar Schreiber, Tom Zahavy, Guillaume Desjardins, Alon Cohen
- Published: 20 Jul 2023, Last Modified: 29 Aug 2023
- EWRL16
- Readers: Everyone
Entropic Desired Dynamics for Intrinsic Control
Steven Stenberg Hansen, Guillaume Desjardins, Kate Baumli, David Warde-Farley, Nicolas Heess, Simon Osindero, Volodymyr Mnih
- 13 May 2022
- OpenReview Archive Direct Upload
- Readers: Everyone
Reward is enough for convex MDPs
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
- Published: 22 Jul 2021, Last Modified: 05 May 2023
- URL 2021 Poster
- Readers: Everyone
Entropic Desired Dynamics for Intrinsic Control
Steven Stenberg Hansen, Guillaume Desjardins, Kate Baumli, David Warde-Farley, Nicolas Heess, Simon Osindero, Volodymyr Mnih
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Entropic Desired Dynamics for Intrinsic Control
Steven Stenberg Hansen, Guillaume Desjardins, Kate Baumli, David Warde-Farley, Nicolas Heess, Simon Osindero, Volodymyr Mnih
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Poster
- Readers: Everyone
Reward is enough for convex MDPs
Tom Zahavy, Brendan O'Donoghue, Guillaume Desjardins, Satinder Singh
- Published: 09 Nov 2021, Last Modified: 05 May 2023
- NeurIPS 2021 Spotlight
- Readers: Everyone
Behavior Priors for Efficient Reinforcement Learning
Dhruva Tirumala, Alexandre Galashov, Hyeonwoo Noh, Leonard Hasenclever, Razvan Pascanu, Jonathan Schwarz, Guillaume Desjardins, Wojciech M. Czarnecki, Arun Ahuja, Yee Whye Teh, Nicolas Heess
- 10 May 2021 (modified: 16 Jun 2022)
- OpenReview Archive Direct Upload
- Readers: Everyone
Compress and Control
Joel Veness, Marc G. Bellemare, Marcus Hutter, Alvin Chua, Guillaume Desjardins
- 2015 (modified: 16 Jul 2019)
- AAAI 2015
- Readers: Everyone
Natural Neural Networks
Guillaume Desjardins, Karen Simonyan, Razvan Pascanu, Koray Kavukcuoglu
- 2015 (modified: 11 Nov 2022)
- NIPS 2015
- Readers: Everyone

View all 11 publications

Co-Authors

View all 42 co-authors