Alert button
Picture for Hubert Soyer

Hubert Soyer

Alert button

Hierarchical Reinforcement Learning in Complex 3D Environments

Feb 28, 2023
Bernardo Avila Pires, Feryal Behbahani, Hubert Soyer, Kyriacos Nikiforou, Thomas Keck, Satinder Singh

Figure 1 for Hierarchical Reinforcement Learning in Complex 3D Environments
Figure 2 for Hierarchical Reinforcement Learning in Complex 3D Environments
Figure 3 for Hierarchical Reinforcement Learning in Complex 3D Environments
Figure 4 for Hierarchical Reinforcement Learning in Complex 3D Environments
Viaarxiv icon

V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control

Sep 26, 2019
H. Francis Song, Abbas Abdolmaleki, Jost Tobias Springenberg, Aidan Clark, Hubert Soyer, Jack W. Rae, Seb Noury, Arun Ahuja, Siqi Liu, Dhruva Tirumala, Nicolas Heess, Dan Belov, Martin Riedmiller, Matthew M. Botvinick

Figure 1 for V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Figure 2 for V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Figure 3 for V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Figure 4 for V-MPO: On-Policy Maximum a Posteriori Policy Optimization for Discrete and Continuous Control
Viaarxiv icon

Making Efficient Use of Demonstrations to Solve Hard Exploration Problems

Sep 03, 2019
Tom Le Paine, Caglar Gulcehre, Bobak Shahriari, Misha Denil, Matt Hoffman, Hubert Soyer, Richard Tanburn, Steven Kapturowski, Neil Rabinowitz, Duncan Williams, Gabriel Barth-Maron, Ziyu Wang, Nando de Freitas, Worlds Team

Figure 1 for Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Figure 2 for Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Figure 3 for Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Figure 4 for Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
Viaarxiv icon

Multi-task Deep Reinforcement Learning with PopArt

Sep 12, 2018
Matteo Hessel, Hubert Soyer, Lasse Espeholt, Wojciech Czarnecki, Simon Schmitt, Hado van Hasselt

Figure 1 for Multi-task Deep Reinforcement Learning with PopArt
Figure 2 for Multi-task Deep Reinforcement Learning with PopArt
Figure 3 for Multi-task Deep Reinforcement Learning with PopArt
Figure 4 for Multi-task Deep Reinforcement Learning with PopArt
Viaarxiv icon

IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures

Jun 28, 2018
Lasse Espeholt, Hubert Soyer, Remi Munos, Karen Simonyan, Volodymir Mnih, Tom Ward, Yotam Doron, Vlad Firoiu, Tim Harley, Iain Dunning, Shane Legg, Koray Kavukcuoglu

Figure 1 for IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Figure 2 for IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Figure 3 for IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Figure 4 for IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Viaarxiv icon

Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery

May 13, 2018
Thomas Stepleton, Razvan Pascanu, Will Dabney, Siddhant M. Jayakumar, Hubert Soyer, Remi Munos

Figure 1 for Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Figure 2 for Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Figure 3 for Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Figure 4 for Low-pass Recurrent Neural Networks - A memory architecture for longer-term correlation discovery
Viaarxiv icon

Grounded Language Learning in a Simulated 3D World

Jun 26, 2017
Karl Moritz Hermann, Felix Hill, Simon Green, Fumin Wang, Ryan Faulkner, Hubert Soyer, David Szepesvari, Wojciech Marian Czarnecki, Max Jaderberg, Denis Teplyashin, Marcus Wainwright, Chris Apps, Demis Hassabis, Phil Blunsom

Figure 1 for Grounded Language Learning in a Simulated 3D World
Figure 2 for Grounded Language Learning in a Simulated 3D World
Figure 3 for Grounded Language Learning in a Simulated 3D World
Figure 4 for Grounded Language Learning in a Simulated 3D World
Viaarxiv icon

Learning to reinforcement learn

Jan 23, 2017
Jane X Wang, Zeb Kurth-Nelson, Dhruva Tirumala, Hubert Soyer, Joel Z Leibo, Remi Munos, Charles Blundell, Dharshan Kumaran, Matt Botvinick

Figure 1 for Learning to reinforcement learn
Figure 2 for Learning to reinforcement learn
Figure 3 for Learning to reinforcement learn
Figure 4 for Learning to reinforcement learn
Viaarxiv icon

Learning to Navigate in Complex Environments

Jan 13, 2017
Piotr Mirowski, Razvan Pascanu, Fabio Viola, Hubert Soyer, Andrew J. Ballard, Andrea Banino, Misha Denil, Ross Goroshin, Laurent Sifre, Koray Kavukcuoglu, Dharshan Kumaran, Raia Hadsell

Figure 1 for Learning to Navigate in Complex Environments
Figure 2 for Learning to Navigate in Complex Environments
Figure 3 for Learning to Navigate in Complex Environments
Figure 4 for Learning to Navigate in Complex Environments
Viaarxiv icon

Progressive Neural Networks

Sep 07, 2016
Andrei A. Rusu, Neil C. Rabinowitz, Guillaume Desjardins, Hubert Soyer, James Kirkpatrick, Koray Kavukcuoglu, Razvan Pascanu, Raia Hadsell

Figure 1 for Progressive Neural Networks
Figure 2 for Progressive Neural Networks
Figure 3 for Progressive Neural Networks
Figure 4 for Progressive Neural Networks
Viaarxiv icon