Agent57: Outperforming the Atari Human Benchmark

Mar 30, 2020
Adrià Puigdomènech Badia, Bilal Piot, Steven Kapturowski, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Charles Blundell


  Access Model/Code and Paper
Never Give Up: Learning Directed Exploration Strategies

Feb 14, 2020
Adrià Puigdomènech Badia, Pablo Sprechmann, Alex Vitvitskyi, Daniel Guo, Bilal Piot, Steven Kapturowski, Olivier Tieleman, Martín Arjovsky, Alexander Pritzel, Andew Bolt, Charles Blundell

* Published as a conference paper in ICLR 2020 

  Access Model/Code and Paper
Targeted free energy estimation via learned mappings

Feb 12, 2020
Peter Wirnsberger, Andrew J. Ballard, George Papamakarios, Stuart Abercrombie, Sébastien Racanière, Alexander Pritzel, Danilo Jimenez Rezende, Charles Blundell

* 10 pages, 5 figures 

  Access Model/Code and Paper
MEMO: A Deep Network for Flexible Combination of Episodic Memories

Jan 29, 2020
Andrea Banino, Adrià Puigdomènech Badia, Raphael Köster, Martin J. Chadwick, Vinicius Zambaldi, Demis Hassabis, Caswell Barry, Matthew Botvinick, Dharshan Kumaran, Charles Blundell

* 9 pages, 2 figures, 3 tables, to be published as a conference paper at ICLR 2020 

  Access Model/Code and Paper
Shaping representations through communication: community size effect in artificial learning systems

Dec 12, 2019
Olivier Tieleman, Angeliki Lazaridou, Shibl Mourad, Charles Blundell, Doina Precup

* NeurIPS 2019 workshop on visually grounded interaction and language 

  Access Model/Code and Paper
Generalization of Reinforcement Learners with Working and Episodic Memory

Oct 29, 2019
Meire Fortunato, Melissa Tan, Ryan Faulkner, Steven Hansen, Adrià Puigdomènech Badia, Gavin Buttimore, Charlie Deck, Joel Z Leibo, Charles Blundell

* To be published in NeurIPS 2019. Equal contribution of first 4 authors 

  Access Model/Code and Paper
Neural Execution of Graph Algorithms

Oct 23, 2019
Petar Velińćkovińá, Rex Ying, Matilde Padovano, Raia Hadsell, Charles Blundell

* Under review as a conference paper at ICLR 2020. 13 pages, 4 figures 

  Access Model/Code and Paper
Fast deep reinforcement learning using online adjustments from the past

Oct 18, 2018
Steven Hansen, Pablo Sprechmann, Alexander Pritzel, André Barreto, Charles Blundell

* Accepted at NIPS 2018 

  Access Model/Code and Paper
Pushing the bounds of dropout

Sep 27, 2018
G√°bor Melis, Charles Blundell, Tom√°Ň° Końćisk√Ĺ, Karl Moritz Hermann, Chris Dyer, Phil Blunsom


  Access Model/Code and Paper
Been There, Done That: Meta-Learning with Episodic Recall

Jul 06, 2018
Samuel Ritter, Jane X. Wang, Zeb Kurth-Nelson, Siddhant M. Jayakumar, Charles Blundell, Razvan Pascanu, Matthew Botvinick

* ICML 2018 

  Access Model/Code and Paper
DARLA: Improving Zero-Shot Transfer in Reinforcement Learning

Jun 06, 2018
Irina Higgins, Arka Pal, Andrei A. Rusu, Loic Matthey, Christopher P Burgess, Alexander Pritzel, Matthew Botvinick, Charles Blundell, Alexander Lerchner

* ICML 2017 

  Access Model/Code and Paper
Bayesian Recurrent Neural Networks

Mar 21, 2018
Meire Fortunato, Charles Blundell, Oriol Vinyals


  Access Model/Code and Paper
Memory-based Parameter Adaptation

Feb 28, 2018
Pablo Sprechmann, Siddhant M. Jayakumar, Jack W. Rae, Alexander Pritzel, Adrià Puigdomènech Badia, Benigno Uria, Oriol Vinyals, Demis Hassabis, Razvan Pascanu, Charles Blundell

* Published as a conference paper at ICLR 2018 

  Access Model/Code and Paper
Noisy Networks for Exploration

Feb 15, 2018
Meire Fortunato, Mohammad Gheshlaghi Azar, Bilal Piot, Jacob Menick, Ian Osband, Alex Graves, Vlad Mnih, Remi Munos, Demis Hassabis, Olivier Pietquin, Charles Blundell, Shane Legg

* ICLR 2018 

  Access Model/Code and Paper
Matching Networks for One Shot Learning

Dec 29, 2017
Oriol Vinyals, Charles Blundell, Timothy Lillicrap, Koray Kavukcuoglu, Daan Wierstra


  Access Model/Code and Paper
Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles

Nov 04, 2017
Balaji Lakshminarayanan, Alexander Pritzel, Charles Blundell

* NIPS 2017 

  Access Model/Code and Paper
Distributed Bayesian Learning with Stochastic Natural-gradient Expectation Propagation and the Posterior Server

Sep 07, 2017
Leonard Hasenclever, Stefan Webb, Thibaut Lienart, Sebastian Vollmer, Balaji Lakshminarayanan, Charles Blundell, Yee Whye Teh

* Journal of Machine Learning Research 18 (2017) 1-37 
* 37 pages, 7 figures 

  Access Model/Code and Paper
Neural Episodic Control

Mar 06, 2017
Alexander Pritzel, Benigno Uria, Sriram Srinivasan, Adrià Puigdomènech, Oriol Vinyals, Demis Hassabis, Daan Wierstra, Charles Blundell


  Access Model/Code and Paper
Learning Deep Nearest Neighbor Representations Using Differentiable Boundary Trees

Feb 28, 2017
Daniel Zoran, Balaji Lakshminarayanan, Charles Blundell


  Access Model/Code and Paper
PathNet: Evolution Channels Gradient Descent in Super Neural Networks

Jan 30, 2017
Chrisantha Fernando, Dylan Banarse, Charles Blundell, Yori Zwols, David Ha, Andrei A. Rusu, Alexander Pritzel, Daan Wierstra


  Access Model/Code and Paper
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

* 17 pages, 7 figures, 1 table 

  Access Model/Code and Paper
Early Visual Concept Learning with Unsupervised Deep Learning

Sep 20, 2016
Irina Higgins, Loic Matthey, Xavier Glorot, Arka Pal, Benigno Uria, Charles Blundell, Shakir Mohamed, Alexander Lerchner


  Access Model/Code and Paper
Deep Exploration via Bootstrapped DQN

Jul 04, 2016
Ian Osband, Charles Blundell, Alexander Pritzel, Benjamin Van Roy


  Access Model/Code and Paper
Model-Free Episodic Control

Jun 14, 2016
Charles Blundell, Benigno Uria, Alexander Pritzel, Yazhe Li, Avraham Ruderman, Joel Z Leibo, Jack Rae, Daan Wierstra, Demis Hassabis


  Access Model/Code and Paper
Weight Uncertainty in Neural Networks

May 21, 2015
Charles Blundell, Julien Cornebise, Koray Kavukcuoglu, Daan Wierstra

* In Proceedings of the 32nd International Conference on Machine Learning (ICML 2015) 

  Access Model/Code and Paper
The Bayesian Echo Chamber: Modeling Social Influence via Linguistic Accommodation

Jan 27, 2015
Fangjian Guo, Charles Blundell, Hanna Wallach, Katherine Heller

* 14 pages, 7 figures, to appear in AISTATS 2015. Fixed minor formatting issues 

  Access Model/Code and Paper
Deep AutoRegressive Networks

May 20, 2014
Karol Gregor, Ivo Danihelka, Andriy Mnih, Charles Blundell, Daan Wierstra

* Karol Gregor, Ivo Danihelka, Andriy Mnih, Charles Blundell, Daan Wierstra. Deep AutoRegressive Networks. In Proceedings of the 31st International Conference on Machine Learning (ICML), JMLR: W&CP volume 32, 2014 
* Appears in Proceedings of the 31st International Conference on Machine Learning (ICML), Beijing, China, 2014 

  Access Model/Code and Paper
Bayesian Rose Trees

Mar 15, 2012
Charles Blundell, Yee Whye Teh, Katherine A. Heller

* Appears in Proceedings of the Twenty-Sixth Conference on Uncertainty in Artificial Intelligence (UAI2010) 

  Access Model/Code and Paper
Mixed Cumulative Distribution Networks

Aug 31, 2010
Ricardo Silva, Charles Blundell, Yee Whye Teh

* 11 pages, 4 figures 

  Access Model/Code and Paper