Task-Relevant Adversarial Imitation Learning

Oct 02, 2019
Konrad Zolna, Scott Reed, Alexander Novikov, Sergio Gomez Colmenarej, David Budden, Serkan Cabi, Misha Denil, Nando de Freitas, Ziyu Wang


  Access Model/Code and Paper
A Framework for Data-Driven Robotics

Sep 26, 2019
Serkan Cabi, Sergio G贸mez Colmenarejo, Alexander Novikov, Ksenia Konyushkova, Scott Reed, Rae Jeong, Konrad 呕o艂na, Yusuf Aytar, David Budden, Mel Vecerik, Oleg Sushkov, David Barker, Jonathan Scholz, Misha Denil, Nando de Freitas, Ziyu Wang


  Access Model/Code and Paper
Modular Meta-Learning with Shrinkage

Sep 12, 2019
Yutian Chen, Abram L. Friesen, Feryal Behbahani, David Budden, Matthew W. Hoffman, Arnaud Doucet, Nando de Freitas

* 14 pages (4 main, 8 supplement), under review 

  Access Model/Code and Paper
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


  Access Model/Code and Paper
Learning Compositional Neural Programs with Recursive Tree Search and Planning

May 30, 2019
Thomas Pierrot, Guillaume Ligner, Scott Reed, Olivier Sigaud, Nicolas Perrin, Alexandre Laterre, David Kas, Karim Beguir, Nando de Freitas


  Access Model/Code and Paper
Meta-learning of Sequential Strategies

May 08, 2019
Pedro A. Ortega, Jane X. Wang, Mark Rowland, Tim Genewein, Zeb Kurth-Nelson, Razvan Pascanu, Nicolas Heess, Joel Veness, Alex Pritzel, Pablo Sprechmann, Siddhant M. Jayakumar, Tom McGrath, Kevin Miller, Mohammad Azar, Ian Osband, Neil Rabinowitz, Andr谩s Gy枚rgy, Silvia Chiappa, Simon Osindero, Yee Whye Teh, Hado van Hasselt, Nando de Freitas, Matthew Botvinick, Shane Legg

* DeepMind Technical Report (15 pages, 6 figures) 

  Access Model/Code and Paper
Bayesian Optimization in AlphaGo

Dec 17, 2018
Yutian Chen, Aja Huang, Ziyu Wang, Ioannis Antonoglou, Julian Schrittwieser, David Silver, Nando de Freitas


  Access Model/Code and Paper
Intrinsic Social Motivation via Causal Influence in Multi-Agent RL

Oct 19, 2018
Natasha Jaques, Angeliki Lazaridou, Edward Hughes, Caglar Gulcehre, Pedro A. Ortega, DJ Strouse, Joel Z. Leibo, Nando de Freitas


  Access Model/Code and Paper
One-Shot High-Fidelity Imitation: Training Large-Scale Deep Nets with RL

Oct 11, 2018
Tom Le Paine, Sergio G贸mez Colmenarejo, Ziyu Wang, Scott Reed, Yusuf Aytar, Tobias Pfaff, Matt W. Hoffman, Gabriel Barth-Maron, Serkan Cabi, David Budden, Nando de Freitas


  Access Model/Code and Paper
Large-Scale Visual Speech Recognition

Oct 01, 2018
Brendan Shillingford, Yannis Assael, Matthew W. Hoffman, Thomas Paine, C铆an Hughes, Utsav Prabhu, Hank Liao, Hasim Sak, Kanishka Rao, Lorrayne Bennett, Marie Mulville, Ben Coppin, Ben Laurie, Andrew Senior, Nando de Freitas


  Access Model/Code and Paper
Sample Efficient Adaptive Text-to-Speech

Sep 27, 2018
Yutian Chen, Yannis Assael, Brendan Shillingford, David Budden, Scott Reed, Heiga Zen, Quan Wang, Luis C. Cobo, Andrew Trask, Ben Laurie, Caglar Gulcehre, A盲ron van den Oord, Oriol Vinyals, Nando de Freitas


  Access Model/Code and Paper
Playing hard exploration games by watching YouTube

May 29, 2018
Yusuf Aytar, Tobias Pfaff, David Budden, Tom Le Paine, Ziyu Wang, Nando de Freitas


  Access Model/Code and Paper
Reinforcement and Imitation Learning for Diverse Visuomotor Skills

May 27, 2018
Yuke Zhu, Ziyu Wang, Josh Merel, Andrei Rusu, Tom Erez, Serkan Cabi, Saran Tunyasuvunakool, J谩nos Kram谩r, Raia Hadsell, Nando de Freitas, Nicolas Heess

* 13 pages, 6 figures, Published in RSS 2018 

  Access Model/Code and Paper
Hyperbolic Attention Networks

May 24, 2018
Caglar Gulcehre, Misha Denil, Mateusz Malinowski, Ali Razavi, Razvan Pascanu, Karl Moritz Hermann, Peter Battaglia, Victor Bapst, David Raposo, Adam Santoro, Nando de Freitas


  Access Model/Code and Paper
Learning Awareness Models

Apr 17, 2018
Brandon Amos, Laurent Dinh, Serkan Cabi, Thomas Roth枚rl, Sergio G贸mez Colmenarejo, Alistair Muldal, Tom Erez, Yuval Tassa, Nando de Freitas, Misha Denil

* Accepted to ICLR 2018 

  Access Model/Code and Paper
Compositional Obverter Communication Learning From Raw Visual Input

Apr 06, 2018
Edward Choi, Angeliki Lazaridou, Nando de Freitas

* Published as a conference paper at ICLR 2018 

  Access Model/Code and Paper
Few-shot Autoregressive Density Estimation: Towards Learning to Learn Distributions

Feb 28, 2018
Scott Reed, Yutian Chen, Thomas Paine, A盲ron van den Oord, S. M. Ali Eslami, Danilo Rezende, Oriol Vinyals, Nando de Freitas


  Access Model/Code and Paper
Cortical microcircuits as gated-recurrent neural networks

Jan 03, 2018
Rui Ponte Costa, Yannis M. Assael, Brendan Shillingford, Nando de Freitas, Tim P. Vogels

* To appear in Advances in Neural Information Processing Systems 30 (NIPS 2017). 13 pages, 2 figures (and 1 supp. figure) 

  Access Model/Code and Paper
Learned Optimizers that Scale and Generalize

Sep 07, 2017
Olga Wichrowska, Niru Maheswaranathan, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Nando de Freitas, Jascha Sohl-Dickstein

* Final ICML paper after reviewer suggestions 

  Access Model/Code and Paper
Learning to Perform Physics Experiments via Deep Reinforcement Learning

Aug 17, 2017
Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas


  Access Model/Code and Paper
Robust Imitation of Diverse Behaviors

Jul 14, 2017
Ziyu Wang, Josh Merel, Scott Reed, Greg Wayne, Nando de Freitas, Nicolas Heess


  Access Model/Code and Paper
The Intentional Unintentional Agent: Learning to Solve Many Continuous Control Tasks Simultaneously

Jul 11, 2017
Serkan Cabi, Sergio G贸mez Colmenarejo, Matthew W. Hoffman, Misha Denil, Ziyu Wang, Nando de Freitas


  Access Model/Code and Paper
Sample Efficient Actor-Critic with Experience Replay

Jul 10, 2017
Ziyu Wang, Victor Bapst, Nicolas Heess, Volodymyr Mnih, Remi Munos, Koray Kavukcuoglu, Nando de Freitas

* 20 pages. Prepared for ICLR 2017 

  Access Model/Code and Paper
Programmable Agents

Jun 20, 2017
Misha Denil, Sergio G贸mez Colmenarejo, Serkan Cabi, David Saxton, Nando de Freitas


  Access Model/Code and Paper
Learning to Learn without Gradient Descent by Gradient Descent

Jun 12, 2017
Yutian Chen, Matthew W. Hoffman, Sergio Gomez Colmenarejo, Misha Denil, Timothy P. Lillicrap, Matt Botvinick, Nando de Freitas

* Accepted by ICML 2017. Previous version "Learning to Learn for Global Optimization of Black Box Functions" was published in the Deep Reinforcement Learning Workshop, NIPS 2016 

  Access Model/Code and Paper
Parallel Multiscale Autoregressive Density Estimation

Mar 10, 2017
Scott Reed, A盲ron van den Oord, Nal Kalchbrenner, Sergio G贸mez Colmenarejo, Ziyu Wang, Dan Belov, Nando de Freitas


  Access Model/Code and Paper
LipNet: End-to-End Sentence-level Lipreading

Dec 16, 2016
Yannis M. Assael, Brendan Shillingford, Shimon Whiteson, Nando de Freitas


  Access Model/Code and Paper
Learning to learn by gradient descent by gradient descent

Nov 30, 2016
Marcin Andrychowicz, Misha Denil, Sergio Gomez, Matthew W. Hoffman, David Pfau, Tom Schaul, Brendan Shillingford, Nando de Freitas


  Access Model/Code and Paper
Learning to Communicate with Deep Multi-Agent Reinforcement Learning

May 24, 2016
Jakob N. Foerster, Yannis M. Assael, Nando de Freitas, Shimon Whiteson


  Access Model/Code and Paper
Dueling Network Architectures for Deep Reinforcement Learning

Apr 05, 2016
Ziyu Wang, Tom Schaul, Matteo Hessel, Hado van Hasselt, Marc Lanctot, Nando de Freitas

* 15 pages, 5 figures, and 5 tables 

  Access Model/Code and Paper