Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Tom Schaul

When should agents explore?


Aug 26, 2021
Miruna Pîslar, David Szepesvari, Georg Ostrovski, Diana Borsa, Tom Schaul


  Access Paper or Ask Questions

Return-based Scaling: Yet Another Normalisation Trick for Deep RL


May 11, 2021
Tom Schaul, Georg Ostrovski, Iurii Kemaev, Diana Borsa


  Access Paper or Ask Questions

Policy Evaluation Networks


Feb 26, 2020
Jean Harb, Tom Schaul, Doina Precup, Pierre-Luc Bacon

* 12 pages, 11 figures 

  Access Paper or Ask Questions

Adapting Behaviour for Learning Progress


Dec 14, 2019
Tom Schaul, Diana Borsa, David Ding, David Szepesvari, Georg Ostrovski, Will Dabney, Simon Osindero


  Access Paper or Ask Questions

Conditional Importance Sampling for Off-Policy Learning


Oct 16, 2019
Mark Rowland, Anna Harutyunyan, Hado van Hasselt, Diana Borsa, Tom Schaul, Rémi Munos, Will Dabney


  Access Paper or Ask Questions

Non-Differentiable Supervised Learning with Evolution Strategies and Hybrid Methods


Jun 07, 2019
Karel Lenc, Erich Elsen, Tom Schaul, Karen Simonyan


  Access Paper or Ask Questions

Ray Interference: a Source of Plateaus in Deep Reinforcement Learning


Apr 25, 2019
Tom Schaul, Diana Borsa, Joseph Modayil, Razvan Pascanu

* Full version of RLDM abstract 

  Access Paper or Ask Questions

Transfer in Deep Reinforcement Learning Using Successor Features and Generalised Policy Improvement


Jan 30, 2019
André Barreto, Diana Borsa, John Quan, Tom Schaul, David Silver, Matteo Hessel, Daniel Mankowitz, Augustin Žídek, Rémi Munos

* Published at ICML 2018 

  Access Paper or Ask Questions

Universal Successor Features Approximators


Dec 18, 2018
Diana Borsa, André Barreto, John Quan, Daniel Mankowitz, Rémi Munos, Hado van Hasselt, David Silver, Tom Schaul


  Access Paper or Ask Questions

The Barbados 2018 List of Open Issues in Continual Learning


Nov 16, 2018
Tom Schaul, Hado van Hasselt, Joseph Modayil, Martha White, Adam White, Pierre-Luc Bacon, Jean Harb, Shibl Mourad, Marc Bellemare, Doina Precup

* NIPS Continual Learning Workshop 2018 

  Access Paper or Ask Questions

Unicorn: Continual Learning with a Universal, Off-policy Agent


Jul 03, 2018
Daniel J. Mankowitz, Augustin Žídek, André Barreto, Dan Horgan, Matteo Hessel, John Quan, Junhyuk Oh, Hado van Hasselt, David Silver, Tom Schaul


  Access Paper or Ask Questions

Meta-Learning by the Baldwin Effect


Jun 22, 2018
Chrisantha Thomas Fernando, Jakub Sygnowski, Simon Osindero, Jane Wang, Tom Schaul, Denis Teplyashin, Pablo Sprechmann, Alexander Pritzel, Andrei A. Rusu


  Access Paper or Ask Questions

Successor Features for Transfer in Reinforcement Learning


Apr 12, 2018
André Barreto, Will Dabney, Rémi Munos, Jonathan J. Hunt, Tom Schaul, Hado van Hasselt, David Silver

* Published at NIPS 2017 

  Access Paper or Ask Questions

Deep Q-learning from Demonstrations


Nov 22, 2017
Todd Hester, Matej Vecerik, Olivier Pietquin, Marc Lanctot, Tom Schaul, Bilal Piot, Dan Horgan, John Quan, Andrew Sendonaris, Gabriel Dulac-Arnold, Ian Osband, John Agapiou, Joel Z. Leibo, Audrunas Gruslys

* Published at AAAI 2018. Previously on arxiv as "Learning from Demonstrations for Real World Reinforcement Learning" 

  Access Paper or Ask Questions

Rainbow: Combining Improvements in Deep Reinforcement Learning


Oct 06, 2017
Matteo Hessel, Joseph Modayil, Hado van Hasselt, Tom Schaul, Georg Ostrovski, Will Dabney, Dan Horgan, Bilal Piot, Mohammad Azar, David Silver

* Under review as a conference paper at AAAI 2018 

  Access Paper or Ask Questions

StarCraft II: A New Challenge for Reinforcement Learning


Aug 16, 2017
Oriol Vinyals, Timo Ewalds, Sergey Bartunov, Petko Georgiev, Alexander Sasha Vezhnevets, Michelle Yeo, Alireza Makhzani, Heinrich Küttler, John Agapiou, Julian Schrittwieser, John Quan, Stephen Gaffney, Stig Petersen, Karen Simonyan, Tom Schaul, Hado van Hasselt, David Silver, Timothy Lillicrap, Kevin Calderone, Paul Keet, Anthony Brunasso, David Lawrence, Anders Ekermo, Jacob Repp, Rodney Tsing

* Collaboration between DeepMind & Blizzard. 20 pages, 9 figures, 2 tables 

  Access Paper or Ask Questions

The Predictron: End-To-End Learning and Planning


Jul 20, 2017
David Silver, Hado van Hasselt, Matteo Hessel, Tom Schaul, Arthur Guez, Tim Harley, Gabriel Dulac-Arnold, David Reichert, Neil Rabinowitz, Andre Barreto, Thomas Degris

* Camera-ready version, ICML 2017, with supplement 

  Access Paper or Ask Questions

FeUdal Networks for Hierarchical Reinforcement Learning


Mar 06, 2017
Alexander Sasha Vezhnevets, Simon Osindero, Tom Schaul, Nicolas Heess, Max Jaderberg, David Silver, Koray Kavukcuoglu


  Access Paper or Ask Questions

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 Paper or Ask Questions

Reinforcement Learning with Unsupervised Auxiliary Tasks


Nov 16, 2016
Max Jaderberg, Volodymyr Mnih, Wojciech Marian Czarnecki, Tom Schaul, Joel Z Leibo, David Silver, Koray Kavukcuoglu


  Access Paper or Ask Questions

Unifying Count-Based Exploration and Intrinsic Motivation


Nov 07, 2016
Marc G. Bellemare, Sriram Srinivasan, Georg Ostrovski, Tom Schaul, David Saxton, Remi Munos


  Access Paper or Ask Questions

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 Paper or Ask Questions

Prioritized Experience Replay


Feb 25, 2016
Tom Schaul, John Quan, Ioannis Antonoglou, David Silver

* Published at ICLR 2016 

  Access Paper or Ask Questions

Unit Tests for Stochastic Optimization


Feb 25, 2014
Tom Schaul, Ioannis Antonoglou, David Silver

* Final submission to ICLR 2014 (revised according to reviews, additional results added) 

  Access Paper or Ask Questions

Adaptive learning rates and parallelization for stochastic, sparse, non-smooth gradients


Mar 27, 2013
Tom Schaul, Yann LeCun

* Published at the First International Conference on Learning Representations (ICLR-2013). Public reviews are available at http://openreview.net/document/c14f2204-fd66-4d91-bed4-153523694041#c14f2204-fd66-4d91-bed4-153523694041 

  Access Paper or Ask Questions

No More Pesky Learning Rates


Feb 18, 2013
Tom Schaul, Sixin Zhang, Yann LeCun


  Access Paper or Ask Questions

Efficient Natural Evolution Strategies


Sep 26, 2012
Yi Sun, Daan Wierstra, Tom Schaul, Juergen Schmidhuber

* Puslished in GECCO'2009 

  Access Paper or Ask Questions

Measuring Intelligence through Games


Sep 06, 2011
Tom Schaul, Julian Togelius, Jürgen Schmidhuber


  Access Paper or Ask Questions

Natural Evolution Strategies


Jun 22, 2011
Daan Wierstra, Tom Schaul, Tobias Glasmachers, Yi Sun, Jürgen Schmidhuber


  Access Paper or Ask Questions

A Linear Time Natural Evolution Strategy for Non-Separable Functions


Jun 13, 2011
Yi Sun, Faustino Gomez, Tom Schaul, Juergen Schmidhuber


  Access Paper or Ask Questions