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 Georg Ostrovski

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

On The Effect of Auxiliary Tasks on Representation Dynamics


Feb 25, 2021
Clare Lyle, Mark Rowland, Georg Ostrovski, Will Dabney

* AISTATS 2021 

  Access Paper or Ask Questions

Temporally-Extended ε-Greedy Exploration


Jun 02, 2020
Will Dabney, Georg Ostrovski, André Barreto


  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

Autoregressive Quantile Networks for Generative Modeling


Jun 14, 2018
Georg Ostrovski, Will Dabney, Rémi Munos

* ICML 2018 

  Access Paper or Ask Questions

Implicit Quantile Networks for Distributional Reinforcement Learning


Jun 14, 2018
Will Dabney, Georg Ostrovski, David Silver, Rémi Munos

* ICML 2018 

  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

Count-Based Exploration with Neural Density Models


Jun 14, 2017
Georg Ostrovski, Marc G. Bellemare, Aaron van den Oord, Remi Munos


  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

Increasing the Action Gap: New Operators for Reinforcement Learning


Dec 15, 2015
Marc G. Bellemare, Georg Ostrovski, Arthur Guez, Philip S. Thomas, Rémi Munos

* Bellemare, Marc G., Ostrovski, G., Guez, A., Thomas, Philip S., and Munos, Remi. Increasing the Action Gap: New Operators for Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, 2016 

  Access Paper or Ask Questions