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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Disentangling Transfer in Continual Reinforcement Learning


Sep 28, 2022
Maciej Wołczyk, Michał Zając, Razvan Pascanu, Łukasz Kuciński, Piotr Miłoś

* Accepted at NeurIPS 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

An Empirical Study of Implicit Regularization in Deep Offline RL


Jul 07, 2022
Caglar Gulcehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matt Hoffman, Razvan Pascanu, Arnaud Doucet

* 40 pages, 37 figures, 2 tables 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

When Does Re-initialization Work?


Jun 20, 2022
Sheheryar Zaidi, Tudor Berariu, Hyunjik Kim, Jörg Bornschein, Claudia Clopath, Yee Whye Teh, Razvan Pascanu


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

The CLRS Algorithmic Reasoning Benchmark


Jun 04, 2022
Petar Veličković, Adrià Puigdomènech Badia, David Budden, Razvan Pascanu, Andrea Banino, Misha Dashevskiy, Raia Hadsell, Charles Blundell

* To appear in ICML 2022. 19 pages, 4 figures 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pre-training via Denoising for Molecular Property Prediction


May 31, 2022
Sheheryar Zaidi, Michael Schaarschmidt, James Martens, Hyunjik Kim, Yee Whye Teh, Alvaro Sanchez-Gonzalez, Peter Battaglia, Razvan Pascanu, Jonathan Godwin


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Architecture Matters in Continual Learning


Feb 01, 2022
Seyed Iman Mirzadeh, Arslan Chaudhry, Dong Yin, Timothy Nguyen, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar

* preprint 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Pushing the limits of self-supervised ResNets: Can we outperform supervised learning without labels on ImageNet?


Jan 13, 2022
Nenad Tomasev, Ioana Bica, Brian McWilliams, Lars Buesing, Razvan Pascanu, Charles Blundell, Jovana Mitrovic


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Wide Neural Networks Forget Less Catastrophically


Oct 21, 2021
Seyed Iman Mirzadeh, Arslan Chaudhry, Huiyi Hu, Razvan Pascanu, Dilan Gorur, Mehrdad Farajtabar

* preprint 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Powerpropagation: A sparsity inducing weight reparameterisation


Oct 06, 2021
Jonathan Schwarz, Siddhant M. Jayakumar, Razvan Pascanu, Peter E. Latham, Yee Whye Teh

* Accepted at NeurIPS 2021 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
6
7
>>