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 Pierre H. Richemond

BYOL works even without batch statistics


Oct 20, 2020
Pierre H. Richemond, Jean-Bastien Grill, Florent Altché, Corentin Tallec, Florian Strub, Andrew Brock, Samuel Smith, Soham De, Razvan Pascanu, Bilal Piot, Michal Valko


  Access Paper or Ask Questions

Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning


Jun 13, 2020
Jean-Bastien Grill, Florian Strub, Florent Altché, Corentin Tallec, Pierre H. Richemond, Elena Buchatskaya, Carl Doersch, Bernardo Avila Pires, Zhaohan Daniel Guo, Mohammad Gheshlaghi Azar, Bilal Piot, Koray Kavukcuoglu, Rémi Munos, Michal Valko


  Access Paper or Ask Questions

Biologically inspired architectures for sample-efficient deep reinforcement learning


Nov 25, 2019
Pierre H. Richemond, Arinbjörn Kolbeinsson, Yike Guo

* Deep Reinforcement Learning Workshop, NeurIPS 2019, Vancouver, Canada 

  Access Paper or Ask Questions

Static Activation Function Normalization


May 03, 2019
Pierre H. Richemond, Yike Guo


  Access Paper or Ask Questions

Combining learning rate decay and weight decay with complexity gradient descent - Part I


Feb 07, 2019
Pierre H. Richemond, Yike Guo


  Access Paper or Ask Questions

A short variational proof of equivalence between policy gradients and soft Q learning


Dec 22, 2017
Pierre H. Richemond, Brendan Maginnis


  Access Paper or Ask Questions

On Wasserstein Reinforcement Learning and the Fokker-Planck equation


Dec 19, 2017
Pierre H. Richemond, Brendan Maginnis


  Access Paper or Ask Questions

Efficiently applying attention to sequential data with the Recurrent Discounted Attention unit


Jun 19, 2017
Brendan Maginnis, Pierre H. Richemond

* Updated results of RDA-exp-tanh unit for the wikipedia char prediction task 

  Access Paper or Ask Questions