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 William Fedus

On Bonus-Based Exploration Methods in the Arcade Learning Environment

Sep 22, 2021
Adrien Ali Taïga, William Fedus, Marlos C. Machado, Aaron Courville, Marc G. Bellemare

* Published as a conference paper at ICLR 2020 
* Full version of arXiv:1908.02388 

  Access Paper or Ask Questions

Scale Efficiently: Insights from Pre-training and Fine-tuning Transformers

Sep 22, 2021
Yi Tay, Mostafa Dehghani, Jinfeng Rao, William Fedus, Samira Abnar, Hyung Won Chung, Sharan Narang, Dani Yogatama, Ashish Vaswani, Donald Metzler

  Access Paper or Ask Questions

Revisiting ResNets: Improved Training and Scaling Strategies

Mar 13, 2021
Irwan Bello, William Fedus, Xianzhi Du, Ekin D. Cubuk, Aravind Srinivas, Tsung-Yi Lin, Jonathon Shlens, Barret Zoph

  Access Paper or Ask Questions

Do Transformer Modifications Transfer Across Implementations and Applications?

Feb 23, 2021
Sharan Narang, Hyung Won Chung, Yi Tay, William Fedus, Thibault Fevry, Michael Matena, Karishma Malkan, Noah Fiedel, Noam Shazeer, Zhenzhong Lan, Yanqi Zhou, Wei Li, Nan Ding, Jake Marcus, Adam Roberts, Colin Raffel

  Access Paper or Ask Questions

Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity

Jan 11, 2021
William Fedus, Barret Zoph, Noam Shazeer

  Access Paper or Ask Questions

Revisiting Fundamentals of Experience Replay

Jul 13, 2020
William Fedus, Prajit Ramachandran, Rishabh Agarwal, Yoshua Bengio, Hugo Larochelle, Mark Rowland, Will Dabney

* Published at ICML 2020. First two authors contributed equally and code available at 

  Access Paper or Ask Questions

On Catastrophic Interference in Atari 2600 Games

Feb 28, 2020
William Fedus, Dibya Ghosh, John D. Martin, Marc G. Bellemare, Yoshua Bengio, Hugo Larochelle

* First two authors contributed equally. Code available to reproduce experiments at 

  Access Paper or Ask Questions

Algorithmic Improvements for Deep Reinforcement Learning applied to Interactive Fiction

Nov 28, 2019
Vishal Jain, William Fedus, Hugo Larochelle, Doina Precup, Marc G. Bellemare

* To appear in Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence (AAAI-20). Accepted for Oral presentation 

  Access Paper or Ask Questions

Benchmarking Bonus-Based Exploration Methods on the Arcade Learning Environment

Aug 06, 2019
Adrien Ali Taïga, William Fedus, Marlos C. Machado, Aaron Courville, Marc G. Bellemare

* Accepted at the second Exploration in Reinforcement Learning Workshop at the 36th International Conference on Machine Learning, Long Beach, California 

  Access Paper or Ask Questions

Hyperbolic Discounting and Learning over Multiple Horizons

Feb 28, 2019
William Fedus, Carles Gelada, Yoshua Bengio, Marc G. Bellemare, Hugo Larochelle

  Access Paper or Ask Questions

Language GANs Falling Short

Nov 08, 2018
Massimo Caccia, Lucas Caccia, William Fedus, Hugo Larochelle, Joelle Pineau, Laurent Charlin

  Access Paper or Ask Questions

Deep Graph Infomax

Sep 27, 2018
Petar Veličković, William Fedus, William L. Hamilton, Pietro Liò, Yoshua Bengio, R Devon Hjelm

* Under review as a conference paper at ICLR 2019. 15 pages, 8 figures 

  Access Paper or Ask Questions

Recall Traces: Backtracking Models for Efficient Reinforcement Learning

Apr 02, 2018
Anirudh Goyal, Philemon Brakel, William Fedus, Timothy Lillicrap, Sergey Levine, Hugo Larochelle, Yoshua Bengio

* In Review at ICML 2018 

  Access Paper or Ask Questions

MaskGAN: Better Text Generation via Filling in the______

Mar 01, 2018
William Fedus, Ian Goodfellow, Andrew M. Dai

* 16 pages, ICLR 2018 

  Access Paper or Ask Questions

Disentangling the independently controllable factors of variation by interacting with the world

Feb 26, 2018
Valentin Thomas, Emmanuel Bengio, William Fedus, Jules Pondard, Philippe Beaudoin, Hugo Larochelle, Joelle Pineau, Doina Precup, Yoshua Bengio

* Presented at NIPS 2017 Learning Disentangling Representations Workshop 

  Access Paper or Ask Questions

Many Paths to Equilibrium: GANs Do Not Need to Decrease a Divergence At Every Step

Feb 20, 2018
William Fedus, Mihaela Rosca, Balaji Lakshminarayanan, Andrew M. Dai, Shakir Mohamed, Ian Goodfellow

* 18 pages 

  Access Paper or Ask Questions