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 Sainbayar Sukhbaatar

Memory-Augmented Reinforcement Learning for Image-Goal Navigation


Jan 13, 2021
Lina Mezghani, Sainbayar Sukhbaatar, Thibaut Lavril, Oleksandr Maksymets, Dhruv Batra, Piotr Bojanowski, Karteek Alahari


  Access Paper or Ask Questions

Learning to Visually Navigate in Photorealistic Environments Without any Supervision


Apr 10, 2020
Lina Mezghani, Sainbayar Sukhbaatar, Arthur Szlam, Armand Joulin, Piotr Bojanowski


  Access Paper or Ask Questions

Accessing Higher-level Representations in Sequential Transformers with Feedback Memory


Mar 09, 2020
Angela Fan, Thibaut Lavril, Edouard Grave, Armand Joulin, Sainbayar Sukhbaatar


  Access Paper or Ask Questions

Augmenting Self-attention with Persistent Memory


Jul 02, 2019
Sainbayar Sukhbaatar, Edouard Grave, Guillaume Lample, Herve Jegou, Armand Joulin


  Access Paper or Ask Questions

Adaptive Attention Span in Transformers


May 19, 2019
Sainbayar Sukhbaatar, Edouard Grave, Piotr Bojanowski, Armand Joulin

* Accepted to ACL 2019 

  Access Paper or Ask Questions

Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks


Dec 23, 2018
Amanpreet Singh, Tushar Jain, Sainbayar Sukhbaatar

* Accepted to ICLR 2019 

  Access Paper or Ask Questions

Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning


Nov 22, 2018
Sainbayar Sukhbaatar, Emily Denton, Arthur Szlam, Rob Fergus


  Access Paper or Ask Questions

Planning with Arithmetic and Geometric Attributes


Sep 06, 2018
David Folqué, Sainbayar Sukhbaatar, Arthur Szlam, Joan Bruna


  Access Paper or Ask Questions

Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play


Apr 27, 2018
Sainbayar Sukhbaatar, Zeming Lin, Ilya Kostrikov, Gabriel Synnaeve, Arthur Szlam, Rob Fergus

* Published in ICLR 2018 

  Access Paper or Ask Questions

Composable Planning with Attributes


Mar 01, 2018
Amy Zhang, Adam Lerer, Sainbayar Sukhbaatar, Rob Fergus, Arthur Szlam


  Access Paper or Ask Questions

Learning Multiagent Communication with Backpropagation


Oct 31, 2016
Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus

* Accepted to NIPS 2016 

  Access Paper or Ask Questions

MazeBase: A Sandbox for Learning from Games


Jan 07, 2016
Sainbayar Sukhbaatar, Arthur Szlam, Gabriel Synnaeve, Soumith Chintala, Rob Fergus


  Access Paper or Ask Questions

Simple Baseline for Visual Question Answering


Dec 15, 2015
Bolei Zhou, Yuandong Tian, Sainbayar Sukhbaatar, Arthur Szlam, Rob Fergus

* One comparison method's scores are put into the correct column, and a new experiment of generating attention map is added 

  Access Paper or Ask Questions

End-To-End Memory Networks


Nov 24, 2015
Sainbayar Sukhbaatar, Arthur Szlam, Jason Weston, Rob Fergus

* Accepted to NIPS 2015 

  Access Paper or Ask Questions

Training Convolutional Networks with Noisy Labels


Apr 10, 2015
Sainbayar Sukhbaatar, Joan Bruna, Manohar Paluri, Lubomir Bourdev, Rob Fergus

* Accepted as a workshop contribution at ICLR 2015 

  Access Paper or Ask Questions

Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences


Mar 18, 2013
Sainbayar Sukhbaatar, Takaki Makino, Kazuyuki Aihara

* 9 pages, 10 figures. Submission for ICLR 2013 

  Access Paper or Ask Questions