Sainbayar Sukhbaatar
I am a research scientist at Meta Fundamental AI Research (FAIR) focusing on reasoning and memory in AI. I did my PhD with Rob Fergus at the Department of Computer Science of New York University.
Publications
- For more recent publications, see Google Scholar or Semantic Scholar
-
A. Singh, T. Jain, S. Sukhbaatar
Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks.
ICLR, 2019 code -
S. Sukhbaatar, E. Denton, A. Szlam, R. Fergus
Learning Goal Embeddings via Self-Play for Hierarchical Reinforcement Learning.
Deep RL Workshop at NeurIPS, 2018 -
S. Sukhbaatar
Elements of Intelligence: Memory, Communication and Intrinsic Motivation.
PhD Thesis, 2018 -
A. Zhang, A. Lerer, S. Sukhbaatar, R. Fergus, A. Szlam
Composable Planning with Attributes.
ICML, 2018 -
S. Sukhbaatar, Z. Lin, I. Kostrikov, G. Synnaeve, A. Szlam, R. Fergus
Intrinsic Motivation and Automatic Curricula via Asymmetric Self-Play.
ICLR, 2018 code video slide talk -
S. Sukhbaatar, A. Szlam, R. Fergus.
Learning Multiagent Communication with Backpropagation.
NIPS, 2016 code video -
S. Sukhbaatar, A. Szlam, G. Synnaeve, S. Chintala, R. Fergus.
MazeBase: A Sandbox for Learning from Games.
arXiv preprint: 1511.07401, 2016 code video -
B. Zhou, Y. Tian, S. Sukhbaatar, A. Szlam, R. Fergus.
Simple Baseline for Visual Question Answering.
arXiv preprint: 1512.02167, 2015 code demo -
S. Sukhbaatar, A. Szlam, J. Weston, R. Fergus.
End-To-End Memory Networks.
NIPS, 2015. Oral Presentation (Top 0.8% of submissions) code slide talk -
S. Sukhbaatar, J. Bruna, M. Paluri, L. Bourdev, R. Fergus.
Training Convolutional Networks with Noisy Labels.
ICLR Workshop track, 2015 code -
S. Sukhbaatar, T. Makino, K. Aihara.
Auto-pooling: Learning to Improve Invariance of Image Features from Image Sequences.
arXiv preprint: 1301.3323, 2013 -
S. Sukhbaatar, T. Makino, K. Aihara, T. Chikayama.
Robust Generation of Dynamical Patterns in Human Motion by a Deep Belief Nets.
The 3rd Asian Conference on Machine Learning, 2011 code video
Education
-
2013-2018
New York University, Ph.D studentDepartment of Computer Science (thesis) -
2011-2013
The University of Tokyo, Master's degreeDepartment of Mathematical Informatics, Graduate School of Information Science and Technology (thesis) -
2007-2011
The University of Tokyo, Bachelor's degreeDepartment of Electrical and Electronic Engineering, School of Engineering (thesis)
Work experience
-
Summer 2017
Research Internship at DeepmindResearch on encouraging diversity in reinforcement learning -
Summer 2016
Research Internship at Facebook AI ResearchResearch on multiagent communication in reinforcement learning -
Summer 2015
Research Internship at Facebook AI ResearchResearch on reinforcement learning -
Summer 2014
Research Internship at Facebook AI ResearchResearch on noisy labels, memory networks -
Summer 2011
Engineering Internship at Google, JapanWorked on a memory profiler for Chromium browser. -
2007-2011
Research & Development, Tokyo, JapanWeb application development on ASP.NET.
Achievements
- Janet Fabri Prize for the department's most outstanding dissertation
- Two silver and one bronze medals from International Mathematical Olympiad
- Awarded the Japanese Government Scholarship (MONBUSHO) between 2006 and 2013
- Six gold medals from Mongolian National Mathematical and Physics olympiads