Denis Yarats


I am a PhD student at New York University working with Rob Fergus.
My research interests broadly include reinforcement and deep learning.
[Google Scholar] [GitHub] [CV] [denisyarats at cs dot nyu dot edu]

Publications

Parameterizing Policies with Natural Language in Hierarchical Reinforcement Learning.
Hengyuan Hu*, Denis Yarats*, Qucheng Gong, Yuandong Tian, Mike Lewis.
Submitted to ICML 2019.
[PDF]

Quasi-hyperbolic momentum and Adam for deep learning.
Jerry Ma, Denis Yarats.
ICLR 2019.
[PDF] [arXiv] [Code]

Hierarchical Text Generation and Planning for Strategic Dialogue.
Denis Yarats, Mike Lewis.
ICML 2018.
[PDF] [arXiv] [Code]

Deal or No Deal? End-to-End Learning for Negotiation Dialogues.
Mike Lewis, Denis Yarats, Yann Dauphin, Devi Parikh, Dhruv Batra.
EMNLP 2017.
[PDF] [arXiv] [Code]

Convolutional Sequence to Sequence Learning.
Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann Dauphin.
ICML 2017.
[PDF] [arXiv] [Code]

Talks

Task-Oriented Dialogue.
OSD Meetup, Minsk March 2018.
[Slides]

Convolutional Sequence to Sequence Learning.
Treehouse Talk at CLMS, University of Washington.
[Slides]

Convolutional Sequence to Sequence Learning.
International Conference on Artificial Intelligence (www.aiukraine.com).
[Slides]