Will Feng — accepted AI-conference papers

2018

Mastering the Dungeon: Grounded Language Learning by Mechanical Turker Descent

Zhilin Yang, Saizheng Zhang, Jack Urbanek, Will Feng, Alexander Miller, Arthur Szlam +2

ICLR 2018poster

Contrary to most natural language processing research, which makes use of static datasets, humans learn language interactively, grounded in an environment. In this work we propose an interactive learning procedure called Mechanical Turker Descent (MTD) that trains agents to execute natural language…

Cited by 32 Source ↗PDF ↗Scholar ↗

2017

Learn2Smile: Learning non-verbal interaction through observation

Will Feng, Anitha Kannan, Georgia Gkioxari, C. Lawrence Zitnick

IROS 2017poster

Interactive agents are becoming increasingly common in many application domains, such as education, healthcare and personal assistance. The success of such embodied agents relies on their ability to have sustained engagement with their human users. Such engagement requires agents to be socially inte…

Cited by 46 Source ↗Scholar ↗