Minae Kwon
minae [at] cs [dot] stanford [dot] edu

I am a PhD student at Stanford University advised by Dorsa Sadigh. I spent Fall 2022 at DeepMind with the Game Theory and Multiagent Team. Before that, I spent Summer 2021 at Facebook AI Research working on language agents for CICERO.

I'm interested in making AI systems easy to use for all humans --- can we communicate our objectives intuitively and can we train agents that are aligned with those objectives? My research lies in the intersection of reinforcement learning and human-AI interaction with a recent focus on Foundation Models. My research also has a heavy emphasis on human studies and learning from human data.

email   |   google scholar   |   twitter   

profile photo

News

  • [Jan 2023]

    Our paper on Reward Design with LMs was accepted to ICLR 2023.
  • [Aug 2022]

    I will be starting an internship at DeepMind!

Publications

For the most up-to-date list of publications, please see google scholar.

* indicates equal contribution and co-authorship.

Reward Design with Language Models
Minae Kwon, Sang Michael Xie, Kalesha Bullard, Dorsa Sadigh
ICLR, 2023

paper

Evaluating Human-Language Model Interaction
Mina Lee, Megha Srivastava, Amelia Hardy, John Thickstun, Esin Durmus, Ashwin Paranjape, Ines Gerard-Ursin, Xiang Lisa Li, Faisal Ladhak, Frieda Rong, Rose E. Wang, Minae Kwon, Joon Sung Park, Hancheng Cao, Tony Lee,Rishi Bommasani, Michael Bernstein, Percy Liang
arXiv, 2022

paper

Human-level Play in the Game of Diplomacy by Combining Language Models with Strategic Reasoning
Meta Fundamental AI Research Diplomacy Team (FAIR) and others
Science, 2022

paper   blog

Targeted Data Acquisition for Evolving Negotiation Agents
Minae Kwon, Siddharth Karamcheti, Mariano-Florentino Cuellar, Dorsa Sadigh
ICML, 2021

paper   talk

Transfer Reinforcement Learning across Homotopy Classes
Zhangjie Cao*, Minae Kwon*, Dorsa Sadigh
IEEE Robotics and Automation Letters (RA-L), 2021

paper   code

When Humans Aren't Optimal: Robots that Collaborate with Risk-Aware Humans
Minae Kwon, Erdem Biyik, Aditi Talati, Karan Bhasin, Dylan P Losey, Dorsa Sadigh
HRI, 2020

(Honorable Mention for Best Paper)



paper   talk   blog

Continual Adaptation for Efficient Machine Communication
Robert D. Hawkins, Minae Kwon, Dorsa Sadigh, Noah D. Goodman
ICML Adaptive and Multitask Learning Workshop, 2019
Proceedings of the 24rd Conference on Computational Natural Language Learning (CoNLL), 2020

(Best Paper Award at ICML Adaptive and Multitask Learning Workshop)



paper   talk

Influencing Leading and Following in Human-Robot Teams
Minae Kwon*, Mengxi Li*, Alexandre Bucquet, Dorsa Sadigh
Robotics Science and Systems (RSS), 2019

paper   talk   blog

Expressing Robot Incapability
Minae Kwon, Sandy H. Huang, Anca D. Dragan
Human Robot Interaction (HRI), 2018

(Best Paper Nomination)



paper  

Planning with Verbal Communication for Human-Robot Collaboration
Stefanos Nikolaidis, Minae Kwon, Jodi Forlizzi, Siddhartha Srinivasa
Human Robot Interaction (HRI), 2018

paper  

Human Expectations of Social Robots
Minae Kwon, Malte F Jung, Ross A Knepper
Human Robot Interaction (HRI) Workshop, 2016

paper  



website adapted from here