Wonjoon Goo Ph.D. Candidate
@ University of Texas at Austin
(Expected Graduation, Fall 22)

Educational Background

Aug. 2016 - Current

  • University of Texas at Austin
    Ph.D. in Computer Science

Mar. 2008 - Feb. 2016

  • Seoul National University
    B.S. in Computer Science and Engineering (Summa Cum Laude, 3rd/56)
    GPA 4.03/4.3, GPA in major 4.07/4.3

Sep. 2014 - Dec. 2014

  • University of Toronto
    Exchange Student in Computer Science Dept.
    GPA in major 4.0/4.0

Work and Research Experience

May. 2021 - Aug. 2021

  • Research Scientist Intern
    Naver Clova AI Research@Seongam-si, Gyeongi-do, Korea
    Advisor : Prof. Joseph Lim and Dr. Minsuk Chang
    Research Topic: Offline Reinforcement Learning

Sep. 2019 - Dec. 2019

  • Teaching Assistant, CS394R: Reinforcement Learning: Theory and Practice
    University of Texas at Austin

May. 2018 - Aug. 2018

Sep. 2016 - Dec. 2016

  • Teaching Assistant, CS313E: Elements of Software Design
    University of Texas at Austin

Apr. 2016 - Jun. 2016

  • Lead Web Programmer
    Art 247@Paju, Gyeonggi-Do, Korea
    I developed a commercial website selling baby clothes with Django web framework.
    [site link] (currently unavailable)

Mar. 2015 - Apr. 2016

Dec. 2010- Jan. 2014

  • Lead Game Server Programmer(worked as alternative military service agent)
    Netmarble Npark (before kwon as Ani-park)@Seoul, Korea
    It was an great opportunity since I was able to get an industrial field experience during my undergraduate. The three year experience taught me various programming skills from traditional, widely used skill-set, like C++, RDBMS to trending technologies, such as Node.js, NoSQL(mongoDB).

Jun. 2010- Aug. 2010

  • Summer Intern
    Redduck@Seoul, Korea

Awards & Honors

Publications

  • Know Your Boundaries: The Necessity of Explicit Behavior Cloning in Offline RL
    Wonjoon Goo and Scott Niekum
    arXiv:2206.00695, June 2022.
    [paper / code]
  • A Ranking Game for Imitation Learning
    Harshit Sikchi, Akanksha Saran, Wonjoon Goo, and Scott Niekum
    arXiv:2202.03481, February 2022.
    [paper]
  • You Only Evaluate Once — a Simple Baseline Algorithm for Offline RL
    Wonjoon Goo and Scott Niekum
    Conference on Robot Learning (CoRL)
    London, UK, 2021
    [paper / code / short paper at NeurIPS 2020 workshop on Offline RL]
  • Self-Supervised Online Reward Shaping in Sparse-Reward Environments
    Farzan Memarian*, Wonjoon Goo*, Rudolf Lioutikov, Ufuk Topcu, and Scott Niekum (*equal contribution)
    International Conference on Intelligent Robots and Systems (IROS)
    Online, 2021
    [paper / code]
  • Local Nonparametric Meta-Learning
    Wonjoon Goo and Scott Niekum
    arXiv:2002.03272, February 2020.
    [paper / code]
  • Better-than-Demonstrator Imitation Learning via Automatically-Ranked Demonstrations
    Daniel Brown, Wonjoon Goo, and Scott Niekum
    Conference on Robot Learning (CoRL)
    Osaka, Japan, 2019
  • Extrapolating Beyond Suboptimal Demonstrations via Inverse Reinforcement Learning from Observations
    Daniel Brown*, Wonjoon Goo*, Prabhat Nagarajan, and Scott Niekum (*equal contribution)
    International Conference on Machine Learning (ICML)
    Long Beach, CA, 2019
  • One-Shot Learning of Multi-Step Tasks from Observation via Activity Localization in Auxiliary Video
    Wonjoon Goo and Scott Niekum
    International Conference on Robotics and Automation (ICRA)
    Montreal, Canada, 2019
    [paper / code]
  • Taxonomy-Regularized Semantic Deep Convolutional Neural Networks
    Wonjoon Goo, Juyong Kim, Gunhee Kim, Sung Ju Hwang
    European Conference on Computer Vision (ECCV)
    Amsterdam, The Neterlands, 2016

Address

GDC 3.504A
2317 Speedway
Austin, TX 78712

If you feel stressed out, see this lazy picture!