About me

Hi, I'm a CS Ph.D. student at the University of Pennsylvania advised by Dinesh Jayaraman. My goal is to develop robots can learn and act by themselves. I received my BS/MS in CS from the University of Southern California, where I worked with Joseph J. Lim. I also developed software for nonprofits at Code The Change, and interned at Tesla and Intel.

News
  • Jan 2023: Paper on model-based exploration is accepted to ICLR with spotlight distinction (top 25% of accepted papers)
  • Dec 2022: Interactive Reward Functions wins best paper award at CoRL; Paper on model-based exploration wins best paper award at CoRL Roboadapt Workshop.
  • Sep 2022: Paper on interactive reward functions is accepted to CoRL as oral (6.5% acceptance rate).
  • Jan 2022: Paper on generalizing policies between robots is accepted to ICLR.

Publications

I develop data-driven algorithms for robots that enable them to act more intelligently and autonomously. I am particularly interested in exploration, model-based RL, and active perception.

Planning Goals for Exploration
Edward S. Hu, Richard Chang, Oleh Rybkin, Dinesh Jayaraman

International Conference on Learning Representations, 2023 (Spotlight)
CoRL22 Roboadapt Workshop, (Oral, Best Paper Award)

Keywords: World Models, Exploration, Goal-conditioned RL

image for IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning
Kun Huang, Edward S. Hu, Dinesh Jayaraman

Conference on Robot Learning, 2022 (Oral, Best Paper Award)

Keywords: Interactive Perception, Task Specification, RL

image for IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
Transferable Visual Control Policies Through Robot-Awareness
Edward S. Hu, Kun Huang, Oleh Rybkin, Dinesh Jayaraman

International Conference on Learning Representations (ICLR), 2022
ICLR Generalizable Policy Learning Workshop, 2022 (Oral)

Keywords: World Models, Transfer, Manipulation

image for IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks

International Conference on Robotics and Automation (ICRA), 2021

Keywords: RL, Manipulation, Benchmark

image for To Follow or not to Follow: Selective Imitation Learning from Observations
To Follow or not to Follow: Selective Imitation Learning from Observations

Conference on Robot Learning (CoRL), 2019

Keywords: Learning from Demonstrations, Goal-conditioned RL

Composing Complex Skills by Learning Transition Policies

International Conference on Learning Representations (ICLR), 2019

Keywords: Hierarchical RL

Fun Projects

Optical Illusion in Python
Make black and white images seem vibrantly colored with a sparsely colored grid overlay.

GPT-2 Slackbot
Enables slack users to converse with OpenAI’s GPT-2 language model

Medmind
Open-source medication management software.

Mentorship

Current:
  • Richard Chang, ESE BS @ UPenn
  • Harsh Goel, ROBO MS @ UPenn
  • Lucy Shi, CS BS @ USC
Past:
  • Kun Huang, Prev. ROBO MS @ UPenn. Now ML Eng. @ Cruise