I'm a CS Ph.D. student at the University of Pennsylvania advised by Dinesh Jayaraman. I am broadly interested in artifical intelligence, ranging from virtual agents to physical robots. As a result, my research spans perception, reinforcement learning, and robotics.


I received my BS/MS in CS from the University of Southern California, where I worked with Joseph J. Lim on RL. In Summer 2024, I interned at Microsoft NYC, developing LLM training and planning techniques.


Publications

Code and reviews for all of my PhD papers are public. Check them out!

Learning to Achieve Goals with Belief State Transformers
Edward S. Hu, Kwangjun Ahn, Qinghua Liu, Haoran Xu, Manan Tomar, Ada Langford, Dinesh Jayaraman, Alex Lamb, John Langford

In Submission to ICLR

Keywords: LLM, Transformers, Planning

Paper
Privileged Sensing Scaffolds Reinforcement Learning
Edward S. Hu, James Springer, Oleh Rybkin, Dinesh Jayaraman

ICLR 2024 (Spotlight, 5% accept rate, 3rd Highest Rated Paper in ICLR)

Keywords: Privileged Information, Multimodal Perception, RL

Paper / Website / Code / Reviews
Planning Goals for Exploration
Edward S. Hu, Richard Chang, Oleh Rybkin, Dinesh Jayaraman

ICLR 2023 (Spotlight, 5% accept rate)
CoRL22 Roboadapt Workshop, (Oral, Best Paper Award)

Keywords: Exploration, Goal-conditioned RL, World Models

Paper / Website / Talk / Code / Reviews
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

CORL 2022 (Oral, 6.5% accept rate, Best Paper Award)

Keywords: Interactive Perception, Task Specification, RL

Paper / Website / Code / Reviews
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

ICLR 2022
ICLR Generalizable Policy Learning Workshop, 2022 (Oral)

Keywords: World Models, Robot Transfer, Manipulation

Paper / Website / Code / Reviews
image for IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks
Youngwoon Lee, Edward S. Hu, Joseph J. Lim

ICRA 2021

Keywords: RL, Manipulation, Benchmark

Paper / Website / Code
image for To Follow or not to Follow: Selective Imitation Learning from Observations
To Follow or not to Follow: Selective Imitation Learning from Observations
Youngwoon Lee, Edward S. Hu, Zhengyu Yang, Joseph J. Lim

CORL 2019

Keywords: Learning from Demonstrations, Goal-conditioned RL

Paper / Website / Talk
Composing Complex Skills by Learning Transition Policies
Youngwoon Lee*, Shao-Hua Sun*, Sriram Somasundaram, Edward S. Hu, Joseph J. Lim

ICLR 2019

Keywords: Hierarchical RL

Paper / Website / Code

peg

Implementation of Planning Exploratory Goals, an unsupervised RL agent for hard exploration tasks. ICLR 2023

● Python 47

robot_aware_control

Code for "Know Thyself: Transferable Visual Control Policies Through Robot-Awareness" (ICLR'22)

● Python 5

interactive_reward_functions

Code release for "Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning" (CoRL'22)

● Python 14

furniture

IKEA Furniture Assembly Environment for Long-Horizon Complex Manipulation Tasks (ICRA'21)

● Python 448 52

slack-gpt2

OpenAI's GPT2 integrated with slack.

● Python 40 9

optical_illusion

A simple optical illusion in python

● Python 40 1

Mentorship

Current:
  • James Springer, UPenn MS
Past:
  • Harsh Goel, UPenn MS -> UT Austin PhD
  • Kun Huang, UPenn MS -> Fulltime SWE at Cruise
  • Richard Chang, UPenn BS
  • Lucy Shi, USC undergrad -> Stanford visitor