- This event has passed.
Spring 2023 GRASP SFI: Edward Hu, University of Pennsylvania, “Focusing on Task-Relevant Information in RL for Robots”
March 1 at 3:00 PM - 4:00 PM
This is a hybrid event with in-person attendance in Levine 307 and virtual attendance via Zoom. This week’s presenter will be in-person as well.
While it is tempting to view robotics as a nail that can be solved with the deep learning hammer, we have seen that deep-learning based perception and action pipelines for robots are notoriously brittle and data hungry. In this talk, I advocate for a more measured approach for designing data-driven controllers by focusing learning on task-relevant portions of the MDP. Through this philosophy, I show that we can acquire capable learning systems that can transfer between morphologically distinct robots, intelligently probe the environment for imperceptible reward signals, and perform deep exploration with no priors.
University of Pennsylvania
Edward Hu is a 3rd-year Ph.D. student in the Computer and Information Science department and the GRASP lab advised by Professor Dinesh Jayaraman. Ed’s research focuses on model-based reinforcement learning and interactive perception for robotics, and his work received the Best Paper Award at CoRL22. Prior to Penn, Ed completed his BS/MS in Computer Science at the University of Southern California, where he worked on robot learning with Professor Joseph Lim. His recent work can be found on www.edwardshu.com.