Marwa Abdulhai

I am a PhD student at UC Berkeley in the Berkeley Artificial Intelligence Research (BAIR) lab advised by Sergey Levine. I am interested in social reinforcement learning, cooperative multi-agent learning, and social intelligence. Previously, I did my masters and undergraduate studies at MIT, where I worked with Jonathan P. How, and Luca Carlone.

Email  /  Github  /  Twitter  /  LinkedIn

profile photo

News

  • September 2021: I began my PhD at UC Berkeley!
  • January 2021: New Course! I led a program sponsored by Helping Hand Relief & Development to teach refugee students in Jordan how to code in Java. Check out course content here.
  • December 2020: I gave a TEDxMIT Talk on the importance of interfaith dialouge and its connection to my research. Check it out here.
  • September 2020: I began my Masters at MIT in EECS!

Research

cradol Context-Specific Representation Abstraction for Deep Option Learning
Marwa Abdulhai, Dongki Kim, Matthew Riemer, Miao Liu, Gerald Tesauro, Jonathan P. How
AAAI-22
Paper / Code Video

We introduce Context-Specific Representation Abstraction for Deep Option Learning (CRADOL), a new framework that considers both temporal abstraction and context-specific representation abstraction to effectively reduce the size of the search over policy space.

meta_mapg A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning
Dongki Kim, Miao Liu, Matthew Riemer, Chuangchuang Sun, Marwa Abdulhai, Golnaz Habibi, Sebastian Lopez-Cot, Gerald Tesauro, Jonathan P. How
ICML-21, AAAI-20 Symposium
Paper / Code Video

We develop a novel meta-multiagent policy gradient theorem that directly accommodates for the non-stationary policy dynamics inherent to multiagent settings. Our meta-agent directly considers both an agent’s own non-stationary policy dynamics and the non-stationary policy dynamics of other agents to adapt fast.

car DRIV3N: The Autonomous Racecar
Marwa Abdulhai, Austin Floyd, Sean Patrick Kelley, David Klee, Luxas Novak, Rose E. Wang
Robotics: Science and Systems I, 2017.
Video | Project Page

My team and I developed programmed a fast autonomous racecar, working on projects in controls, computer vision, path planning, and mapping throughout the semester.

Teaching

planning Teaching Assistant for 6.141: Robotics Science & Systems
Spring 2019
Assignments / Medium Article

react Student Instructor for MIT Refugee Action Hub
January 2019
Program Page

009graph Lab Assistant for 6.009: Fundamentals of Programming in Python
December 2018
Course Page

Template from this website.