Marwa Abdulhai

Hello! I am a Masters Student at the MIT Laboratory for Information & Decision Systems. I am advised by Professor Jonathan P. How and am concentrating in AI. I am interested in reinforcement learning, deep learning, and robotics, and enjoy working on problems at the intersection of artificial intelligence and human decision-making. I recently finished my computer science undergraduate studies at MIT, where I worked with Professor Jonathan P. How (AeroAstro) and Professor Luca Carlone (AeroAstro), and Professor Cynthia Breazeal (Media Lab). During my undergrad, I interned at Amazon Robotics, Uber ATG, IBM, and Lincoln Laboratory.

Outside of my academic pursuits, I enjoy having discussions on morality, spirituality, and religion as part of MIT's Interfaith Community, Addir. I am also committed to improving the condition of underprivileged women and children as part of Helping Hand Relief & Development and Indian Muslim Relief & Charities. I hope to combine technology with my passion to help the developing world and beyond. Feel free to reach out and have a conversation!

Email  /  Github  /  Twitter  /  LinkedIn

profile photo


  • January 2021: New Course! I am leading a program sponsored by Helping Hand Relief & Development to teach refugee students in Jordan how to code in Java. Check out our progress here.
  • December 2020: I recently 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!


single_moe Sharing Skills in Continual Learning
Marwa Abdulhai, Dongki Kim, Matthew Riemer, Miao Liu, Gerald Tesauro, Jonathan P. How
To be submitted to conferences in 2021

We modify the option critic approach, a hierarchical reinforcement learning method, to help an artificial agent learn generalizable skills and preserve past knowledge in continual learning settings.

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
Under Review as Conference Paper, AAAI-20 Symposium
Paper / Code

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.


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.