Aravind Rajeswaran

Research Scientist at Meta AI (FAIR)

Visiting PostDoc / Collaborator,
Berkeley AI Research Lab (BAIR)

Google Scholar | Bio | CV | GitHub | Twitter

I am a research scientist in the Fundamental AI Research (FAIR) division of Meta AI. In addition to my role at FAIR, I also spend time at UC Berkeley as a visiting researcher, hosted by Prof. Pieter Abbeel.

My research focuses on building foundation models for all manner of Embodied AI agents operating in the open world, such as smart glasses and robots. Relevent topics include self-supervised representation learning, sequence models for decision making, and offline RL.

Previously, I was a research scientist and visiting researcher at CMU mentored by Prof. Abhinav Gupta. I recieved my PhD in Computer Science from the University of Washington working with Profs. Sham Kakade and Emo Todorov. During this time, I also worked closely with Sergey Levine and Chelsea Finn, and spent time as a student researcher at Google Brain and OpenAI. Before that, I recieved my Bachelors degree along with the best undergraduate thesis award from IIT Madras.

Representative Papers

Foundation Models for Embodied AI

VC-1: Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Cortex Team @ FAIR
Neural Information Processing Systems (NeurIPS) 2023 | Project Website

R3M: A Universal Visual Representation for Robot Manipulation
Suraj Nair, Aravind Rajeswaran, Vikash Kumar, Chelsea Finn, Abhinav Gupta
Scaling Robot Learning Workshop at ICRA 2022 | (Best Paper Award) | Project Webpage

Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?
Yuchen Cui, Scott Niekum, Abhinav Gupta, Vikash Kumar, Aravind Rajeswaran
Learning for Dynamics and Control (L4DC) 2022
Scaling Robot Learning Workshop at RSS 2022 | (Finalist for Best Paper Award) | Project Webpage

Sequence Models for Reinforcement Learning

Masked Trajectory Models for Prediction, Representation, and Control
Philipp Wu, Arjun Majumdar, Kevin Stone, Yixin Lin, Igor Mordatch, Pieter Abbeel, Aravind Rajeswaran
International Conference on Machine Learning (ICML) 2023 | Project Website

Decision Transformer: Reinforcement Learning via Sequence Modeling
Lili Chen*, Kevin Lu*, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Michael Laskin,
Pieter Abbeel, Aravind Srinivas, Igor Mordatch
Neural Information Processing Systems (NeurIPS) 2021 | Project Website

Tools for Robotics

RoboHive: A Unified Framework for Robot Learning
Vikash Kumar, Rutav Shah, Gaoyue Zhou, Vincent Moens, Vittorio Caggiano,
Jay Vakil, Abhishek Gupta, Aravind Rajeswaran
Neural Information Processing Systems (NeurIPS) 2023 | Project Website

Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations
Aravind Rajeswaran, Vikash Kumar, Abhishek Gupta, John Schulman, Emanuel Todorov, Sergey Levine
Robotics: Science and Systems (RSS) 2018; Project Webpage


I enjoy collaborating with a diverse set of students and researchers. I have had the pleasure of mentoring some highly motivated students at both the undergraduate and PhD levels. List of current students and alumni.


CSE599G: Deep Reinforcement Learning (Instructor)
I designed and co-taught a course on deep reinforcement learning at UW in Spring 2018. The course presents a rigorous mathematical treatment of various RL algorithms along with illustrative applications in robotics. Deep RL courses at UW, MIT, and CMU have borrowed and built upon the material I developed for this course.

CSE547: Machine Learning for Big Data (Teaching Assistant)
This is an advanced graduate level course on machine learning with emphasis on machine learning at scale and distributed algorithms. Topics covered include hashing, sketching, streaming, large-scale distributed optimization, federated learning, and contextual bandits. I was the lead TA for this class.

CSE546: Machine Learning (Teaching Assistant)
This is the introductory graduate level machine learning class at UW.