![]() |
|
I am a research scientist in the FAIR labs division of Meta AI. I also collaborate closely with Prof. Pieter Abbeel's lab at UC Berkeley and Prof. Abhinav Gupta's lab at CMU. I work on algorithmic foundations of deep learning and reinforcement learning. My current research focuses on pretraining and foundation models for decision making and Embodied Intelligence. Relevent topics include self-supervised representation learning, sequence models for decision making, and offline RL. I recieved my PhD in CSE 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
Representation Learning for Decision Making The (Un)Surprising Effectiveness of Pre-Trained Vision Models for Control R3M: A Universal Visual Representation for Robot Manipulation Can Foundation Models Perform Zero-Shot Task Specification For Robot Manipulation?
Offline Reinforcement Learning Decision Transformer: Reinforcement Learning via Sequence Modeling MOReL : Model-Based Offline Reinforcement Learning
Meta-Learning: Theoretical & Algorithmic Foundations Meta Learning with Implicit Gradients Online Meta-Learning
Applications in Robotics Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrations Reinforcement learning for non-prehensile manipulation: Transfer from simulation to physical system | |
|
Mentoring 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. | |
|
|
|
All Publications and Preprints | |
|
Teaching
CSE599G: Deep Reinforcement Learning (Instructor)
CSE547: Machine Learning for Big Data (Teaching Assistant)
CSE546: Machine Learning (Teaching Assistant) | |
|