Rahul Ramesh


I am Ph.D. student at the University of Pennsylvania and am advised by Pratik Chaudhari. I work on building machine learning models using limited amounts of data; My interests span areas like multi-task learning, meta-learning, transfer learning and semi-supervised learning.

I graduated from the Indian Institute of Technology Madras in 2019 with a Dual Degree (Bachelor’s and Master’s) in Computer Science, where I was advised by Balaraman Ravindran.

I recently started a blog.


A picture of the space of typical learnable tasks
Rahul Ramesh, Jialin Mao, Itay Griniasty, Han Kheng Teoh, Mark Transtrum, James P. Sethna, Pratik Chaudhari

Model Zoo: A Growing Brain that Learns Continually
Rahul Ramesh, Pratik Chaudhari
ICLR 2022

Deep Reference Priors: What is the best way to pretrain a model?
Yansong Gao*, Rahul Ramesh*, Pratik Chaudhari
ICML 2022

Successor Options: An Option Discovery Framework for Reinforcement Learning
Rahul Ramesh*, Manan Tomar*, Balaraman Ravindran
IJCAI 2019

Option Encoder: A Framework for Discovering a Policy Basis in Reinforcement Learning

FigureNet : A Deep Learning model for Question-Answering on Scientific Plots
IJCNN 2019

AUPCR Maximizing Matchings : Towards a Pragmatic Notion of Optimality for One-Sided Preference Matchings
AAAI 2018 - MPREF Workshop

Learning to Factor Policies and Action-Value Functions: Factored Action Space Representations for Deep Reinforcement learning