Dhruv Sreenivas

I recently completed my BS and MS at Cornell University, where I was advised by Wen Sun.

Research

My main research interests lie in machine learning for decision making and control, specifically in reinforcement learning and imitation learning. I am also interested in general deep learning, including LLMs, deep generative models and representation learning.

Publications

Adversarial Imitation Learning via Boosting
Jonathan Chang, Dhruv Sreenivas, Yingbing Huang, Kianté Brantley, Wen Sun
ICLR 2024
openreview

By viewing off-policy adversarial imitation learning through the framework of gradient boosting, we develop a novel, theoretically principled algorithm that outperforms state-of-the-art methods.

Deep Multi-Modal Structural Equations For Causal Effect Estimation with Unstructured Proxies
Shachi Deshpande, Kaiwen Wang, Dhruv Sreenivas, Zheng Li, Volodymyr Kuleshov
NeurIPS 2022
arXiv

We leverage advances in deep learning to propose a universal multimodal deconfounder for causal inference, with applications in genome-wide association studies (GWAS).

Mitigating Covariate Shift in Imitation Learning via Offline Data Without Great Coverage
Jonathan D. Chang*, Masatoshi Uehara*, Dhruv Sreenivas, Rahul Kidambi, Wen Sun
NeurIPS 2021
code / arXiv

We leverage offline data with partial coverage over the expert state distribution to mitigate the covariate shift problem in imitation learning.

* indicates equal contribution

Teaching

Spring 2023: Graduate TA for CS 6789: Foundations of Reinforcement Learning (PhD)
Fall 2022: Graduate TA for CS 6756: Learning for Robot Decision Making (PhD)
Spring 2022: Graduate TA for CS 4789: Introduction to Reinforcement Learning
Fall 2021: Graduate TA for CS 2110: OOP & Data Structures

Service

Reviewer: NeurIPS 2023, ICLR 2024

Website template is from Jon Barron's website.