About Me

I’m a masters (Robotics) student at Carnegie Mellon University (CMU) advised by Prof. Ben Eysenbach, Prof. Ruslan Salakhutdinov, and Prof. Jeff Schneider. I am broadly interested in machine learning problems and their applications in computer vision and robotics.

I am currently a student researcher in the DARPA RACER project, where I am working on reinforcement learning methods for autonomous navigation in off-road environments. I spent the summer of 2022 as an ML intern in the Maneuver Planning team at Cruise. Before joining CMU, I was a research intern in TensorLab (Caltech), where I closely collaborated with Prof. Kamyar Azizzadenesheli (Purdue University), Prof. Anima Anandkumar (Caltech), Prof. Yisong Yue (Caltech), and Dr. Mohammad Ghavamzadeh (Google Research). I received my Bachelor's degree from IIT Roorkee, with a major in Electronics and Communication Engineering and minors in Computer Science.

Publications

Bayesian Quadrature for Policy Gradient

An introduction to Bayesian quadrature for policy gradient estimation, and the computation methods required for scaling it to high-dimensional settings. Introduces two policy gradient estimators, (i) Deep Bayesian Quadrature Policy Gradient (DBQPG) and (ii) Uncertainty Aware Policy Gradient (UAPG), that serve as a drop-in replacement for Monte-Carlo estimation in most policy gradient algorithms while offering more accurate policy gradient estimates, superior sample complexity, and higher average return.

[Jul 2023] "Distributional Distance Classifiers for Goal-Conditioned Reinforcement Learning" accepted to the New Frontiers in Learning, Control, and Dynamical Systems Workshop, ICML 2023.
[May 2022] Starting as an ML Engineer Intern in the Maneuver Planning team at Cruise.
[Aug 2021] Starting my M.S. Robotics (MSR) degree at the Robotics Institute, Carnegie Mellon University (CMU).
[Aug 2021] Attended Machine Learning Summer School (MLSS) Taipei.
[Dec 2020] "Deep Bayesian Quadrature Policy Optimization" accepted to AAAI 2021.
[Oct 2020] "Deep Bayesian Quadrature Policy Optimization" accepted to NeurIPS Deep RL and Real-World RL workshops.
[Sep 2020] "Reinforced Multi-task Approach for Multi-hop Question Generation" accepted to COLING 2020.
[May 2020] " Enhancing Perceptual Loss with Adversarial Feature Matching for Super-Resolution" accepted to IJCNN 2020.
[Oct 2019] Serving as Secondary Reviewer for AAAI 2020.
[Sept 2019] Serving as Secondary Reviewer for Machine Learning and the Physical Sciences (ML4PS), NeurIPS (2019) workshop.