Hi there! I’m Gokul, a PhD student in the Robotics Institute at Carnegie Mellon University working on reliable learning in feedback systems.
I work with Drew Bagnell, Steven Wu, and Sanjiban Choudhury. I completed an M.S. at UC Berkeley with Anca Dragan on Learning with Humans in the Loop.
I’ve spent summers working as a Data Engineering Intern @ SpaceX, Autonomous Vehicles Perception Intern @ NVIDIA, Motion Planning ML Intern @ Aurora, and Graduate Research Intern @ MSR.
In my free time, I do origami, hackathons, and lift. I’m a huge fan of birds (especially lovebirds), books (especially those by Murakami), and indie or alt. music (especially that of Radiohead).
Events & News
May 2022 - New preprint on minimax optimal online imitation learning on ArXiv!
May 2022 - Our paper on causal imitation learning was accepted for oral presentation at ICML ‘22!
March 2022 - I’ll be spending the summer at MSR working with Geoff Gordon!
October 2021 - If you’re interested in applying for graduate studies at the CMU RI and come from an underrepresented background, I recommend you check out our graduate application support program here!
October 2021 - Our paper on causal imitation learning was selected as an oral at multiple NeurIPS workshops (Offline RL, Safe RL, Causal Sequential Decisions) ! Check out the website for more info.
May 2021 - Our paper on a unifying framework, efficient reductions, and practical algorithms for imitation learning was accepted to ICML ‘21! Check out the website for videos+code. Also check out this blog post!
Research Highlights
Of Moments and Matching: A Game-Theoretic Framework for Closing the Imitation Gap
We construct a taxonomy for imitation learning algorithms, derive bounds for each class, construct novel reduction-based algorithmic templates that achieve these bounds, and implement simple elegant realizations with competitive emperical performance. Published at ICML 2021. [Website][Blog]
Scaled Autonomy
As fleet sizes grow, it becomes difficult for a single teleoperator to supervise all robots. We learn from user preferences to make automated switches. Our work was published at ICRA 2020.
On the Utility of Model Learning in HRI
We compare three methods of modeling human driving behavior on their sample efficiency and transferability. Our work was published at HRI 2019.