Publications

Please check my Google Scholar for details. Equal contributions are denoted by *.

Preprints

Simulator Enabled Offline Reinforcement Learning

Pulkit Katdare, Lyuxing He and Katherine Driggs-Campbell
To be submitted to International Conference on Learning Representations, (ICLR), 2024

Towards Provable Log Density Policy Gradient

Pulkit Katdare and Katherine Driggs-Campbell
To be submitted to 5th Conference on Learning for Control (L4DC), 2024

Equivariant Few-Shot Learning from Pretrained Models

Pulkit Katdare, Sourya Basu, Prasanna Sattigeri, Vijil Chentaramakrishnan, Katherine Driggs-Campbell, Payel Das and Lav Varshney
Under Review Conference on Neural Information Processing Systems (Neurips), 2023
[paper]

Conference

Marginalized Importance Sampling for Off-Environment Policy Evaluation

Pulkit Katdare, Nan Jiang, and Katherine Driggs-Campbell
In Conference on Robot Learning (CoRL), 2023
[code]

Gauge Equivariant Deep Q-Learning on Discrete Manifolds

Pulkit Katdare, Sourya Basu, Katherine Driggs-Champbell and Lav Varshney
In Workshop on Geometrical and Topological Representation Learning at International Conference on Learning Representations (ICLR) 2022
[Paper]

Off Environment Evaluation Using Convex Risk Minimization

Pulkit Katdare, Shuijing Liu, and Katherine Driggs-Champbell.
In IEEE International Conference on Robotics and Automation (ICRA), 2022
[Paper] [Code] [Website]

Trajectory Tracking using Motion Primitives for the Purcell’s Swimmer

Pulkit Katdare, Shuijing Liu, and Katherine Driggs-Champbell.
In IEEE International Conference on Intelligent Robots and Systems (IROS), 2017
[Paper] [Code] [Website]

Thesis

Formation Control of the Purcell’s swimmer

Pulkit Katdare Masters Thesis, May 2018.
[Report]