Back to all members...
PhD, started 2021
Gunshi Gupta is a DPhil student in the OATML group, supervised by Prof. Yarin Gal. She is interested in problems related to probabilistic and causally-correct learning from data, with a focus on robotics tasks. She grew up in New Delhi, India where she got her applied-math engineering degree from DTU. After dabbling in software engineering and robotics research, she went on to study machine learning at Mila supervised by Prof. Liam Paull. Her master’s research was on the topics of bayesian deep-learning, meta learning and continual learning. Before joining AIMS CDT, she worked at the autonomous driving startup Wayve that aims to solve the self-driving problem using end-to-end deep learning.
Publications while at OATML • News items mentioning Gunshi Gupta • Reproducibility and Code • Blog Posts
Publications while at OATML:
Can Active Sampling Reduce Causal Confusion in Offline Reinforcement Learning?
Causal confusion is a phenomenon where an agent learns a policy that reflects imperfect spurious correlations in the data. Such a policy may falsely appear to be optimal during training if most of the training data contain such spurious correlations. This phenomenon is particularly pronounced in domains such as robotics, with potentially large gaps between the open- and closed-loop performance of an agent. In such settings, causally confused models may appear to perform well according to open-loop metrics during training but fail catastrophically when deployed in the real world. In this paper, we study causal confusion in offline reinforcement learning. We investigate whether selectively sampling appropriate points from a dataset of demonstrations may enable offline reinforcement learning agents to disambiguate the underlying causal mechanisms of the environment, alleviate causal confusion in offline reinforcement learning, and produce a safer model for deployment. To answer this q... [full abstract]
Gunshi Gupta, Tim G. J. Rudner, Rowan McAllister, Adrien Gaidon, Yarin Gal
NeurIPS Workshop on Causal Machine Learning for Real-World Impact, 2022
News items mentioning Gunshi Gupta:
Gunshi Gupta is announced as Equality, Diversity and Inclusion Fellow
22 Sep 2022
OATML PhD Student Gunshi Gupta has been announced as one of the new Equality, Diversity and Inclusion fellows for the Mathematical, Physical & Life Sciences Division. Congratualtions to her, and all of the Fellows, who will help promote an inclusive and supportive culture for all.
OATML Conference papers at NeurIPS 2022
OATML group members and collaborators are proud to present 8 papers at NeurIPS 2022 main conference, and 11 workshop papers. …Full post...
Yarin Gal, Freddie Kalaitzis, Shreshth Malik, Lorenz Kuhn, Gunshi Gupta, Jannik Kossen, Pascal Notin, Andrew Jesson, Panagiotis Tigas, Tim G. J. Rudner, Sebastian Farquhar, Ilia Shumailov, 25 Nov 2022