Kushagra Gupta
CV PDF - Google Scholar Google Scholar - GitHub GitHub

PhD Student
Electrical and Computer Engineering
The University of Texas at Austin

Part of the CLeAR Lab and the Autonomous Systems Group

I explore problems at the intersection of game theory, machine learning, and optimization. I am particularly interested in developing rigorous theoretical frameworks for problems that are inspired by real-world challenges. My work to date has found applications in adversarial learning, multi-task learning and multi-agent planning/learning problems with heterogenous agent information.

I am advised by David Fridovich-Keil and Ufuk Topcu. Before coming to UT Austin, I did my undergrad at Indian Institute of Technology Delhi (IIT Delhi), where I explored topics in game theory, public policy and deep learning.


Contact Info

Email Email: kushagrag@utexas.edu
Github GitHub: kaugsrha
Google Scholar Google Scholar: Click Here
LinkedIn LinkedIn: Click Here

Latest News

Jan 2026: Paper on Multi-Fidelity RL accepted at TMLR

Dec 2025: Paper on Planning with VLMs accepted at AAMAS 2026

Nov 2025: Paper on Privacy guarantees for real-time video accepted at TMLR

Oct 2025: Paper on inverse games accepted at IEEE RA-L

Sept 2025: Paper on Bargaining with Binary Preferences accepted at NeurIPS 2025

June 2025: Paper on Zero-sum Dynamic Games accepted at IEEE L-CSS. My first paper to be accepted in the PhD!



Representative Publications (click here for all my papers at Google Scholar)
* denotes equal contributions

Paper thumbnail
Cooperative Bargaining Games Without Utilities: Mediated Solutions from Direction Oracles
Kushagra Gupta*, Surya Murthy*, Mustafa O. Karabag, Ufuk Topcu, David Fridovich-Keil
NeurIPS 2025
Keywords: Cooperative Bargaining Game Theory, Learning from Binary Preferences, Multi-task Learning
PDF Website Presentation Video

Paper thumbnail
Second-Order Algorithms for Finding Local Nash Equilibria in Zero-Sum Games
Kushagra Gupta, Xinjie Liu, Ross Allen, Ufuk Topcu, David Fridovich-Keil
Under review
Keywords: Nonconvex-nonconcave zero-sum games, Local Nash equilibria, Adversarial learning
PDF

Paper thumbnail
More Information is Not Always Better: Connections between Zero-Sum Local Nash Equilibria in Feedback and Open-Loop Information Patterns
Kushagra Gupta, Ross Allen, David Fridovich-Keil, Ufuk Topcu
IEEE L-CSS (presented at IEEE CDC 2025)
Keywords: Zero-sum games, Information structures in dynamic games
PDF

Paper thumbnail
Game-theoretic Occlusion-Aware Motion Planning: an Efficient Hybrid-Information Approach
Kushagra Gupta, David Fridovich-Keil
CoRL Workshop 2022
Keywords: Occlusion-aware motion planning, Dynamic noncooperative game theory, Information structures in dynamic games
PDF Presentation Video


This site is built with the template graciously provided by Amy X. Zhang! GitHub code here.